机器学习学术速递[10.5]

AI 总结：针对地表预测中状态空间模型吸收非平稳混杂偏差的问题，提出SSU-LSF框架，利用影响函数和正则化梯度上升实现高效遗忘，在三个基准上显著降低混杂，且GPU成本远低于重训练。

链接：https://arxiv.org/abs/2610.02248

机构：Heritage Institute of Technology（遗产技术学院）

作者：Anidipta Pal

英文摘要：Operational land surface forecasting systems built on Mamba-family Structured State Space Models absorb non-stationary confounding events (unrecorded irrigation booms, dam-operation shifts, sensor recalibrations) into their state-transition matrices, silently biasing NDVI, LST, and crop phenology predictions long after the physical cause ends. This paper introduces SSU-LSF (State-Space Unlearning for Land Surface Forecasting), the first machine-unlearning framework purpose-built for geoscientific Mamba-based SSMs. We develop EKFac influence functions specialized to the Mamba state matrices via a closed-form matrix-exponential gradient, use spectral-radius-weighted elbow thresholding to localize a temporal confounding footprint $\Phi$, and apply Hessian-free projected gradient ascent within a KL-divergence trust region augmented by spatial total-variation (TV) regularization. Proposition 1 establishes that residual confounding is bounded by $\mathcal{O}\big((1-\rho(\bar{A})^{T_c})/((1-\rho(\bar{A}))\mu)\big)$, which grows with the window length $T_c$. Across three heterogeneous benchmarks and eleven baselines, SSU-LSF achieves confounding reduction rates of $0.773$ (CropHarvest), $0.821$ (NDVI-LST), and $0.859$ (ERA5), with worst-case clean-domain RMSE degradation of $4.2\%$ on ERA5, converging in 3--5 epochs at $8.4\times$ lower GPU-cost per unlearning request than full retraining. Code: this https URL

AI 总结：本文提出统一JEPA表示坍缩缓解策略的早期训练稳定性理论，并基于此设计ResidualPred预测器，在表格基准和图像预训练中提升有效秩与下游准确率。

链接：https://arxiv.org/abs/2610.02344

机构：Université Paris-Saclay（巴黎-萨克雷大学）； CNRS（法国国家科学研究中心）； CentraleSupélec（中央理工-高等电力学院）； LISN（LISN实验室）

作者：José Lucas De Melo Costa, Seong Woo Ahn, Fabrice Popineau, Arpad Rimmel, Bich-Liên Doan

英文摘要：Joint-Embedding Predictive Architectures (JEPAs) are prone to representation collapse, typically mitigated through empirical heuristics. We develop an early-training stability theory that unifies these heuristics. Linearising the coupled JEPA gradient flow around the trivial fixed point reveals two competing effects: a driving force ($\gamma$) and a decay effect ($\sigma$). Under approximate spectral decoupling, a per-mode stability ratio $\mu_i = \gamma_i / \sigma_i$ factorises into independent data-side and predictor-side terms and the count of unstable modes tracks the rank of representations that can emerge. The framework predicts a phase boundary, which we confirm empirically across more than 800 Tabular-JEPA configurations. It also unifies predictor scaling, masking ratio, and EMA as distinct mechanisms for shifting $\mu$. Guided by this analysis, we introduce ResidualPred, a transformer predictor whose attention is biased toward the identity at initialisation; it improves both effective rank and downstream accuracy on tabular benchmarks and in I-JEPA pretraining on CIFAR-10, CIFAR-100, STL-10, and ImageNet. Our framework connects empirical collapse-avoidance heuristics to an explicit dynamical picture, yielding theory-driven stabilizers. Code is available at this https URL.

AI 总结：本文提出字典序多目标在策略蒸馏（LMOPD），通过门控选择缺陷专家并投影修正，在多个数学基准上保留高优先级能力，优于现有基线。

链接：https://arxiv.org/abs/2610.02359

机构：Cohere； Mila, Université de Montréal（Mila，蒙特利尔大学）

作者：Doseok Jang, Jon Ander Campos, Youran Qi

英文摘要： Reinforcement learning from verifiable rewards (RLVR) usually optimizes answer correctness, yet useful language-model behavior also requires high-quality reasoning and concise responses. Existing multi-reward post-training methods typically scalarize rewards or combine specialists without explicitly protecting a reward priority order. This is problematic when trade-offs are asymmetric: conciseness, for example, should not improve at the cost of correctness. We introduce Lexicographic Multi-Objective On-Policy Distillation (LMOPD), a multi-teacher method for integrating reward-specialized policies under explicit priorities. For each student rollout, LMOPD selects the specialist for the first objective whose gate detects a deficiency, then locally projects its centered log-policy correction to remove components that oppose higher-priority specialists. We evaluate 30B-A3B mixture-of-experts transformer models in two- and four-expert settings on three math benchmarks, measuring retained specialist gains. With two experts, LMOPD's point estimates fully retain the accuracy and reasoning-quality gains while acquiring $46.9\%$ of the conciseness gain. With four experts, it retains $\approx90\%$ of both the accuracy gain and reasoning-correctness gain, compared to only $\approx57\%$ by the next best evaluated baseline. Matched four-expertablations show that lexicographic routing outperforms random routing and that projection further strengthens both top-priority capabilities. Across both scales, LMOPD preserves the highest-priority capabilities more effectively than the existing baselines we evaluate, demonstrating the value of explicit priorities for specialist integration.

AI 总结：本文提出基于逆激活回归的神经元合并方法，结合聚类与最小二乘估计，实现sigmoid网络训练后压缩，并验证权重与激活信息在合并中的不同作用。

链接：https://arxiv.org/abs/2610.02559

机构：Saitama University（埼玉大学）

作者：Ao Kuniya, Jun Ohkubo

英文摘要：As neural networks continue to grow in scale, model compression is becoming increasingly important for efficient inference under limited computational resources. Structured pruning methods remove neurons or channels that are estimated to be less important, but the removed units may still contain useful information. From the viewpoint of coarse-graining a trained network, it is valuable to ask which information should be retained when multiple neuronal degrees of freedom are consolidated. In this paper, we discuss cluster-based merging methods for compression of trained neural networks. In addition to a data-free contribution-weighted averaging method, we propose neuron-merging methods in which neuron responses are mapped back to the pre-activation space via the inverse activation function, and the weights and biases of each representative neuron are estimated using the least-squares method. We also examine both a data-assisted strategy with actual training inputs and a data-free strategy using randomly generated inputs. The comparisons provide empirical evidence, in the tested sigmoid networks, that weight information is particularly useful for clustering whereas activation information is useful for representative-neuron reconstruction in the merging process.

AI 总结：本文通过固定计算下的稠密MoE粒度扫描，发现K=2的软门控FFN性能最佳，验证损失改善0.0048，并揭示集中路由的功能重要性。

链接：https://arxiv.org/abs/2610.02584

机构：University of Information Technology（信息技术大学）； Vietnam National University, Ho Chi Minh City（越南国立大学胡志明市分校）

作者：Vu Quang Hoang, Nghia Hieu Nguyen

英文摘要：Sparse Mixture-of-Experts (MoE) models combine learned routing with selection from a large expert pool. We isolate the contribution of dynamic expert combination using a dense analogue: $K$ SwiGLU experts, all active for every token and combined by a softmax gate, at fixed total FFN width. With no larger pool or discrete selection, the dense baseline is the $K=1$ case. Validation loss varies non-monotonically with $K$: $K=2$ improves over the baseline by $0.0048$, whereas $K=4$ and $K=6$ worsen it by $0.0053$ and $0.0197$, respectively. Routing generally remains soft and expert usage balanced, except in the first layer of the $K=4$ model, where routing is nearly one-hot. Forcing this gate to uniform increases loss by $2.4$ nats on a diagnostic subset, indicating that its concentrated routing is functionally important. We further show that the architecture is exactly a dense SwiGLU with token-dependent, simplex-constrained group scaling and contains the dense baseline in its function class. These single-run results suggest a granularity sweet spot for always-active, softly gated FFNs at fixed width, with $K=2$ performing best among the configurations tested.

AI 总结：本文比较了MoE大语言模型低预算下两种AR到扩散转换方法，发现冻结上下文塔比原地转换保留更多父模型知识，并在HumanEval上提升11.6倍。

链接：https://arxiv.org/abs/2610.02657

机构：Celeris

作者：Wentao Lu, Jesse Clark, Tianyu Zhu

英文摘要：Converting a pretrained autoregressive (AR) model to a diffusion language model (dLLM) enables parallel generation without pretraining a new model. Published conversion methods differ by roughly three orders of magnitude in training data and have not been compared under a common protocol. We compare two conversions of the same 30B Mixture-of-Experts (MoE) parent, holding the corpus, supervised-token budget, trainable parameter set and evaluation harness fixed, each under its own training recipe. The in-place model updates a subset of the parent's weights using denoising and representation-alignment losses; the frozen-tower model instead conditions through cross-attention on a frozen causal copy of the parent. With 1B training tokens, the frozen-tower model scores 71.60 on HumanEval pass@10 against 6.19 for the in-place model, an 11.6x improvement. At the same budget it also keeps 95% of the parent's GSM8K score and 99% of its MMLU-Pro score. A dense-parent experiment reproduces the HumanEval separation. Within the two-tower design at about 500M tokens, freezing the context tower retains substantially more MMLU-Pro performance than training it, while both give similar observed HumanEval scores. Our theoretical analysis establishes that both conversion classes contain an exact sampler for the AR parent under a hard attention mask and left-to-right commitment of one position per round. Under a shared loss, freezing removes the gradient contribution through the context states. Furthermore, evaluation protocol substantially affects a published 500B-token conversion's scores in both directions across tasks, while its AR parent's scores vary by less than three points, so comparing dLLMs needs a common protocol. These results show that, in the tested low-budget regime, the frozen-tower configuration retains substantially more of the parent's generation performance than in-place conversion.

AI 总结：针对现代选择性状态空间模型（如Mamba2）在联邦学习中的架构无关问题，推导架构感知的梯度和收敛界，并通过数值验证及九种算法在六个文本域上的实验，揭示稳定性、离散化与投影范数对联邦优化的影响。

链接：https://arxiv.org/abs/2610.02659

机构：Purdue University（普渡大学）； IBM Research（IBM研究院）

作者：Adam Piaseczny, Md Kamran Chowdhury Shisher, Shiqiang Wang, Christopher G. Brinton

英文摘要：Modern state space models (SSMs), such as Mamba2, provide a compelling alternative to transformers by combining linear-time sequence modeling with recurrent state-space dynamics. However, the behavior of SSMs in distributed learning settings remains poorly understood. In particular, the existing standard federated learning methods are largely architecture-agnostic, and do not account for the stability, selectivity, and state-space parameterization that characterize modern selective SSMs. To address this, we derive architecture-aware gradient and smoothness bounds for single- and multi-layer selective SSMs, and convergence bounds for FedAvg and FedProx, characterizing how recurrent stability, input-dependent discretization, and state projection norms affect federated optimization. We then numerically validate the single-layer bounds on sequences generated by a teacher SSM, using a learner that follows the analyzed recurrence. We use this analysis to formulate expectations about the effects of local training and client heterogeneity, and examine these expectations by comparing nine federated learning algorithms on Mamba2 language modeling across six text domains. These experiments illustrate how SSM-specific bounds can provide a basis for interpreting the behavior of practical federated learning algorithms.

AI 总结：提出RAOA循环架构，利用可编程无线电传播实现交替算子计算，在离散优化和语言模型适配中验证了其有效性，连接了计算、传播与神经适配。

链接：https://arxiv.org/abs/2610.02683

机构：Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室）

作者：Toshiaki Koike-Akino

英文摘要：Can programmable radio propagation serve as computational depth rather than only as a communication channel or one-shot analog transform? We introduce the Radio Alternating Operator Ansatz (RAOA), a recurrent computing architecture that alternates an energy-derived problem update with a mixing update over a persistent latent state. Recomputing the problem field after each mix makes repeated passes compositional even when the same learned controls are reused across depth. We evaluate this idea through exact discrete optimization, constrained programmable-propagation simulation, and pretrained-model adaptation. On discrete objectives, repeated execution can improve solution quality without increasing the learned-control count, and the same formulation handles higher-order interactions directly. A passive phase-only free-space model further shows that the required operators can be approximated by programmable propagation while retaining useful downstream behavior despite realization error. When inserted as a zero-initialized residual adapter, RAOA adapts pretrained language models with WikiText performance close to a matched shallow MLP across three model families, while reasoning-task transfer remains model-dependent. Together, these results connect alternating-operator computation, programmable radio propagation, and neural adaptation within one recurrent framework. The RF realization evidence is simulation-based rather than a hardware demonstration.

AI 总结：本研究在JetClass-II上对比密集与MoE粒子Transformer，发现top-1 MoE在计算量不变时提升精度，多专家激活增加计算成本但提升预测，并强调需区分存储容量、活跃计算、路由容量与组织。

链接：https://arxiv.org/abs/2610.02701

机构：University of California San Diego（加州大学圣迭戈分校）； University of Illinois at Chicago（伊利诺伊大学芝加哥分校）； Fermi National Accelerator Laboratory（费米国家加速器实验室）； University of California Davis（加州大学戴维斯分校）

作者：Kaushik Pendiyala, Haris Zia, Trevin Lee, Timothy Legge, Alejandro J. De Leon, Zihan Zhao, Aaron Wang, Abhijith Gandrakota, Jennifer Ngadiuba, Richard Cavanaugh, Javier Duarte

英文摘要：Mixture-of-Experts (MoE) models can increase parameter capacity without proportionally increasing active computation, but it is unclear how this trade-off behaves in particle-physics transformers. We study dense and MoE Particle Transformers on 188-class JetClass-II, varying expert count, routing capacity, top-K, and auxiliary loss. We find that, when token dropping is avoided, top-1 MoE models improve over the dense baseline at nearly unchanged nominal forward compute, while further increasing the number of stored experts produces little additional accuracy gain. Activating multiple experts per token yields additional predictive improvements at higher computational cost. Routing analyses show that expert assignments become more strongly associated with particle identity and kinematics in some configurations, but this structure does not increase monotonically with classification performance. These results highlight the need to distinguish stored parameter capacity, active computation, routing capacity, and routing organization when evaluating sparse expert models for jet classification. Code and experiment configurations are available at this https URL.

AI 总结：本文提出约束感知训练目标，将程序分析外部化于训练过程，通过三个定理和合成实验证明其相比交叉熵训练在同等参数和数据下降低预测损失，提升模型效率。

链接：https://arxiv.org/abs/2610.02909

机构：University of California-San Diego（加州大学圣迭戈分校）； Microsoft Research（微软研究院）

作者：Jinwoo Kim

英文摘要：When generating programs with language models, constrained decoding can apply program analyses to exclude tokens that violate syntax, scope, or typing rules. However, there is a duplication: standard training already teaches the model to suppress the tokens rejected by these analyses. This duplication leads to the question: if we will perform some analysis to filter a set tokens out during inference anyways, can we avoid teaching the model the said analysis altogether during training, and does this externalization lead to more efficient models? This paper defines a general constraint-aware objective satisfying this externalization desideratum and formalizes the benefits of externalization into three concrete theorems about model size and data efficiency. We show, through a controlled synthetic experiment, that the theorems survive training dynamics: constraint-aware training yields lower prediction loss at a matched parameter count and data compared to ordinary cross-entropy training, motivating training objectives that incorporate the analyses used during generation.

AI 总结：针对多智能体系统中静态专家剪枝无法适应异构工作负载的问题，提出动态专家剪枝（DEP），利用提示文本预测每请求专家掩码，在多种任务和模型上优于静态基线，且专家越少优势越大。

链接：https://arxiv.org/abs/2610.02951

机构：Pohang University of Science and Technology (POSTECH)（浦项科技大学）； Microsoft Research Asia（微软亚洲研究院）

作者：Jabin Koo, Soheil Abbasloo, Sungjae Lee, Jungseul Ok

英文摘要：Mixture-of-Experts (MoE) architectures scale language models efficiently by activating only a few experts per token, but the saving is confined to computation: every expert must stay resident on the accelerator, so memory bounds where these models can be deployed. Expert pruning reduces this footprint, yet existing methods are static --- a single mask, calibrated offline, is applied to the model for every subsequent request. This assumption can fail when the workload is heterogeneous, most prominently in multi-agent systems, where one backbone serves many tasks and roles at once: our analysis shows that different tasks and roles recruit different experts, while static methods assign one fixed subset to all of them. We therefore propose Dynamic Expert Pruning (DEP), which rests on a finding we establish here: an agent's system and task prompts are by themselves sufficient to identify the experts that agent and its task require, since that text already describes what the agent will do. A lightweight predictor, trained once on workflow transcripts, turns those prompts into a specialized per-request mask in a single forward pass, with no per-configuration calibration. Across diverse tasks and roles, model scales, and MoE architectures, DEP achieves better overall accuracy than static pruning and merging baselines, and generalizes to workflows unseen in training without retraining. Its margin over those baselines is largest when few experts are retained, suggesting that the role specialization inherent to multi-agent systems permits sparser serving than static pruning allows.

AI 总结：本文提出一种基于庞加莱双曲几何的时间参数图元学习框架，以动态表示MLP训练轨迹，捕捉网络自组织演化，实现内在可解释性。

链接：https://arxiv.org/abs/2610.03000

机构：Jheronimus Academy of Data Science（杰罗尼穆斯数据科学学院）； Eindhoven University of Technology（埃因霍温理工大学）

作者：Ambarish Moharil

英文摘要：Intrinsic explainability remains a challenging problem, particularly in contexts where multilayer perceptrons (MLPs) require dynamic re-training within an optimization environment. This paper investigates how MLPs and their training dynamics can be represented and studied in non-Euclidean spaces; our representation features the Poincaré model of hyperbolic geometry. We aim to capture the geometric evolution of their weighted topology and self-organization over time. Instead of restricting the analysis to single checkpoints---as per established measure-based explainability methods---we construct temporal \textit{parameter graphs}, i.e., snapshots over time $T$ steps of the optimization/training process for MLPs. This reflects the view that neural networks encode information not only in their weights but also in the trajectory traced during training. Drawing on the idea that many complex networks admit embeddings in hidden metric spaces where distances correspond to connection likelihood, we present a geometric and temporal graph-based metalearning framework for obtaining dynamic hyperbolic representations of the underlying neural parameter graphs. Our model embeds temporal parameter graphs in the Poincaré model ball, and learns from them while maintaining equivariance to within-snapshot neuron permutations and invariance to permutations of past snapshots. In doing so, the approach preserves functional equivalence over time and recovers the latent evolving geometry of the network. Experiments on regression and classification tasks with trained MLPs show strong meta-network performance, accompanied by hyperbolic temporal representations. This reveals how the network structure emerges over time under specific training environments, thus providing insights into the network's self-organization.

AI 总结：本研究首次评估机器学习在乌干达和南非临床数据上的结核病筛查分类，提出联合优化特征选择与排序的CNN策略，LR模型AUROC达0.8-0.84，接近WHO灵敏度要求，证明神经网络分类器可行。

链接：https://arxiv.org/abs/2610.03256

机构：University of Stellenbosch（斯泰伦博斯大学）； Stellenbosch University（斯泰伦博斯大学）； University of Amsterdam（阿姆斯特丹大学）； University of Göttingen（哥廷根大学）； Makerere University（马凯雷雷大学）

作者：Joshua M. Jansen van Vüren, Devendra S. Parihar, Daphne Naidoo, Marisa Klopper, Frank Cobelens, Lutz Kolbe, Kimsey Zajac, Willy Ssengooba, Moses Joloba, Grant Theron, Thomas R. Niesler

英文摘要：We present a first evaluation of machine learning applied to patient clinical and demographic data gathered in two different countries for the purpose of tuberculosis (TB) screening to identify people who would benefit from expensive molecular testing. Experiments are based on the recently-compiled CAGE-TB dataset, which includes sub-cohorts of people with presumptive TB presenting at community health care centres in South Africa and Uganda. Three neural network architectures (logistic regression (LR), multilayer perceptrons (MLP) and convolutional neural networks (CNN)) are considered in conjunction with greedy feature selection. For the convolutional neural network, a strategy that jointly optimises feature selection and feature ordering is proposed and shown to lead to consistent development and test set improvements. For all three models, development set area under the receiver operating characteristic (AUROC) curve is improved by 2-7% using feature selection. LR after feature selection achieves an AUROC of 0.8 [0.75,0.86] (95% CI) and 0.84 [0.78,0.9] when testing on the held-out Ugandan and South African data respectively. Although outperforming LR on the development cohort, the deeper networks (MLP, CNN) show inconsistent trends on the held-out cohorts, while LR achieves performance within 1-2% of the best achieved in terms of AUROC. LR narrowly misses the WHO minimum requirements by 4-9% in sensitivity even though the network is being evaluated on a completely held-out cohort. The development of neural-network based classifiers for TB screening therefore appears viable.

AI 总结：针对智能体大语言模型的无评论家强化微调，提出“跟随胜者”（FTW）算法，用交叉熵方法和序数过滤替代组rollout，在Sokoban和Search-R1上匹配GRPO和PPO性能，实现方差缩减的保守策略改进。

链接：https://arxiv.org/abs/2610.03361

机构：Trent AI Limited（Trent AI有限公司）； University of Cambridge（剑桥大学）

作者：Joery Ariën de Vries, Neil David Lawrence, Zhenwen Dai

英文摘要：Critic-free reinforcement fine-tuning (RFT) for agentic large language models is often done through GRPO-style methods, which compute a group baseline over repeated rollouts to reduce target variance. However, this setup is ill-suited to agents acting in stateful environments such as live services or security sandboxes, where repeated rollouts are impractical to obtain and aggressive updates entrench the noise of long, sparsely verified trajectories. We propose \textit{Follow the Winners} (FTW), a critic-free policy-learning algorithm that adapts the cross-entropy method to RFT, replacing group rollouts with an ordinal filter on replay-buffer samples that yields polynomial concentration in the order statistic of returns. We derive FTW through a control-as-inference lens, which also recovers GRPO and DPO as specific modelling choices, identifying GRPO as risk-neutral while DPO and FTW share a bounded risk-seeking offset that FTW controls. We identify this offset as an inherent trade-off of variance reduction through ordinal filters on samples, whereas a critic model induces a different trade-off between bias and variance. Scaled to agentic LLM post-training, FTW matches GRPO and PPO on Sokoban and Search-R1 baselines, showing a viable trade-off from a value model or group rollouts to CPU memory.

AI 总结：Pivot-SD通过信息增益选择高影响承诺进行自蒸馏，仅用200个问题和四次展开即提升LLaDA-8B-Instruct在数学和代码基准上的表现。

链接：https://arxiv.org/abs/2610.03665

机构：KAIST AI（韩国科学技术院人工智能学院）； University of Toronto（多伦多大学）； Vector Institute（向量研究所）

作者：Seo Hyun Kim, Sunwoo Hong, Younwoo Choi, Chen-Hao Chao, Se-Young Yun, Rahul G. Krishnan

英文摘要：Masked diffusion language models (dLMs) offer a promising parallel alternative to autoregressive models for complex reasoning. However, they face a distinct credit-assignment challenge, since a few commitments during denoising sharply reduce the uncertainty over the remaining masked positions and shape much of the response. Most post-training recipes for dLMs do not use this signal to decide which tokens to train on: they typically train on the final text or assign rewards to whole denoising steps, rather than selecting the individual commitments that shape the response. We introduce Pivot-SD, an efficient offline self-distillation framework that supervises only these high-impact commitments (pivots). Pivot-SD selects pivots using an information-gain metric measuring uncertainty reduction over the remaining masked positions. Pivots from successful trajectories are trained with cross-entropy, and pivots from failed trajectories with targeted unlikelihood, leaving the rest of the failed trajectory untouched. Using only 200 questions and four rollouts each, Pivot-SD improves LLaDA-8B-Instruct over full-sequence SFT and budget-matched diffusion RL baselines across math and code benchmarks.

AI 总结：本研究提出HyMLRaman混合拉曼光谱框架，结合深度特征提取与生成式增强，实现六种药物的高精度识别，准确率达96.31%。

链接：https://arxiv.org/abs/2610.02224

机构：University of Science, Ho Chi Minh City（胡志明市理科大学）； Vietnam National University, Ho Chi Minh City（越南国立大学胡志明市分校）； University of Health Sciences (UHS), Viet Nam National University Ho Chi Minh City（越南国立大学胡志明市分校健康科学大学）； Frontier Research Institute for Interdisciplinary Sciences, Tohoku University（东北大学跨学科前沿研究所）

作者：Quach Thi Thai Binh, Ton Nu Quynh Trang, Thang B. Phan, Vu Thi Hanh Thu, Nguyen Tuan Hung

英文摘要：Rapid and reliable identification of pharmaceutical residues is important for safeguarding public health, ensuring food safety, and enabling practical Raman-based screening. In this study, we propose HyMLRaman, a hybrid Raman spectroscopy framework that combines deep spectral feature extraction, generative models, and classical machine-learning classifiers to identify six pharmaceutical compounds, including amoxicillin, chloramphenicol, ciprofloxacin, tetracycline, ibuprofen, and paracetamol. Raman spectra are converted into spectral images and encoded with several deep neural-network backbones, among which EfficientNet-B3 yields the most effective representation. The resulting 1536-dimensional embeddings are then used to train downstream classifiers, including SVM, KNN, logistic regression, random forest, XGBoost, and ANN, using stratified 10-fold cross-validation. The hybrid EfficientNet-B3--SVM configuration achieves the strongest baseline performance, reaching 96.31% accuracy and a macro-F1 score of 96.36%, outperforming the standalone CNN baseline. To address limited-data conditions, a generative model, a DDPM-based feature augmentation, is introduced in a PCA-reduced EfficientNet-B3 latent space. The low-data ablation results show that DDPM augmentation provides selective benefits, particularly for KNN with reduced training fractions, and that its effect remains classifier-dependent. Finally, an application-level Raman Pharmaceutical Analyzer demonstrates the feasibility of embedding the trained model into an interactive Raman analysis workflow. These results suggest that HyMLRaman provides a practical and interpretable route for rapid Raman-based pharmaceutical screening.

AI 总结：AIGS提出一种轻量级闭环自适应门控系统，通过冲击比和连续可塑性控制器解决在线表示学习中的稳定性-可塑性困境，在保持线性复杂度下提升边缘设备对概念漂移的适应能力。

链接：https://arxiv.org/abs/2610.02661

机构：Xiamen University Malaysia（厦门大学马来西亚分校）； Multimedia University（多媒体大学）； School of Economics and Management, Xiamen University Malaysia（厦门大学马来西亚分校经济与管理学院）； School of Computing and Data Science, Xiamen University Malaysia（厦门大学马来西亚分校计算与数据科学学院）

作者：SiRui He, Kai Liang Lew, Chui Zi Ong, Chean Khim Toa

英文摘要： Real-time data streams in Web of Things (WoT) and edge computing environments often evolve through latent regime changes. For online representation learning under strict computational constraints, the central problem is resolving the stability-plasticity dilemma: keeping useful historical knowledge while rapidly reacting to concept drift. Existing methods employ fixed update schedules or rolling windows. However, they suffer from parameter ossification during sudden shifts and waste computational resources when the stream remains stable. This paper proposes the Adaptive Incremental Gating System (AIGS), a lightweight closed-loop state-aware adaptation framework. AIGS introduces the Shock Ratio, an endogenous residual feedback mechanism that normalizes current reconstruction error against recent variation. This signal drives a Continuous Plasticity Controller that smoothly interpolates between learning plasticity and memory retention. By treating representation learning as a closed-loop control mechanism, AIGS avoids catastrophic forgetting and maintains a strictly linear $\mathcal{O}\left(k\cdot d\right)$ per-step complexity suitable for latency-sensitive edge devices. Experiments on real-world smart city dynamic streams-spanning traffic networks, meteorological systems, and industrial infrastructure-demonstrate distinct domain-dependent advantages. On Electricity Transformer Temperature datasets, AIGS achieves preventative early-warning lead times of 8.31 (ETTm1) and 9.88 (ETTm2) steps under gradual degradation. On Performance Measurement System traffic datasets, it shows significantly faster post-shift recovery after abrupt mutations. On the highly noisy Weather dataset, it improves anomaly recall while resisting stochastic noise overfitting. These findings establish AIGS as a practical, plug-and-play adapter for resource-constrained edge monitoring systems.

AI 总结：针对动态图对比学习缺乏显式时间演化建模的问题，提出嵌入可微Koopman算子的自监督框架KAIROS，在九个基准上异常检测达最优，最高提升23.15 ROC-AUC点。

链接：https://arxiv.org/abs/2610.02990

机构：University of Southern California（南加州大学）； Islamic University of Technology（伊斯兰理工大学）； Qatar Computing Research Institute (QCRI)（卡塔尔计算研究所）

作者：Md Abrar Jahin, Taufikur Rahman Fuad, Md Rizwan Parvez

英文摘要：Real-world interaction networks are inherently dynamic: edges form and dissolve as node behavior shifts over time. Most snapshot-based contrastive methods encode temporal dependencies implicitly in encoder weights, without an explicit model of how node representations evolve, making them brittle under distribution shifts. We propose KAIROS (Koopman-Aligned Invariant Representations for Open Dynamic Systems), a self-supervised framework that embeds a differentiable Koopman operator within a dynamic graph contrastive learning loop to linearize temporal evolution in the learned embedding space. A dual-view encoder pairs raw node features with a graph-diffused structural view and is optimized with multi-granularity contrastive objectives across temporal windows. For anomaly detection, KAIROS uses the Koopman prediction residual together with temporal inconsistency and local neighborhood deviation to separate irregular behavior from predictable graph evolution. Evaluated on nine dynamic graph benchmarks, KAIROS achieves state-of-the-art anomaly detection results on all nine datasets, with gains of up to 23.15 ROC-AUC points over prior work, while remaining competitive for unsupervised node classification. These results show that explicit dynamics modeling provides a scalable and effective inductive bias for temporal graph representation learning.

AI 总结：HyperFuse提出一种无标签快速超图嵌入方法，通过谱松弛、多尺度特征和效用加权编码器，在保持精度的同时实现13-179倍加速，适用于多超图或演化场景。

链接：https://arxiv.org/abs/2610.03211

机构：Indian Institute of Science Education and Research Thiruvananthapuram（印度科学教育与研究学院蒂鲁文南特普拉姆分校）； Indian Institute of Science Education and Research Kolkata（印度科学教育与研究学院加尔各答分校）； University of Rostock（罗斯托克大学）； Stellenbosch Institute for Advanced Study (STIAS)（斯泰伦博斯高等研究院）

作者：Megha P, Harshit Kumar, Srajan Agarwal, Anirban Banerjee, Olaf Wolkenhauer, Saptarshi Bej

英文摘要：Self-supervised hypergraph representation learning can produce informative node embeddings, but existing methods often require deep encoders trained for hundreds of epochs, making embedding generation costly even for hypergraphs with a few thousand nodes. This limits applications requiring embeddings for many or evolving hypergraphs. We present HyperFuse, a label-free pipeline for fast hypergraph representation learning. HyperFuse (i) computes structural node coordinates by maximizing a spectral relaxation of hypergraph modularity using Banerjee's hypergraph adjacency and a matrix-free operator with cost linear in node-hyperedge incidences; (ii) constructs multi-scale feature summaries and assigns bounded utility weights to hyperedges based on member stability under feature and membership masking; and (iii) trains a lightweight utility-weighted hypergraph encoder for 100 epochs using an invariance-decorrelation objective. We compare HyperFuse with TriCL, SE-HSSL, VilLain, and HypeBoy on nine public hypergraphs using six downstream classifiers and k-means clustering. On the eight datasets where all methods completed, HyperFuse required 8.7 s per dataset on average, achieving 13-179x geometric-mean speed-ups over the baselines. It achieved the highest average accuracy with five of six classifiers, while classification and clustering performance was not significantly different from TriCL and SE-HSSL. Compared with HypeBoy, HyperFuse was 13x faster and 2.1-4.1 percentage points more accurate across all classifiers. HyperFuse provides a practical approach for fast, repeated hypergraph embedding generation.

AI 总结：针对非平稳时间序列，提出iCReN框架，利用辅助变量和对比学习识别潜在状态及其瞬时与滞后因果关系，实验验证了其准确性及预测效用。

链接：https://arxiv.org/abs/2610.03452

机构：The University of Osaka（大阪大学）； RIKEN（理化学研究所）； Shiga University（滋贺大学）

作者：Tatsuya Yamada, Hiroshi Morioka, Yoshinobu Kawahara

英文摘要： Causal representation learning for time-series data aims to identify latent states and their causal relations from observations. In this setting, an important challenge is to model both lagged causal relations across observation intervals and faster causal effects that appear as instantaneous relations within an interval, while accounting for nonstationarity in time-series data. However, methods that jointly handle these causal relations and nonstationarity remain limited. To address this gap, we establish sufficient conditions for identifying latent states up to component permutation and component-wise invertible transformations, and their instantaneous and lagged causal structures up to the same permutation, using an observed auxiliary variable, such as time or a condition label, associated with changes in transition-noise distributions. Based on these results, we propose iCReN, a framework that uses contrastive learning with discrete or continuous auxiliary variables to learn latent representations and estimate their instantaneous and lagged causal structures. Experiments demonstrate accurate recovery of latent states and both instantaneous and lagged causal structures on synthetic data and the utility of the learned representations for downstream forecasting on real-world data.

AI 总结：本文提出ECHO-$k$，一种任务无关的自监督模态获取方法，利用基础模型内部表示作为代理目标，通过强化学习策略顺序选择信息丰富的模态，在预算约束下提升下游性能。

链接：https://arxiv.org/abs/2610.03454

机构：EPFL（洛桑联邦理工学院）

作者：Eeshaan Jain, Linus Bleistein, Bart Deplancke, Charlotte Bunne

英文摘要：Recent progress in multimodal, high-dimensional learning has enabled foundation models to process heterogeneous, large-scale data. However, at test time, acquiring all features or modalities can be prohibitively costly and often redundant. Sequentially selecting informative modalities is therefore critical, yet challenging when the downstream task or prediction target is unknown. To this end, we introduce ECHO-$k$, a task-agnostic and self-supervised learning principle for modality acquisition: we use a deep model's internal pretrained representations (e.g., from a foundation model) as proxy targets that summarize cross-modal information. We provide theoretical guarantees in a stylized linear setting that motivate a reinforcement learning (RL) policy for sequential modality selection. Across task-agnostic and label-free acquisition baselines, ECHO-$k$ consistently improves budgeted downstream performance across diverse foundation-model backends. Our method provides a principled route to cost-aware test-time deployment, with implications for any multimodal system where measurements are expensive or time-constrained, and downstream tasks unknown a priori.

AI 总结：ZeroMAG提出零样本多模态适配器生成框架，通过函数约束潜在空间和模态-主体-任务条件，为冻结脑电图基础模型生成适配器权重，在六个目标数据集上平均提升平衡准确率7.22个百分点，接近监督适配性能。

链接：https://arxiv.org/abs/2610.03546

机构：Brown University（布朗大学）； Stanford University（斯坦福大学）； National University of Singapore（新加坡国立大学）； Zhejiang University（浙江大学）； University of Oxford（牛津大学）； Nanyang Technological University（南洋理工大学）； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）

作者：Yubo Wang, Jingying Ma, Xinliang Zhou, Yangxuan Zhou, Jiquan Wang, Sha Zhao, Yiyuan Yang, Yi Ding, Ziyu Jia, Chenyu Liu, Cuntai Guan

英文摘要：EEG foundation models (EFMs) capture reusable knowledge from large-scale EEG data, while many EEG recordings also include companion physiological signals that provide complementary information beyond the EEG-only interface. The challenge is to preserve this pretrained knowledge while extending the EFM to heterogeneous multimodal recordings through an adaptation inferred from unlabeled target data. We introduce ZeroMAG, a zero-shot multimodal adapter generation framework that extends a frozen EEG encoder and prediction head using unlabeled target recordings, without target labels or target-side optimization. The target datasets are held out from all model training and selection in the ZeroMAG pipeline. ZeroMAG organizes companion modalities around a configuration-invariant adapter, constructs a modality-subject-task condition from unlabeled recordings and task context, and generates adapter weights in a function-constrained latent space learned from source adapters. Across six held-out target datasets and three EFM backbones, ZeroMAG improves balanced accuracy by 7.22 percentage points over EEG-only inference and 4.89 points over direct weight regression, while coming within 0.50 points of supervised multimodal adaptation on average. Ablations further show that removing functional supervision from either representation learning or conditional generation degrades generated-adapter performance, confirming the contribution of both components.

AI 总结：本文提出Wayfarer，一种通过拉普拉斯表示学习发现选项的通用深度RL智能体，在Atari 2600游戏中显著提升探索、信用分配和泛化，实现最先进性能。

链接：https://arxiv.org/abs/2610.03604

机构：University of Alberta（阿尔伯塔大学）； Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所）

作者：Erik M. Lintunen, Marlos C. Machado

英文摘要：Temporal abstractions, often instantiated as options, have long been regarded as a mechanism for accelerating credit assignment, facilitating exploration, and enabling generalisation in reinforcement learning (RL). However, developing general option discovery methods that are effective in large-scale, high-dimensional domains remains a fundamental challenge. Existing option discovery methods are either confined to relatively simple domains, depend on handcrafted or quasi-symbolic representations, or offer little improvement over learning without options. We present Wayfarer, a general, domain-agnostic, online deep RL agent that discovers options through Laplacian representation learning from high-dimensional observations and leverages them for control. We show that the resulting options simultaneously improve exploration, accelerate credit assignment, and generalise effectively to unseen settings, enabling substantially faster learning of complex policies. Wayfarer achieves state-of-the-art performance among single-stream agents on the most challenging Atari 2600 games, with the largest gains in games that require long-horizon exploration and strategic behaviour, such as Montezuma's Revenge and Private Eye.

AI 总结：RNADynBench提供2585条标准化RNA动力学轨迹，RNADynNet通过统一模型实现轨迹生成与动力学指纹提取，物理基础提升性能，RMSF相关性达0.875和0.766。

链接：https://arxiv.org/abs/2610.03712

机构：Imperial College London（帝国理工学院）； The Chinese University of Hong Kong（香港中文大学）； Technical University of Munich（慕尼黑工业大学）

作者：Yiming Huang, Lennart Bastian, Hanqun Cao, Luis Vollmers, Tolga Birdal

英文摘要： Ribonucleic acid (RNA) functions through conformational changes that are not fully captured by static structures. However, large-scale standardized RNA dynamics data remain limited, and existing approaches typically treat trajectory generation and dynamics understanding as separate objectives. Here, we introduce RNADynBench, a standardized RNA molecular dynamics (MD) benchmark with 2585 quality-controlled 100-ns all-atom trajectories and leakage-controlled splits. Building on RNADynBench, we develop RNADynNet, a unified model for RNA dynamics learning that uses a shared backbone for both trajectory generation and dynamics fingerprint extraction from a single conformer. It combines coordinate denoising, single-frame-to-trajectory alignment, and physical grounding to connect all-atom trajectory generation with dynamics representation learning. Physical grounding improves both generated dynamics and the physical information recoverable from these fingerprints. Across both test sets, including the high-flexibility challenge set, the generated trajectories achieve RMSF correlations of 0.875 and 0.766, while single-conformer predictions show comparable agreement with MD-derived dynamics. RNADynBench and RNADynNet together establish a benchmark and unified modeling framework for generating and understanding RNA dynamics.

AI 总结：本文提出残差量化（RQ）作为表示层，使上下文 Bandits 算法在严格有界内存下实现非线性表达，在 13 个数据集上多数优于非 RQ 方法，并以千倍内存缩减匹配强基线。

链接：https://arxiv.org/abs/2610.02440

机构：Meta Platforms（Meta 平台）

作者：Ami Tavory, Noam Touitou, Tal Sarig, Frank Cheng, Ido Guy

英文摘要：Contextual bandits require balancing nonlinear reward modeling with online efficiency. Tree ensembles and neural methods capture nonlinearities but require periodic retraining and large replay buffers. Linear models update efficiently per observation with O(1) memory, but are fundamentally restricted to linear reward structures. We propose Residual Quantization (RQ) as a representation layer to bridge this gap. An offline-trained RQ codebook maps continuous contexts into discrete centroid assignments across multiple levels, set dynamically through a shadow mechanism. This enables a spectrum of additive bandit algorithms that achieve nonlinear expressivity with strictly bounded memory. Across 13 datasets, RQ variants beat their non-RQ counterparts on 11 of 13 datasets, often by wide margins, while matching doubling-retrain XGBoost and neural baselines using up to 1000 times less memory.

AI 总结：提出MFPG-PPO，用低保真数据构建控制变量，稳定数据稀缺场景下的策略梯度强化学习，在模拟和真实机器人上均优于仅用高保真数据的PPO。

链接：https://arxiv.org/abs/2610.02505

机构：University of Texas at Austin（德克萨斯大学奥斯汀分校）； University of British Columbia（不列颠哥伦比亚大学）

作者：Xinjie Liu, Ruihan Zhao, Anirban Chaudhuri, Cyrus Neary, Ufuk Topcu, David Fridovich-Keil

英文摘要：Policy gradient methods for on-policy reinforcement learning (RL) can become unstable when expensive, scarce target-domain data yield noisy gradient estimates. We address this challenge by complementing limited high-fidelity (HF) target-domain data with abundant, cheap, but biased low-fidelity (LF) data, e.g., from a simplified simulator. Most existing methods directly optimize biased objectives based on LF data. In contrast, the recently introduced multi-fidelity policy gradient (MFPG) framework uses LF data solely to construct a control variate that reduces variance and improves HF data efficiency without biasing the policy gradient estimator. However, published work on MFPG is limited to REINFORCE on small-scale simulation tasks. We develop MFPG for modern actor-critic learning in GPU-parallel simulation and on a physical robot. Our analysis and experiments show that naive extensions to proximal policy optimization (PPO) can lose cross-fidelity correlation or inflate variance. Our MFPG-PPO addresses these failures by redesigning the sampling, advantage estimation, and control variate construction to preserve cross-fidelity correlation, and by monitoring estimator uncertainty to prevent variance inflation. We also introduce a budget-aware MFPG-PPO to divide a fixed sampling budget among high- and low-fidelity data sources. Across simulated robot locomotion tasks of varying LF-to-HF transfer difficulty and HF data budgets, MFPG-PPO improves upon PPO trained on HF data alone in nearly all settings, and consistently matches the performance of PPO trained with 16x more HF data on the hardest task at the smallest HF budgets. In contrast, most baselines that use LF data perform well only where direct LF-to-HF transfer succeeds. MFPG-PPO enables stable learning on a physical Franka arm using only 4 real-robot episodes per update and no human demonstrations.

AI 总结：提出学生引导教师蒸馏流程，用紧凑ModernBERT生成top-k候选并由DeBERTa-v3重排序，实现高效LLM任务路由，达到77.5%教师一致性，并揭示截断软标签的偏差问题。

链接：https://arxiv.org/abs/2610.02516

机构：PayPal

作者：Haifeng Wu, Srinivasan Manoharan, Jian Wan, Fangbo Tu, Junhua Zhao, Xin Chen

英文摘要： Zero-shot classifiers are useful for routing user requests to specialized LLM tasks, but scoring every request against a large candidate set is expensive: a zero-shot NLI classifier must evaluate one premise-hypothesis pair per label, so cost scales linearly with taxonomy size. We study a student-guided teacher distillation pipeline for a fixed taxonomy of 60 LLM task categories: a compact ModernBERT classifier predicts the full category distribution in one forward pass and retrieves a small top-k candidate set, and a larger DeBERTa-v3 zero-shot NLI classifier reranks only those candidates rather than all 60 labels; the resulting teacher labels iteratively improve the student, which produces sharper candidates for the next round. Unlike generic embedding retrieval or clustering-derived shortlists used in extreme multi-label classification, our candidate generator is trained end-to-end on the target taxonomy and is the same model serving production traffic, distinguishing it from LLM-routing work that routes between candidate models, and from concurrent System-1 encoder-classifier proposals (e.g. TypeSafe AI's Jev and the open-source Laya project) whose training methodology is undocumented or RL-based. Our best student checkpoint reaches 77.5% teacher agreement on a 200-example evaluation set, and preliminary coverage measurements show Coverage@16 of 91-100%, suggesting top-k sets retain most of the teacher's decision-relevant information. We further show truncated top-k teacher scores should not be treated as full 60-class soft targets for KL distillation: zeroing untruncated classes destroys the dark knowledge soft-label distillation depends on, introducing systematic bias rather than a harmless sparse approximation. A complete evaluation, including coverage at multiple k on a held-out set, an embedding-retrieval baseline, and a larger human-reviewed test set, remains in progress.

AI 总结：针对逐步约束的表格型CMDP，提出SVAE算法，利用安全子图结构进行方差自适应探索，实现实例相关的最优遗憾界和约束违反界，并证明其必要性。

链接：https://arxiv.org/abs/2610.02520

机构：University of Edinburgh（爱丁堡大学）； Politecnico di Milano（米兰理工大学）； University College London（伦敦大学学院）

作者：Qian Zuo, Francesco Emanuele Stradi, Leyang Xue, Sattar Vakili

英文摘要：We study online learning in episodic tabular constrained Markov decision processes with step-wise safety constraints. In such a setting, the constraints induce a safe subgraph that shapes the variance of cumulative rewards under feasible policies and, consequently, the difficulty of learning. Exploiting this structure, however, requires learning which actions are safe while controlling constraint violations. We propose Safe Variance-Adaptive Exploration (SVAE), an efficient algorithm that learns candidate safe subgraphs and performs variance-adaptive optimistic planning within them. With high probability, SVAE achieves cumulative regret of order $\widetilde{\mathcal{O}}(\sqrt{SAH\min\{\mathbb{V}_\Sigma,K\mathrm{Var}^{\star}\}}+S\sqrt{AH^3\min\{K,\mathcal{C}\}}+S^2AH^2)$ over $K$ episodes, where $H$ is the horizon of a single episode, while $S$ and $A$ are the numbers of states and actions, respectively. Here, $\mathrm{Var}^{\star}$ is the maximum return variance among safe policies, $\mathbb{V}_\Sigma$ is the variance accumulated before the first unsafe action is encountered, and $\mathcal{C}$ captures the statistical complexity of eliminating actions incorrectly considered potentially safe. SVAE additionally attains $\widetilde{\mathcal{O}}(H\sqrt{SAK}+S^2AH^2)$ step-wise constraint violation and a gap-dependent violation bound that is polylogarithmic in $K$. Finally, we establish a lower bound showing that dependence on these instance-specific quantities is unavoidable.

AI 总结：本文提出奖励膨胀，即在训练中逐步缩放奖励，作为强化学习的健康刺激，通过隐式近期加权和维持梯度信号提升适应性与可塑性，并在ALE和MuJoCo任务上验证其有效性，同时提出自适应变体Fed。

链接：https://arxiv.org/abs/2610.02545

机构：Seoul National University（首尔大学）

作者：Ganghun Lee, Minji Kim, Minsu Lee, Byoung-Tak Zhang

英文摘要：Reward serves as the primary learning signal in reinforcement learning (RL). However, while reward magnitudes are typically held fixed throughout training, their temporal modulation remains underexplored. In this paper, we propose reward inflation, a gradual scaling of rewards over the course of training, and show that it can act as a healthy stimulus for RL. Theoretically, reward inflation induces an implicit recency weighting that upweights recent transitions during policy updates, enabling faster adaptation. We further show that, by sustaining gradient signals as the policy saturates, reward inflation suppresses the emergence of dormant neurons and helps preserve plasticity. Empirical results on ALE games and MuJoCo tasks corroborate these findings, showing that an appropriate level of reward inflation benefits a broad range of tasks. Finally, we introduce Fed, an adaptive variant that adjusts the inflation level on the fly, and find that it often improves upon fixed inflation.

AI 总结：针对离线多智能体强化学习中生成策略与价值优化的权衡，提出SCOUT框架，通过测试时动作细化结合流匹配先验与分解值函数，利用Stein变分梯度下降实现可扩展协调，在基准上取得最优性能。

链接：https://arxiv.org/abs/2610.02554

机构：The University of Texas at Austin（德克萨斯大学奥斯汀分校）

作者：Dongsu Lee, Haoran Xu, Amy Zhang

英文摘要：Offline multi-agent reinforcement learning (MARL) faces a persistent trade-off. Expressive generative policies can represent multi-modal coordination in the data, but cannot distinguish high-value regions, while value-optimized policies exploit the learned Q-function but collapse the multi-modal into a single dominant mode. A single agent's mode collapse can break joint coordination, and simultaneous drift across agents can push the joint policy into unseen regions of the action space. We propose scalable coordination via optimal unified transport (SCOUT), the first offline MARL framework to combine a generative foundation model with a learned value function through test-time action refinement. SCOUT trains two decoupled components: a flow-matching behavioral prior and a decomposed value function. At test-time, it transports behavioral samples toward high-value regions via Stein variational gradient descent. The number of transport steps controls adaptive test-time scaling, replacing a fixed regularization coefficient. Under the individual-global-max (IGM) principle, we prove a single-term KL bound on the joint soft-value gap that vanishes as transport converges, with an irreducible additive residual proportional to the IGM violation. Empirically, SCOUT achieves the best average performance across discrete and continuous offline MARL benchmarks and yields performance improvements in all offline-to-online configurations.

AI 总结：提出测试时校准学习（TTCL），一种无标签框架，在未标注目标数据上联合优化推理准确性和置信度校准，显著提升模型性能。

链接：https://arxiv.org/abs/2610.02695

机构：Hong Kong Baptist University（香港浸会大学）

作者：Zizhuo Zhang, Xiong Peng, Jingwei Sun, Rong Yao, Shixiong Kai, Mingxuan Yuan, Bo Han

英文摘要： Reliable large language models (LLMs) must not only produce accurate answers but also express confidence that faithfully reflects their probability of being correct. Such calibration is essential for identifying uncertain predictions and supporting reliable decision-making in real-world deployment. Recent studies incorporate calibration learning into reinforcement learning (RL), jointly optimizing answer correctness and verbalized confidence using ground-truth correctness supervision. However, their reliance on labeled data limits their applicability in practical test-time settings, where ground-truth labels are unavailable and calibration may need to adapt to newly encountered target tasks. To address this challenge, we propose Test-Time Calibration Learning (TTCL), a label-free framework that jointly adapts reasoning accuracy and verbalized confidence directly on unlabeled target-task data. Specifically, TTCL derives self-supervision signals for both correctness and calibration from multiple model-generated responses, enabling calibration learning at test time without ground-truth labels. Theoretical analysis further establishes TTCL as a bounded surrogate for the ideal calibration objective. Extensive experiments on mathematical reasoning and factual question answering demonstrate that TTCL consistently improves both accuracy and calibration across diverse models and tasks. On base models, TTCL achieves an average relative accuracy improvement of +40.13% and an ECE reduction of +70.80% across eight benchmarks. Moreover, TTCL can further improve both accuracy and calibration for already calibrated models under domain shift, particularly when source-domain calibration transfers poorly to target tasks. In the math-to-factQA setting, TTCL achieves an average relative accuracy gain of +20.35% and reduces ECE by +53.83%. The source code is released at this https URL.

AI 总结：本文提出结合深度神经网络与线性规划归一化的函数逼近方法，以减少高维动态规划中的贝尔曼误差，并在收益管理网络容量控制问题上验证了其竞争力。

链接：https://arxiv.org/abs/2610.02730

机构：Independent Consultant（独立顾问）

作者：Haining Yu

英文摘要：This paper proposes a new functional approximation approach to reduce Bellman error in high-dimensional dynamic programming and Reinforcement Learning problems. Using a classic dynamic programming problem (network capacity control in revenue management) as the motivational example, the paper illustrates that deep neural networks and linear programming approximation algorithms can be combined to derive approximate solutions to dynamic programming problems. Simulation results show the proposed approximation algorithms achieves competitive performance when compared with benchmark.

AI 总结：提出前瞻性后见之明（PH）自校准训练原则，利用预测-现实差距加权梯度，在单轮与多轮任务中同时提升性能与校准，且适用于不同模型规模。

链接：https://arxiv.org/abs/2610.02740

机构：Salesforce AI Research（赛富时人工智能研究院）

作者：Jiaxin Zhang, Xiangyu Peng, Qinglin Chen, Yu Li, Hiroaki Hayashi, Chien-Sheng Wu

英文摘要：Reinforcement learning for long-horizon agents relies on purely retrospective training signals: credit is assigned only after observing environmental consequences, leaving the agent's belief at action time invisible to the gradient. We introduce Prospective Hindsight (PH), a self-calibrating training principle that augments any retrospective base method with a signal derived from the gap between the agent's prospective prediction (before feedback) and the retrospective evaluation (after feedback). This per-rollout surprise identifies samples where the agent's self-model is most inaccurate and amplifies their gradient contribution through a stop-gradient surprise-weighted advantage. Since the prospective predictor shares parameters with the policy, the two co-evolve, progressively shifting focus to the agent's remaining blind spots. We connect this principle to a privileged-information gap and show that minimizing the surprise residual provides a descent pathway on the agent's miscalibration rate; calibration thus emerges as a byproduct of optimization rather than from an added objective. On single-turn verifiable tasks and a multi-turn personal-agent task (under GRPO, on-policy distillation, and their combination), PH improves both task performance and calibration, with consistent gains across model scales. Notably, the dominant miscalibration mode shifts structurally between regimes, overconfident failures in single-turn, underconfident successes in multi-turn, yet the same training principle addresses both successfully.

AI 总结：针对1比特反馈下的固定置信度最佳臂识别，提出基于随机阈值查询的均值估计原语，并嵌入候选-挑战者算法，实现间隙自适应样本复杂度，且证明对数惩罚下界。

链接：https://arxiv.org/abs/2610.02771

机构：Hanoi University of Science and Technology（河内科技大学）； Quantum AI & Cyber Security Institute, FPT Corporation（FPT公司量子人工智能与网络安全研究院）

作者：Khang Luong, Dinh Thai Son, Hoang Ta, Hung The Tran, Tuan Quang Dam

英文摘要：We study fixed-confidence best-arm identification under strict 1-bit feedback constraints. At each round, the learner selects an arm and a query set, and receives only a single bit indicating whether the sampled reward belongs to that set. We consider a distribution-free finite-variance setting with arm-wise localization, where direct empirical mean estimation is no longer available and clipping becomes unavoidable. We first formulate a time-uniform 1-bit mean-estimation primitive based on randomized threshold queries and a clipped tail-integral identity. We then embed this primitive into candidate-challenger best-arm identification algorithms. A fixed-clipping algorithm gives a simple anytime $(\epsilon,\delta)$-PAC guarantee, while a phased adaptive-clipping algorithm matches the clipping level to the current resolution and yields a gap-adaptive sample complexity. We also prove a $K$-arm worst-case information-theoretic lower bound showing that the logarithmic penalty caused by finite-variance 1-bit feedback is intrinsic. This bound matches the leading dependence of the phased algorithm up to lower-order $\log\log$ factors.

AI 总结：针对基于量规的强化学习无法定位具体决策贡献的问题，提出先用量规特权在线策略蒸馏提供密集令牌监督，再优化量规奖励的两阶段框架，在健康与科学任务上取得最优性能且奖励黑客迹象有限。

链接：https://arxiv.org/abs/2610.02781

机构：New York University（纽约大学）； Meta

作者：Xinpeng Wang, Wei Shi, Yu-Chia Chen, Maria Zontak, Yun He, Richard Yuanzhe Pang

英文摘要：Many useful language-model tasks cannot be evaluated by exact outcome verification. Rubric-based reinforcement learning (RL) addresses this issue by scoring open-ended responses against explicit criteria. However, because the reward is assigned after the complete response, the training signal does not directly identify which individual decisions contributed to the final score. We propose a two-stage training framework that uses rubrics first as privileged teacher context for dense token-level supervision, then as rewards for further RL. In the first stage, rubric-privileged on-policy distillation (RP-OPD), a student without access to the rubric matches a rubric-aware teacher's next-token distributions at student-generated prefixes. In the second stage, RL directly optimizes the rubric reward and improves beyond the observed distillation plateau. We evaluate the framework on health and science tasks using open-weight models. Across HealthBench, ResearchQA, and RubricHub Science, we compare post-training methods and vary the amount of SFT or RP-OPD training before RL, finding that our two-stage framework achieves the highest scores among the methods evaluated. RP-OPD + RL shows limited signs of reward hacking on RubricHub Science, whereas the SFT + RL baseline increasingly receives high rewards for claims of rubric compliance without providing the required content. These findings support using rubrics to guide on-policy distillation before applying rubric-based RL.

AI 总结：本研究揭示RLVR中GRPO算法导致策略容量收缩引发灾难性崩溃，提出网格学习暴露多策略并防主导，在多个基准上提升达13.4个百分点。

链接：https://arxiv.org/abs/2610.02835

机构：Peking University（北京大学）

作者：Qiyuan Huang, Tianshi Xu, Meng Li

英文摘要：During post-training of large language models (LLMs) with Reinforcement Learning with Verifiable Rewards (RLVR), GRPO-style algorithms can exhibit severe late-stage collapse. Prompt-based probing reveals that this is not benign strategic pruning, but a harmful contraction of effective strategy capacity that makes distinct reasoning strategies increasingly inaccessible. To characterize this phenomenon, we define strategies through trajectory-level policy-update interactions and develop a unified theoretical framework combining optimization dynamics and information theory. We prove that major RLVR objectives progressively concentrate probability mass onto a single strategy, while sustaining nontrivial task accuracy requires a minimum strategy capacity. The conflict between these two results provides a mechanistic explanation for catastrophic collapse. We further derive the {Mirrored Entanglement Index (MEI)} as a lightweight online warning signal. To prevent collapse, we propose \textbf{Mesh Learning}, which exposes multiple reasoning strategies and prevents any single strategy from dominating optimization. Across AIME26, AIME25, MATH-500, GPQA, and LiveCodeBench, Mesh Learning consistently outperforms strong baselines across Qwen and Phi model families, with gains of up to 13.4 pp and 11.5 pp, respectively. These results establish strategy preservation as a key principle for stable RLVR. Code is available at this https URL.

AI 总结：本文从数学上分解富集轨迹修正的梯度误差为尺度、旋转和方差，提出序贯蒙特卡洛权重修正机制，并在OpenMathReasoning上验证其避免稀疏域崩溃的作用。

链接：https://arxiv.org/abs/2610.02846

机构：University of California-San Diego（加州大学圣迭戈分校）； Microsoft Research（微软研究院）

作者：Jinwoo Kim, Shraddha Barke

英文摘要：When rewards are sparse, reinforcement learning with verifiable rewards (RLVR) often uses hints or intermediate guidance to generate more successful rollouts. This enrichment biases policy-gradient updates unless corrected via importance weights, but existing methods omit correction or truncate importance weights in order to avoid the high variance of correction. It thus remains unclear what exactly is gained or lost in RLVR by correcting enriched rollouts. We show, mathematically, that omitted or truncated correction implicitly reweights the defined reward, and we decompose the resulting gradient error into scale, rotation, and variance to explain their distinct effects on learning. To make correction practical, we develop a novel sequential Monte Carlo (SMC) weight correction mechanism that, under stability and particle-order assumptions, tempers the exponential compounding of standard correction variance over the length of a sample to an additive accumulation. We then apply our analysis of enrichment to interpreting the results of a fine-tune of Qwen3-1.7B on a sparse band of OpenMathReasoning, establishing a concrete mechanism of how enrichment, both corrected and uncorrected, helps avoid collapse in sparse domains. Our main contribution is to understand, in general, how enrichment and correction can affect training, as opposed to claiming that either mode of operation is superior to unenriched RL.

AI 总结：本研究揭示实验框架细节可逆转陈旧数据强化学习方法排名，提出PTH检查工具，验证后TIS与SAN性能持平，贡献了关键细节特征与参考结果。

链接：https://arxiv.org/abs/2610.02911

机构：The University of Melbourne（墨尔本大学）

作者：Taiheng Pan

英文摘要：Methods for training language models on stale samples are judged by comparisons against importance-corrected baselines. We show that details of the experimental harness can reverse the observed ranking of methods, and we introduce PTH (Probe The Harness), a set of checks that makes the harness visible. Our case is a comparison between SAN, a behaviour-free method, and truncated importance sampling (TIS) on verl and in a single-GPU trainer, in which SAN first finished ahead in both stacks. Four details of the harness changed this comparison: the PPO ratio was taken against the learner's own recomputed probabilities, the data seed did not reach the TIS arm, the replay queue reused its first batch for 33 updates, and two loss normalisers differed from their description. In each case the logged quantity looked consistent with a working setup, while the quantity that defines the comparison went unchecked. With the harness checked, TIS matches SAN on verl, and in the trainer TIS learns steadily while SAN keeps a margin. We contribute the signature of each detail and its effect on the comparison, reference results for TIS and uncorrected GRPO under sampler lag, and the PTH checklist.

AI 总结：本文提出层次化模型强化学习框架，利用低维动力学嵌入共享结构，从无动作记录学习可迁移控制策略，在Lorenz-63和双摆系统上验证了提升的迁移性能与机制分析能力。

链接：https://arxiv.org/abs/2610.03065

机构：Hector Institute for AI in Psychiatry (HITKIP)（赫克托人工智能精神病学研究所）； Central Institute of Mental Health (CIMH)（中央精神健康研究所）； Heidelberg University（海德堡大学）； Interdisciplinary Center for Scientific Computing (IWR)（跨学科科学计算中心）； Hertie Institute for AI in Brain Health（赫蒂人工智能脑健康研究所）； University of Tübingen（蒂宾根大学）

作者：Niklas Emonds, Georgia Koppe

英文摘要：Learning control from action-free recordings is challenging because intervention effects are unobserved and policies may exploit errors in reconstructed dynamics. We present a hierarchical model-based reinforcement learning framework that uses shared structure across related systems to learn system-specific control policies from action-free recordings. A hierarchical dynamical system reconstruction model captures shared dynamics and individual variation through low-dimensional embeddings. These embeddings are then reused to parameterize shared policy and value networks, linking differences in reconstructed dynamics to differences in control. Policies are trained entirely via simulation under an explicit intervention model with additive latent perturbations. Piecewise-linear recurrent neural networks enable mechanistic analyses of the controlled dynamics, while decoder-based constraints make the immediate effects of interventions interpretable in observation space and permit interventions on one modality while protecting another from direct manipulation. On Lorenz-63 and double-pendulum systems, hierarchical policies improve transfer over independently trained policies. On Lorenz-63, they also achieve a higher mean reward than repeated planning with the same reconstructed models, perform comparably to methods trained with controlled interactions, and generalize to systems absent from policy training after embedding inference alone. Applications to neural-behavioral recordings demonstrate suppression of predicted movement under constrained neural perturbations. Together, these findings show how shared dynamical representations support transferable control and mechanistic hypothesis generation from action-free recordings.

AI 总结：本研究提出AMSC方法，利用Wasserstein任务嵌入估计相似性并组合先前策略，在终身强化学习中实现高效迁移，实验显示更高性能且无遗忘。

链接：https://arxiv.org/abs/2610.03119

作者：Saptarshi Nath, Inish M. D'Souza, Antonio Carta, Soheil Kolouri, Andrea Soltoggio

英文摘要：In lifelong reinforcement learning, retaining previously learned policies is not sufficient for effective transfer to a new task. Useful knowledge may be distributed across several prior policies, and its relevance may change as the learner acquires experience. One hypothesis is that task similarity can be effectively used in a continual learning setting to find and combine previously learned policies. To test it, Adaptive Mask Selection and Composition (AMSC) is designed to estimate similarity from online experience via non-parametric Wasserstein task embeddings from state-action-reward samples. The z-score-normalized sparsemax of the similarity scores are used to derive a variable-size support to periodically choose and weight policies to form a prior when learning a new task. On CT-graph and MiniGrid, AMSC achieves higher mean performance and forward transfer than the evaluated modular composition baselines while exhibiting no forgetting. Results on Continual World suggest that identifying relevant prior knowledge and determining its layer-specific composition may require additional layer-specific tuning. Ablations show that selecting relevant sources and determining how strongly to reuse them are central to these gains. Independently measured pairwise transfer is also positively associated with task-embedding similarity. These results indicate that task similarity can be an effective criterion to select and weight specific knowledge for reuse in lifelong reinforcement learning.

AI 总结：针对硬件感知NAS中RL循环破坏共形预测可交换性假设的问题，提出在线共形校准方法，实现可操控覆盖率，在保持精度下剪除25-50%评估，并优于基线。

链接：https://arxiv.org/abs/2610.03127

机构：Vicomtech Foundation, Basque Research and Technology Alliance (BRTA)（维科姆技术基金会，巴斯克研究与技术联盟（BRTA））

作者：Pedro Brandimarte, Nerea Aranjuelo, Marcos Nieto, Oihana Otaegui

英文摘要：Hardware-aware neural architecture search (NAS) is dominated by evaluation cost: every architecture must be trained before its reward is known. Conformal-prediction filters cut this cost by pruning candidates whose predicted-reward upper bound misses a threshold, with a distribution-free guarantee that at most a fraction $\delta$ are wrongly discarded. That guarantee assumes exchangeability between calibration and test candidates, which the surrounding reinforcement-learning (RL) loop violates: the policy's proposals improve as search proceeds and, in layer-by-layer construction, shift within every episode. We replace one-shot quantile estimation with online feedback control (Adaptive Conformal Inference, with tuning-free, locally-adaptive, and group-conditional variants), restoring steerable coverage: dialing the target delivers it, monotonically and reproducibly, for arbitrary sequences. Across three neural-network architecture families and both single-step and sequential search (three seeds), it tracks every requested level to within ${\sim}10^{-3}$ while pruning 25-50% of evaluations at no measured accuracy cost, whereas static calibration loses control of its coverage and a Gaussian-process baseline stays conservative regardless of the request. Finally, used as an acquisition function on one constrained testbed, the same optimistic bound beats random search, a gain that fixed optimism already carries and online calibration sharpens. The source code is available at this https URL.

AI 总结：本文提出防御性策略梯度算法，在无重要性权重方差假设下达到$O(\epsilon^{-3})$样本复杂度，并通过广义黑盒模型下界证明其速率最优，优于普通策略梯度。

链接：https://arxiv.org/abs/2610.03165

机构：Politecnico di Milano（米兰理工大学）； Budapest University of Technology and Economics（布达佩斯科技经济大学）； University of Milan（米兰大学）

作者：Gabor Paczolay, Matteo Papini, Alberto Maria Metelli, Istvan Harmati, Marcello Restelli

英文摘要：Several variance-reduced versions of REINFORCE based on importance sampling achieve an improved $O(\epsilon^{-3})$ sample complexity to find an $\epsilon$-stationary point, under an unrealistic assumption on the variance of the importance weights. In this paper, we propose the \algo (Defensive Policy Gradient) algorithm, based on defensive importance sampling, which achieves the same rate without any assumption on the variance of ordinary importance weights. We also establish lower bounds in a generalized black-box policy-optimization model that hides states and actions and permits parameter-dependent rewards. In this model, the optimal rates are $\Theta(\epsilon^{-4})$ with bounded-variance one-policy feedback and $\Theta(\epsilon^{-3})$ with mean-square-smooth coupled two-policy feedback. Under standard policy-regularity conditions, REINFORCE and \algo realize the corresponding oracle conditions and attain the $O(\epsilon^{-4})$ and $O(\epsilon^{-3})$ upper bounds, respectively. Although the lower bounds do not apply directly to the classical MDP interaction model in which these algorithms operate, this correspondence provides oracle-level evidence that the faster rate of \algo is optimal and genuinely separated from that of vanilla policy gradient.

AI 总结：针对长视界LLM智能体稀疏奖励下信用分配不精确的问题，提出AdaStep自适应步骤信用加权方法，通过最优收缩系数平衡局部与全局信号，在低计算成本下提升多环境性能。

链接：https://arxiv.org/abs/2610.03223

机构：Tsinghua University（清华大学）； Nanjing University（南京大学）； Xiaomi Inc.（小米公司）

作者：Xin Wang, Wenhao Wu, Menghao Zhang, Zhi Wang, Kun Shao, Jian Luan

英文摘要：Long-horizon LLM agents are typically trained with sparse outcome rewards, making trajectory-level objectives too coarse to distinguish the contribution of individual decisions. Step-level credit assignment provides finer-grained supervision, but its estimates can be unreliable because observed returns also depend on subsequent actions, environment transitions, and trajectory length. We propose AdaStep, an Adaptive Step-credit weighting method that controls how strongly each group-derived local advantage modifies the trajectory-level signal. We formulate this weighting as a mean-squared-error estimation problem for the latent step advantage and, under an explicit conditional sampling assumption, derive an optimal per-state shrinkage coefficient. The coefficient admits a signal-to-total-variance interpretation: it preserves local credit when return variation is attributable to the selected action and suppresses it when variation is dominated by downstream randomness. AdaStep requires only lightweight scalar computation, with no critic, additional rollouts, or extra model inference. Experiments with three model backbones on ALFWorld, WebShop, and ScienceWorld show consistent improvements over baselines at low computational cost.

AI 总结：针对稀疏奖励长时程任务，提出双向Voronoi偏置探索课程（BVER），从目标与初始状态两端同时扩展，加速目标条件强化学习，实验显示显著优于单侧扩展方法。

链接：https://arxiv.org/abs/2610.03395

机构：ETH Zürich（苏黎世联邦理工学院）； NVIDIA（英伟达）

作者：Juri Pfammatter, Kaixian Qu, Clemens Schwarke, Victor Klemm, Marco Hutter

英文摘要：Long-horizon tasks with sparse rewards pose an exploration bottleneck for goal-conditioned reinforcement learning: a policy started from the initial state rarely reaches the goal and receives no learning signal. Reference motions, hand-designed curricula, and shaped rewards supply this signal but require demonstrations or task-specific engineering; automatic start-state and goal curricula avoid this but typically expand from one side only, so the full distance to the target must be covered from that side. We propose the Bidirectional Voronoi-biased Exploration curriculum for Reinforcement learning (BVER), which expands from both ends at once. Inspired by bidirectional RRT planning, BVER grows start states outward from the goal and goals outward from the initial state distribution, biases both toward unexplored task space, and steers them toward each other, training one goal-conditioned policy on both. On point-mass mazes, quadrupedal box climbing, and robot-arm ring-on-peg transfer, BVER learns faster than all compared reference-free curricula. On box climbing, it reaches 95% success on a 0.4 m box in roughly 65% fewer iterations than the best of them, is the only one of them to learn to climb a 0.7 m box, and yields a policy robust to start, goal, and yaw variation. Without a demonstration, it approaches the sample efficiency of reference-based curricula on the 0.4 m box and on ring-on-peg transfer. Ablations show that expanding from both ends outperforms either direction alone.

AI 总结：本研究探讨阶段结构强化学习中单一共享策略与多策略的优劣，提出基于机制持续时间的阶段分解方法，并通过实验验证四个关键假设。

链接：https://arxiv.org/abs/2610.03475

机构：Imperial College London（伦敦帝国学院）

作者：Guilhem Loussouarn, Nancy Nayak, Kin K. Leung

英文摘要： Many reinforcement-learning (RL) problems are non-stationary yet structured and can be decomposed into phases, each with its own transition probabilities and reward functions. When the phase sequence is known, the common solution augments the state with information to satisfy the Markovian property and applies standard RL techniques. However, prior work finds that the multi-policy approach for different phases can outperform a single state-augmented policy shared among the phases, for reasons that remain unclear. In this work, we first show that the shared policy can theoretically achieve performance of any multi-policy solution. However, whether a multi-policy solution can perform better than the corresponding single shared policy in practice depends on function approximation, learning and optimization processes, as well as, for multi-policy solutions, the sample efficiency and loss of continuity from one policy to another. We propose a regime-based phase decomposition method to identify which policy can provide better performance. The method is based on consideration of the duration of transient system dynamics relative to the duration of the quasi-stationary period. Numerical experiments are conducted with different non-stationary RL problems to validate our four major hypotheses: (a) longer phase durations favor multi-policies, (b) the heterogeneity between phases increases the burden on single policy, (c) multi-policies need sufficient data for each phase, and (d) environment-specific transition dynamics between phases can affect which policy is preferable.

AI 总结：提出自适应干预智能体UniIntervene++，通过半马尔可夫决策过程学习控制分配，动态决定干预时机与方式，在真实世界操作任务中成功率89.67%，干预率仅0.77%。

链接：https://arxiv.org/abs/2610.03620

机构：Nanyang Technological University（南洋理工大学）

作者：Yudong Lin, Haoyuan Deng, Zhuoxuan Yuan, Zaijia Yang, Yuanjiang Xue, Ziwei Wang

英文摘要：Online reinforcement learning (RL) enables robot policies to improve through physical interaction, but the assistance they require changes as their competence evolves. Existing intervention strategies based on offline estimates or fixed decision rules can therefore become mismatched to the current policy. To address this, we propose UniIntervene++, an adaptive intervention agent that learns to allocate control between autonomous execution and heterogeneous assisted behaviors during online RL. Specifically, UniIntervene++ first formulates the evolving RL policy, trajectory correction, and a task-structured CodePolicy as Options in a unified semi-Markov decision process and learns their relative values online. Building on this, competence-adaptive intervention periodically probes the RL policy through unassisted execution, keeping control allocation responsive to its evolving capability. Finally, coupled experience learning allows assisted behaviors to improve the RL policy, whose evolving outcomes in turn reshape future intervention decisions. In this way, UniIntervene++ jointly determines when to intervene, how to intervene, and when to return control as the RL policy improves. Across five real-world manipulation tasks, UniIntervene++ achieves an average success rate of 89.67%, outperforming all baselines by at least 6 percentage points, while reducing human intervention to 0.77%, a relative reduction of at least 94.6% from the best baseline. Code is available in our \href{ this https URL }{GitHub repository}.

AI 总结：本文研究成功条件化策略在随机环境中的收敛性，证明其在广泛MDP类上收敛到最优策略，并给出折扣和单周期情形下的收敛速率。

链接：https://arxiv.org/abs/2610.03642

机构：Massachusetts Institute of Technology（麻省理工学院）

作者：Matthew Brun, Xu Andy Sun

英文摘要：Success conditioning is a strategy for improving decision-making policies in stochastic environments; it updates a policy by increasing the probability of taking actions that yield successful outcomes. Success conditioning is common to many reinforcement learning applications, yet its limiting behavior and convergence rates are not well understood. In this work, we demonstrate that success conditioning converges to an optimal policy on a broad class of Markov decision processes (MDPs). We also derive convergence rates in some common settings. For discounted MDPs, we prove convergence within $\mathcal{O}(1/\varepsilon^p)$ iterations to an $\varepsilon$-optimal policy, where the exponent $p$ depends on problem data. For single-period MDPs, such a policy is obtained within $\mathcal{O}(\log(1/\varepsilon))$ iterations.

AI 总结：研究非平稳多臂赌博机中何时允许遗忘，提出E-过程授权的汤普森采样（e-ATS），通过随时有效的E-过程控制折扣状态启用，在平稳性下以$\alpha_E$概率保持乐观采样，实验显示授权影响因环境而异。

链接：https://arxiv.org/abs/2610.03646

机构：UC Santa Barbara（加州大学圣塔芭芭拉分校）； Purdue University（普渡大学）

作者：Mayand Gulati, Kerong Wang, WeiChen Au

英文摘要：Stationarity rewards memory, but after a change the same history can mislead. We ask when forgetting should be permitted. E-process-authorized Thompson sampling (e-ATS) gives each arm full-history and discounted Beta states. An anytime-valid e-process first authorizes the discounted state, then a reversible relevance score controls its influence. Before authorization, e-ATS exactly follows optimistic Thompson sampling (OTS). Under a Beta-Bernoulli prior-predictive stationary model, e-ATS's probability of ever departing from OTS is at most the chosen $\alpha_E$, without fitted thresholds. Relative to e-ATS, removing authorization increased mean normalized dynamic pseudo-regret by $38.4\%$ on the registered suite but reduced it by $7.5\%$ on the literature-derived replay suite. Therefore, evidence controls when adaptation begins, not whether it always helps.

AI 总结：针对策略梯度在分类中的短视问题，提出视界损失，通过截断交叉熵的总误差，在训练中从交叉熵过渡到精确策略梯度，在MNIST和ImageNet上提升了准确率。

链接：https://arxiv.org/abs/2610.03667

机构：Google DeepMind（谷歌DeepMind）

作者：Ian Osband

英文摘要：Policy-gradient methods are central to modern reinforcement learning, including LLM post-training. When they struggle, the usual suspects are exploration, credit assignment and action-sampling noise. Classification has none of them. A classifier is a policy whose expected reward, its \emph{expected accuracy}, is the probability it assigns to the correct label, and because that label is known, the policy gradient is exact and smooth. Yet exact policy gradient loses to cross-entropy, even on expected accuracy. The exact gradient is myopic: it values an update only by what it buys now, but each update also sets where the next one starts, so an update's value depends on how much learning remains. Viewed this way, cross-entropy is patient accuracy, the total error an example would pay if its log-odds rose at unit speed forever, while exact policy gradient is the zero-horizon limit. Truncating this total at the learning that remains yields the horizon loss, a one-line change that moves from cross-entropy toward exact policy gradient as training runs out. In a simple allocation model, it provably escapes the trap that catches each endpoint. On MNIST and on ImageNet with ResNet-50, ResNet-101 and ViT-S/16, the horizon loss improves top-1 accuracy over cross-entropy at a flat learning rate, and the gain grows with label noise.

AI 总结：LESSER利用输出层梯度近似全参数梯度进行训练后数据选择，仅需前向传播，将SFT和RL的FLOP成本分别降低9.7倍和3.0倍，同时保持下游性能。

链接：https://arxiv.org/abs/2610.03702

机构：University of Pennsylvania（宾夕法尼亚大学）； University of Texas at Austin（德克萨斯大学奥斯汀分校）

作者：Lyuxin David Zhang, Eric Wong, Surbhi Goel, Anton Xue

英文摘要：The choice of post-training data for large language models substantially affects downstream performance. Gradient-based data selection is a popular approach that ranks training data by how well their gradients align with those of a small validation set. However, ranking with full-parameter gradients requires an expensive backward pass on every sample, making computation intractable for large candidate pools. This raises a natural question: can we approximate full-gradient features at a fraction of the cost? Conveniently, we find that output-layer gradients suffice for effective data selection, yet require only the cheaper forward pass. We implement this as LESSER, a drop-in wrapper for selection methods that reduces the feature-extraction FLOP cost by $9.7\times$ for SFT and $3.0\times$ for RL benchmarks, while tracking full-gradient performance on downstream tasks. Empirically, we find that even when output-layer and full gradients rank individual samples differently, they select batches with aligned gradients.

AI 总结：本研究利用扩散模型生成合成传感器数据，通过预训练加微调策略提升CABiGRU在饮食活动识别中的性能，在DEO数据集上达到90.6%的平衡准确率，有效缓解类别不平衡问题。

链接：https://arxiv.org/abs/2610.02292

作者：E. Riveros (1), D. Vega-Oliveros (2), A. Soriano-Vargas (3), A. Rocha (1) ((1) Institute of Computing, State University of Campinas, Campinas, Brazil, (2) Institute of Science and Technology, Federal University of Sao Paulo, Sao Jose dos Campos, Brazil, (3) Universidad de Ingenieria y Tecnologia, Lima, Peru)

英文摘要：Human activity recognition (HAR) is increasingly important for healthcare, well-being, and daily monitoring ap- plications, for which detecting alimentary activities such as eating and drinking can provide actionable insight into dietary habits and chronic disease management. HAR systems, however, often underperform on subtle and underrepresented classes, limiting their utility in real-world dietary monitoring. This work builds upon CABiGRU, a convolutional architecture with Bidirectional GRU layers, multi-head attention, and residual connections, designed to capture discriminative temporal patterns from smart- watch accelerometer, gyroscope, and magnetometer data. To improve CaBiGRU's generalization and reduce underfitting in the minority class, we leverage synthetic sensor data windows using a diffusion model and adopt a two-stage training strategy: pre-training CABiGRU on synthetic data, followed by fine-tuning on the real-world data. On the DEO (drinking/eating/other) dataset, the proposed pipeline achieves a balanced accuracy of 90.6%, improving over a strong supervised baseline and showing the benefits of diffusion-based synthetic pre-training for recognizing alimentary activities and representing a step forward dealing with unbalanced classes. These results suggest that combining diffusion-generated data with targeted fine-tuning enhances robust recognition of dietary behaviors, supporting more reliable deployment in healthcare and nutrition-monitoring settings.

AI 总结：提出多模态超图流匹配框架MHG-FM，联合生成结构-功能脑连接并跨模态翻译，通过超图编码和双交叉注意力保留高阶关系，在HCP-YA上优于基线且采样快8倍。

链接：https://arxiv.org/abs/2610.02722

机构：Monash University Malaysia（莫纳什大学马来西亚校区）； University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）； Nanyang Technological University（南洋理工大学）

作者：Chyong Yi Poh, Hwa Hui Tew, Junn Yong Loo, Raphaël C.-W. Phan, Fuad Noman, Pew-Thian Yap, Chee-Ming Ting

英文摘要：Structural connectivity (SC) and functional connectivity (FC) provide complementary information on interactions between brain regions and are widely used in neuroimaging studies of neuropsychiatric disorders. Generative modelling can alleviate the scarcity of large-scale paired SC-FC data, but existing approaches typically use pairwise graphs that capture only dyadic interactions and often generate SC and FC independently, limiting preservation of higher-order structure-function relationships. We propose a Multimodal Hypergraph Flow Matching (MHG-FM) framework for joint SC-FC connectivity generation and cross-modal translation. MHG-FM constructs modality-specific hypergraphs, learns higher-order representations with Hypergraph Neural Network (HGNN) encoders, and performs bidirectional cross-modal fusion using Dual Cross-Attention (DCA). A variational autoencoder maps the fused representations to a compact latent space, where conditional flow matching enables connectivity synthesis and multimodal translation via latent transport. Experiments on the Human Connectome Project Young Adult (HCP-YA) dataset show that MHG-FM outperforms several state-of-the-art baselines in reconstruction quality, topology preservation, distributional similarity, and SC-FC coupling, while achieving approximately 8x faster sampling than a matched diffusion backbone.

AI 总结：本文提出上下跳跃（JUD），首个面向离散有序数据的去噪器扩散模型家族，支持双向扰动，在不同数据模态上取得竞争性结果。

链接：https://arxiv.org/abs/2610.02754

机构：Brown University（布朗大学）； University of Toronto（多伦多大学）； Sakana AI

作者：Yair Shenfeld, Ricardo Baptista, Stefano Peluchetti

英文摘要： Diffusion models are highly developed in continuous spaces for image and video domains. Recently, major advances have been made for discrete diffusion models for categorical data, specifically in the language domain. In contrast, diffusion models for discrete integer-valued data are less developed, despite the prevalence of this modality, ranging from images and music to gene counts. We introduce Jumping Up and Down (JUD)---a new family of denoiser-based diffusion models for discrete ordinal data. This is the first family of diffusion models for ordinal data which centers around training denoisers, which at the same time allows for bi-directional (up and down) perturbations of the data. The simplicity of the training objective, combined with the flexibility of bi-directional perturbations, leads us to obtain competitive results across different data modalities.

AI 总结：本研究提出质量门控去白化（QGD）控制器，通过控制极性暴露延迟扩散模型记忆化，结合复制预算选择（CBS），在CIFAR-10上将有用间隔扩展8.32倍并减少75.9%复制，改善质量-复制权衡。

链接：https://arxiv.org/abs/2610.02780

机构：The University of Sydney（悉尼大学）

作者：Xuanchen Wang, Heng Wang, Weidong Cai

英文摘要：Diffusion models can reach useful sample quality before copying training examples, but fast optimization can compress this generalization window by accelerating sample-specific fitting. We investigate this effect through update geometry and propose Quality-Gated De-whitening (QGD), a controller that retains a fast polar-update prefix and progressively restores fixed-gain momentum. Our random-feature analysis separates covariance-controlled, curvature-equalized and amplitude-controlled memorization clocks. Under aligned spectral assumptions, it establishes a finite-exposure condition under which a fixed-gain tail recovers a delay proportional to dataset size. QGD implements this principle with a confirmed quality gate, a bounded decay envelope and causal copy feedback. Immediate switching is the conservative limit; gradual control balances delayed copying against continued quality improvement. We pair QGD with Copy-Budgeted Selection (CBS), which applies simultaneous binomial calibration to a frozen checkpoint family, followed by a fresh evaluation of the released checkpoint. On 2,000-image CIFAR-10 subsets, QGD preserves the polar baseline's quality-arrival time while expanding its useful interval by 8.32x and reducing common-checkpoint copying by 75.9%. With identical calibration and independent quality evaluation, QGD achieves FID 75.56 versus 79.37 for SGD with the same selector. Exposure-matched controls, independent detector audits and transfer to flow matching and dance generation support adaptive exposure control as a practical way to improve the quality-copying tradeoff.

AI 总结：本文提出自适应二阶求解器，通过比例-积分控制加速扩散采样，在图像和语言任务上以更低计算成本获得更优或相当的质量，并发现逐样本自适应的收益因问题而异。

链接：https://arxiv.org/abs/2610.03034

机构：Radboud University（拉德堡德大学）

作者：Ella Kemperman, Luca Ambrogioni

英文摘要：Diffusion models rely on numerical solvers requiring time-discretization, which has a large influence on the tradeoff between sampling cost and quality. However, the computational difficulty of the reverse process varies along the sampling trajectory and across data distributions, making the choice of discretization important. We adapt proportional-integral (PI) step-size control to diffusion, using our diffusion noise-normalised error estimator. Unlike existing adaptive methods in diffusion that respond only to the current error, the PI solver also incorporates the previous error, yielding smoother step adaptation. We further show that these per-sample trajectories exhibit shared structure and can be aggregated into a fixed schedule that retains much of the benefit of adaptive sampling. We evaluate both approaches on natural-image and language datasets, in terms of quality, measured by FID at a matched number of neural network evaluations (NFE), comparing them with widely used stochastic solvers and schedules. For images, our fixed discretization outperforms the commonly used EDM schedule in terms of sample quality when used with the stochastic Heun sampler, and with the EDM-churn sampler at low NFE. Additionally, our PI adaptive solver obtains better FID than most stochastic and adaptive baselines, although it does not beat the EDM-churn sampler at low NFE. Moreover, we find our solver outperforms both the EDM and the entropy schedule on language diffusion at low-to-medium NFE in terms of perplexity, with the drawback of lower token entropy. Lastly, we find that the benefit of per-sample adaptivity is problem-dependent. It is highly beneficial in 1D toy examples, while only marginal for image and language data, where the average schedule sometimes even outperforms the PI-adaptive solver. Code is available at this https URL

AI 总结：本文提出免导数扩散框架D$^3$Opt，通过一次学习机会可行结构并冻结为先验，结合退火粒子Feynman--Kac修正，实现固定机会约束下非凸非光滑目标的免重训优化。

链接：https://arxiv.org/abs/2610.03071

机构：Beijing University of Posts and Telecommunications（北京邮电大学）； Nankai University（南开大学）； University of the Chinese Academy of Sciences（中国科学院大学）； Southwest University of Finance and Economics（西南财经大学）

作者：Ziwen Liu, Yan Liu, Congying Han, Tiande Guo, Yao Yan, Weichen Zhao

英文摘要：Chance-constrained programs (CCPs) optimize decisions under uncertainty by limiting the probability of constraint violation. Despite advances in traditional and learning-based approaches, optimizing non-convex or non-smooth objectives and adapting to different objectives under fixed chance constraints remain challenging. In this paper, we propose a \textbf{D}erivative-free \textbf{D}iffusion-based framework that \textbf{D}isentangles constraint modeling from objective optimization, termed \textbf{D$^3$Opt}. We learn the chance-feasible structure once, independently of any particular objective, by training a risk-conditioned diffusion model solely on constraint-filtered decisions and freezing it as a reusable prior for post-specified objectives. At inference time, we propose an annealed, particle-based Feynman--Kac correction along the frozen reverse diffusion process to optimize post-specified objectives using only function evaluations. This enables derivative-free optimization of non-convex and non-smooth objectives without objective-specific retraining. We prove that the correction preserves feasibility when this property holds for the frozen prior, and derive an optimization-error bound separating learned-prior coverage, finite-particle approximation, and finite-temperature effects. Experiments on linear Gaussian CCPs, objective-transfer tasks, and chance-constrained economic dispatch demonstrate effective optimization across smooth and non-smooth objectives, including non-convex cases, and objective generalization under fixed chance constraints without retraining.

AI 总结：提出神经-物理反演器（NPI），一种耦合集成条件化与残差学习的模块化大地电磁反演框架，通过合成实验和野外数据验证，能降低误差并保持不确定性估计。

链接：https://arxiv.org/abs/2610.03225

机构：Massachusetts Institute of Technology（麻省理工学院）； Woods Hole Oceanographic Institution（伍兹霍尔海洋研究所）

作者：Jae Deok Kim, Sai Ravela, Rob. L. Evans

英文摘要：We present the Neuro-Physical Inverter (NPI), a modular, uncertainty-aware framework for geophysical inversion that couples ensemble-based conditioning with constrained residual learning, demonstrated in the 1D magnetotelluric (MT) setting as a controlled testbed. The framework operates in two stages. An Ensemble-Conditional Gaussian Process (EnsCGP) conditions a prior ensemble of resistivity models on the observed response, producing a physically admissible reference ensemble. A residual-learning neural network then predicts targeted corrections to this reference, trained on synthetic data and fine-tuned per station for field application through a physics-coupled objective. Because an ensemble is conditioned, refined, and propagated through both stages, every estimate carries an associated ensemble spread. Synthetic experiments show that NPI systematically reduces ensemble-mean error without destabilizing the ensemble. Applied to broadband MT data from the Gabbs Valley geothermal region (Nevada, USA), NPI reduces the across-station mean misfit over the mid-period band while retaining comparable ensemble spread. The propagated ensemble yields a factor of uncertainty that serves as an operational measure of constraint within the assumed model class. Both stages are dimension-agnostic in formulation, and the design principles established here are intended to scale to higher-dimensional parameterizations.

AI 总结：本研究比较四种非线性因果发现方法，揭示各自瓶颈，并提出SPADE评分方案，通过重用充分统计量将组合搜索复杂度从O(nd^3)降至O(nd^2+d^3)，在保持高准确性的同时大幅提升可扩展性。

链接：https://arxiv.org/abs/2610.03258

机构：CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）

作者：Hendrik Suhr, Sascha Xu, Jilles Vreeken

英文摘要：Scalable nonlinear causal discovery requires methods that combine flexible mechanism estimators with efficient search over large graph spaces. Several algorithmic families have been proposed to address this challenge, yet their accuracy-runtime trade-offs remain poorly understood. We empirically compare the four major approaches: differentiable structure learning, amortized structure learning, score-matching, and combinatorial search. Our results reveal complementary bottlenecks: differentiable and amortized methods scale well but exhibit an accuracy gap, score-matching methods can be accurate in low dimensions but degrade quickly for increasing feature sizes, and combinatorial methods remain accurate but are slowed by repeated and redundant local scoring. Motivated by this bottleneck, we develop SPADE, a spline-based score-evaluation scheme that compiles sufficient statistics once and reuses them throughout combinatorial search. Under bounded indegree, its Gaussian variant reduces algorithmic complexity from O(nd^3) to O(nd^2+d^3). Empirically, SPADE shifts the observed scalability-accuracy frontier by orders of magnitude: it solves 100-variable problems with 160K samples in seconds and 1600-variable problems with 2.5K samples in minutes, while retaining high structural accuracy across synthetic and real-world benchmarks. These results reveal a substantial shift in the practical scale of combinatorial search and highlight the importance of evaluating scalable causal-discovery methods along the full accuracy-runtime frontier.

AI 总结：提出观测插值框架，将预训练生成模型转化为无需重训的后验采样器，统一随机与确定性采样，并在高维动力学中验证。

链接：https://arxiv.org/abs/2610.03396

作者：Nikolaj T. Mücke, Benjamin Sanderse

英文摘要：Bayesian data assimilation combines model forecasts with noisy observations, but sampling high-dimensional, non-Gaussian posteriors remains challenging. We introduce an observation-interpolant framework that turns pretrained stochastic interpolant, flow matching, and diffusion models into posterior samplers without retraining. Conditioning the interpolant path on observations yields a shared likelihood-score correction to the drift or velocity, unifying stochastic and deterministic posterior sampling. The resulting SDEs and ODEs sample the exact posterior when the intermediate likelihood score is known. For practical computation, we approximate this score using a closed-form Gaussian surrogate with a bias-corrected mean and covariance inflated by the model's source covariance. Jacobian-free and ensemble-shared approximations make the method tractable in high dimensions. We evaluate the framework on linear-Gaussian dynamics, stochastic two-dimensional Navier-Stokes, and urban airflow with up to $O(10^4)$ degrees of freedom.

AI 总结：提出一种离线自动调优扩散与流匹配后验采样中引导权重的方法，将其化为二维线性最小二乘问题，无需重训，提升重建性能并可将采样步数降至50步。

链接：https://arxiv.org/abs/2610.03503

机构：Heriot-Watt University, EPS（赫瑞-瓦特大学，工程与物理科学学院）； IMS (Univ. Bordeaux, CNRS, BINP)（IMS（波尔多大学，法国国家科学研究中心，BINP））； ONERA（法国国家航空航天研究院）

作者：Liam Moroy, Jean-François Giovannelli, Yoann Altmann, Steve McLaughlin, Frédéric Champagnat, Guillaume Bourmaud

英文摘要： Training-free posterior sampling methods, also known as Plug-and-Play methods, leverage pretrained unconditional diffusion or flow-matching models to solve inverse problems. Most existing approaches rely on guidance weights to balance, at each time step, prior information from the unconditional score or velocity network with measurement consistency, yet the tuning of these weights is often not discussed and is largely left to heuristics. We introduce a simple and principled offline strategy for automatically tuning these guidance weights. Our key observation is that, at each time step, the conditional denoising score-matching objective for diffusion models, or the conditional flow-matching objective for flow-matching models, is a least-squares objective. Therefore, when the conditional prediction is expressed as a weighted sum of the unconditional network output and a measurement-guidance term, optimizing over these weights reduces to a two-dimensional linear least-squares problem. The resulting time-dependent guidance weights can be optimized offline for a given measurement operator, noise level and sampler at the cost of a single minibatch of sampling trajectories, without retraining or fine-tuning the pretrained generative model. Instantiated with the standard Tweedie-based measurement-consistency term, our approach improves posterior sampling and achieves state-of-the-art reconstruction performance across diffusion- and flow-matching-based methods. Moreover, the optimized guidance weights enable diffusion samplers to reduce the number of sampling steps from 1000 to 50 with no significant degradation in reconstruction quality. Code will be made available.

AI 总结：IDRF通过逆蒸馏正则化替代序列级KL惩罚，实现少步掩码离散扩散模型的奖励微调，在DNA、图像和文本生成中减少32倍去噪步骤，同时保持高质量。

链接：https://arxiv.org/abs/2610.03641

机构：Applied AI Institute（应用人工智能研究所）； MBZUAI（穆罕默德·本·扎耶德人工智能大学）； CMAP, École Polytechnique（巴黎综合理工学院应用数学中心）； Institute of Foundation Models（基础模型研究所）； LRE, EPITA（EPITA 研究与工程实验室）

作者：Vladislav Gromadskii, David Li, Samson Gourevitch, Yazid Janati, Eric Moulines, Maxim Panov, Alexander Korotin

英文摘要：Masked discrete diffusion models offer a promising alternative to autoregressive generation, but iterative sampling can be costly, and intractable sequence likelihoods complicate reward fine-tuning. We introduce IDRF, a framework for reward fine-tuning of few-step masked discrete diffusion generators. Starting from a standard reverse-KL-regularized objective, IDRF replaces the intractable sequence-level KL penalty with inverse-distillation regularization. With an optimal auxiliary denoiser, we prove that the population inverse-distillation loss upper-bounds the sequence-level KL divergence to the reference distribution. IDRF optimizes a trajectory-based surrogate of this loss without reference-model rollouts, so the student keeps its own few-step sampler. We view few-step generation as a finite-horizon Markov decision process and optimize reward with a clipped policy-gradient objective over the student's trajectories. Across DNA, image, and text generation, IDRF achieves high reward with up to $32\times$ fewer denoising steps than the reference while mitigating reward hacking and preserving sample quality.

AI 总结：本文提出一种无参数在线凸优化算法，在重尾噪声下实现区间动态遗憾界，通过区间自适应保持最优静态速率，并给出下界验证其最优性。

链接：https://arxiv.org/abs/2610.02258

机构：Purdue University（普渡大学）

作者：Vaneet Aggarwal

英文摘要：We study online convex optimization with one unbiased stochastic subgradient per round and an unknown finite conditional $p$th noise moment, $1

AI 总结：本文研究扰动目标上梯度下降的有限迭代隐私，证明其微分同胚条件并给出无维度因子的隐私界，同时以几何递减修正恢复精确最小化器隐私证书。

链接：https://arxiv.org/abs/2610.02716

机构：Johns Hopkins University（约翰霍普金斯大学）

作者：Austin Watkins, Raman Arora

英文摘要：Objective perturbation adds a random linear term to a regularized empirical risk and releases the exact perturbed minimizer. We study the finite computation obtained by releasing the $N$-th iterate of deterministic gradient descent on $w\mapsto F(w;S)+\langle z,w\rangle$, where $z\sim\mathcal N(0,\sigma^2I_d)$ is drawn once before optimization. For strongly convex and smooth objectives with Lipschitz Hessian, we prove an explicit condition under which the map $z\mapsto w_N$ is a $C^1$-diffeomorphism on the bounded domains used in the privacy argument, with a quantitative lower bound on the smallest singular value of its Jacobian. This permits a direct change-of-variables analysis of the finite iterate. For generalized linear models, the resulting privacy-profile bound has no explicit ambient-dimension factor once the iteration condition holds, and its finite-iteration correction decreases geometrically. By letting the free truncation parameter grow slowly with $N$, we recover the corresponding exact-minimizer certificate in the limit. We also bound the expected excess empirical risk by $d\sigma^2/(2\mu)$ plus a geometrically decreasing optimization term, and transfer the result to population risk without an additional multiplicative condition-number factor in the leading statistical terms.

AI 总结：本研究通过事实回忆模型揭示，Muon 的谱正交化将梯度下降的学习时间比从 Θ̃(√(S/R)) 降至 Θ̃(1)，并加速误差指数衰减，同时保持正交等变性，从而更优地学习事实。

链接：https://arxiv.org/abs/2610.02798

机构：University of California, Los Angeles（加州大学洛杉矶分校）； The University of Hong Kong（香港大学）

作者：Xuheng Li, Qiwei Di, Yuan Cao, Quanquan Gu

英文摘要：The Muon optimizer applies spectral orthogonalization to matrix-valued updates and has shown strong performance in large-scale neural network training, yet the mechanisms of this transformation in feature learning remain poorly understood. In this work, we investigate this question through a tractable factual-recall model, where a fact maps each subject-relation pair to an answer, and a linear transformer learns the subject- and relation-dependent information required to recover this mapping. The transformer is optimized with gradient flow (GF), spectral GF, or Sign GF, which are continuous-time limits of gradient descent, Muon, and Adam, respectively. Prior studies (Nichani et al., 2025) have shown that when the number of subjects exceeds the number of relations, GF learns relation-dependent information before subject-dependent information, producing a feature-separation phase during training. We characterize this separation with the learning times when the subject- and relation-dependent components of the prediction reach a target accuracy. With $S$ subjects and $R$ relations, GF has a learning-time ratio of $\widetilde{\Theta}(\sqrt{S/R})$, whereas Spectral GF reduces this ratio to $\widetilde{\Theta}(1)$. In addition, for fixed $S$ and $R$, the subject- and relation-dependent errors decay as $1/(T\log T)$ in training time $T$ under GF, but as $\exp(-\mathrm{poly}(T))$ under spectral GF. Finally, we show that GF and spectral GF are equivariant under orthogonal transformations of the token embeddings, whereas Sign GF is not: Different orthonormal embeddings can potentially produce no feature separation, a large feature-separation phase, or even a reversed learning order. These results provide a mechanistic view of how spectral orthogonalization can fundamentally reshape feature-learning dynamics.

AI 总结：提出ManifoldLightOT，一种在常见黎曼流形上利用核形式构建熵最优传输耦合的轻量方法，通过几何特定吉布斯核实现闭式归一化与直接采样，并在实验中优于现有流形OT方法。

链接：https://arxiv.org/abs/2610.03085

机构：Applied AI Institute（应用人工智能研究所）

作者：Xavier Aramayo-Carrasco, Petr Mokrov, Alexander Korotin

英文摘要：Entropic Optimal Transport (EOT) has become a practical framework for learning stochastic couplings between complex distributions, with applications in generative modeling and domain adaptation. However, most EOT solvers are designed for Euclidean spaces, while manifold extensions remain limited and often rely on costly iterative methods, simulated dynamics, or generic neural models that do not fully exploit the underlying geometry. We introduce ManifoldLightOT, a light approach for learning kernel-induced EOT couplings directly on common manifolds. Using the kernel form of the EOT solution, we construct geometry-specific Gibbs kernels together with compatible potential parameterizations for spheres, tori, $\mathrm{SO}(3)$, and $\mathrm{SE}(3)$. These choices yield closed-form normalization and directly sampleable conditional distributions. Our formulation naturally extends to products of manifolds, making it applicable to more complex geometries. The parameters of the potentials are optimized directly from samples using Monte Carlo estimates of the learning objective. Through synthetic and real-world experiments, we show that ManifoldLightOT often outperforms existing manifold OT methods while retaining direct sampling.

AI 总结：本研究揭示欠完备线性自编码器中SGD破坏尺度对称性，偏向大解码器权重，产生定向尺度漂移并受稳定性边界限制，展示损失几何将梯度噪声转为定向运动。

链接：https://arxiv.org/abs/2610.03640

作者：Farhad Pashakhanloo, Jacob A. Zavatone-Veth

英文摘要：Neural network loss landscapes have many symmetries, which are preserved by gradient flow but broken by finite-stepsize stochastic gradient descent (SGD). A canonical example of such a symmetry is scale in homogeneous networks: one can scale up the parameters in one layer and down in the next without changing the network output. Previous work has documented cases in which SGD breaks this symmetry in favor of balancing gradient noise or minimizing fluctuations. Here, we show that the solution geometry of undercomplete linear autoencoders instead selects a preferred sign for scale drift: on the PCA solution manifold, SGD favors large decoder weights. This directed scale drift occurs on a slow timescale, and its dynamics admit an analytically-tractable effective description. However, it cannot continue indefinitely: increasing scale eventually drives the dynamics towards a finite-stepsize stability boundary. The resulting solutions are sharper than a balanced baseline in the sense of the maximum eigenvalue of the loss Hessian, but different sharpness measures can move in opposing directions. Thus, undercomplete autoencoders give a concrete illustration of how loss geometry can convert residual gradient noise into directed motion along a manifold of functionally-equivalent solutions.

AI 总结：针对长上下文LLM的KV缓存内存瓶颈，提出联合令牌-特征压缩方法SlimKV，利用低秩感知训练和位置不对称性实现无重建注意力，在保持高压缩比下性能领先并显著加速解码。

链接：https://arxiv.org/abs/2610.02953

机构：University of Science and Technology of China（中国科学技术大学）； Nanyang Technological University（南洋理工大学）； Tencent（腾讯）

作者：Zihan Teng, Jiayu Zhao, Wentao Ren, Minhao Fan, Tianrui Ma, Song Chen, Weichen Liu

英文摘要： Long-context LLM serving is increasingly bottlenecked by KV-cache memory, especially in resource-constrained scenarios. Among existing KV-cache compression strategies, token-wise methods reduce cached states but risk information loss through eviction or condensation, while feature-wise methods reduce per-token KV dimensions but can require full-dimensional reconstruction to apply positional embedding, limiting decoding speedups. We introduce SlimKV, a question-agnostic joint token-feature KV-cache compression method. SlimKV uses low-rank-aware training to compress long contexts into beacon memory states with latent KV representations, together with layer-adaptive rank allocation. We further uncover a positional asymmetry: removing key-side RoPE affects beacon and raw tokens differently, with much smaller degradation for beacon tokens. Exploiting this asymmetry, SlimKV trains beacon KV projections under a K-RoPE-free constraint and enables latent-space attention during decoding, mitigating reconstruction latency. On LongBench, SlimKV outperforms baselines at 16x/32x compression and remains leading at 4x/8x, where it retains over 96% of the uncompressed model's score. Needle-in-a-Haystack confirms robustness across evidence positions, and efficiency evaluation shows up to 7.34x attention speedup and 3.38x end-to-end decoding speedup over the uncompressed model at 128K length.

AI 总结：AvoKV-E提出无需训练的负载感知KV缓存驱逐策略，通过延迟资格、归一化读取压力及值负载潜力排序，在严格缓存下超越现有基线，强调保留值负载以维持长推理轨迹。

链接：https://arxiv.org/abs/2610.03007

机构：LinkedIn Corporation（领英公司）； Clemson University（克莱姆森大学）； Rice University（莱斯大学）； Arizona State University（亚利桑那州立大学）

作者：Han Yu, Wenhui Zhu, Xiwen Chen, Zhipeng Wang, Hejian Sang, Han Shi, Menglin Zhou, Xuanzhao Dong, Minzhou Huang, Rui Cai, Hao Wang, Alborz Geramifard

英文摘要：Long-output reasoning shifts the KV-cache bottleneck from the fixed prompt to the generated trace. Existing reasoning-cache eviction methods largely treat cached entries as routing objects, estimating whether an old key will still be read, will recur, or can be replaced. This routing-only view overlooks two effects: low-attention entries can carry large value payloads whose removal changes future predictions, and newly generated states can appear stale before later queries have had a chance to read them. We introduce AvoKV-E, a training-free eviction policy that first delays eligibility for recent states and then ranks eligible entries using candidate-normalized read pressure, key redundancy, and value-payload potential. According to empirical evaluation across different models and datasets, AvoKV-E matches or exceeds redundancy-aware, recurrence-based, and thought-adaptive eviction baselines at matched active-KV budgets, with its largest gains in the tightest-cache regime. Component and counterfactual analyses further connect these gains to delayed observation, payload-aware scoring, redundancy, and scale-robust normalization. Together, the results show that long-reasoning KV eviction should preserve not only keys that are likely to be read, but also the value payloads that sustain the reasoning trajectory.

AI 总结：针对长上下文推理中KV缓存的内存瓶颈，提出TaSQ方法，通过查询引导通道加权、跨头归一化和协方差感知通道分组定制VQ量化空间，在1比特压缩下显著优于现有基线，并支持更大批处理与更高吞吐量。

链接：https://arxiv.org/abs/2610.03027

机构：Seoul National University（首尔大学）； Stanford University（斯坦福大学）

作者：Minsoo Cheong, Donghyun Son, Sungjoo Yoo

英文摘要：The key-value (KV) cache becomes a major memory bottleneck in long-context LLM inference, placing substantial pressure on memory capacity and bandwidth. To mitigate this bottleneck, vector quantization (VQ) has emerged as a promising approach for aggressive KV cache compression. However, existing VQ methods degrade substantially in the 1-bit regime. At such extreme compression, each codebook must represent a larger group of channels with a limited set of centroids, making effective use of its capacity increasingly challenging. To address this, we introduce $\textbf{TaSQ}$, which tailors the VQ target space by combining query-guided channel weighting, cross-head normalization, and covariance-aware channel grouping to better reflect the error sensitivity and statistical structure of cached activations. Since these transforms are RoPE-compatible and can be easily merged into projection weights and codebooks, TaSQ preserves the conventional VQ lookup structure and adds negligible serving overhead. Across general, long-chain-of-thought reasoning, and long-context retrieval benchmarks, TaSQ consistently outperforms existing low-bit KV cache VQ baselines while preserving reasoning stability. On a single RTX 6000 Ada GPU, its SGLang implementation supports up to $14\times$ larger batch sizes and achieves $1.87\times$ higher peak throughput compared to the BF16 baseline.

AI 总结：针对GQA下KV缓存驱逐的硬件对齐问题，提出Page-EntroKV框架，利用熵加权池化与页级驱逐，消除并集开销，提升针检索率并保持预算精确。

链接：https://arxiv.org/abs/2610.03135

机构：SRM Institute of Science and Technology（SRM科学与技术学院）

作者：Inbasekaran S

英文摘要：Serving long-context autoregressive language models is constrained by the key-value (KV) cache. Most dynamic eviction methods score token importance per query head and choose tokens independently. This fits poorly with grouped-query attention (GQA), where several query heads share one physical KV buffer: divergent per-head selections force the serving engine to retain the union of their choices - inflating the cache by up to the group ratio r - while arithmetic mean pooling dilutes the specialized retrieval heads that carry factual recall. We introduce Page-EntroKV, a formal framework for KV-cache eviction operating at the granularity GQA serving actually allocates. Heads within each physical group are pooled by weights derived from sink-isolated collision (Renyi-2) entropy - one inner product per head, computed once at prefill with no calibration - so sink heads cannot masquerade as retrieval heads. Pooled scores are projected onto PagedAttention page frames, and eviction executes at the hardware tuple (layer, group, page). We formalize the union overhead ratio (UOR) and intra-group disagreement, prove an exact identity linking them for two-head groups alongside two-sided bounds at every group ratio, prove strict budget preservation and a finite-context needle-retention bound that arithmetic mean pooling provably violates, and give exact per-layer page accounting. On a pilot architecture (Qwen2.5-1.5B-Instruct, r=6), head-independent replay over 2,240 group measurements yields union overhead up to 4.75x at a 2% budget, while Page-EntroKV holds UOR exactly 1.000; sink isolation removes a 13x sink masquerade; needle recall is 100% versus 0% for mean pooling at a 20% budget; retained cardinality is exact for every page size; and QA and code tasks remain solvable at 20% retention.

AI 总结：本文提出W16A16，一种16位高精度量化方法，在Armv7E-M微控制器上以8位成本实现约10倍更低的量化误差，同时保持相似或更优的速度与能耗。

链接：https://arxiv.org/abs/2610.03402

机构：Bielefeld University（比勒费尔德大学）

作者：Rui Liu, Benjamin Paaßen

英文摘要：To deploy deep neural networks on edge hardware, highly efficient inference schemes are necessary that retain high accuracy. This work presents W16A16, a high precision (16-bit), fast speed, low energy quantization method. On a widely applied microcontroller architecture Armv7E-M, our proposed approach achieves faster speed and lower energy consumption on layer- and model-level compared to alternative quantization schemes. We analyze the architecture of Armv7E-M, explain the underlying principles behind the performance advantages of 16-bit approaches, and evaluate the empiric quantization errors for regression and classification tasks, as well as empiric time- and energy consumption in MCU deployment. We observe ca.\ 10 times lower quantization errors compared to 8-bit quantization schemes while achieving similar or better inference times and energy consumption.

AI 总结：针对机器遗忘中数学保证与部署工件脱节的问题，提出ExecCert发布时认证层，通过原生证书或RRV验证候选工件，实现增量认证并降低成本，实验证明其有效性。

链接：https://arxiv.org/abs/2610.02268

机构：Arizona State University（亚利桑那州立大学）； McGill University（麦吉尔大学）

作者：Ziyu Zhao, Xinyu Wang, Xiaowen Chang, Yixuan He

英文摘要：Machine unlearning is needed when data must be removed because of deletion requests, outdated records, or data-quality concerns, while retraining from scratch can be costly. Certified machine unlearning methods provide mathematical guarantees, while deployed systems release concrete finite-precision artifacts produced by software. To bridge the gap between mathematical guarantees and practical deployment, we introduce Executable Release Certification (ExecCert), a release-time layer that certifies the candidate artifact considered for release. ExecCert either closes a method's native certificate for the executed candidate or applies Retraining-Reference Release Verification (RRV) to certify fidelity to current retain-set retraining. Sequential deletion makes the latter nontrivial because the exact retain-set reference and the stored numerical state evolve separately. For frozen representations with a mutable ridge head, we develop an incremental realization of RRV that maintains certified evidence across deletion requests rather than reconstructing it at each release. On four published unlearning implementations, ExecCert preserves valid certificates, changes release decisions, tightens conservative bounds, and identifies the retraining-reference fidelity supported by concrete outputs. In sequential-service experiments, RRV eliminates false releases caused by stored-equation verification while closely tracking realized error, and incremental certification remains cheaper than both fresh and maintained verified-factor alternatives once release checks become sufficiently frequent.

AI 总结：针对差分隐私训练中裁剪扭曲Muon更新几何的问题，提出在裁剪前对样本梯度进行历史平均，以限制裁剪失真并保持极因子，在私有GPT-2微调中提升BLEU和ROUGE-L。

链接：https://arxiv.org/abs/2610.02738

机构：Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）； University of Missouri（密苏里大学）； Georgia Institute of Technology（佐治亚理工学院）

作者：Bishnu Bhusal, Minh Vu, Ben Southworth, Geigh Zollicoffer, Rohit Chadha, Manish Bhattarai

英文摘要：Differentially private training clips each per-example gradient before adding noise. This clipping is radial for each example, yet unequal clipping factors can distort the relative singular-vector geometry of their average. Muon is particularly exposed to this effect, since its update is an approximate polar factor UV^T that depends only on the singular vectors that clipping can shift. To curb this degradation, we propose averaging each sampled example's Muon gradient over the current model and a short history of recent models before clipping. The clipped batch matrix then separates into a common rescaling and a covariance residual R between sampled gradients and clipping values, with ||R||_F <= sigma_lambda sigma_G, bounding the clipping-induced distortion directly. We further show that a finite Newton-Schulz iteration preserves the polar factor of its input under these spectral conditions, confirming that our correction survives orthogonalization. In private GPT-2 fine-tuning on E2E and DART at epsilon in {1, 2, 4, 8}, DP-Muon-IM improves BLEU and ROUGE-L over DP-Muon in every seed-matched comparison, and non-private diagnostics show 2-4% lower pre-noise polar error.

AI 总结：本研究通过MIMIC-IV临床预测基准，揭示联邦世界模型中轨迹异质性对时间覆盖、算法误差和更新行为的影响，提出多维评估框架。

链接：https://arxiv.org/abs/2610.02957

机构：Wuhan University（武汉大学）； China Academy of Information and Communications Technology（中国信息通信研究院）； The University of Sydney（悉尼大学）； Tsinghua University（清华大学）； The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））

作者：Yipan Wei, Zhaokun Yan, Ziming Hong, Jiaqi Wu, Lixu Wang

英文摘要： World models learn state evolution from trajectories, making access to temporal context a central training requirement. Federated learning can use distributed records, while ownership boundaries within a trajectory restrict the examples each client can construct. Our study benchmarks this cross-time setting through hourly action-conditioned clinical prediction on eight MIMIC-IV disease cohorts, comprising 40.87 million transition memberships. We specify severity-based client ownership, patient-separated construction, local history and future-window rules, and paired rollout evaluation from one to 32 hours. A matrix of ten federated algorithms covers 32 disease--partition configurations under five rounds of ten-percent participation. Three findings emerge from existing results and training logs. First, client ownership and participation jointly restrict long-window coverage: only 7.55\%--21.36\% of pooled-available 32-step windows have a locally complete anchor visited during training, averaged across diseases. Second, finer severity partitions accompany higher FedAvg error in 15 of 16 paired comparisons, while algorithm gains are small and horizon-dependent: FedProx reduces mean error by 0.56\%, with no consistent improvement at 32 steps. Third, algorithm labels conceal distinct update behavior, including inactive extrapolation and orders-of-magnitude differences in update scale. Cached-update performance also varies strongly across trajectory partitions under the same benchmark protocol. These results establish temporal access, participation coverage, optimization behavior, and horizon-resolved prediction as complementary dimensions for evaluating federated clinical world models.

AI 总结：RIPPLE提出一种联邦学习聚类框架，利用小波散射变换离线计算簇分配，实现零样本聚类，通信成本与FedAvg相当，并在多个基准上优于现有方法。

链接：https://arxiv.org/abs/2610.03054

机构：Politecnico di Torino（都灵理工大学）

作者：Alessandro Licciardi

英文摘要：Clustered Federated Learning (FL) partitions a client population into groups of similar local distributions and trains one specialized model per cluster, mitigating client drift that degrades single-model methods under non-IID data. Prior methods discover cluster structure inside the training loop through gradient similarity, loss evaluation, or EM-style updates, thus increasing communication overhead, exposing gradients to inversion attacks, and providing no mechanism to assign clients absent from training. We propose RIPPLE, a clustered FL framework in which cluster assignment is computed entirely offline from a spectral characterization of each client's local data: a variance-weighted principal-component prototype embedded via the Wavelet Scattering Transform and decoded by a Gaussian Mixture VAE trained server-side on synthetic client populations before federation begins. Per-round communication cost matches FedAvg exactly, and a client absent from training obtains a personalized model from a single forward pass, without gradient computation, model evaluation, or extra communication round. We prove that the gap between RIPPLE's surrogate clustered objective and the oracle is bounded by a computable quantity decaying with client sample size and independent of federation duration; per-cluster convergence matches the minimax-optimal rate for non-convex smooth objectives. Across five benchmarks spanning controlled and realistic heterogeneity, RIPPLE consistently outperforms all baselines, with margins growing on the most realistic partitions.

AI 总结：针对智能体数据相关导致的分布式学习性能下降问题，提出cordial学习，通过仅共享低维输出并训练本地模型提取同伴信号，在非凸目标下以概率一收敛到全局最优，实验验证了其高效性。

链接：https://arxiv.org/abs/2610.03330

机构：Tel Aviv University（特拉维夫大学）

作者：Sarah Shitrit, Ilai Bistritz

英文摘要：We consider a distributed learning task with agents that have correlated data. Specifically, the label of an agent depends on the input of other agents for the same sample, and these inputs are also correlated. Correlated data is the reality when agents share the same environment. Existing decentralized methods, such as federated learning, ignore the structure of the problem and perform poorly on correlated data. On the other hand, centralized approaches are infeasible due to privacy and communication constraints. We introduce cordial (correlated and distributed) learning to address this gap by sharing only low-dimensional outputs between the agents while training local models to extract informative signals from peers. This distributed learning induces a game in which the loss function of each agent depends on the models of others. Assuming a linear model, we prove that cordial learning converges with probability one to a globally optimal solution, despite the nonconvex global objective. Experiments on structured multi-digit MNIST tasks demonstrate that cordial learning remains highly effective even in highly nonlinear settings.

AI 总结：提出路径积分替代模型扩展（PI-SME），通过高斯-勒让德求积近似梯度场路径积分，在CIFAR-100和FEMNIST上更忠实地重建联邦学习中的私有输入。

链接：https://arxiv.org/abs/2610.03597

机构：Indian Institute of Technology Kharagpur（印度理工学院卡哈拉格普尔分校）

作者：Agnivo Ghosh, Saumik Bhattacharya

英文摘要：Federated learning lets many clients train a shared model together without ever sending their private data to a central server. Each client shares only a model update, and this update should reveal far less about the client than its raw training examples would. This premise is what protects the privacy of the clients. Gradient inversion attacks challenge it directly by trying to reconstruct a client's private input images from the single update it shared. Under FedAvg, a client's update accumulates several local training steps, so the server sees only the two endpoints of a hidden weight trajectory. Recent gradient inversion attacks fit a surrogate model along the path between these two endpoints but they still read its gradient at a single point. We propose the Path-Integral Surrogate Model Extension (PI-SME) which treats the accumulated update as a path integral of the gradient field and approximates it by Gauss--Legendre quadrature over several nodes along a learnable Bézier path. On CIFAR-100 and FEMNIST images across a range of trajectory lengths and class-restricted batches PI-SME reconstructs the private inputs more faithfully than the strongest surrogate baseline on several inversion metrics and the matching loss.

AI 总结：提出ReRoute框架，结合事实数据与部分机制知识，无需受控实验即可在科学仿真器中实现高精度反事实预测，并在气候仿真中显著降低误差。

链接：https://arxiv.org/abs/2610.02252

机构：California Institute of Technology（加州理工学院）； NVIDIA（英伟达）； Institute of Science Technology Austria（奥地利科学技术研究所）

作者：Dingling Yao, Kahaan Gandhi, Valentin Duruisseaux, Boris Bonev, Francesco Locatello, Anima Anandkumar

英文摘要： Many scientific questions require reasoning about what was never observed: What if the conditions, interventions, or history had been different? Models can predict accurately on observed data yet fail on such what-if queries when correlated inputs are varied independently. A common remedy is to add controlled simulation data in which these factors are explicitly disentangled, but this requires access to a simulator, can be computationally expensive, and inherits the simulator's modeling assumptions. We introduce ReRoute, a framework for targeted scientific what-if prediction that combines factual data with partial mechanistic knowledge, without requiring controlled intervention data for adaptation. ReRoute fixes the queried input of a pretrained backbone to a reference value, reintroduces its variation through a known mechanistic pathway, and fine-tunes on the original factual data, while leaving downstream effects to the learned dynamics. We provide a causal identification result for this construction under explicit structural assumptions, with the core argument machine-checked in Lean. After showing that ReRoute achieves highly accurate counterfactual predictions in a controlled advection-diffusion system where exact responses are available, we turn to state-of-the-art climate emulation. On held-out coupled-climate interventions, ReRoute reduces aggregate climate error by 18.2-31.8% under severe CO$_2$ distribution shifts while preserving skill under standard conditions, at a small fraction of the cost of retraining on additional controlled simulations, without even accounting for the substantial expense of generating such data. Finally, on an emulator trained from historical ERA5 reanalysis, where no counterfactual reference exists, ReRoute preserves substantially more of the surface warming implied by the observed boundary conditions under a fixed-CO$_2$ counterfactual.

AI 总结：本文提出利用合成预训练数据构建可验证的归因测试平台，通过行为条件归因与反事实干预，验证表格基础模型归因的忠实性，并揭示溯源关联与干预效果的不一致性。

链接：https://arxiv.org/abs/2610.02347

机构：Lexsi Labs

作者：Mohamed Bouadi, Nassim Bouarour, Shivam Dubey, Aditya Tanna, Vinay Kumar Sankarapu

英文摘要：Training-data attribution aims to identify which training examples shape model behavior, yet validating such claims is difficult because causal training influence is rarely observable. We argue that controlled synthetic pretraining makes attribution experimentally testable. Using O'PRIOR, a provenance-rich synthetic task generator for tabular foundation models, we construct a testbed in which every pretraining task carries explicit lineage over structural mechanisms, missingness, confounding, shortcuts, and distribution shift. We combine behavior-conditioned attribution with counterfactual retraining and provenance-aware interventions to test both task-level faithfulness and mechanism-level consistency. On held-out real tasks, removing the top-attributed 5% of synthetic tasks decreases mean ROC-AUC by 0.013, compared with 0.002$\pm$0.004 under random removal, while removing bottom-attributed tasks improves performance by 0.003. Within shortcut-provenance tasks, targeted removal yields an effect of 0.043 versus 0.016 for matched random removal. Provenance discrimination is more modest by ranking AUROC (0.55-0.62), despite substantial top-k enrichment, revealing that provenance association and interventional faithfulness need not coincide. Our results establish synthetic provenance as a controlled setting for verifiable contributive attribution

AI 总结：本研究探究LLM智能体激活探针监控中，在用户回合后附加分类提示后缀能否提升野外恶意输入检测泛化能力，发现分类格式而非具体标准带来增益，且效果依赖模型与读取方式，为部署提供廉价改进方案。

链接：https://arxiv.org/abs/2610.02413

机构：Zenity

作者：Elad David, Max Fomin

英文摘要：LLM agents increasingly rely on activation probes as runtime monitors for prompt injection, jailbreaks, and unsafe requests, reading the model's own hidden state to catch a harmful input before the agent acts on it. A cheap, increasingly common move, borrowed from LLM-as-judge prompting, is to append a short classification instruction after the user's turn and read the probe at that point, to sharpen it: the instruction asks the model to represent the incoming request as a class, concentrating the signal the probe must separate, at negligible serving cost. But does the wording of that suffix matter, and does its benefit hold in the wild, on attack types the probe never saw in training, the regime a deployed monitor faces? We test this with a controlled ladder of post-user suffixes under strict leave-one-dataset-out (LODO) evaluation across 13 safety benchmarks (jailbreak, injection, and benign chat) and three open-weight model families (Llama-3.1-8B, Qwen3.5-9B, Gemma-4-12B). On a single-position probe, a classification suffix consistently improves out-of-distribution detection over no suffix (up to ~4 AUC points); yet which suffix matters: prompting the model to classify the input, even into content-free labels, reliably wins; an off-topic or merely-attentive suffix helps little. The gain comes from the classification format, not the named criterion: a content-free suffix matches the real malicious/benign one, with the criterion adding precision only at strict thresholds. This is not an artifact of the single-position read: the benefit carries to the multi-position pooling probes used in production (attention, multi-max, MLP), though the best-performing suffix there is readout-dependent. Served through a KV-cache fork, it is a cheap drop-in for any activation-probe monitor, though not an automatic win: which suffix helps, and by how much, depends on the model and the readout.

AI 总结：提出自适应迭代修复框架AIR-OPD，通过错误到修复的监督改进在线策略蒸馏，在数学推理基准上显著提升性能。

链接：https://arxiv.org/abs/2610.02700

机构：University of Science and Technology of China（中国科学技术大学）； Nanyang Technological University（南洋理工大学）

作者：Rui Li, Liyang He, Zheng Zhang, Zhenya Huang, Linbo Zhu, Qi Liu

英文摘要： On-policy self-distillation (OPSD) supplies dense token-level feedback on trajectories sampled from the student's own policy, a richer training signal than the outcome-level rewards of reinforcement learning. This feedback comes from a teacher conditioned on a full reference solution unavailable to the student. The reference solution specifies the target but not how to move from the student's current error toward it, creating a solution-conditioned shortcut risk. We introduce AIR-OPD, an adaptive iterative repair framework for on-policy distillation that provides error-to-repair supervision. Given a failed response, a guidance generator synthesizes repair guidance for the current error. The student samples an on-policy retry with this guidance. If the retry remains incorrect, the generator produces new repair guidance for the newly observed error. At each round, a fixed teacher receives the guidance as privileged context and supervises the student on an error-aligned region of its latest failed response. Outcome-aware stage weighting favors early repair stages and credits stages whose immediate retry passes verification. We train AIR-OPD on the DAPO-Math-17K dataset and evaluate on AIME24, AIME25, and HMMT25, alongside out-of-distribution tests on MMLU-Pro and GPQA. We examine two guidance sources, self-guidance from the current student policy and external guidance from a larger model. For both Qwen3-4B and Qwen3-8B, AIR-OPD attains the best mathematical-reasoning averages, improving over the strongest baseline by up to 3.6 points, while preserving base-model performance on the out-of-distribution benchmarks.

AI 总结：提出免训练的EMC框架，通过闭式解将图域结晶为紧凑记忆，以高效应对非平稳分布偏移，显著降低运行时间和内存消耗。

链接：https://arxiv.org/abs/2610.02795

机构：State Key Laboratory of Complex & Critical Software Environment, Beihang University（北京航空航天大学复杂关键软件环境国家重点实验室）； Shen Yuan Honors College, Beihang University（北京航空航天大学沈元荣誉学院）

作者：Yue Hou, Ruomei Liu, Yingke Su, Junran Wu, Ke Xu

英文摘要：Deep graph learning models deployed in real-world systems often need to cope with non-stationary environments, where the underlying graph distribution drifts continually over time. Prevailing solutions rely on training auxiliary generative modules to synthesize memory graphs for cross-domain adaptation, which incurs substantial computational overhead and scales poorly under prolonged distribution shifts. We argue that a more economical path exists: rather than generating memory, one can crystallize it. To this end, we propose Efficient Memory Crystallization (EMC), a training-free test-time framework that distills each incoming graph domain into a compact, semantically faithful memory through a closed-form solution to a memory-oriented distribution-matching objective, thereby eliminating redundant domain information under continual covariate shifts. To preserve both generalizability and adaptability as the model traverses a long sequence of target domains, EMC further models inter-domain dependencies through state-evolving memories and admits a theoretically grounded, tighter generalization error bound than direct adaptation. Extensive experiments demonstrate the superior performance of EMC over state-of-the-art baselines on graphs under non-stationary distribution shifts, while reducing average runtime by 87.4% and GPU memory consumption by 92.4% relative to the recent competitor, making continual graph adaptation practical at scale.

AI 总结：针对异质群体中分布偏移和异常值污染导致的生存模型性能下降问题，提出结合外部最小化与内部最大化的分布鲁棒框架，在模拟和基准实验中稳定训练并显著提升最差组性能。

链接：https://arxiv.org/abs/2610.02868

机构：Pohang University of Science and Technology（浦项科技大学）

作者：Seonghwi Kim, Sung Ho Jo, Minwoo Chae

英文摘要：Learning robust survival models under distribution shift is an important but challenging problem in many applications. In heterogeneous populations, a model that performs well on average may still perform poorly on certain subpopulations, and this issue becomes even more severe when the training data are contaminated by outliers. In this paper, we propose a novel distributionally robust framework for survival analysis that jointly addresses latent subpopulation shift and outlier contamination. The proposed method combines an outer minimization that selects a refined nominal distribution by reducing the influence of contaminated samples and an inner maximization that focuses on the most challenging subpopulation. This formulation directly accommodates non-decomposable survival losses while preserving interactions across samples, including the risk-set structure of the Cox negative partial log-likelihood. We develop an alternating gradient-based algorithm with outer updates derived from the KKT conditions of the inner maximization. Experiments on simulated data and two survival benchmarks demonstrate that the proposed method remains robust when subpopulation shift and outlier contamination occur simultaneously. It stabilizes training in contaminated settings and substantially improves worst-group performance across both linear and nonlinear survival models, while maintaining competitive and sometimes superior overall performance.

AI 总结：AIBL将实例学习扩展到神经嵌入空间，通过活跃、遗忘和惊喜记忆结构及毕业算法处理高维顺序数据，在多个任务上准确率提升6-17个百分点。

链接：https://arxiv.org/abs/2610.03413

作者：Radha Poovendran, Andrea Stocco, Linda Bushnell

英文摘要：Sequential learning systems often make decisions from accumulated experience while receiving high-dimensional inputs whose distribution may change over time. Instance-Based Learning Theory (IBLT) provides a principled case-based framework for such settings through stored situation-decision-utility instances, partial matching, activation, and blending. IBLT relies on symbolic knowledge representation in dictionary-like formats, but text, images, transaction vectors, and user-item histories often require learned similarity rather than hand-specified matching rules. In this paper, we introduce AIBL (Augmented Instance-Based Learning), an instance-learning model formulated in a learned vector space for high- dimensional sequential data. AIBL generalizes symbolic situation matching to neural embedding similarity while retaining instance storage, activation- weighted retrieval, and utility blending. The AIBL model organizes memory into active, forgotten, and surprise stores. Surprise memory separates weakly matched, possible out-of-distribution, or corner-case observations from active memory, reducing forced fitting to the nearest available cases. An observation-driven graduation algorithm promotes recurring surprise instances to active memory, allowing the memory to incorporate repeated novel patterns that may arise under concept drift. We evaluate the same implementation on five machine learning tasks and three controlled simulation tasks, comparing AIBL with classical IBLT variants and task-specific baselines where appropriate. AIBL improves accuracy by 6 to 17 percentage points. The results show where vector-space retrieval improves over symbolic matching and how the added memory mechanisms govern novelty detection, cold-start handling, drift adaptation, and reward learning under the tested protocols.

AI 总结：针对现有图证据深度学习在节点分类中认知不确定性不可约减的问题，提出统计框架与图自助集成方法，通过信息增长实验验证其一致性，有效减少认知不确定性。

链接：https://arxiv.org/abs/2610.03418

机构：University of Trento（特伦托大学）； Fondazione Bruno Kessler, FBK（布鲁诺·凯斯勒基金会）； University of Tromsø（特罗姆瑟大学）

作者：Emma Meneghini, Francesco Ferrini, Bruno Lepri, Andrea Passerini, Veronica Lachi

英文摘要：Epistemic uncertainty should decrease as additional information about the data-generating process (DGP) becomes available to the predictor. Yet, existing graph evidential deep learning (EDL) methods for node classification typically construct epistemic uncertainty from graph-specific properties and evaluate it on downstream tasks such as out-of-distribution detection, which do not test its reducibility as information about the DGP increases. To make reducibility directly testable, we introduce a statistical framework for studying epistemic uncertainty under information growth. Our framework specifies an information-growth experimental protocol and a consistency criterion for epistemic predictors, while using projective graph DGPs to ensure that growing graphs, which in general need not provide increasing information about the same DGP, constitute coherent observations of the same underlying process. We show that EDL methods do not explicitly estimate data uncertainty arising from a single finite graph observation and instead regulate epistemic uncertainty through model hyperparameters, precluding consistency, as corroborated by controlled information-growth experiments. As an alternative, we propose graph bootstrap ensembles, capturing both data and procedural uncertainty through graph resampling and randomized training. Under the same experimental protocol, these ensembles exhibit epistemic uncertainty reduction beyond standard deep ensembles. These findings support bootstrap ensembles as candidate consistent epistemic predictors under information growth.

AI 总结：本文提出深度贝叶斯REFoCUS，将超声多静态恢复建模为贝叶斯推断，利用深度生成先验应对秩亏缺，优于线性基线并表达不确定性，且对分布偏移具有强泛化能力。

链接：https://arxiv.org/abs/2610.03419

机构：Eindhoven University of Technology（埃因霍温理工大学）

作者：Simon Penninga, Ruud van Sloun

英文摘要：In this work we formulate ultrasound multistatic recovery from arbitrary transmit sequences as a Bayesian inference problem. To that end, we train a deep generative prior on multistatic data sets to tackle the rank-deficient regime in which classical linear REFoCUS decoders fail. This appproach, which we term Deep Bayesian REFoCUS, outperforms the linear baselines for all regimes of rank-deficiency and noise levels, and regresses to linear decoding when inversion is exact. The model also expresses uncertainty in the null space of the acquisitions, whereas the linear REFoCUS decoders only provide point estimates. Finally, we analyze the impact of distribution shift between simulation and in-vivo acquisitions, showing remarkable generalization ability without any fine-tuning or adaptation.

AI 总结：本研究通过化学和生物学分布偏移评估药物-靶点亲和力模型，发现架构选择依赖于外推形式，而非仅平均误差，建议基准匹配部署场景。

链接：https://arxiv.org/abs/2610.03456

机构：Georgia Institute of Technology（佐治亚理工学院）

作者：Minjae Chung, Clara Li, Malar Paavai Muthukumaran, Shaunna Wang, Aniket Ramkrishnan Iyer, Shaun Qien Yeau Tan, Harinishree Sathu, Micky C. Nnamdi, J. Ben Tamo, Benoit Louis Marteau, May Dongmei Wang

英文摘要：Drug-target affinity (DTA) prediction is widely used to prioritize candidate compounds before costly experimental screening. DTA models are often compared under a single data split, even though deployment may require extrapolation to new chemical series, new protein targets, or both. We ask whether the distribution shift used for evaluation changes which architecture appears best. We curate 718,800 unique drug-protein pairs from the ChEMBL and BindingDB datasets. We compare a Morgan-fingerprint + protein-CNN baseline with 12 controlled architectures that combine four drug representations with three ESM-2 interaction modes. Mean validation RMSE increases from 0.950 and 0.945 under scaffold and fingerprint-cluster OOD to 1.299 and 1.321 under protein-cluster and dual OOD. Model rankings are similar across the two chemical shifts (tau = 0.79), but agreement with scaffold OOD falls under protein OOD (tau = 0.39) and reverses under dual OOD (tau = -0.55). Held-out evaluation, repeated seeds, group-aware bootstrap analysis, and a size-matched control support the same conclusion: architecture selection depends on the form of extrapolation, not only on average error or training-set size. DTA benchmarks should therefore match the chemical and target shifts expected at deployment.

AI 总结：本研究提出Gracr编译器，将模态逻辑公式编译为GNN权重，构建GracrBench基准，以精确真实标签评估解释器，发现多数解释器对间接影响不稳健。

链接：https://arxiv.org/abs/2610.03526

机构：University of Trento（特伦托大学）； Sapienza University（罗马大学）； Intesa Sanpaolo AI Research（意大利联合圣保罗银行人工智能研究院）； Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）

作者：Steve Azzolin, Francesco Paolo Nerini, Stefano Teso, Francesco Bonchi, Bruno Lepri, André Panisson, Andrea Passerini

英文摘要： Explainers for Graph Neural Networks (GNNs) are commonly evaluated by their plausibility, i.e., how well their explanations recover a predefined ground truth, such as a motif planted in the data. This protocol implicitly assumes that a GNN trained on such data relies on the intended motif. Although prior work has questioned this assumption, plausibility remains widespread. First, we show that the assumption is violated on several widely used benchmarks, where, e.g., degree statistics alone suffice to solve the task. Then, we remove this confounder by replacing training with compilation. We achieve this by introducing $\mathsf{Gracr}$, the first compiler translating graded modal logic formulas into GNN weights, yielding models that replicate the behaviour of the corresponding formulas. Since the behaviour of the model is now known by construction, we can define its ground truth explanation formally and compute it exactly. Building on this, we introduce $\mathsf{Gracr}\mathsf{Bench}$, a benchmark of compiled GNNs for the evaluation of explainers against this exact ground truth. Experiments on eleven explainers across six tasks show its effectiveness for fine-grained diagnostic evaluation: notably, we discover that most explainers are not robust to indirect influences or alternative implementations of the same formula. These results position $\mathsf{Gracr}\mathsf{Bench}$ as a novel, rigorous evaluation setting for graph post-hoc explainability.

AI 总结：针对长程图基准缺乏可验证长程性的问题，提出四个公理及TRIP/GRIP构造框架，可生成可证明的长程任务并提供测试误差下界，用于审计现有基准并揭示过压缩的拓扑与计算瓶颈。

链接：https://arxiv.org/abs/2610.03556

机构：University of Cambridge（剑桥大学）； Ruhr University Bochum（波鸿鲁尔大学）； Microsoft（微软）

作者：Ferran Hernandez Caralt, Simon Heilig, Adrián Bazaga, Asja Fischer, Moshe Eliasof, Pietro Liò

英文摘要：Empirical claims about the connection between over-squashing and long-range interactions in GNNs, can only be trusted if the benchmarks used to validate them genuinely require long-range interactions. The de-facto standard, the Long Range Graph Benchmark, has been repeatedly shown to be saturated by tuned short-range models, with existing synthetic alternatives being tied to specific topologies. As such, there is a lack of principled certificate of long-rangedness on arbitrary graphs. This state reflects the absence of a precise characterization of long-ranged benchmarks. We address this fundamental gap by introducing four verifiable axioms: Predictability, Tightness, Strictly $k$-Range, and Topology-Invariance, that any task claiming to test $k$-hop interactions must satisfy. We formally prove that violating any one of them admits failure modes that undermine conclusions drawn from the task. Based on these axioms, we introduce TRIP (Truly Ranged Interactions Problem) and its generalisation GRIP (Generally Ranged Interactions Problem), constructive procedures that turn any graph into a provably long-ranged task by drawing features from stable distributions. Moreover, by construction, GRIP admits a closed-form, per-range Maximum-Likelihood oracle that yields the first a priori per-range lower bound on test error available on any benchmark. Using our framework, we: (i) audit 4 common long-range benchmarks and identify their failures modes with respect to our axioms; (ii) on TRIP-instantiated topologies, we find a popular notion of curvature is uncorrelated with GNN performance, supporting topological-vs-computational bottleneck distinction; and (iii) we show that a novel benchmark's over-squashing measures factors beyond pure long-rangedness. Code to use the framework and reproduce experiments is released this https URL.

AI 总结：针对增量认知诊断中概念空间扩展导致的历史诊断不一致问题，提出CLEAN框架，通过架构隔离与正交掩码实现零表示漂移，保证心理测量学一致性并提升新题性能。

链接：https://arxiv.org/abs/2610.02278

机构：Shenzhen University（深圳大学）； Guangdong Polytechnic Normal University（广东技术师范大学）

作者：Tao He, Jinxing Xiang, Fan Jiang

英文摘要：Cognitive diagnosis (CD) is a fundamental task in intelligent education that profiles learner proficiency over knowledge concepts. In real-world learning platforms, newly added items continually introduce previously unseen concepts, necessitating dynamic expansion of the underlying concept space. Yet existing incremental CD models assume a fixed concept space, allowing gradients from new items to overwrite historical pathways and induce catastrophic forgetting. More critically, these methods rely solely on soft constraints to preserve historical diagnoses. Such constraints may fail to satisfy the requirement of diagnostic invariance after incremental updates, a requirement known as psychometric consistency in cognitive diagnosis. Therefore, we propose CLEAN (Continual Learning with Expandable and Architecturally Isolated Networks), a novel incremental CD framework supporting concept-space expansion while providing structural guarantees for pointwise invariance of historical diagnoses. Specifically, CLEAN first introduces a strict topological bipartition protocol, freezes historical diagnostic functions and applies deterministic orthogonal column masking to sever gradient interference. Second, to accommodate concept expansion, expandable full-rank branches with micro-variance initialization are deployed to learn novel concepts. Finally, to verify that this architectural design achieves invariance by construction, we formalize Representation Drift (RD) to quantify the perturbation of historical traits. Extensive experiments on three large-scale educational datasets demonstrate that CLEAN achieves zero RD, preserving old-item metrics identically to static anchors through architectural isolation while remaining competitive with or superior to strong continual-learning baselines on new items.

AI 总结：针对持续学习中低秩适配的谱可塑性坍缩问题，MuLoRA通过历史白化与动量更新的近似极正交化联合控制容量分配与利用，在多个类增量基准上取得最优平均准确率。

链接：https://arxiv.org/abs/2610.02283

机构：Tianjin University（天津大学）

作者：Junkang Liu

英文摘要： Low-rank adaptation (LoRA) provides a parameter-efficient approach to continual learning, but its nominal rank can conceal a loss of effective adaptation capacity. We identify \emph{spectral plasticity collapse}: during sequential adaptation, update energy becomes concentrated in a small subset of singular modes, leaving much of the available low-rank space underutilized. This exposes a limitation of interference avoidance alone: protecting historical representations does not ensure that the remaining adaptation capacity is responsive to new tasks or effectively utilized. To address this problem, we propose \texttt{MuLoRA}, which jointly controls capacity allocation and utilization. First, historical whitening identifies input directions with strong current-task response relative to accumulated historical response, yielding a task-adaptive basis that remains fixed during training. Second, approximate polar orthogonalization of momentum updates reduces spectral concentration within theselected space. An orthonormal basis connects these mechanisms by transferring the factor-update spectrum exactly tothe induced weight update. We establish a max--min characterization of exact subspace selection and derive cumulative spectral bounds under controlled cross-step anisotropy. Across five class-incremental benchmarks and eight incremental settings, \texttt{MuLoRA} achieves the highest mean accuracy in 15 of 16 reported metrics.

AI 总结：本研究提出LINEUP框架，通过共享低秩个性化因子库和极小的用户编码（每用户仅8个标量），在12项指标上全面超越私有LoRA，证明个性化可主要依赖可复用共享容量。

链接：https://arxiv.org/abs/2610.02353

机构：Samsung Semiconductor, US（三星半导体（美国））； Rice University（莱斯大学）

作者：Songyuan Sui, Srikanth Malla, Chiho Choi, Joon Hee Choi

英文摘要：Personalized large language models often require a complete adaptation state for each user. However, this paradigm scales poorly as the user population grows. We revisit this design through the lens of personalization capacity allocation: how much adaptation capacity can be shared across users, how the shared capacity should be composed, and how much must remain user-specific. We answer them through three complementary empirical analyses. We find that independent user adapters contain substantial cross-user reusable structure, that the utility of reusable directions reflects both user relevance and variation across queries, and that user histories provide transferable signals for compact individual correction. Motivated by these findings, we propose LINEUP. It learns a bank of reusable low-rank personalization factors, composes them through user-conditioned recall and query-dependent calibration, and restricts target-user adaptation to a tiny user code over a shared correction space. This design decouples expressive personalization capacity from per-user trainable state. Each target user optimizes only eight scalars, while all shared components remain fixed. By comparison, the evaluated private-LoRA configuration uses 4.19 million per-user parameters. Our theoretical analysis gives a finite-step, finite-history risk bound and sufficient conditions for user-code refinement to improve on history initialization. Across six tasks spanning personalized classification, prediction, and generation, LINEUP leads on all 12 metrics, each averaged over three independent runs (e.g., reducing LaMP-3 RMSE by 11.4% relative to the strongest baseline). It maintains advantages under limited history. These results show that rich personalization can be supported primarily by reusable, conditionally composed shared capacity, while independent user adaptation remains confined to a tiny correction state.

AI 总结：针对时间域泛化中噪声过拟合和复杂历史建模问题，提出谱正则化Koopman动力学与目标条件注意力机制，在八个基准上取得最优性能。

链接：https://arxiv.org/abs/2610.02822

机构：East China Normal University（华东师范大学）

作者：Tengxue Zhang, Yu Ke, Yang Shu, Chenchen Sun, Yisheng An, Chenjuan Guo, Bin Yang

英文摘要：Temporal Domain Generalization (TDG) has emerged to address real-world streaming data with distribution shifts over time. However, existing methods are either prone to overfitting to domain-specific noise in the data space or become overly complex and less interpretable in the parameter space. To bridge these gaps, we propose \textbf{AdaSpecK}, a spectral-Koopman framework with adaptive context extraction for TDG. To mitigate noise fitting to irregularly sampled domains, we introduce spectral-regularized Koopman dynamics modeling, which applies spectral-aware filtering in the latent space to extract denoised low-frequency trajectories and learn a Koopman operator to model the system dynamics in a linearized space. To model complex historical environments under non-stationarity, we design a context-informed heterogeneous pattern extraction mechanism. Specifically, we employ a target-conditioned attention module to attend to distinct past windows, producing a dynamic, target-specific historical summary. By constructing an environmental signature from the current evolutionary pattern, our model adaptively perceives which aspects of the past context are most informative for future prediction via a learned router. Extensive experiments on eight diverse classification and regression benchmarks demonstrate that AdaSpecK achieves state-of-the-art performance. The code and datasets are available at \href{}{ this https URL }.

AI 总结：针对世界模型在持续适应中需区分可遗忘与不可遗忘知识的问题，提出按不变性时间尺度分层保留的差分保留方法，并联合报告不变量回归测试与修订延迟。

链接：https://arxiv.org/abs/2610.03713

机构：University of Maryland, College Park（马里兰大学学院公园分校）

作者：Nishit Anand, Ramani Duraiswami, Dinesh Manocha

英文摘要：Continual learning treats degradation on previously seen data as evidence of failure, a convention inherited from settings with a stationary prediction target, where a correct label remains correct indefinitely. World models do not satisfy this condition. Their prediction target is the environment, which changes, so knowledge that was accurate when acquired may later become false, and discarding it is required behavior rather than a defect. Non-stationary ground truth is well studied in the concept drift literature and in the temporal factuality of language models, but has not been formulated for world models, which are distinctive in that they also encode knowledge that must never be revised. We argue that continual world models require retention stratified by invariance timescale, separating invariants such as physics and object permanence, which must never be revised, from instance-level facts that should be revised as soon as the environment changes. Standard forgetting metrics cannot distinguish a world model that has correctly revised outdated knowledge from one that has suffered catastrophic forgetting, and consequently rank a frozen model highest, while existing physical-reasoning benchmarks evaluate only frozen checkpoints. We propose differential retention, which reports invariant regression testing across the adaptation stream jointly with revision latency, without aggregation.

AI 总结：TRACE是一个可复现的电价预测基准，结合官方运行文本与价格数据，评估语义一致性并验证预测价值，上尾损失中位数降低7.4%。

链接：https://arxiv.org/abs/2610.02256

机构：University of Cambridge（剑桥大学）

作者：Xinyi Yi, Moy Yuan, Ioannis Lestas

英文摘要：Electricity price forecasting (EPF) supports scheduling, bidding, and risk management in electricity markets, yet existing benchmarks focus mainly on numerical inputs, leaving the forecasting value of forecast-time textual context insufficiently evaluated. We introduce TRACE, a reproducible benchmark of 7,300 zone--day instances pairing prices from five zones in a major U.S. market with official operational text available at the forecast cutoff. TRACE reconstructs official operational text at each cutoff, preventing post-cutoff information leakage. We evaluate TRACE for semantic alignment and forecasting value. Semantic assessments align with central movement and both tail risks in ground-truth prices, most consistently for upper-tail price risk. Forecasting value is reflected in a median 7.4\% reduction in upper-tail pinball loss across time-series foundation models. A controlled cross-day text-mismatch ablation reverses the gains, falling below the no-text baseline.

AI 总结：本研究探讨脉冲间隔变化对蝙蝠叫声分类的影响，发现其对Transformer和CNN模型作用有限，但归一化条件结果难以直接迁移至自然录音。

链接：https://arxiv.org/abs/2610.02284

机构：Naturalis Biodiversity Centre（荷兰自然生物多样性中心）； Tilburg University（蒂尔堡大学）

作者：Welmoed R. Eversteijn, Burooj Ghani, A. Leonie Baier, Dan Stowell

英文摘要：Temporal context may aid automated bat-species classification, but the contribution of specific features remains unclear. We investigated whether variation in the interpulse interval (IPI)-the time between consecutive call onsets-provides species-discriminative information and whether transformer-based models are more sensitive to this information than convolutional neural networks. We created two matched datasets from European bat recordings: a natural-IPI condition retaining the original call timing and a normalized-IPI condition in which call onsets were spaced at 50-ms intervals. EfficientNet-B0 and PaSST were fine-tuned and evaluated within each condition. In an additional experiment, each architecture was trained separately on natural-IPI and normalized-IPI recordings, and evaluated on the same natural-IPI test set. Finally, the pretrained classifiers BatDetect2 and BAT were evaluated on both conditions. Within-condition IPI normalization had model-dependent effects. PaSST accuracy differed little between the natural-IPI ($71 \pm 2.3\%$) and normalized-IPI ($70 \pm 6.3\%$) conditions, whereas EfficientNet accuracy increased from $47 \pm 4.7\%$ to $57 \pm 3.9\%$. PaSST exceeded EfficientNet under both conditions. In the cross-condition evaluation, models trained on natural-IPI recordings outperformed those trained on normalized-IPI recordings on the natural-IPI test set: accuracy decreased from 54% to 50% for EfficientNet and from 65% to 57% for PaSST. BatDetect2 and BAT differed little between IPI conditions. Overall, we found limited support for the hypotheses that natural IPI variation contributes substantially to bat-species classification and that it is used more effectively by transformer-based than CNN-based models. Nevertheless, the cross-condition performance decrease shows that results obtained under normalized conditions may not transfer fully to natural recordings.

AI 总结：PowerBench是一个评估语言模型在权力转移请求中偏见的基准，通过区分自我赋权、去权和权力攫取，发现模型拒绝权力攫取多于去权，且存在国籍和用户类型相关的系统性偏见。

链接：https://arxiv.org/abs/2610.02303

机构：Universidad de Buenos Aires（布宜诺斯艾利斯大学）； Buenos Aires AI Safety Hub（布宜诺斯艾利斯AI安全中心）； The World Bank（世界银行）； Universidad Nacional de General San Martín（国立圣马丁大学）

作者：Nicolas Martorell, Wendy Brau, Gonzalo A. Heredia, Tomás Pablo Korenblit, Gaspar Labastié, Tomás Gimenez Molina

英文摘要：Language models increasingly assist people with power-related requests, so systematic differences in whom they help could shift the distribution of power at scale, or be exploited by users who learn which identities are refused less. We introduce PowerBench, an evaluation of power-shifting requests that distinguishes self-empowerment, disempowerment, and power grabbing, plus a control of refusal-inducing requests that shift no power. We build, curate, and open-source a dataset of such requests varying the power domain, the context, the scale of the affected party, and the prior power standing of the user, and evaluate 24 models (12 from US and 12 from Chinese developers) under three experimental conditions: reciprocal nationalities of user and affected party, an AI agent as the user, and 8 request languages. Models refuse power grabbing more than disempowerment, and disempowerment more than self-empowerment. Refusal of power grabbing rises with the scale of the affected party, from an individual to a society. Models are biased toward helping others take power from the US and against helping US users take power from others, but favor the US when it gains power and nobody loses it. When the user is an AI agent, refusal of power-shifting requests increases, especially in power grabbing against an individual. Finally, language biases refusal, but in model-specific ways that largely cancel on average. We release PowerBench to make these asymmetries measurable in current and future models.

AI 总结：提出协同设计健身房基准，涵盖20个领域、85种预设，用于联合优化智能体体现与策略，并系统评估现有算法，推动该领域研究。

链接：https://arxiv.org/abs/2610.02366

机构：University of Cambridge（剑桥大学）； Carnegie Mellon University（卡内基梅隆大学）； MorphoAI； Technical University of Munich（慕尼黑工业大学）

作者：Aviraj Newatia, Yordan Tsvetkov, Leonard Pleiss, Andrew Spielberg, Rika Antonova

英文摘要： Finding an optimal behaviour policy within a given environment is a widely studied problem in domains as diverse as games, robotics, energy infrastructure, communication networks, and multi-agent systems. Numerous benchmarks have been developed to support such research, but the vast majority assume that the agent's embodiment (design) is fixed, focusing instead on policy learning alone. Lifting this assumption gives rise to a broader class of problems in which optimizing embodiment and policy separately is highly suboptimal. An agent's embodiment strongly shapes which control policies can be discovered, while the optimal embodiment is in turn defined by the policies it admits. To help the research community study this class of problems explicitly and systematically, we introduce Co-Design Gym - a suite of benchmark environments for jointly optimizing embodiment and policy. Our environments span domains such as robotic manipulation and locomotion, multi-robot cooperation, deformable and soft dynamics, video games, electricity grids, wireless networks, F1 racing, multi-agent warehouses, and optimal control, offering 20 environment families (domains), with over 85 distinct co-design presets in total. We further contribute a systematic evaluation of representative co-design algorithms, characterizing the current state of the art. Together, these contributions lay the groundwork for cumulative, comparable progress in co-design.

AI 总结：本报告提出一种仅利用预测时信息的数据接入流程，检测并修复建筑计量数据缺陷，受控实验表明其能将梯度提升预测器误差恢复至清洁水平，并保留93%训练目标。

链接：https://arxiv.org/abs/2610.02397

作者：Yixuan Liang

英文摘要：Electric utilities and grid operators increasingly rely on machine-learning models to forecast next-day demand, and those models learn from meter data that is routinely defective: readings go missing, sensors freeze, buildings read zero for hours, and units change by a factor of 100. This report presents a data-onboarding pipeline that detects and repairs such defects before a model is trained, using only information available at forecast time, and a controlled experiment that measures whether the pipeline protects a 24-hour-ahead forecast. On hourly electricity data for twelve U.S. buildings from the public Building Data Genome 2 dataset (210,528 rows, 2016-2017), seeded, hash-logged defects touching 0.10% of the training period raised the error of a gradient-boosting forecaster by 86%; after detection and past-only repair the error returned to the clean-data level (mean absolute scaled error 0.760 clean, 1.415 corrupted, 0.729 repaired) while 93% of training targets were retained. At a defect prevalence calibrated to published field studies (1.6% of training rows) the unprotected forecaster's error reached 4.4 times that of a seasonal-naive rule, and the repaired forecaster again matched the clean baseline. The same pattern held for ridge regression and a random forest and across horizons of 1 to 24 hours. A first version of the pipeline over-cleaned natural data and made forecasts 25% worse; that result is retained, its cause is traced in the published artifacts, and the per-building calibration that corrects it is documented as a dated amendment. Every number is reproducible from pinned public inputs with SHA-256 verification, 84 automated tests and continuous integration.

AI 总结：针对多模态智能体在可视化自主审查中的不足，提出 VisAudit 基准，含 1,900 个缺陷实例和 300 个正确图表，评估诊断、修复和验证，实验显示最强模型仅恢复 47.4% 缺陷图表。

链接：https://arxiv.org/abs/2610.02399

作者：Shicheng Liu, Adam Kahirov, Qi Zhang, Zhimin Hu, Song Wang, Junhong Lin, Julian Shun, Yada Zhu

英文摘要：Multimodal agents are increasingly used for data visualization tasks but remain limited in autonomous review. Unlike humans, they may fail to recognize when a visualization is incorrect, determine what to change, repair it without disrupting correct content, and verify whether the intervention succeeded. Existing benchmarks largely evaluate predefined individual capabilities such as chart generation, instruction-guided editing, or defect detection, and therefore do not capture this gap in autonomous review. We introduce VisAudit, a benchmark for evaluating visualization diagnosis, repair, and verification. Given a rendered chart and configurable auxiliary evidence, including its source data table, intended text summary, and visualization code, an agent iteratively diagnoses potential defects, modifies and executes visualization code, inspects execution and visual feedback, and determines when no further intervention is needed. VisAudit defines three tracks spanning diagnosed repair, autonomous repair, and open-world verification, and contains 1,900 flawed instances across 21 chart types and 10 flaw categories, together with 300 initially correct charts. We construct the benchmark through controlled perturbations of validated source visualizations, with systematic verification and human-aligned quality control to ensure that injected defects are well-defined and recoverable from the available evidence. Experiments with leading multimodal models reveal a substantial gap from reliable autonomous review: the strongest evaluated model fully recovers only $47.4\%$ of flawed charts in the autonomous-repair setting.

AI 总结：本文提出AlgoREval基准，评估LLM在经典算法代码检索中的能力，发现准确率因语言和输入表示而异，提示增强和微调可提升性能，并警示需验证AI生成代码。

链接：https://arxiv.org/abs/2610.02438

机构：University of Edinburgh（爱丁堡大学）

作者：Nickil Maveli, Antonio Vergari, Shay B. Cohen

英文摘要：Large language models (LLMs) have demonstrated strong performance in code generation, where success depends on both recalling relevant algorithmic knowledge and reasoning about how to apply it. However, existing LLM pipelines are opaque, with no explicit separation between these two components. We argue that for well-known algorithms whose canonical implementations are widely accessible in pretraining corpora, code generation is better measured as \textit{parametric code retrieval}: reproducing a named algorithm from internalised knowledge rather than synthesizing a novel one. We introduce AlgoREval, a benchmark of 599 problems spanning classical 77 algorithms across 14 domains, 7 programming languages, and 4 graph-input representations to evaluate this capability in isolation, and assess 15 models (7B--34B parameters) in a zero-shot setting. We find substantial variation in retrieval accuracy across languages and input representations, even for widely documented algorithms and show that prompt augmentation with retrieved code snippets or structured algorithmic hints improve accuracy on complex algorithms, while SFT achieves broader language gains and GRPO achieves larger per-language gains on specific languages. Together, our results establish parametric code retrieval as a distinct, measurable capability and caution against deploying AI-generated algorithmic code without systematic validation.\footnote{Code and dataset are available at this https URL

AI 总结：OpenGameEval在Roblox Studio中评测智能体编程，通过分离观察与编辑工具直接衡量探索，发现探索行为显著预测任务成功率，且当前模型在84个任务上表现困难。

链接：https://arxiv.org/abs/2610.02563

机构：Roblox

作者：Eray Turkel, Mengsha Sun, Kartik Ayyar, Sean Dunigan, Jack Lu, Vlad Shcherban, Hsiang-Shun Shih, Xin Wang, Tiantian Zhang

英文摘要：We present OpenGameEval, a benchmark and evaluation framework for agentic game development inside Roblox Studio. It runs language models as agents in reproducible, stateful game-engine sessions and scores each run with executable checks, both on the edited scene and in a simulated play session. Most agentic coding benchmarks require exploration but score only final task success. OpenGameEval separates observation tools from editing tools in its eight-tool action space, so exploration can be measured directly. We measure the pass rates and exploration behavior of 13 frontier models on 84 human-curated core tasks, with 16 attempts per task. The tasks are hard for current models. The best model solves 51.7% of tasks on a single attempt and 39.4% five times out of five, and no tested model solves six of the tasks. Models at the frontier reach similar pass rates by solving different tasks: splitting tasks by the kind of work they require spreads the top five by 5.0pp on script-authoring tasks and 12.5pp on scene-change tasks. Exploration behavior predicts whether a run succeeds. Holding task and model fixed, a run that inspects every object a reference solution touches before acting on it passes 13.4pp more often than a run that inspects none of them on scene-only tasks, and 9.8pp more often on script-only tasks. We release the task suite, its place files, the per-task annotations, a plugin that runs the tasks inside Roblox Studio, and an updated leaderboard under the MIT license at this https URL.

AI 总结：本文提出MAG-SCOUT框架，在构建图前评估其预期效用，决定是否图化多模态数据，实验节省33.1%图工作并保留96.7%正增益。

链接：https://arxiv.org/abs/2610.02768

机构：Beijing Institute of Technology（北京理工大学）； Sun Yat-sen University（中山大学）； Shandong University（山东大学）

作者：Zekai Chen, Kai Hu, YuXin Zeng, Xunkai Li, Xun Wu, Yinlin Zhu, Zhengyu Wu, Xu Wang, Rong-Hua Li

英文摘要：Multimodal graph learning has recently emerged as an effective paradigm for in corporating inter-entity relationships into multimodal representations. Existing studies have made substantial progress on how to construct and optimize graphs, but rarely consider a more fundamental question: whether additional relational structures should be introduced for a given dataset and task. Through empirical studies across diverse datasets, tasks, and graph constructors, we reveal that graphification is not consistently beneficial: introducing relational structures can provide substantial improvements in some cases, while offering limited or even negative gains. This observation motivates a new perspective that graph construction should be treated as a selective decision based on its expected utility rather than a default preprocessing step. To address this issue, we propose MAG-SCOUT, a pre-construction graph assessment framework that estimates whether introducing graph structures is beneficial before generating the complete topology. MAG-SCOUT collects limited relational evidence, analyzes its potential taskspecific contribution, and estimates the expected utility of graphification together with construction cost to make a build-or-skip decision. Extensive experiments across six multimodal datasets, three downstream tasks, and diverse graph constructors demonstrate that MAG-SCOUT effectively identifies when graph structures should be introduced, saving 33.1% of task-macro graph work while retaining 96.7% of held-out positive-gain mass under the pre-registered floor.

AI 总结：D2K-Bench通过26个任务和85个工作负载诊断基准，评估LLM智能体在专家设计指导下生成GPU内核的效率，实验表明指导显著提升正确率与性能，并揭示未实现的设计属性。

链接：https://arxiv.org/abs/2610.03226

机构：HKUST（香港科技大学）； Alibaba Group（阿里巴巴集团）； USTC（中国科学技术大学）

作者：Daifeng Li, Huiqiang Jiang, Chengruidong Zhang, Wei Wu, Xudong Guo, Jianhong Tu, Jianwei Zhang, Binhang Yuan, Dayiheng Liu

英文摘要：GPU kernels generated by large language model (LLM) agents can remain less efficient than expert implementations, but runtime alone does not reveal how the gap relates to design discovery and implementation. We introduce D2K-Bench, a diagnostic benchmark of 26 tasks and 85 workloads that measures how effectively agents translate expert design guidance into efficient GPU kernels. The guidance covers L1: high-level algorithmic insights, L2: dataflow design, and L3: low-level optimization tricks, including dependencies among these levels. Pairwise runs with and without guidance share task descriptions, workloads, tools, hardware, and a 350-turn budget. Complementary assessments examine independently proposed designs and the design properties implemented in generated code. Across five models on NVIDIA B200 GPUs, guidance raises correctness over 130 model-task pairs from 93.1% to 98.5% and increases the Performance Score over all 26 tasks from 1.46 to 1.95. For the three frontier models with correct submissions on all 26 tasks in both runs (GPT-6-Astra, Claude-Opus-4.8, and GPT-5.6-Sol), geometric mean speedup increases from $1.69\times$ to $2.49\times$. Across all five models, the mean combined implementation score increases from 57 to 70 out of 100. These results show the value of expert design guidance while identifying design properties that remain unimplemented.

AI 总结：PaMIR是一个开放基准，汇集19个公共信用违约数据集（124万样本），在标签稀缺且延迟到达场景下，通过到达时评分和标签预算报告AUC，为信用违约预测提供标准化评估。

链接：https://arxiv.org/abs/2610.03259

作者：Mikhail Liashkov, Ilyas Varshavskiy, Shuhratjon Khalilbekov, Azizjon Azimi, Bonu Boboeva

英文摘要： We release PaMIR (Public Arrival-ordered Measurement for Inference in Risk), an open benchmark for credit-default prediction when labels are scarce and arrive late. The field's reference benchmark studies use eight datasets each, only two or four of them public. PaMIR brings together 19 public datasets with binary default labels -- 1.24M loans, firms and card accounts from nine countries -- rebuilt from pinned source snapshots by one leakage-audited recipe and never redistributed; to our knowledge it is the one of its kind as of today. Every model is a single function, scored under a repeated i.i.d. split and a label-delayed stream in which each application is scored on arrival, with AUC reported by label budget; fleet means are withheld unless every dataset is scored. A synthetic-data harness tests generated training rows without letting a generator see held-out rows. This report describes release 0.4.0 of this living benchmark.

AI 总结：本研究通过预注册的规模阶梯基准测试发现，深度表格生成器在训练样本少于20,000行时通常无法超越平凡基线，且排名稳定性在小规模下反而更高，质疑了子采样大数据集作为小数据集替代品的有效性。

链接：https://arxiv.org/abs/2610.03500

机构：VIT Bhopal University（维特博帕尔大学）

作者：Shivam Shrivastava

英文摘要：Deep tabular generative models are benchmarked on datasets with tens of thousands of rows; clinical datasets have hundreds. We preregistered and ran a size-ladder benchmark to find where the two regimes diverge: 8 public datasets subsampled from 200 to 20,000 training rows, seven generators (independent marginals, Gaussian copula, SMOTE, unconditional SMOTE, CTGAN, TVAE, TabDDPM) with a fixed 20-trial tuning budget and 5 evaluation seeds, plus 4 natively small clinical datasets at true size, for 2,220 committed runs in total. The primary metric is the AUROC of fixed classifiers trained on synthetic and tested on real data. In 23 of 24 (dataset, deep model) pairs no deep model ever beats the best trivial baseline by more than seed noise, at any training size we measured. The best baseline wins 40 of 49 (dataset, size) cells. Our preregistered prediction that the deep models' ranking would be unstable at small sizes is falsified: mean Kendall tau between adjacent rungs below 5,000 rows is 0.806, above our 0.8 threshold, and stability is highest at the smallest sizes rather than lowest. One caveat bounds all of this: in 81% of cells the gap between the top two methods is smaller than the variation between seeds. Finally, method rankings on natively small clinical datasets agree only moderately with rankings on subsampled large ones (mean tau 0.57 to 0.64), which questions whether a subsampled large dataset can stand in for a small one. All 2,220 result files, the preregistration and its hash, and the code that regenerates every figure and number from those files are public.

AI 总结：该研究发布了一个包含三名受试者各30小时fMRI数据的深度数据集，用于解码自然语音，并提出了音频片段检索基准，实验表明解码性能随训练数据量增加而提升。

链接：https://arxiv.org/abs/2610.03558

机构：Karavela； UNICOG, CNRS, INSERM, CEA, Paris-Saclay University（UNICOG，CNRS，INSERM，CEA，巴黎萨克雷大学）； LSCP, EHESS, ENS, CNRS, PSL University（LSCP，EHESS，ENS，CNRS，巴黎文理研究大学）； Centre de NeuroImagerie de Recherche (CENIR), Sorbonne Université, ICM（索邦大学巴黎大脑研究所神经影像研究中心（CENIR））； Department of Radiology, Hôpital Fondation Adolphe de Rothschild（罗斯柴尔德基金会医院放射科）； Inria, CEA, Paris-Saclay University（法国国家信息与自动化研究所，CEA，巴黎萨克雷大学）

作者：Antoine Collas, Louis Jalouzot, Géraud Ilinca, Corentin Caris, Romain Valabrègue, Ahmed Hassayoune, David Goncalves, Madeleine Hueber, Thaddée Delebarre, Julien Savatovsky, Clara Fonteneau, Charles Maussion, Bertrand Thirion, Alexis Thual

英文摘要：Cephalonauts One is a whole-brain 3 Tesla (3T) functional magnetic resonance imaging (fMRI) dataset recorded while subjects listened to audio podcasts. Three healthy subjects underwent multiple scanning sessions, each consisting of five 15-minute runs, while listening to podcasts in their native language. With 30 hours of fMRI data per subject, the current release is the deepest available fMRI dataset using naturalistic speech stimuli. The dataset pairs brain activity with the corresponding podcast audio, transcript annotations, and derived stimulus embeddings. Furthermore, we introduce a brain decoding benchmark formulated as audio segment retrieval: given fMRI activity from a held-out session, the decoder must identify the corresponding time-aligned podcast audio segment among candidate segments. We provide standardized splits, evaluation metrics, and baseline decoders for this task. Finally, a scaling analysis shows that decoding performance improves continuously with the amount of training data per subject.

AI 总结：针对现有时间序列预测方法在机制转换、跨域迁移和多模态集成上的不足，提出MACTS-EM多智能体协作框架，通过涌现记忆与元认知分配，在多个领域实现8-12%准确率提升及显著更强的零样本迁移和鲁棒性。

链接：https://arxiv.org/abs/2610.02255

机构：Unitec Institute of Technology（Unitec理工学院）

作者：Ahmad Shahi, Mamehgol Yousefi

英文摘要：Time series forecasting remains a critical challenge across numerous domains. Despite significant advancements, existing approaches struggle with complex phenomena such as regime shifts, cross-domain knowledge transfer, and multimodal data integration. This paper introduces Multi-Agent Collaborative Time Series Forecasting with Emergent Memory (MACTS-EM), a novel framework where specialised agents collaborate to achieve superior forecasting performance. The MACTS-EM architecture integrates: (1) domain-specialised forecasting agents for pattern recognition, anomaly detection, causal inference, and uncertainty quantification; (2) a meta-cognitive layer for dynamic agent allocation; (3) an emergent memory mechanism enabling cross-domain pattern transfer; (4) multimodal contextual integration; and (5) adversarial robustness components. Evaluation across financial markets, climate patterns, energy consumption, and pandemic propagation demonstrates that MACTS-EM outperforms existing approaches in most scenarios, with 8-12% improvement in forecasting accuracy, 22-27% better zero-shot transfer capability, 16-21% enhanced resilience during regime shifts, and 15-18% faster recovery after distribution shifts. Our findings suggest that collaborative, agentic approaches to time series forecasting represent a promising direction beyond traditional architectures, particularly for complex real-world scenarios requiring multi-resolution temporal understanding and contextual adaptation.

AI 总结：针对固定目标神经异常检测器在收敛时残差信号消失的坍缩问题，提出核锚定正则化器（KAR），通过惩罚预测与核加权目标偏差保持局部性，在ADBench上缓解坍缩并提升AUROC。

链接：https://arxiv.org/abs/2610.02345

机构：Université Paris-Saclay（巴黎-萨克雷大学）； CNRS（法国国家科学研究中心）； CentraleSupélec（中央理工-高等电力学院）； LISN UMR 9015（数字科学跨学科实验室）； Laboratoire Interdisciplinaire des Sciences du Numérique（数字科学跨学科实验室）

作者：José Lucas De Melo Costa, Fabrice Popineau, Arpad Rimmel, Bich-Liên Doan

英文摘要：A family of tabular anomaly detectors trains a neural map toward a fixed target under squared-error loss and scores anomalies by the test-time residual; contraction matching, one-step rectified flow, and reconstruction autoencoders all fit this template. We characterize a convergence collapse: better optimization makes the detector worse. At convergence, the learned map tracks the target even off-distribution, so the residual signal vanishes on anomalies as well as on normal data. These detectors therefore rely on implicit non-convergence (early stopping, capacity caps) to retain signal. We argue this is structural: effective anomaly detection requires a locality constraint that blocks unconstrained extrapolation. Classical detectors (kNN, KDE, isolation forests, LOF) enforce locality explicitly; fixed-target neural detectors do not. We formalize the connection by showing that the kernel-regression analog of a fixed-target detector is a finite-bandwidth Nadaraya-Watson smoother, which we call Kernel Contraction Matching (KCM). KCM is closed-form, training-free, and CPU-efficient, yet matches established neural baselines on ADBench. Building on this bridge, we introduce the Kernel-Anchored Regularizer (KAR), which penalizes deviation of the neural prediction from a kernel-weighted average of training targets. Across collapse-prone ADBench datasets and three backbones, KAR mitigates collapse and improves AUROC under prolonged training.

AI 总结：提出DAIST，一种可组合的AI加速迭代热求解器，通过域分解和神经算子实现块级重用，在多芯片系统上达178倍加速且误差低于0.33%。

链接：https://arxiv.org/abs/2610.02461

机构：Cadence Design Systems（楷登电子）； University of Notre Dame（圣母大学）

作者：Yixing Li, Jiahang Zhou, Zhiyu Zeng, Xin Ai

英文摘要：Accurate thermal analysis of heterogeneous 2.5D/3D-IC packages is essential yet computationally prohibitive. A single full-package FEM simulation can take hours, while AI-based surrogates treat the entire stack as a monolithic prediction target and must be retrained whenever the die count or topology changes. To address this limitation, this work proposes Domain-Decomposed AI-Accelerated Iterative Solver for Thermal Analysis (DAIST), a composable thermal solver that decomposes the global package simulation into block-level subdomain problems, replaces subdomain solvers with neural operators, and couples them through iterative exchanges of interfacial temperature and heat flux. This local-to-global architecture eliminates the topology lock-in of monolithic models: block-level neural operators can be directly reused in unseen package assemblies without retraining. The iterative coupling strategy further provides a controllable accuracy-runtime tradeoff, where the iteration budget can be adjusted to trade accuracy for runtime. Evaluated on a multi-chiplet system and an advanced packaging system, DAIST achieves up to $178\times$ speedup over traditional FEM solvers with mean temperature errors of 0.068% and 0.323%, respectively, while demonstrating cross-topology reuse of block-level models across structurally distinct package assemblies.

AI 总结：本研究探索后训练量化（PTQ）在自回归天气模拟器（DLWP和FourCastNet）中的应用，验证其能在短程预报中保持定性有效的预测，为动态系统DL模型的量化优化提供首个基准。

链接：https://arxiv.org/abs/2610.02511

机构：University of Michigan（密歇根大学）； University of Texas at Dallas（德克萨斯大学达拉斯分校）

作者：Ananyo Bhattacharya, Swastik Bhattacharya, Christiane Jablonowski

英文摘要：Advancements in high-resolution numerical weather prediction (NWP) and data assimilation (DA) have shaped the developments in deep learning (DL) architectures emulating atmospheric dynamics. Emulators for weather forecasting exhibit forecast quality comparable to physics based models at forecast horizon scaling from few days to subseasonal time scales. The emulators are driven by hardware-accelerated matrix multiplication in autoregressive inferences, significantly reducing the computation time and resources required for NWP. Optimization of the matrix multiplication processes in GPU architectures provides opportunities to scale towards high-resolution domain, and offers implementation of out of the box solutions. Post-training quantization (PTQ) has been demonstrated across multiple DL architectures to accelerate and increase the number of computations in unit time while consuming less power, enabling applications on edge hardware. In this study, we investigate the effect of PTQ on pre-trained AI emulators for global-scale weather forecasting. We implement PTQ algorithms in Deep Learning Weather Prediction (DLWP) and FourCastNet (FCN) models as a proof of concept for geophysical fluid dynamics applications. We systematically investigate the effect of PTQ on emulator inferences over short-range forecast horizons. Evaluation of PTQ configurations using simulated quantization hints at qualitatively meaningful forecasts over short-time horizons. These results provide a first benchmark of PTQ for autoregressive weather emulators and a basis for quantization-based optimization of DL models for dynamical systems.

AI 总结：提出一种两阶段统计-编码器级联方法，利用Sentinel-1时间序列实现近实时森林异常检测，克服云层遮挡和季节性后向散射干扰，输出可审计的置信度与风险等级。

链接：https://arxiv.org/abs/2610.02763

作者：Pann Thinzar Seint, Subas Chhatkuli, Bryan Atwood

英文摘要： Tropical forest monitoring is essential for global climate stability and biodiversity preservation. To address the urgent need for rapid, reliable detection of forest loss which is essential for timely intervention against illegal logging, supply chain transparency, land-use governance and carbon market standards, we introduce a two-stage statistics-encoder cascade for near-real-time anomaly detection using Sentinel-1 time series. Our system is designed to overcome two fundamental challenges in remote sensing: the cloud-cover limitations that restrict optical monitoring and seasonal backscatter variation that causes SAR systems to mistake natural moisture changes for forest loss. The architecture integrates two distinct analytical engines to ensure high-fidelity detection: (1) an adaptive, robust-statistics z-score test on co-registered Sentinel-1 VH backscatter, same-season historical baseline and (2) a learned confirmation gate based on the latent-space structural similarity (SSIM) of a convolutional autoencoder trained on stable-forest patches. A candidate disturbance is confirmed as an alert only when both stages agree, and is assigned a confidence score and a Low/Medium/High risk tier from its repeat-occurrence history. The system produces per-alert auditable confidence scores and area-in-hectares estimates directly compatible with Monitoring, Reporting and Verification (MRV) workflows, sustainable forestry management, operational field checks and environmental risk assessments. Beyond its primary application, the model's flexibility allows for critical environmental applications ranging from selective logging to large-scale agricultural encroachment mapping, flood mapping and so on.

AI 总结：针对时间序列预测中机器遗忘的挑战，提出RDTU残差扩散框架，通过神经正切核基础预测与扩散残差校正生成伪标签，实现轻量级模型更新，实验证明其效果最接近精确重训练。

链接：https://arxiv.org/abs/2610.02865

机构：The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））； Zhejiang University（浙江大学）； University of Sydney（悉尼大学）； Northwestern University（西北大学）； Analogy AI, Inc.（Analogy AI公司）； Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）

作者：Zeyu Shi, Yanhui Luo, Ziming Hong, Chongyang Gao, Kezhen Chen, Shanshan Ye, Lixu Wang

英文摘要：Time-series forecasting is widely used in sensitive domains. Models in these settings are often trained on longitudinal user- or entity-level records, which may later require removal because they contain sensitive or proprietary information or have been corrupted by sensor failures. To address such deletion requests without costly retraining, machine unlearning has been widely studied as a practical mechanism for privacy protection and data governance. However, the application of machine unlearning to time series prediction has not yet been well realized; this is mainly due to the following unique challenges: Gradient-based unlearning can be unstable because a deleted observation participates in multiple causally connected forecasting windows, causing parameter updates to propagate beyond the requested interval and degrade retained forecasting utility. Label-guided updating offers a more controlled alternative, but continuous and context-dependent forecasts lack a suitable replacement target, while the exact-retrained output is unavailable during unlearning. Moreover, the remaining support for a deleted temporal pattern is highly non-uniform. Some affected windows retain structurally similar counterparts in the retained data, whereas others become underrepresented or isolated. We present RDTU, a Residual Diffusion framework for time-series unlearning. RDTU first uses a retained-set neural tangent kernel predictor to obtain a deletion-compatible base forecast. Then it quantifies the global and local structural support of each affected window using the volume contribution of the retained-reference data. Then a diffusion model generates a residual correction that estimates the counterfactual forecast, yielding a pseudo-label field that guides a lightweight model update. Experiments show that RDTU consistently produces unlearned models that most closely match exact retraining.

AI 总结：针对生物信息神经网络在方程学习中的超参数选择难题，提出一种基于三个诊断问题的结构化工作流程，并在合成系统上验证其有效性，提供实用经验法则和起始值建议。

链接：https://arxiv.org/abs/2610.02954

机构：Uppsala University（乌普萨拉大学）； The College of New Jersey（新泽西学院）

作者：William Lavery, Jodie A. Cochrane, John T. Nardini, Sara Hamis

英文摘要：Biologically-informed neural networks (BINNs) have emerged as a flexible subclass of physics-informed neural networks (PINNs) for learning terms in partial differential equations from data. BINNs are particularly suited for biological systems, where the governing equations are highly nonlinear and only partially known a priori, and where data observations are often sparse, noisy, and incomplete. However, applying BINNs effectively in practice depends critically on hyperparameter selection, which remains a central challenge in equation-learning frameworks. Hyperparameters are often chosen heuristically and only cursorily documented, which limits the reproducibility of results and the transferability of methods. We present a diagnostic workflow for hyperparameter selection that can be used when the ground-truth equations are not known. The workflow is guided by three main questions: (1) Are the benefits of greater network capacity worth the cost? (2) Do more training epochs keep reducing the validation loss? (3) Do the learned terms stop changing as network capacity and training increase? We apply our workflow to synthetic systems of varying complexity with known ground truth, spanning diffusion and growth right-hand side terms and data ranging from 1D+t to 2D+t. We demonstrate that the validation loss generally follows the true error in the learned terms and distil practical rules of thumb for selecting hyperparameters in the BINN architecture. By providing a structured workflow, practical guidelines, and suggested starting values for hyperparameter selection, this work lowers the barrier to BINN-based equation learning.

AI 总结：该研究通过信号-预测-系统诊断框架，发现短期波动率预测中统计残差简化（方差降低约82%）并不改善残差LSTM的预测精度（MSE从0.3049升至0.3594），揭示了预测器-预处理器不对称性。

链接：https://arxiv.org/abs/2610.03019

机构：University of Maryland, College Park（马里兰大学帕克分校）

作者：Bingqi Lian, Linfeng Cheng, Mei Lu, Jerry Wu

英文摘要： Hybrid statistical-neural pipelines often assume that a successful statistical first stage leaves a cleaner and more learnable residual target. We examine that assumption in short-horizon volatility forecasting through a signal-forecast-system diagnostic framework. Across five liquid U.S. assets, a volatility-aligned HAR-style model outperforms AR, MA, and ARIMA. Within expanding training windows, the pre-standardization fitted residual process used to construct residual-LSTM sequences has about 82% lower variance than the corresponding target and near-zero lag-1 autocorrelation; independently, rolling pseudo-out-of-sample HAR errors show about 74% variance reduction and similarly weak lag-1 dependence. Residual-only LSTM augmentation nevertheless raises mean squared error from 0.3049 to 0.3594 on average, with deterioration on every asset. Pure LSTM records the lowest selected pseudo-out-of-sample MSE, 0.2649, while the residual hybrid requires substantially more end-to-end runtime without improving accuracy. We describe this pattern as forecaster-preconditioner asymmetry: first-stage forecasting success and statistical residual simplification need not translate into useful downstream neural preconditioning.

AI 总结：本文利用信号处理与孤立森林机器学习模型对挪威桥梁传感器数据进行异常检测，通过多种指标评估并验证了机器学习方法的有效性。

链接：https://arxiv.org/abs/2610.03082

机构：Smart Sensor Systems AS（智能传感器系统公司）

作者：Rahul Jaiswal, Joakim Hellum, Halvor Heiberg

英文摘要：Bridges contribute significantly to transportation connectivity and urban development. Therefore, reliable bridge monitoring is crucial for protecting public safety and detecting anomalous behavior in bridge sensor data that may provide early indications of abnormal structural conditions. This paper investigates anomaly detection in real-world bridge sensor data using two different complementary approaches, namely signal processing and the data-driven machine learning model Isolation Forest. The real-time bridge sensor data is collected from an iBridge sensor device installed on a bridge in Norway. The methods are evaluated using anomaly counts, anomaly detection time, processing rate, anomaly rates, visualization, and temporal agreement. Moreover, a controlled anomaly-injection analysis is performed to evaluate the sensitivity of each method. Numerical results demonstrate distinct detection characteristics and computational requirements, highlighting the potential of machine learning, particularly the data-driven Isolation Forest, alongside signal processing for identifying anomalies in bridge sensor measurements.

AI 总结：针对PDE预训练中异质动力学和专家冗余问题，提出谱解耦MoE神经算子SPEAR，通过知识引导聚合减少50%专家并保持精度，在12个数据集上验证了优越性能。

链接：https://arxiv.org/abs/2610.03265

机构：Anhui University（安徽大学）

作者：Dengdi Sun, Xiaoya Zhou, Xiao Wang, Wanli Lyu, Jin Tang, Bin Luo

英文摘要：Large-scale pre-training has improved the generalization of neural operators across diverse PDEs. However, existing PDE foundation models still struggle with heterogeneous dynamics, where shared representations may cause knowledge interference, while mixture-of-experts (MoE) architectures suffer from increasing expert redundancy. We propose SPEAR, a spectral-disentangled MoE neural operator with knowledge-guided expert aggregation for large-scale PDE pre-training. SPEAR decouples latent features into low- and high-frequency components, enabling shared modeling of transferable dynamics and specialized learning of PDE-specific patterns. To address expert redundancy, we design a knowledge-guided expert aggregation strategy that measures expert similarity from dataset-specific learned knowledge and routing preferences, enabling the identification and consolidation of similar experts. Experiments on twelve PDE datasets and multiple downstream benchmarks demonstrate superior performance in pre-training, fine-tuning, and transfer learning. Furthermore, our aggregation strategy reduces the number of experts by 50\% while maintaining or improving prediction accuracy, achieving a balance between model efficiency and generalization for PDE foundation models.

AI 总结：针对随机PDE的UQ，提出S$^{2}$-PINN，利用可分离张量结构结合gPC基，在多个基准上优于九种基线，参数更少，并验证了泛化能力。

链接：https://arxiv.org/abs/2610.03303

机构：Lehigh University（理海大学）

作者：Zhendong Li, Akwum Onwunta

英文摘要：Uncertainty quantification (UQ) for random partial differential equations (PDEs) is ubiquitous in computational science and engineering. However, classical spectral solvers for this class of problems face the curse of dimensionality, and existing neural solvers often ignore the stochastic structure that makes moments and calibration tractable. We introduce a stochastic separable physics-informed neural network, dubbed S$^{2}$-PINN, that represents the solution $u(t,\mathbf{x},\mathbf{Z})$ of a random PDE with a learnable Gaussian spatial dictionary, Fourier temporal features, and a generalized polynomial chaos (gPC) stochastic basis, coupled by a low-rank Canonical Polyadic (CP) tensor decomposition core. The method is trained with a hybrid strong-form and gPC-projected residual loss. Our theoretical analysis establishes that the separable class is dense in $L^2$ under mild conditions, and the projected residual corresponds exactly to a stochastic Galerkin constraint. Furthermore, we show that mini-batch projection coefficients are logarithmically dependent on the number of gPC modes, and that the orthogonality penalty controls the conditioning of the learned spatial dictionary. Using four manufactured random PDE benchmarks, we show that S$^{2}$-PINN outperforms nine baselines in terms of mean and variance accuracy, as well as calibration, while using significantly fewer parameters. Further evaluations on non-manufactured Poisson and Darcy problems, a stochastic Navier--Stokes problem, a diffusion scaling study of higher random dimensions, and two stochastic inverse problems reveal the generalization capabilities of the proposed structure. Together, these results support stochastic separability as an effective design principle for physics-informed neural UQ. The code for the experiments can be found in this https URL

AI 总结：针对物理信息神经网络的频谱偏差问题，提出一种基于神经正切核理论分析的算子感知初始化策略，通过定制初始权重分布平衡各频率收敛速率，提升预测精度且不增加训练成本。

链接：https://arxiv.org/abs/2610.03378

机构：National Center for Artificial Intelligence（国家人工智能中心）； University of Pennsylvania（宾夕法尼亚大学）； Pontificia Universidad Católica de Chile（智利天主教大学）； Millennium Institute for Intelligent Healthcare Engineering, iHEALTH（千禧智能医疗工程研究所）

作者：Juan Molina, Paris Perdikaris, Mircea Petrache, Matías Courdurier, Francisco Sahli Costabal

英文摘要：Physics-Informed Neural Networks (PINNs) typically exhibit spectral bias, where some frequencies of the target function converge more slowly than others. In this work, we analyze the training dynamics of Fourier Feature PINNs in the Neural Tangent Kernel regime to address this limitation. We derive an explicit evolution equation to estimate the residual error in the frequency domain, demonstrating that the convergence rate of specific frequencies is primarily governed by the product of the differential operator's symbol and the spectral density of the initialization weights. Leveraging this theoretical insight, we propose an informative initialization strategy that tailors the initial weight distribution to the specific PDE being solved. With this method, we can diminish the operator-induced spectral bias, balancing the convergence rates across the frequency spectrum and achieving better prediction accuracy. Numerical experiments on linear and nonlinear partial differential equations confirm that this initialization strategy improves learning dynamics and approximation accuracy across frequencies compared to standard initialization methods, with no additional training cost.

AI 总结：提出DuoTS双上下文时间序列预测模型，通过检索模拟证据并逐补丁细化基础预测，平衡当前与细节上下文，实现最先进性能且模型无关。

链接：https://arxiv.org/abs/2610.03491

机构：University of Hildesheim（希尔德斯海姆大学）； VWFS Data Analytics Research Center (VWFS-DARC)（VWFS数据分析研究中心）

作者：Jung Min Choi, Ngoc Son Le, Ibram Abdelmalak, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme

英文摘要：Most long-term time-series forecasting models map the look-back window directly to the full horizon in a single pass. While efficient, this design does not explicitly identify which historical states are most relevant to different future segments or exploit what followed those states. Analog forecasting addresses this by retrieving past states similar to the present and using their observed continuations, but single nearest matches can be unreliable and overlapping patches may produce redundant candidates. We propose DuoTS, a Dual-Context Time Series forecasting model that uses retrieved evidence without relying on it exclusively. DuoTS first produces a base forecast with a parallel patch encoder and linear prediction head, then progressively refines it one future patch at a time. Each refinement combines two views: a current context that attends to recent tokens and captures the latest dynamics, and a detail context that provides distinct retrieved analogs together with their subsequent trajectories. Patch-wise refinement allows the model to balance these views across the forecast horizon and associate each future segment with evidence appropriate to its temporal distance from the present. Experiments on multiple real-world datasets show that DuoTS achieves state-of-the-art performance, while ablations confirm the contribution of each context. The refinement mechanism is also model-agnostic, requiring only an encoded look-back window and the future-patch position, and can therefore be integrated into existing forecasting models.

AI 总结：提出MARO模型，通过以最近补丁为锚点的循环排序处理回看窗口，在多个真实数据集上实现长期与短期预测的最先进性能。

链接：https://arxiv.org/abs/2610.03494

机构：University of Hildesheim（希尔德斯海姆大学）； VWFS Data Analytics Research Center (VWFS-DARC)（VWFS数据分析研究中心）

作者：Jung Min Choi, Ngoc Son Le, Ibram Abdelmalak, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme

英文摘要：Long-term forecasting models commonly process all patches in a look-back window using the same fixed stack. Older contextual patches and recent evidence therefore receive the same computational depth. Yet the information closest to the forecast and the more distant context do not contribute equally. Uniform processing leaves this distinction unexpressed in the architecture. We propose MARO, a Most-Recent Anchoring with Recurrent Ordering model that processes the look-back window from the most recent patch to the oldest. The most recent patch serves as the anchor. It initializes the latent state and conditions each subsequent step, so older patches are folded into a representation that remains centered on recent evidence. A single shared module is reused at every step, so extending the scan further into the past introduces no additional parameters. Intermediate states retained during the scan allow the forecast head to weigh short and long portions of the history separately. This expresses recency through the order of recurrent refinement. Extensive experiments across multiple real-world time series datasets show that MARO achieves state-of-the-art performance on both long-term and short-term forecasting this http URL studies examine the contribution of the main architectural components.

AI 总结：本研究通过两个真实库存控制部署，验证了反事实模拟器推演训练预测模型可解决新策略冷启动问题，显著降低MAPE误差，且后续校准可进一步优化。

链接：https://arxiv.org/abs/2610.03662

机构：Amazon（亚马逊）

作者：Angel Wang, Dominique Perrault-Joncas, Alvaro Maggiar, Dean Foster, Carson Eisenach

英文摘要： Deploying a new decision policy creates a cold-start problem for prediction models whose targets depend on the policy's actions: historical observations reflect earlier policies, while real observations under the new policy are not yet available. Simulation offers a way to address this gap by rolling out the target policy across counterfactual scenarios and using the resulting trajectories to learn how the system responds to those controls. The simulation-to-reality (Sim2Real) transfer of this simulator-trained model can then be backtested by evaluating it against real observations from past deployments. Using two real-world inventory-control deployments, we evaluate this process from three angles: simulator fidelity, zero-shot transfer to real behavior, and adaptation as real target-policy observations accumulate. The simulator-trained forecaster achieves lower point-estimate mean absolute percentage error (MAPE) than the same architecture trained on historical real data, reducing MAPE by 1.2-3.1 percentage points in Study 1 and 12.5-18.7 points in Study 2. After deployment, lightweight calibration using early real observations further reduces error by up to 2.5 percentage points. These results provide empirical evidence that simulator-generated counterfactual data can support cold-start forecasting under a new policy, and the resulting model can be further refined as real deployment data become available.

AI 总结：本研究融合SEC财务数据与EPA排放登记，利用梯度提升和Mondrian共形预测构建CWCD指标，证明算法排放散度与市场估值及盈利能力显著负相关，为市场纪律和算法审计提供量化依据。

链接：https://arxiv.org/abs/2610.02225

作者：Sourav Bose, Taoufik Bouraoui

英文摘要：While corporate sustainability mandates are expanding, the systemic reliance on self-reported emissions data exposes financial markets to pervasive greenwashing. Current literature relies heavily on subjective ESG ratings or textual sentiment analysis, leaving a critical econometric gap in objectively quantifying physical climate realities. To resolve this information asymmetry, we fuse U.S. SEC financial fundamentals with facility-level EPA greenhouse gas registries to establish a mathematically guaranteed baseline of physical corporate emissions. Leveraging a gradient boosting architecture and Mondrian Conformal Prediction, we quantify the shortfall between self-reported data and this algorithmic baseline into a novel Conformal-Weighted Continuous Divergence (CWCD) metric. Evaluating this divergence via a cross-sectional lead-lag econometric design, we uncover a robust mechanism of market discipline: algorithmic emissions divergence exhibits a severe, statistically significant negative relationship with subsequent market valuation (Tobin's Q) and operational profitability (ROA). Providing definitive evidence against the market blindness hypothesis, this study proves that institutional capital actively prices environmental deception not merely as an ethical lapse, but as a leading indicator of fundamental corporate mismanagement. Ultimately, these findings provide the quantitative justification necessary for asset managers and regulators to deploy algorithmic auditing infrastructure at scale.

AI 总结：本文系统比较了不同信息假设下的最近邻检索变体，为MS/MS谱图指纹预测建立更严格的基线，以促进更严谨的基准测试和进展衡量。

链接：https://arxiv.org/abs/2610.02249

作者：Ling Min Serena Khoo

英文摘要：It has recently been shown that nearest-neighbour retrieval provides a strong baseline for molecular fingerprint prediction from MS/MS spectra, with several variants matching or outperforming current deep learning models (Khoo and Barzilay, 2026; Liu et al., 2026; Gupta et al., 2026). Importantly, "nearest neighbour" encompasses a family of retrieval methods that differ in the information assumed to be available at inference. In this report, we systematically compare several nearest-neighbour variants and show how these differing assumptions affect performance. Our goal is to establish stricter baselines that enable more rigorous benchmarking and better measure progress in this area.

AI 总结：提出排序感知投机采样（RASS），利用草稿候选的排序信息优化扩散草稿树的验证，在多个生成任务上较 D-GRS 提升约 20% 效率。

链接：https://arxiv.org/abs/2610.02251

作者：Marcello Bullo, Yanxiao Liu, Öykü Sıla Güner, Arpan Mukherjee, Deniz Gündüz

英文摘要：Speculative sampling accelerates diffusion generation by verifying inexpensive draft states in parallel while preserving the target law. Recent tree-based methods allocate the parallel compute budget more effectively than single-chain drafts, as demonstrated by Diffusion Greedy Rejection Sampling (D-GRS). D-GRS generates $K$ conditionally independent candidates per node, and sequentially tests them in their generation order. Yet the sampled candidates admit an informative ranking without additional target-model evaluations. To exploit this, we introduce Rank-Aware Speculative Sampling (RASS), a verification rule for speculative draft trees based on rank-aware list coupling. RASS orders draft candidates along the proposal-target mean displacement and samples a rank with weights optimized to minimize total variation between the selected-proposal and target laws. Finally, the selected candidate is maximally coupled with the target, with residual correction ensuring exact sampling for any choice of rank weights. We evaluate RASS on a Gaussian-mixture target, unconditional pixel-space generation on FFHQ, conditional generation on CIFAR-10, and latent diffusion with Stable Diffusion 3.5 using COCO2014 prompts. Measured by the ratio of standard to speculative sampling's target-model evaluation counts, RASS improves on D-GRS across the evaluated settings, with gains reaching approximately 20% on CIFAR-10 at matched compute budgets.

AI 总结：本文研究Dropout ReLU网络对Sobolev函数类的逼近，给出网络规模的上界与下界，并证明在固定或对数深度下精度指数匹配，揭示了随机保留边对逼近能力的影响。

链接：https://arxiv.org/abs/2610.02253

作者：Jia-He Yao

英文摘要： The universal approximation property of dropout neural networks does not by itself describe the network size required for an accurate random realization. In this work, we study approximation of the unit ball of $W^{n,\infty}([0,1]^d)$ by ReLU networks whose edges are retained independently with probability $p$. The approximation error is measured uniformly over the input domain, and the guarantee holds with probability at least $1-\delta$ for a single sampled network. We construct networks of constant depth and size $\widetilde O_{n,d}(p^{-9}\varepsilon^{-\max\{d/n,2\}} \log(1/\delta))$. The construction combines bounded local subnetworks, localization on a successful approximation event, and a multiscale Taylor decomposition. Conversely, Sobolev capacity imposes a lower bound on the number of surviving edges, while approximation of a fixed affine function requires an output-layer cost of order $((1-p)/p)\varepsilon^{-2}\log(1/\delta)$ at sufficiently high confidence. For fixed $p\in(0,1)$ and $\delta

AI 总结：本研究提出利用大型语言模型作为不完美专家，集成LLM-ISM方法以自动化解释结构建模，通过比较多种因果图发现方法，发现逐行和全图方法表现最优，有效克服传统ISM的扩展性挑战。

链接：https://arxiv.org/abs/2610.02254

机构：Oak Ridge National Laboratory（橡树岭国家实验室）； University of Tennessee（田纳西大学）

作者：Everett Rush, David J. Icove, Ari Kim, Byung H. Park, Michael A. Langston

英文摘要：Interpretive Structural Modeling (ISM) is a well-known process for multi-criteria decision making. The success of ISM over other methodologies is its ability to model causal relationships, the binary scale of factors, and resulting hierarchical representation. Traditionally, the modeling process is performed by repeated interactions with subject matter experts until consensus is reached. This process is tedious, labor-intense, and most importantly limits the ability of ISM to scale to studies with hundreds of variables. Drawing on existing work of causal graph discovery with large language models (LLM) as imperfect experts, this work explores an integrated LLM-ISM approach for ISM. Pairwise, k-wise, rowwise, and full graph discovery methodologies are compared and evaluated. It is shown that causal graph discovery methods for ISM perform best using rowwise (SHD=160, F1-score=0.77) and full graph methods (SHD=135, F1-score=0.73).

AI 总结：提出免模型特征重要性方法$\Psi$-Resilience，利用一维拓扑信号构建类不一致景观并聚合持久性特征，在合成与真实数据上分别达到0.8和0.9的Spearman相关性，实现无需预测模型的分布级审计。

链接：https://arxiv.org/abs/2610.02299

机构：University of Sevilla（塞维利亚大学）

作者：Fabian Galis, Darian Onchis, Pedro Real Jurado

英文摘要：We introduce $\Psi$-Resilience, a model-free feature importance method that derives explanations directly from the data itself via 1D topological signals. Our method constructs a class-disagreement landscape by estimating class-conditional densities and taking their pointwise absolute difference along the feature axis. Then, the 0-dimensional persistence of this 1D signal defines a resilience functional that aggregates only those topological features that survive perturbations up to a robustness scale which is set by the user. This gives us a context-robust importance score that is inherently auditable via the underlying 1D landscapes and their persistence. We evaluate our method on both synthetic and real datasets. On synthetic generators with specified ground-truth importance, $\Psi$-Resilience recovers the ranking of features with high fidelity, achieving Spearman rank correlations up to 0.8 and performing competitively with multiple feature importance methods, including SHAP and mutual information. On real datasets with no known ground truth, our technique agrees with these methods, with correlations up to 0.9. These results show that $\Psi$-Resilience is a stable explanation method that enables rigorous, distribution-level auditing of feature importance without relying on a predictive model.

AI 总结：针对多教师蒸馏导致学生模型通用能力下降的问题，提出SF-MOPD方法，通过快速与慢速模型耦合，仅移除偏离慢速模型的更新成分，有效缓解能力干扰并提升多模态专长。

链接：https://arxiv.org/abs/2610.02324

机构：Ant Security Lab, Ant Group（蚂蚁安全实验室，蚂蚁集团）； Fudan University（复旦大学）

作者：Xiaofei Yin, Tong Chu, Jiyuan Fu, Jun Lan, Shuheng Zhou, Huijia Zhu

英文摘要：Foundation multimodal large language models are designed to support a broad spectrum of capabilities across diverse domains. Multi-teacher on-policy distillation (MOPD) provides an effective framework for consolidating domain-specific expertise into a single student model. However, MOPD training gradually drives the student away from its initialization model, and general capabilities decline as the displacement grows, resulting in capability interference. A direct remedy is constraining the student toward its initialization, but this suppresses the acquisition of domain expertise as well. We propose Slow-Fast Multi-Teacher On-Policy Distillation (SF-MOPD), which couples a fast model, the current student updated directly by each teacher, with a slow model, an exponential moving average of the student. The slow model absorbs the learning signal gradually, serving as a moving capability reference that fuses the general foundation with confirmed domain expertise. For each teacher, SF-MOPD computes the teacher-induced update in log-probability space and removes only the component that pushes the fast model further away from the slow model, while retaining aligned and orthogonal components. Experiments across multiple model scales demonstrate that SF-MOPD effectively mitigates capability interference, enhances specialized multimodal capabilities, and reduces the average degradation on general-capability benchmarks, consistently outperforming vanilla MOPD.

AI 总结：针对LLM预训练中批大小调度的理论缺失，提出广义BG-$a$噪声模型并推导复杂度界限，设计自适应批调度器，在OLMo2预训练中以更少迭代取得更低验证损失。

链接：https://arxiv.org/abs/2610.02355

机构：Elmore Family School of Electrical and Computer Engineering（埃尔莫尔家族电气与计算机工程学院）； Purdue University（普渡大学）

作者：Arda Fazla, Antesh Upadhyay, Ege C. Kaya, M. Berk Sahin, Abolfazl Hashemi

英文摘要： Increasing the batch size during training is a common practice in large language model (LLM) pretraining, yet the theoretical justification behind its success is not well understood. Analyses of stochastic optimization often assume uniformly bounded stochastic gradient variance, yet recent evidence suggests that this assumption fails in many practical nonconvex problems. The Blum--Gladyshev (BG-$0$) noise model relaxes this assumption by allowing the variance to grow quadratically with the distance from initialization, suggesting that batch size schedulers can help by controlling the variance growth during training. However, this growth can be overly conservative in practice. We empirically investigate variance growth in LLM pretraining and observe that a generalized BG model with a tunable growth exponent provides a tighter description of practical noise behavior. Motivated by this observation, we introduce the generalized BG-$a$ noise model, which interpolates between bounded variance ($a=0$) and BG-$0$ noise ($a=2$). Under $L$-smoothness, we derive an information-theoretic lower bound with growth-dependent oracle complexity $\Omega(\epsilon^{-(4+a)})$ and establish a matching upper bound in $\epsilon$-dependence by increasing the batch size as the iterates move away from initialization. Finally, we propose an adaptive batch scheduler that controls variance growth through dynamic batch size adjustments during training. In pretraining OLMo2 models of up to 1B parameters on C4, our scheduler achieves a lower validation loss than both small and large batch training under matched token budgets, while using less than 10\% of the iterations of small batch training.

AI 总结：ArrivalBench通过对抗性可重放调度重新执行智能体管道，以批量重算为预言机，发现单次执行认证的管道在重放下有7.0-79.2%静默出错，并区分错误与崩溃以改进干预。

链接：https://arxiv.org/abs/2610.02363

机构：University of Oxford（牛津大学）

作者：Pranay Kothari

英文摘要：Benchmarks for agent-generated data work grade a pipeline by running it once against a fixed snapshot. ArrivalBench instead re-executes the pipeline an agent leaves behind under adversarial but replayable delivery schedules (late, duplicated, out-of-order and retried records) and requires its final state to equal a batch recomputation of the complete log. Because the oracle recomputes rather than classifies, a wrong table and a crash are distinct verdicts: a crash is visible to monitoring a team already runs, and a wrong table is not. On 40 tasks we built, our reimplementation of single-execution grading certifies 86-100% of the pipelines eleven models produce; re-executing the same artifacts finds 7.0-79.2% of the certified ones silently wrong. The gap is not produced by the repair loop: within the same model and task, pipelines repaired against the snapshot test fail replay about as often as those that passed it first time. In every model, idempotency hazards fail more often than ordering hazards. Separating a wrong answer from a crash also changes how interventions read: a hazard warning cuts one model's silent failure from 48.2% to 10.5% while raising its crash rate from 9.0% to 37.0%, so all-in failure moves only from 51.0% to 44.0%. All eleven arms were independently re-run, and rates moved by at most 5.9 points.

AI 总结：提出首个面向大语言模型的表示级多教师在线策略蒸馏方法，通过整合专家模型的预测与隐藏状态，无需额外教师训练，在数学、代码和逻辑基准上优于多种基线。

链接：https://arxiv.org/abs/2610.02381

机构：Case Western Reserve University（凯斯西储大学）； Zillow Group, Inc.（Zillow集团）； University of Illinois at Chicago（伊利诺伊大学芝加哥分校）； University of Florida（佛罗里达大学）

作者：Zhengyu Fang, Seoyeon Hong, Jie Yang, Muyang Li, Koyoshi Shindo, Brandon Joseph Lwowski, Jing Li

英文摘要：On-policy distillation (OPD) trains a student on the responses it generates. Existing LLM multi-teacher OPD transfers what specialists predict through their output distributions. We introduce Latent-MOPD, to our knowledge the first representation-level multi-teacher OPD method for LLMs. It integrates existing specialists through both their predictions and the hidden states used to compute them, without additional teacher training. To coordinate representation supervision from multiple specialists, we select late-layer targets according to the teacher-student relationship, bridge unequal hidden widths with a shared projection, and group updates by domain. Each teacher's supervision gradually shifts from hidden states to token predictions, with both channels using the same routed specialist. In our main same-family setting, Latent-MOPD outperforms the token-only, representation-only and uniform-averaging baselines on all nine benchmarks across math, code and logic. With the same parameter count as each teacher, the student also surpasses the per-benchmark best teacher on a majority of these benchmarks. With larger, separately developed cross-family teachers, Latent-MOPD outperforms both single-channel baselines on all benchmarks. A same-family all-layer representation-only control remains stable with domain-pure updates but collapses when teacher domains are interleaved within an update. Our results show that a single student can integrate capabilities from several specialists through both their output distributions and internal representations.

AI 总结：循环Transformer中共享内存可提升质量并大幅减少内存使用，新模型LPT及其混合变体在FineWeb-Edu上以更少内存取得更低困惑度。

链接：https://arxiv.org/abs/2610.02383

机构：IBM Research（IBM研究院）； Cornell University（康奈尔大学）

作者：Giovanni Monea, Keshav Ramji, Yousef El-Kurdi, Luis A. Lastras, Yoav Artzi, Nathan Godey, Ramón Fernandez Astudillo

英文摘要：Looped Transformers apply the same layers several times per token, adding compute to improve quality without more parameters. Each recursion, however, writes its own key-value cache, so memory still grows with compute. Inference-time techniques can shrink this cache at a cost in quality. We pretrain looped language models to share memory: only the first recursion writes a cache, and later recursions read it while keeping a short window of their own. Surprisingly, we find that sharing memory does not cost quality and instead improves it. At 150M-1B parameters, our Looped Prediction Transformer (LPT) and its hybrid variant set a new quality-memory frontier for looped models: with five recursions, the hybrid lowers validation perplexity on FineWeb-Edu by 1.12-1.82 relative to a same-size standard Transformer while using 76-79% less context memory. Through an extensive analysis, we investigate why memory sharing helps. Shared and local memory develop different representations, and later recursions attend mostly to the shared memory, which also acts as a gradient highway to the first recursion.

AI 总结： 提出双曲熵引导（HEST），利用基于熵训练的双曲探针在稀疏令牌处沿测地线引导激活，提升数学推理准确率，最高达1.8个百分点。

链接：https://arxiv.org/abs/2610.02391

机构：New Jersey Institute of Technology（新泽西理工学院）； University of California, Los Angeles（加利福尼亚大学洛杉矶分校）； Stony Brook University（石溪大学）

作者：Zeyong Zhang, Tung Sum Thomas Kwok, Tengfei Ma, Mengjia Xu

英文摘要：When a large language model solves a mathematical problem, its reasoning is largely hierarchical, and the solution often branches at a few tokens where the next-token entropy is high. Such tree-like structure embeds in hyperbolic space with far lower distortion than in Euclidean space. Activation steering, however, usually edits the hidden states of a pretrained model by adding one fixed Euclidean vector at every token, even though most tokens of a solution are already determined by the context. We propose Hyperbolic Entropy Steering (HEST), which embeds the hidden states in the Poincaré ball with a lightweight probe whose only label is the model's own next-token entropy. Where this entropy exceeds a threshold, HEST moves the embedded state along the geodesic of steepest descent of a readout of the probe and maps the change back to the hidden state. For the Busemann readout of a learned ideal point, we prove that a step of fixed length lowers it by the same amount at every state. On three instruction-tuned models from the Qwen2.5-Math and Llama-3.1 families, HEST with the Busemann readout improves greedy accuracy on MATH-500 and GSM8K in five of six settings, by up to 1.8 points, whereas a contrastive steering vector added at every token lowers accuracy. With a Euclidean probe trained in the same way, this gain disappears on Qwen2.5-Math-1.5B-Instruct. The gains are largest on problems where the model hesitates often, and accuracy on the remaining problems is almost unchanged.

AI 总结：提出Inherit-MAS，通过工作流与执行继承机制，在测试时利用反馈改进多智能体系统，提升任务完成率并显著降低令牌消耗。

链接：https://arxiv.org/abs/2610.02396

机构：University of Texas at Dallas（德克萨斯大学达拉斯分校）

作者：Songtao Wei, Yi Li, Zhichun Guo, Bingzhe Li

英文摘要：Multi-agent systems (MAS) built from large language models coordinate specialized agents to tackle complex tasks, but effective workflows are difficult to design in advance. Test-time evolution refines workflows using execution feedback, yet broad revisions can disturb useful components, while re-executing unchanged requests can incur redundant computation. Inspired by the interplay of inheritance and selection in biological evolution, we introduce Inherit-MAS, which makes inheritance explicit at the workflow and execution levels. A meta-model first synthesizes a workflow of worker agents with declared roles, communication inputs, and tool permissions, and a separately prompted judge scores each executed candidate and diagnoses its deficiencies. In ordinary refinement rounds, \emph{workflow inheritance} starts from the latest completed candidate, may discard removable nodes judged unhelpful, and applies a validated edit to address the diagnosed deficiency. When the new candidate executes, \emph{execution inheritance} inherits eligible stored results only if the complete resolved request and execution context match, avoiding redundant model and tool calls. With GPT-4o-mini workers, Inherit-MAS achieves 55.4\% completion on WorkBench and 49.7\% joint F1 on HotpotQA FullWiki, outperforming EvoAgent, EvoMAS, and TacoMAS. With Qwen3-32B workers, it also exceeds these evolving-MAS baselines on both benchmarks. Compared with rerunning the same controller with execution inheritance disabled, execution inheritance reduces worker-token usage by 29.1\% on WorkBench and 34.6\% on HotpotQA, and total token usage by 5.3\% and 18.1\%.

AI 总结：本文通过让模型用工具调用自身并读取上下文词元，在8K上下文内微调小模型，使其在长文档任务上媲美百万上下文的GPT-5.4。

链接：https://arxiv.org/abs/2610.02404

作者：Bryce Sandlund

英文摘要：We study long context language models. Instead of training long context natively, or designing a long context harness, we train a model over the simplest possible harness: a tool to call itself with any specified prompt and a tool to read tokens in a range from the input context. We finetune Qwen3.6-35B-A3B on a diverse synthetic dataset using this harness. With only 8,000 tokens of context, our small model is as strong as GPT-5.4 with 1M tokens of context on the OOLONG-synth benchmark when document length exceeds 40K tokens.

AI 总结：针对隐式神经表示训练中均匀采样效率低的问题，提出ACES结构化采样框架，通过自适应空间划分确保覆盖、区域级重要性加权聚焦信息丰富区域，实现更快收敛与更低误差。

链接：https://arxiv.org/abs/2610.02410

机构：Brookhaven National Laboratory（布鲁克海文国家实验室）

作者：Guang Zhao, Xihaier Luo, Huan-Hsin Tseng, Seungjun Lee, Shinjae Yoo, Yihui Ren, Wei Xu

英文摘要：Implicit neural representations (INRs) provide a flexible framework for modeling high-dimensional continuous fields, but their training is often inefficient due to uniform subsampling that ignores spatial heterogeneity. Existing adaptive sampling methods partially address this issue by prioritizing high-error samples, but typically operate at the point level, often leading to redundant sampling in localized regions and insufficient coverage of the domain. We propose ACES (Adaptive Coverage-aware Efficient Sampling), a structured sampling framework that improves training efficiency by decoupling coverage and importance. ACES constructs adaptive spatial partitions to ensure domain coverage and reduce redundancy, and applies region-level importance weighting to prioritize informative regions during training. We provide a theoretical analysis showing that adaptive partitioning reduces gradient variance by increasing within-region homogeneity, and that controlled bias in region-level weighting may improve optimization efficiency relative to standard unbiased estimators. Experiments on scientific field learning tasks demonstrate that ACES achieves faster convergence and lower error than uniform and pointwise adaptive sampling baselines, with the largest gains in fields with highly localized complexity.

AI 总结：本文提出AI理论家系统，通过假设生成、第一性原理计算和证据驱动优化，自主发展物理模型，成功解释了$\alpha$-RuCl$_3$的光学光谱，识别出不同激子态，展示了AI在材料科学中实现自主理论发现的潜力。

链接：https://arxiv.org/abs/2610.02417

机构：University of Oxford（牛津大学）； University of Waterloo（滑铁卢大学）； Stanford University（斯坦福大学）； University College London（伦敦大学学院）

作者：Hongjian Zhou, Xianfan Nie, Sean Wu, Tarun Patel, Jinge Wu, Andrew Liu, Adam Wei Tsen, David A. Clifton

英文摘要：Advances in experimental instrumentation and automation generate increasingly rich datasets, but turning experimental observations into microscopic understanding remains a bottleneck in scientific discovery. To accelerate this process, we introduce AI Theorist, a system of artificial intelligence (AI) agents for autonomous discovery of physical models through hypothesis generation, first-principles calculations and evidence-driven refinement. We apply the framework to $\alpha$-RuCl$_3$, a leading candidate material for realizing a Kitaev quantum spin liquid, to investigate its electronic structure through optical spectra. AI Theorist develops a new interpretation of the optical and photocurrent observations, identifying distinct excitonic states with contrasting optical selection rules and real-space distributions. To our knowledge, this is the first demonstration of an AI system autonomously developing a physical model to explain previously unpublished experimental observations in a quantum material, utilizing first-principles electronic-structure and many-body calculations. Our results establish a route to autonomous theoretical discovery in materials science, in which AI agents use first-principles calculations to turn experimental observations into physical models and testable predictions.

AI 总结：针对流映射蒸馏，提出几何感知时间重参数化方法，通过分配更多学生时间给高法向加速度区域，在保持教师路径的同时提升一步和少步生成质量，实验验证其有效性。

链接：https://arxiv.org/abs/2610.02427

机构：Machine Learning and Data Science Unit（机器学习与数据科学部）； Okinawa Institute of Science and Technology Graduate University（冲绳科学技术大学院大学）

作者：Félix Dedek, Makoto Yamada

英文摘要：Flow-map distillation enables one- and few-step generation by learning finite-time transitions of a pretrained generative ODE. We investigate whether changing the teacher's time parameterization can make these transitions easier to learn. Motivated by the hypothesis that trajectory segments with large normal acceleration are harder to distill, we propose a geometry-aware time reparameterization that allocates more student time to these regions while preserving the teacher's geometric paths and terminal distribution. We derive a shared clock that equalizes a population normal-acceleration statistic under suitable assumptions, and construct a practical approximation from robust, regularized estimates across teacher trajectories. We incorporate this clock into Lagrangian flow-map distillation, using the transformed time coordinate to condition the student. The clock is estimated once before distillation and requires neither teacher retraining nor additional student parameters or inference-time network evaluations. Experiments on synthetic data, CIFAR-10, and CelebA-64 show improved sample quality over identity-time distillation at matched inference budgets, including improvements in one- and two-step image generation. The gains in one-step generation, where no intermediate sampling times can be adjusted, highlight the benefits of time reparameterization during distillation.

AI 总结：提出CRISP框架，将二元神经网络的最后一层激活向量重构为Tsetlin Machine子句，提供可审计的符号决策轨迹，实验验证其保真度与可解释性。

链接：https://arxiv.org/abs/2610.02431

机构：Newcastle University（纽卡斯尔大学）； Northumbria University（诺森比亚大学）； University of Agder（阿格德尔大学）

作者：Alex Chan, Shafi Muhtasim Chowdhury, Ekin Can Erkuş, Ole-Christoffer Granmo, Alex Yakovlev, Rishad Shafik

英文摘要：Deep neural networks achieve high accuracy through layered numerical transformations, yet their decisions remain difficult to audit because decision evidence is encoded in hidden activations rather than explicit rules. This paper introduces CRISP, a framework that reconstructs the last-layer activation vector (LLAV) of binary neural teachers as Tsetlin Machine (TM) clauses. CRISP sign-binarizes the teacher's penultimate pre-logit activations, and assigns one Individual TM (ITM) to each LLAV neuron. Each reconstructed hidden bit is represented by propositional clauses over Booleanized input features, which gives a direct symbolic trace from named input thresholds to a named teacher neuron. CRISP is evaluated on MNIST, KMNIST, FashionMNIST (FMNIST), SVHN, and CIFAR10 using a BinaryConnect convolutional neural network (BCCNN) teacher and a fully binary neural network (BNN) teacher, with an additional study on binary thresholding, thermometer encoding, and quartile binning at multiple bit depths. The results show that LLAV sign-binarization does not reduce teacher-head accuracy in the tested BNN setting, while ITM reconstruction error is the main limiting factor. Quartile one-bit Booleanization gives the strongest reconstruction fidelity on SVHN at 87.52% test fidelity and is competitive on CIFAR10, and the reconstructed LLAV preserves 78.41% teacher-head accuracy on FMNIST. Pooled clause-evidence visualizations show that the learned ITM literals concentrate on the object region in centered benchmarks. CRISP therefore provides a clause-level route for inspecting the final hidden representation of binary neural teachers.

AI 总结：该研究提出一种基于多重分形阶梯图和神经逆算子的生成图模型，在函数空间统一机制可解释性与摊销推理，实现零样本迁移和单观测网络推断，并提升脑状态追踪敏感性。

链接：https://arxiv.org/abs/2610.02439

机构：University of Southern California（南加州大学）； AWS AI（AWS人工智能）

作者：Wooseong Choi, Italo'Ivo Lima Dias Pinto, Chen Sun, Gaurav Gupta, Dong Song, Paul Bogdan

英文摘要： Generative graph models are central to understanding and simulating complex networks. However, existing approaches have complementary strengths and limitations. Mechanistic models offer interpretability but rely on instance-specific estimation methods. Deep generative models, on the other hand, offer amortized inference at the cost of interpretability and are largely limited to graph sizes seen during training. Scientific applications motivate a framework that retains the strengths of both paradigms. We bridge them by formulating both the generative model and parameter recovery in function space. A multifractal step graphon extends standard step graphons with a recursive construction that compactly parameterizes complex networks. This formulation admits a neural inverse operator to recover its parameters, enabling inference on unseen graph sizes. We evaluate our model, trained only on synthetic multifractal step graphon realizations, against both paradigms. Against a graph foundation model pretrained on empirical networks, our method achieves the best average performance on three of four metrics in a zero-shot graph-generation benchmark, indicating that the model transfers to real-world graphs. We also apply our method to single-observation networks, a regime largely inaccessible to deep models that require training corpora, where it performs comparably to an instance-specific method that optimizes on each graph. In a multi-subject EEG case study, the inferred parameters track a reversible change in brain state more sensitively than traditional network statistics. Together, these results indicate that mechanistic interpretability and amortized inference can be effectively unified in a generative graph model to enhance our understanding of complex networks.

AI 总结：针对LLM带来的数据中心热管理挑战，提出AI驱动的热感知容量规划框架，实现秒级规划、毫秒级预测，较CFD加速10000倍，并优化负载与冷却效率。

链接：https://arxiv.org/abs/2610.02442

作者：Yixing Li, Mark Fenton, Matthew Kaufeler, Ka Ming Leung, Xin Ai, Zhiyu Zeng

英文摘要：The emerging of large language models (LLMs) has posed significant challenges to the thermal management of data center. Intense GPU computation for LLMs results in localized hotspots. Moreover, spiking thermal loads during training and inference bursts make real-time cooling response more difficult to predict and control. Thermal-aware capacity planning of data center requires massive expensive high-fidelity CFD simulations. AI models can perform real-time prediction for unseen designs. However, existing works either have large prediction error, or have over-simplified assumptions for data center operations. This work presents an AI-driven framework that can perform thermal-aware capacity planning for a real-world data center in seconds. The embedded AI model learns from numerous key parameters (rack power, server power, server placement, HVAC settings etc.), and provides temperature prediction within milliseconds. This AI model is tested against high-fidelity CFD simulations, and results show that for unseen data center designs, model can achieve high accuracy with 10000X speedup. Driven by the AI model, the authors design the thermal-aware capacity planning framework. This framework can help data center designers and operators instantaneously optimize both workload distribution and HVAC cooling efficiency.

AI 总结：本研究系统探究LLM压缩（剪枝、量化、蒸馏）的能力缩减定律，提出简单预测关系，验证其准确性与泛化性，并展示其在压缩方法选择中的决策价值。

链接：https://arxiv.org/abs/2610.02462

机构：Florida State University（佛罗里达州立大学）； Nokia Applied Research（诺基亚应用研究）

作者：Xueqi Cheng, Liang Wu, Kelly Wan, Liangjie Hong, Yushun Dong

英文摘要：LLM compression reduces inference costs and memory requirements, but selecting a method and configuration remains largely empirical because comparable resource reductions can produce different capability losses. We systematically investigate capability scaling-down laws for LLM compression across pruning, quantization, and distillation. Our framework measures capability loss in mathematics, code generation, and question answering, and relates these measurements to model size, training stage, compression settings, data availability, and training exposure. We develop simple predictive relations and evaluate their accuracy, measurement efficiency, and generalization to unseen configurations and model states. Sharing the density response across pruning levels halves the configuration measurements needed to fit a pruning predictor: on new Pythia states, on pre-registered OLMo-2 test states and under Wanda pruning, the compact relation matches a regression fitted with all measurements on math and code to within 0.020 nats per token, with coefficients refitted for each setting. Controlled distillation experiments show that the cost of heavy data reuse recurs across question-answering distributions, while the net benefit depends on the evaluation distribution. We further evaluate the decision value of these predictions by comparing numerical selection with configuration medians and fixed method priorities. Independent evaluations across two model families show that selection captures most of the available cross-method benefit for question answering within the tested candidate sets, where a fixed method priority attains the same regret, with smaller opportunities for mathematics and code. These results clarify the predictive scope of capability scaling-down laws and their use in compression method selection. Our code is publicly available at: this https URL.

AI 总结：针对高保真模拟与替代模型间的精度-速度权衡，本文提出阈值感知的保形路由（TACR），通过阈值感知目标优化区间分配，在保持无分布覆盖保证的同时，将模拟器调用减少14-75%。

链接：https://arxiv.org/abs/2610.02487

机构：Rutgers University（罗格斯大学）； Siemens（西门子）

作者：Shiwei Tan, Huzefa Rangwala, Danielle C. Maddix

英文摘要： High-fidelity simulations are essential to scientific and engineering design, but can be expensive to run repeatedly. Learned surrogates offer a faster alternative, yet their higher errors may alter downstream decisions. This accuracy-speed tradeoff creates a need to determine whether a surrogate can be used or the full simulator remains necessary. We study decisions determined by whether a scalar quantity of interest lies above or below a fixed threshold. For each input, we use the surrogate when its conformal interval lies entirely on one side of the threshold and route the input to simulation when the interval intersects it. Standard conformal prediction constructs intervals without reference to the downstream decision threshold: even a narrow interval near the threshold can cross it and trigger simulation, whereas a wider interval farther away can remain entirely on one side and require no simulation. We introduce Threshold-Aware Conformal Routing (TACR), which learns an input-dependent scale using a threshold-aware objective that concentrates interval tightness near the decision boundary. Exact split-conformal calibration on held-out data preserves distribution-free marginal coverage, which also upper-bounds the probability of an incorrect threshold decision that is not routed. Across various scientific and engineering datasets, TACR reduces simulator deferrals by 14-75% relative to standard conformal prediction at the same coverage target. Against a variant without threshold-local weighting but with similar predictor accuracy, TACR further reduces deferrals by 10-24% on four datasets. These results show that optimizing interval allocation for routing can reduce simulator calls without weakening the standard conformal guarantee.

AI 总结：本文提出语言模型智能体机器（LAM）抽象，量化LLM智能体支架的计算成本，通过通信、访问、重计算和可靠性四类结果建立资源理论，并在GPT-6 Astra上验证预测。

链接：https://arxiv.org/abs/2610.02488

作者：Zelin Zhao (Georgia Institute of Technology), Xinyu Guo (Georgia Institute of Technology), Jingyuan Zhang (Georgia Institute of Technology), Yuxuan Zhang (Etude AI), Yongxin Chen (Georgia Institute of Technology)

英文摘要：Language-model agents increasingly rely on harnesses that manage bounded context, persistent memory, tools, verification, and repeated execution, yet existing notions of model capability do not quantify the computational resources these mechanisms consume. We introduce the Language Model Agent Machine (LAM), a resource-bounded abstraction that fixes the underlying semantic model while explicitly charging harness-level resources. We establish four classes of results. Communication: LAM execution is instancewise equivalent to red--blue pebbling under simultaneous call--transfer budgets, transferring classical I/O lower bounds to context--memory traffic. Access: memory interfaces induce asymptotic separations, including a $\Theta(n)$ gap between random and non-speculative sequential access on pointer chasing. Recomputation: bit-reversal DAGs require $\Theta(n^2/(C+S)+n)$ model calls with context capacity $C$ and persistent-memory capacity $S$, quantifying when stored intermediate state avoids repeated semantic computation. Reliability: we derive tight stage-local sampling bounds, exact imperfect-verification costs, and a Young--Daly-type checkpoint law with a closed-form optimal verification interval. Controlled and held-out experiments on GPT-6 Astra test communication and reliability predictions, including checkpoint optima, policy selection under programmatic checking, and tradeoffs among call granularity, logical input traffic, and reliability on chained MATH tasks. Together, these results provide a resource theory for the computational cost of language-model agent harnesses.

AI 总结：针对肌电信号跨个体、设备泛化难及现有基础模型计算开销大的问题，提出高效混合CNN-Transformer基础模型LiteEMG-FM，预训练于16个数据集，采用分层唤醒架构，在多种部署模式下优于现有模型，实现高效可部署的鲁棒肌电传感。

链接：https://arxiv.org/abs/2610.02497

机构：University of Georgia（佐治亚大学）； University of Oklahoma（俄克拉荷马大学）； University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）

作者：Tianhao Wu, Xu Wu, Amirmohammad Radmehr, Jiawei Yu, Yi Wu, Phuc Nguyen, Jian Liu

英文摘要：Electromyography (EMG) signals vary substantially across individuals, body regions, recording sessions, and sensing hardware, limiting the generalization of models for assistive devices and human-computer interaction. Existing time-series foundation models are also computationally expensive for real-time wearable deployment and often fail to capture EMG-specific time-frequency characteristics. We present LiteEMG-FM, an efficient hybrid CNN-Transformer foundation model for practical EMG sensing. Pretrained on 16 diverse upper- and lower-limb EMG datasets, LiteEMG-FM learns representations that generalize across users and datasets. For resource-constrained deployment, we implement a hierarchical wake-up architecture in which a lightweight, always-on 1D-CNN filters rest and non-target activity and activates LiteEMG-FM only for valid gestures. We evaluate full inference offloading, split inference, and full on-device processing, characterizing their trade-offs in latency, power consumption, and memory footprint. Across diverse evaluation settings, LiteEMG-FM outperforms state-of-the-art time-series foundation models and supervised baselines, particularly under zero-calibration cross-participant and data-scarce conditions. These results demonstrate that LiteEMG-FM is an effective, efficient, and deployable foundation model for EMG applications.

AI 总结：提出以特征为中心的图数据增强框架SelfAug，通过嵌入空间自监督逆掩码学习潜在结构，在十个数据集上优于现有方法，兼顾准确性与效率。

链接：https://arxiv.org/abs/2610.02517

机构：Michigan State University（密歇根州立大学）； Meta

作者：Yu Song, Zhigang Hua, Yan Xie, Bingheng Li, Jingzhe Liu, Bo Long, Jiliang Tang, Hui Liu

英文摘要：Graph-structured data plays a pivotal role in modeling complex relationships. However, real-world graphs are often incomplete due to data collection and observational constraints, severely limiting the effectiveness of modern graph learning pipelines. While existing Graph Data Augmentation (GDA) methods attempt to refine graph structures for improved downstream performance, they are typically label-dependent, computationally expensive, and inherently transductive, limiting their applicability in practical scenarios. In this work, we present a novel feature-centric graph data augmentation framework that bypasses explicit structure modeling by operating directly in the embedding space. Through a self-supervised inverse masking process, our method captures latent ties between observed and complete graphs, enabling recovery of unobserved structural signals through refined node representations. To enhance robustness under noisy and sparse supervision, we introduce a message regularizer and a bootstrap strategy for effective training and generalization. Evaluated on ten graph datasets spanning multiple domains, our approach, SelfAug, consistently outperforms state-of-the-art methods in both accuracy and efficiency across inductive and cold-start settings, highlighting its potential as a scalable and generalizable solution for real-world graph learning scenarios.

AI 总结：针对极度稀疏剪枝中的表征崩溃问题，提出BaCP方法，通过对比对齐预训练等模型来正则化嵌入空间，在90种设置下显著提升极度稀疏时的准确率。

链接：https://arxiv.org/abs/2610.02524

机构：Lahore University of Management Sciences（拉合尔管理科学大学）

作者：Mohammad Haroon Khawaja, Muhammad Haseeb, Mohammad Fatim Shoaib, Muhammad Tahir

英文摘要：Unstructured pruning at extreme sparsity often suffers from representational collapse, causing sharp drops in accuracy. To address this, we study Backbone Contrastive Pruning (BaCP), which regularizes the sparse network's embedding space by aligning it with pretrained, fine-tuned, and historical snapshot models. Building on the contrastive decomposition of the CAP framework (Xu et al., 2022), we provide a rigorous matched-budget characterization of this approach across multiple pruning criteria. Evaluated across 90 settings, BaCP improves accuracy substantially in extreme sparsity regimes where standard pruning fails, and is close to baseline where representations remain intact.

AI 总结：提出一种自回归可微方法求解0-1整数规划，通过transformer预测比特并利用拉格朗日惩罚与Gumbel-softmax探索可行集，在非凸二次背包问题上优于开源求解器，并发现隧道效应现象。

链接：https://arxiv.org/abs/2610.02528

机构：BCG X AI Science Institute（波士顿咨询X人工智能科学研究院）； Zapata Quantum（Zapata Quantum公司）

作者：Ouns El Harzli, Yudong Cao

英文摘要：We introduce an autoregressive differentiable method to solve 0-1 integer programs. We fix an arbitrary order of the binary variables and we train a transformer to predict the next bit while remaining in the feasible set. Our method is first trained on feasible incumbents provided by any solver, thus allowing us to initialize the transformer in the feasible set. Our procedure then implements a Lagrangian penalty to penalize infeasible solutions, and the transformer is further trained to explore the feasible set using Gumbel-softmax activations on the relaxed objective. We have tested our method on non-convex instances of quadratic knapsack problem and demonstrated consistent improvement upon state-of-the-art open-source solvers for dense problems up to 10,000 binary variables. In particular, we empirically demonstrate a phenomenon akin to a tunneling effect where the effective change of variables from binary variable to the continuous weights of the transformer that the method implements enables crossing barriers in the relaxed objective landscape.

AI 总结：DISSOLVR提出透明且快速的溶解度预测框架，通过物理描述符实现接近实验极限的精度与OOD泛化，并借助LLM解释流水线提升可解释性。

链接：https://arxiv.org/abs/2610.02574

机构：Indian Institute of Technology, Delhi（印度理工学院德里分校）

作者：Vansh Ramani, Har Ashish Arora, Dhairya Kuchhal, Sayan Ranu, Tarak Karmakar

英文摘要：High-fidelity solubility prediction is fundamental to pharmaceutical development and environmental partitioning, where accurate modeling must couple molecular structure with thermodynamic behavior across diverse chemical environments. However, recent advancements have been dominated by deep learning architectures that often sacrifice physical interpretability for predictive power. We challenge this trend by showing that state-of-the-art performance does not require such non-transparent architectures. To address this, we introduce DISSOLVR, a transparent framework for molecular solubility prediction. In addition, we perform a comprehensive literature review and a benchmarking study against various methods. We show that DISSOLVR approaches the aleatoric limit of experimental uncertainty and achieves OOD generalization through structural invariance, derived by mapping molecules to physically-grounded descriptors. Then, we present an LLM-assisted post-hoc explanation pipeline that bridges the gap between symbolic model artifacts and chemically grounded narratives. Finally, a comparative benchmark of a survey involving 22 expert chemists reveals that expert evaluators provide deep insights.

AI 总结：提出Fisher引导的子模数据选择方法，通过分解梯度为锚定和前沿分量，在持续预训练中提升目标领域质量并控制遗忘，实现10倍令牌效率提升。

链接：https://arxiv.org/abs/2610.02593

机构：University of Illinois Chicago（伊利诺伊大学芝加哥分校）； Cisco Research（思科研究院）

作者：Zhenghao Zhao, Gaowen Liu, Zhiling Lan, Yan Yan

英文摘要：Data selection is already a central bottleneck in large-language-model training, where web-scale corpora are noisy and token budgets are finite. In continual pre-training (CPT), it becomes a forgetting-control problem: a poorly chosen target-domain corpus can overwrite capabilities encoded in the pretrained checkpoint. Existing CPT practice either scores candidates with parameter-agnostic scalars such as perplexity, or mitigates forgetting by spending many extra general-domain replay tokens. Neither strategy directly asks how training on a candidate will move the model parameters. We show that loss-based selection causes the post-CPT Fisher diagonal to drift downward on exactly the high-Fisher coordinates the pretrained model had committed to, while leaving low-Fisher coordinates largely untouched. This asymmetry exposes a parameter-space mechanism for catastrophic forgetting. Motivated by this observation, we propose a Fisher-aware CPT selector that decomposes each candidate's gradient into an anchor component, which measures perturbation along committed parameter directions, and a frontier component, which measures update capacity in unconstrained low-Fisher subspaces. We aggregate these signals with a log-determinant submodular objective and optimize it in a single pass using a scalable streaming data selection pipeline. On TinyLlama-1.1B and Llama-3.1-8B CPT over medical data, our selector improves target-domain quality while bounding forgetting on held-out pretraining benchmarks. Most importantly, it is substantially more token-efficient than forgetting-aware replay. 1B selected tokens already outperform the replay strategy trained with 10B tokens on both adaptation and forgetting, giving a 10x token-efficiency advantage.

AI 总结：本文提出CausalBridge框架，利用因果结构而非人类知识来弥合测量与语义之间的鸿沟，通过因果图约束下的嵌入对齐为未命名变量赋予语义，实验表明其比现有方法更准确且成本更低。

链接：https://arxiv.org/abs/2610.02594

机构：University of California, San Diego（加利福尼亚大学圣迭戈分校）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

作者：Shuhao Zhang, Xuran Zhou, Han Guo, Pengtao Xie, Yujia Zheng

英文摘要：Numerical measurements capture how a system behaves, but often leave the meanings of its variables unspecified. Some variables are measured but never labeled, and others are never measured at all. Existing methods assign semantics to such variables by consulting general human knowledge, but this inherits its biases where that knowledge exists and offers nothing where it does not. We bridge this gap between measurements and their meanings with causal structure instead, reading a variable's semantics from how it acts on other variables. We formalize this as structure-constrained semantic alignment, in which the embedding of each unnamed variable is solved under the dependence relations implied by the causal graph, with the embeddings of a few known names as anchors. Accordingly, we build CausalBridge, a framework that discovers the causal graph from the measurements, latent variables included, solves for the embeddings under those relations, and expresses them as names through a language model. The causal structure reflects the mechanism that generated the measurements and is recovered from the measurements alone, which may make it the one source of information free of bias from human knowledge. We evaluate CausalBridge on five questionnaires and three robotics scenarios, with 20 to 90% of the variable names masked. It recovers the semantics of observed and latent variables more accurately than existing methods that rely on association, and its lead widens as less of the system is documented. The graph it discovers names variables as accurately as the documented one, and a new system is named in minutes and at a fraction of the cost of sampling methods. Once the semantic gap is bridged faithfully, machines can understand the world and take actions causally.

AI 总结：针对卸载权重导致的LLM解码慢问题，提出SpAx方法，通过将权重读取分为保留、近似和省略三档，利用激活稀疏性，在CPU和闪存卸载下分别实现最高5.57倍和4.81倍加速，且困惑度增加不超过10%。

链接：https://arxiv.org/abs/2610.02598

机构：LG Electronics（LG电子）； University of Toronto（多伦多大学）

作者：JuneHyung Kim, Sankeerth Durvasula, Nandita Vijaykumar

英文摘要：Deploying LLMs on consumer-grade GPUs with insufficient memory to hold their weights can result in prohibitively slow inference, because decoding repeatedly transfers offloaded weights from system RAM or flash storage into GPU at much lower bandwidth than local GPU-memory access. Activation sparsity reduces these transfers by skipping weights associated with zero or near-zero activations. However, as more activation contributions are omitted, model quality eventually degrades rapidly, indicating that weights associated with small-magnitude activations collectively influence model quality sharply. In this work, we improve the trade-off between model quality and decoding performance when exploiting activation sparsity. Our key idea is to replace the binary choice of whether or not to read a weight with three options: fully retain it, approximate it using a compressed weight representation, or omit it entirely. SpAx skips weights associated with activations closest to zero, reads approximate weights for smaller-magnitude activations, and reads original weights for the largest-magnitude activations. Smaller-magnitude activations attenuate the errors introduced by approximate weights, while compressed weight representations require fewer bytes to be transferred. With weights offloaded to CPU memory, SpAx speeds up decoding by 3.86X on average (up to 5.57X) with 16-bit weights and 2.06X (up to 2.74X) with 4-bit weights, at a WikiText-2 perplexity increase of at most 10%. With weights offloaded to flash storage, the speedups are 3.31X on average (up to 4.81X) and 1.54X (up to 2.03X).

AI 总结：本文提出Seer系统，通过生成分类学习性能观测数据并构建最大似然统计模型，预测达到目标性能所需的训练样本数及最大准确率，并在三个真实领域实验中验证其有效性。

链接：https://arxiv.org/abs/2610.02610

作者：Carl Myers Kadie

英文摘要：The research presented here focuses on modeling machine-learning performance. The thesis introduces Seer, a system that generates empirical observations of classification-learning performance and then uses those observations to create statistical models. The models can be used to predict the number of training examples needed to achieve a desired level and the maximum accuracy possible given an unlimited number of training examples. Seer advances the state of the art with 1) models that embody the best constraints for classification learning and most useful parameters, 2) algorithms that efficiently find maximum-likelihood models, and 3) a demonstration on real-world data from three domains of a practicable application of such modeling. The first part of the thesis gives an overview of the requirements for a good maximum-likelihood model of classification-learning performance. Next, reasonable design choices for such models are explored. Selection among such models is a task of nonlinear programming, but by exploiting appropriate problem constraints, the task is reduced to a nonlinear regression task that can be solved with an efficient iterative algorithm. The latter part of the thesis describes almost 100 experiments in the domains of soybean disease, heart disease, and audiological problems. The tests show that Seer is excellent at characterizing learning-performance and that it seems to be as good as possible at predicting learning performance. Finally, recommendations for choosing a regression model for a particular situation are made and directions for further research are identified.

AI 总结：提出尺度递归修正流，通过先粗后细生成及按尺度分配采样步数，在少步降水集合中提升概率准确性与降雨检测，优于非递归流。

链接：https://arxiv.org/abs/2610.02611

机构：Neurogica Inc.（Neurogica 公司）； LTS, Inc.（LTS 公司）； ME-Lab Japan, Inc.（ME-Lab Japan 公司）

作者：Shunya Nagashima, Takumi Bannai

英文摘要： Fine-resolution precipitation estimates support flood risk assessment and water management, but coarse satellite products cannot resolve rainfall within each grid cell. Generative models address this ambiguity by producing ensembles of plausible high-resolution rainfall fields. Among these models, rectified flows generate samples by iteratively transforming random noise into rainfall fields. Reducing the number of sampling steps accelerates generation but can make ensemble members too similar, understating uncertainty. We propose a scale-recursive rectified flow that generates broad patterns before local details and guides sampling-step allocation by comparing ensemble variability with prediction error across spatial scales. Validation scores and rainfall power spectra constrain the allocation to avoid excessive amplification. In satellite-to-radar downscaling over the contiguous United States, our analysis identified broad rainfall patterns as the main source of insufficient ensemble variability under reduced sampling budgets. Allocating more steps to the coarse flow improved probabilistic accuracy and rain detection across training seeds at fixed architecture and computational cost. The proposed model also achieved better probabilistic accuracy with shorter sampling time than a nonrecursive flow using more steps.

AI 总结：本研究揭示后训练会削弱语言模型在上下文中适应非偏好视角的能力，提出立场分布匹配作为兼顾多样性的替代目标。

链接：https://arxiv.org/abs/2610.02614

机构：Hasso Plattner Institute（哈索·普拉特纳研究所）； University of Potsdam（波茨坦大学）； Harvard University（哈佛大学）

作者：Jessica Dierking, Itai Shapira, Niclas Boehmer

英文摘要：AI models serving a heterogeneous population must act on the principles appropriate to each user and context. While post-training has been shown to narrow the views large language models express, prior work has focused on default behavior rather than the ability to adapt to in-context information. We show that post-training also degrades a model's ability to be steered in-context toward perspectives it was not trained to favor. In controlled experiments, we fine-tune models toward one side of cultural-value disagreements and evaluate checkpoints throughout training. The trained side becomes increasingly dominant in ordinary use, while the ability to recognize and faithfully enact the opposing view declines. These findings point to a tension between prioritizing a single set of values and preserving the technical capacity needed to serve diverse stakeholders. Finally, we propose and analyze an alternative objective that maximizes reward subject to a prescribed distribution over expressed perspectives, and present stance-distribution matching as a practical implementation.

AI 总结：本文提出有效维度这一新学习度量，连接问题属性与学习性能，可经验估计并做平均预测，用于量化构造归纳、噪声过滤和背景知识的价值，并精确预测FRINGE特征构造系统的收益随目标概念复杂度增加而减少。

链接：https://arxiv.org/abs/2610.02615

作者：Carl M. Kadie

英文摘要：Learning research, as one of its central goals, tries to measure, model, and understand how learning-problem properties affect average-case learning performance. For example, we would like to quantify the value of constructive induction, noise filtering, and background knowledge. This paper describes the effective dimension, a new learning measure that helps link problem properties to learning performance. Like the Vapnik-Chervonenkis (VC) dimension, the effective dimension is often in a simple linear relation with problem properties. Unlike the VC dimension, the effective dimension can be estimated empirically and makes average-case predictions. It is therefore more widely applicable to machine and human learning research. The measure is demonstrated on several learning systems including Backpropagation. Finally, the measure is used to precisely predict the benefit of using FRINGE, a feature construction system. The benefit is found to decrease as the complexity of the target concept increases.

AI 总结：针对在线验证语言模型响应时成本与准确性的权衡，提出OMVV算法，通过维护多个弱验证器池并自适应路由，在有限时间内保证误接受与误拒绝率，同时实现次线性遗憾，实验证明其成本更低、准确性更高。

链接：https://arxiv.org/abs/2610.02632

机构：University of California, Irvine（加州大学尔湾分校）

作者：Erfan Hajihashemi, Yanning Shen

英文摘要：As large language models are increasingly deployed for multi-step reasoning, verifying the correctness of their outputs has become essential for maintaining reliability at scale. Verifying the correctness of large language model outputs is often done by querying a costly ground-truth oracle, which is impractical to invoke at every step in an online setting. Prior work addresses this by querying a single weak verifier on every step, and using its score to decide whether the costly strong verifier needs to be queried as well, reserving strong verification for only a small fraction of the steps. However, a single fixed weak verifier may not perform consistently well as the subject matter or difficulty of incoming queries changes over time, and committing to one in advance risks either overly costly or inaccurate verification. We introduce OMVV (Online Multi-Verifier Verification), an algorithm that maintains a pool of $K$ candidate weak verifiers with differing cost and verification performance, and adaptively routes each round's decision to a verifier selected via an online score combiner and an exponential-weights routing policy. OMVV provides a distribution-free, finite-time guarantee on false-accept and false-reject rates across the full pool of verifiers, and further achieves sublinear regret against the best fixed verifier in hindsight under a combined cost and consistency objective. Experiments on reasoning dataset benchmarks show that OMVV achieves higher accuracy at lower verification cost than any single fixed verifier, across a range of operating budgets.

AI 总结：本研究揭示语言机器人系统中安全监控器基于表面计划判定与图细化轨迹判定存在差异，提出轨迹细化作为轻量级缓解与诊断工具。

链接：https://arxiv.org/abs/2610.02662

机构：Prairie View A&M University（草原景观农业机械大学）； Texas A&M University（德克萨斯A&M大学）

作者：Stabak Das, Priyesh Ranjan, Xiangfang Li, Lijun Qian

英文摘要： Language-enabled robot systems increasingly combine semantic-graph planning with temporal-logic safety monitors. We investigate a trace-completeness assumption in these systems: whether the high-level action sequence checked by a monitor represents the navigation and implicit action effects induced during execution. We audit this assumption in RoboGuard by comparing its verdict on a surface plan with its verdict on a graph-refined trace under the same Linear Temporal Logic (LTL) specification. Our evaluation comprises 28 controlled cases spanning five action-abstraction families and 14 end-to-end cases in which SPINE [1] generates plans from natural-language instructions while RoboGuard generates scene-grounded safety specifications. In the controlled evaluation, all 12 targeted abstraction cases exhibit the predicted surface-versus-refined discrepancy while all 16 controls behave as expected, motivating graph-based trace refinement as a lightweight mitigation and a diagnostic tool for physical-AI safety monitors.

AI 总结：LEAP提出一种延迟框架指导的小型草拟模型训练方法，通过针对目标动作序列训练0.6B模型，使LLM智能体端到端加速高达60%，且支持在线训练，便于实际部署。

链接：https://arxiv.org/abs/2610.02670

机构：University of Chicago（芝加哥大学）； Stanford University（斯坦福大学）； Together AI

作者：Zhen Xu, Qizheng Zhang, Gerry Wan, Shang Zhu, Ce Zhang

英文摘要：LLM agents are known to be slow in rollouts. An agent completes a task one step at a time. At each step, it reasons and then chooses an action to execute. The next step and action cannot start until the previous one has finished. Speculative decoding accelerates the rollouts at the reason phase by drafting and verifying the inference tokens. Recent works have also started to apply similar ideas at the action phase. These works use off-the-shelf models, usually large, to draft action proposals for target model to verify. Large drafters match the target more often but take longer to propose, while small off-the-shelf models are fast but rarely make the same decision as the target. We ask a more general question: what determines the end-to-end speedup of action speculation? To answer it, we develop a latency framework for the speculative round. The framework compares what a round gains with what it costs. The gain depends on how well the drafter predicts the target and on how many steps the task can take before it ends. The cost comes from drafting, from waiting for target verification and from executing tools. Guided by the framework, we introduce LEAP (Learning Efficient Action Proposals) which keeps the drafter small and makes it accurate by training it on the target actions sequences. With a small 0.6B model, LEAP agrees with the target on most decisions and makes agents up to 60% faster in end-to-end wall clock time, with no systematic change in task success. Across various datasets, target models and draft models, the framework accounts for most of the measured speedups. We also show the draft model can be online trained with no prior trace collection and match the performance of offline training, making LEAP practical to deploy in the real world.

AI 总结：MuonIO提出针对嵌入表和语言模型头的统一Muon风格更新，利用范数感知几何，在1B LLaMA预训练中减少50%优化器内存和约46%更新FLOPs，并提升验证困惑度。

链接：https://arxiv.org/abs/2610.02705

机构：Purdue University（普渡大学）

作者：Linkai Ma, Xinyu Luo, Mengbo Wang, Ananth Grama, Petros Drineas, Brian Bullins

英文摘要：The Muon optimizer derives its update rule for hidden linear layers by solving a local linearization of the loss penalized by the spectral norm, motivated by an RMS-stability argument for dense linear layers. Standard Muon implementations, however, exclude the input (embedding table) and output (language model head) layers from this principled treatment, for which they use AdamW instead. We present MuonIO, a single Muon-style update for both of these layers. For the language model head $\mathbf{L} \in \mathbb{R}^{V \times d}$, we motivate the use of the $2\to\infty$ operator norm, due to the Lipschitz continuity of the softmax output geometry, while for the embedding table $\mathbf{E} \in \mathbb{R}^{d \times V}$, we draw on the $1 \to 2$ operator norm, based on the one-hot input geometry identified by Bernstein & Newhouse (2025). The identity $\lVert\mathbf{L}\rVert_{2\to\infty}=\lVert\mathbf{L}^\top\rVert_{1\to2}$ then puts both matrices in the same vocabulary-oriented geometry: MuonIO applies a single normalized-vector rule, which appears as column normalization for $\mathbf{E}$ and row normalization for $\mathbf{L}$. Empirical evaluations demonstrate the effectiveness of our approach, with MuonIO reducing I/O optimizer state memory by 50% and I/O update FLOPs by $\sim$46% compared to Muon for 1B LLaMA pretraining on C4, while also improving validation perplexity.

AI 总结：本研究通过置换历史评分进行受控审计，区分个人AI在评分预测中依赖关联还是用户倾向，并评估记忆提取与读取器选择的影响。

链接：https://arxiv.org/abs/2610.02764

作者：Shivam Gupta

英文摘要：In structured rating prediction, does a personal AI use historical item-rating associations, or mainly the user's rating tendencies? We audit this distinction by permuting historical ratings within each user while preserving the exact rating distribution, item support, and metadata. We combine this control with full history, native memory extraction, and matched numerical readers in a publicly frozen evaluation of 400 held-out user profiles and 6,160 target ratings across Coat and MovieLens. On Coat, the tested Qwen-written Mem0 pipeline increases user-macro mean absolute error relative to full history by 0.084 for Qwen and 0.149 for Phi; both family-adjusted bootstrap intervals exclude zero. Correct historical assignments help both readers on Coat, but the corresponding MovieLens effects are smaller and inconclusive after adjustment. A history-only ridge reader outperforms Qwen in both domains and Phi on MovieLens, while the Coat Phi comparison is unresolved. All 2,800 reader calls, including 150 invalid outputs, are retained under a fixed fallback rule. A separate implementation verifies inputs, metrics, and all ten primary contrasts. The contribution is a reproducible diagnostic study showing why extraction, association use, output reliability, and reader choice require separate evaluation.

AI 总结：针对前缀缓存语言模型服务，提出前缀证书保留（PCR）精确优化模型，通过最小割和断点定理求解，并在Mooncake数据集上验证，实现内存-时间权衡的优化。

链接：https://arxiv.org/abs/2610.02766

机构：Independent Researcher（独立研究者）

作者：Shivam Gupta

英文摘要：Retaining language-model prefix states trades recomputation against storage time. Optimizing each cached block independently can overcount savings: a resident block is usable only when the required preceding prefix is also available. We introduce Prefix-Certificate Retention (PCR), an exact finite-trace formulation for static, grouped, reset-on-access timeouts. Usable-prefix rewards become nodes whose prerequisites are timeout thresholds and preceding hit certificates. The resulting maximum-weight closure reduces to one minimum cut, with graph size linear in the number of block lookups and timeout choices. A breakpoint theorem extends the construction to all nonnegative timeouts without discretization error. We also derive a linear-time-in-grid-size dynamic program for ordered timeouts and bounds that certify the cost of this restriction. Exhaustive small-instance checks and chronological replay of 39,632 public Mooncake requests validate the formulation. On the fixed grid, ordered timeouts attain the unrestricted training optimum in 118 of 120 trace-grouping-price cases. Heterogeneous retention improves several held-out memory-time tradeoffs, but finer training optimization does not uniformly improve transfer. The contribution is a tractable optimization model and an auditable benchmark for retention policies; the experiments measure usable prefix blocks and storage time, not GPU latency.

AI 总结：LatticeSMC提出预算匹配的分块引导采样器，在块索引和去噪步骤二维格上精确重采样，提升节拍对齐与提示遵循度，并保持生成质量。

链接：https://arxiv.org/abs/2610.02774

机构：The University of Sydney（悉尼大学）

作者：Xuanchen Wang, Heng Wang, Weidong Cai

英文摘要：Long-form generators for music, motion and video produce sequences chunk by chunk, with each chunk generated by iterative denoising while rewards are defined over the full sequence. Existing inference-time steering methods typically act on one axis at a time: best-of-N at the end, Feynman-Kac steering across denoising steps, or streaming pruning across chunks, and are often compared under unmatched compute or different return rules. We introduce budget-matched chunked steering and propose LatticeSMC, a sampler derived from a Feynman-Kac model on the two-dimensional lattice of chunk index and denoising step. Two telescoping results make its design exact: for chunk-additive rewards, the two axes induce identical weights, so resampling should occur where lookahead is cheapest; for terminal rewards, any prefix score defines an exact intermediate potential, making prefix-evaluable rewards twists with no estimation or extra denoiser calls. LatticeSMC resamples on these potentials at chunk boundaries and, when scoring is free, within chunks, returning either a weighted draw or the best particle. Under matched compute, on music-to-dance diffusion and 40-second text-to-music generation, it raises beat alignment from 0.234 to 0.441 (best-of-N: 0.354) and prompt adherence from 0.470 to 0.560 at 32 particles, while preserving held-out quality. It also retains its advantage on long-range rewards and is preferred by human raters in 60-77 percent of pairwise comparisons. Finally, we show that commitment strength should follow the information in the current potential, while the value of lookahead is predicted by the within-set predictability of future reward.

AI 总结：针对线性注意力固定大小记忆管理难题，提出门控槽注意力-2（GSA2），结合门控Oja规则-2与门控Delta规则-2进行双侧记忆修正，在保持线性时间和恒定内存下提升基准性能。

链接：https://arxiv.org/abs/2610.02816

机构：The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； Tencent（腾讯）

作者：Ruijie Li, Shengnan Ding, Weimin Zhang, Derick Tang, Zhanpeng Zeng, Qinsong Zeng, Ming Chen, Jiaxi Hu, Yuxuan Liang

英文摘要：Linear attention models have emerged as efficient alternatives to standard attention, but effectively managing their fixed-size recurrent memory remains challenging. To improve memory, recent work has explored two distinct directions: delta-rule variants for precise correction of values associated with keys, and slot-based architectures such as Gated Slot Attention for modeling key and value memories in two stages. We observe that these directions are complementary--the delta rule provides effective memory correction, while the two-stage structure provides a natural way to operate on both sides of an association. Building on this insight, we introduce a new Gated Oja Rule for key-side correction and extend it with decoupled erase and write control to obtain Gated Oja Rule-2. We then introduce Gated Slot Attention-2 (GSA2), which combines Gated Oja Rule-2 for key-side correction with Gated Delta Rule-2 for value-side correction through shared latent slots. We further derive a hardware-efficient chunkwise algorithm for parallel training. Experiments demonstrate that GSA2 consistently improves over strong linear-attention baselines across benchmarks while retaining linear-time sequence modeling and constant-memory recurrent decoding.

AI 总结：本文提出SBD框架，将系统行为作为贝叶斯特征纳入ELBO，揭示因果性存在“因果税”现象，并构建非因果变分族GSH，通过NTK谱验证其能降低误差、提升泛化，为LM基础模型设计开辟新方向。

链接：https://arxiv.org/abs/2610.02839

机构：College of Computing and Data Science（计算与数据科学学院）； Nanyang Technological University（南洋理工大学）

作者：Xianzhi Zeng, Jiangneng Li, Gao Cong

英文摘要： We show that the causality of language models (LMs) may not be necessary nor optimal. This is the case when system behavior (denoted as $S$) is incorporated as a first-principle Bayesian feature. Here, $S$ refers to extra dominant factors beyond the data space, and they involve coupled effects. Despite being the de facto foundation of modern architecture, recent studies indicate persistent mismatches and contradictions with causality. These issues largely stem from system behavior rather than the data distribution. We therefore propose the SBD framework, which incorporates $S$ as an irreducible component of the evidence lower bound (ELBO). SBD theoretically reveals a counter-intuitive Causality Tax phenomenon, where causality emerges as a suboptimal approximation with an additional structural error, due to the obliviousness to $S$. To address the challenge of latent variable analysis, we validate the SBD-predicted impact of $S$ via implicit measurements, theoretical-bound-guided controls, and Neural Tangent Kernel (NTK) evaluations. In particular, we construct Green Shell (GSH) to show the possibility of reducing Causality Tax. GSH is a non-causal variational family, and it replaces the sequential dependency chain of $S$ components with a divide-and-conquer partition. NTK spectra in the lazy-training regime confirm that GSH always achieves significantly tighter error bounds than causality, with $7dB+$ improvement in signal-to-noise ratio. In the relatively later stage of lazy-training, GSH further leads to superior generalization (up to $20\%$ richer multi-scale fitting capabilities). Taken together, SBD establishes system behavior as a complementary theoretical abstraction besides causality and distribution fitting, opening new research avenues such as designing and optimizing LM base models.

AI 总结：本文提出一种贯穿模拟器状态、观测、嵌入和预测器的反事实评估协议，发现预测误差低不代表动作区分充分，并揭示观测瓶颈、动作路径利用不足及表示几何问题，强调需分别审计物理效应、可见性、几何和动作依赖性。

链接：https://arxiv.org/abs/2610.02860

机构：Computer Science and Artificial Intelligence Laboratory (CSAIL)（计算机科学与人工智能实验室（CSAIL））； Massachusetts Institute of Technology（麻省理工学院）

作者：Arjun Subramanian

英文摘要：Low latent prediction error does not establish that a world model distinguishes the consequences of its actions. We introduce an evaluation protocol that traces the same intervention through simulator state, raster observations, target embeddings, and predictor outputs. Exact simulator-state forks in a controlled deformable-physics testbed reveal distinct bottlenecks. Changed commands alter particle motion, yet 41.5% of one-step raster pairs are identical. Observation loss is not the whole explanation: among 579 high-visibility counterfactuals, median predictor-to-target response is 0.0051 and 0.0217 across two seeds, falling to 0.0027 and 0.0116 after variance normalization. An isotropic state perturbation matched to the target counterfactual embedding shift produces 190x and 53x larger predictor changes on the same visible pairs, isolating action-path under-use rather than a dead or globally shrunk predictor. MSE-only training gives 8.36x lower 10-step latent error in matched seeds, but in spectrally concentrated spaces; one VICReg target encoder is also strongly concentrated, so neither error nor rank alone certifies physical state. Finally, stiffness remains near chance even from full-resolution rasters and mechanical state while privileged material parameters decode perfectly, indicating weak identifiability under this excitation rather than encoder discard. These results motivate auditing physical effect, observation visibility, representation geometry, and action dependence separately.

AI 总结：NeuroLens利用JEPA框架的自监督模型，从慢性神经记录中学习去噪潜在表征，改善决策和语义解码，支持跨会话泛化与少样本适应，为研究神经表征动态提供新范式。

链接：https://arxiv.org/abs/2610.02864

机构：Northwestern University（西北大学）； University of Cambridge（剑桥大学）； Johns Hopkins University（约翰霍普金斯大学）； Columbia University（哥伦比亚大学）； University of California, Los Angeles（加州大学洛杉矶分校）； Stanford University（斯坦福大学）

作者：Hanrui Lyu, Baiyuan Chen, Tianshu Tan, Matthew R. Whiteway, Maxwell D. Melin, Ji Xia, Linyang He, Bradly C. Stadie, Anne Churchland, Liam Paninski, Yizi Zhang

英文摘要：Understanding how neural activity represents higher-order cognition and how these representations evolve over time has long been a central pursuit in neuroscience. However, current analytical tools cannot easily distinguish representational plasticity from recording instability in chronic neural recordings. Here, we introduce NeuroLens (Latent Embeddings of Neural Semantics), a self-supervised model based on the Joint-Embedding Predictive Architecture (JEPA) framework that learns denoised, semantically informative latents from chronic neural recordings. An adaptive encoder maps changing neural populations into a common latent space, while a temporal predictor learns structure that supports prediction of future latent states. By predicting in latent space, NeuroLens captures temporally predictable structure and reduces sensitivity to transient, recording-specific variability. Across chronic intracortical data in mice and humans, the learned representations improve decoding of decision-making and semantic task variables. Multi-day pretraining enables generalization to future sessions, rapid few-shot adaptation to unseen neural populations, and more stable decoding over time than state-of-the-art baselines. Together, these results establish NeuroLens as a new paradigm for studying how neural representations change during learning and over long timescales.

AI 总结：DIVINE通过从原始OHLCV数据重建技术指标进行跨市场预训练，以轻量0.05M参数编码器在六个股票市场取得最优平均投资组合表现，证明监督设计与市场多样性比模型规模更重要。

链接：https://arxiv.org/abs/2610.02866

机构：SinoPac Holdings（永丰金控）

作者：Kuan-Yu Chen, Shu-Cheng Zheng, Yu-Chen Den, Wei-Cheng Liao, Tien-Hao Chang

英文摘要：Financial time-series pretraining typically learns from masked observations, contrastive relations, or future outcomes---yet existing objectives struggle to simultaneously avoid future-supervision uncertainty and maintain return-prediction alignment. We propose DIVINE (DIVerse INdicator rEconstruction), a simple cross-market pretraining framework that reconstructs technical indicators from raw OHLCV history. Computed from observed price-volume history, technical indicators provide consistently defined supervision across markets while summarizing diverse market dynamics with established relevance to return prediction. Pretrained jointly on six-equity market datasets, DIVINE reconstructs 77 targets derived from 16 standard indicators and transfers only the learned encoder to downstream stock ranking. Across all six markets, DIVINE achieves the strongest average portfolio performance with a lightweight 0.05M-parameter encoder, outperforming pretraining baselines and matching or exceeding substantially larger financial foundation models, while remaining robust and data-efficient. Systematic analyses show that indicator diversity and market diversity provide complementary gains in transfer. Together, these results suggest that supervision design and cross-market diversity---rather than model scale---are the key drivers of strong, transferable financial representations.

AI 总结：本研究提出SiDE估计器，在符号网络中区分正负关系的同伴效应，并通过半合成实验和学校数据验证，揭示符号盲分配会混合影响，为网络干预设计提供指导。

链接：https://arxiv.org/abs/2610.02872

机构：Adelaide University（阿德莱德大学）； Hainan University（海南大学）

作者：Xiaojing Du, Jiuyong Li, Lin Liu, Debo Cheng, Jixue Liu, Thuc Duy Le

英文摘要：Evaluating network interventions requires understanding how treatment affects people through their social relationships. Counting treated neighbors without distinguishing supportive and antagonistic ties can conceal opposing influences. We define effects through positive and negative ties, their interaction, and a sign-composition effect of reallocating treatment between the two types at a fixed total, and give their identification formulas. Under sign-blind assignment, we show how ignoring signs mixes the effects of the two tie types. We propose SiDE (Signed-exposure Doubly robust Estimator), which combines sign-specific outcome models with exposure probabilities induced by individual treatment assignment. We establish double robustness of its score and assess approximate intervals that account for overlapping neighborhoods. Semi-synthetic experiments on six real signed networks demonstrate accurate effect estimation and examine the limits of interval coverage. An exploratory reanalysis of published school-experiment data yields a positive estimate of the peer effect through spend-time ties on wristband wearing, but the intervals for all four effects include zero after adjustment for multiple comparisons. This framework can inform network intervention design by showing when influences through the two tie types reinforce or offset one another.

AI 总结：针对多模态图基础模型在属性不完整及拓扑利用不足的问题，提出拓扑驱动的GraphBind方法，将模态信息绑定至统一空间，在判别与生成任务上相对最强基线提升达28.1%。

链接：https://arxiv.org/abs/2610.02881

机构：Beijing Institute of Technology（北京理工大学）； Sun Yat-sen University（中山大学）

作者：Xunkai Li, Chenxi Wan, Yinlin Zhu, Wang Luo, Hongchao Qin, Rong-Hua Li, Guoren Wang

英文摘要：Multimodal graph foundation models (MGFMs) seek to learn generalizable representations from large-scale graphs with heterogeneous node modalities. However, real-world Multimodal-Attributed Graphs (MAGs) often contain incomplete node attributes, limiting the scale and diversity of available pretraining corpora. Besides, existing MGFMs primarily incorporate graph topology as structural context, overlooking its role in guiding multimodal binding and shaping a unified representation space. To address these challenges, we propose GraphBind, a topology-driven approach that uses graph topology to bind rich modality information into a unified shared space. GraphBind is motivated by the stability of graph topology, which provides structural references and complementary semantic information for multimodal binding. Concretely, GraphBind uses topology to organize self semantics and reliable neighborhood semantics into a global shared space that integrates structure and semantics, and adapts this space to discriminative and generative tasks through lightweight interfaces. Extensive experiments against 11 representative baselines demonstrate that GraphBind achieves leading performance on both discriminative and generative tasks, with relative improvements of up to 28.1% over the strongest baseline.

AI 总结：DyRA通过动态逼近并校正结构化权重逼近产生的输出残差误差，在相同计算预算下更忠实逼近完整矩阵乘法，在视觉、语音和语言模型中一致提升精度-效率权衡，并在DINOv3上实现1.5倍GPU加速和3倍精度下降减少。

链接：https://arxiv.org/abs/2610.02882

机构：University of Michigan（密歇根大学）； Qualcomm AI Research（高通人工智能研究院）

作者：Daewon Chae, Hyunwon Chung, Changwoo Lee, Hun-Seok Kim

英文摘要：Large-scale foundation models achieve strong performance across diverse tasks, but their size makes inference costly, largely due to dense matrix multiplications. Prior work reduces this cost by replacing dense weight matrices with efficient structured forms such as low-rank factorizations. However, these methods approximate weights rather than the output activations that determine inference accuracy. Consequently, small weight-space errors can be amplified by input activations, producing large output errors. In this work, we propose DyRA, an input-adaptive method that improves structured matrix multiplication approximation by correcting residual output errors during inference. We show that matrix multiplication can be approximated more effectively by directly optimizing low-rank factors of the output. DyRA builds on this insight by dynamically approximating and correcting the output error introduced by structured weight approximations. This combines efficient structured computation with input-dependent correction, yielding a more faithful approximation of full matrix multiplication under the same computational budget. Across vision, speech, and language models, DyRA consistently improves the accuracy-efficiency trade-off over structured weight approximations alone. Notably, DyRA achieves a 1.5$\times$ end-to-end GPU speedup for DINOv3 while reducing accuracy degradation by more than 3$\times$ relative to weight-only baselines.

AI 总结：本文提出信任比量化匹配可靠性，并设计置信校准匹配策略，实验表明在低信任时弃权优于始终匹配。

链接：https://arxiv.org/abs/2610.02894

作者：Vishal Rajput

英文摘要： Match only geometry you can identify; otherwise spread the penalty. We quantify that decision by the trust ratio tau = epsilon / gamma (estimation uncertainty over spectral separation). Under the linear-quadratic Matching response, oracle-relative drift between estimated and oracle projector matching scales as tau^2 for probes in the chosen top-r deployment subspace -- O(tau^2) in the Davis-Kahan separation region tau < 1/2, with practical usefulness depending on constants. Confidence-Calibrated Matching (CCM) turns tau into a policy -- directional when tau is small, progressively isotropic when not -- with thresholds from calibration, not from the theorem (match sits in the separation region; soft is mostly heuristic). Experiments show both regimes, including UCI HAR embeddings where always-match is worse than abstain on every cell.

AI 总结：本文提出切线 Schrödinger 桥匹配（Tangent-SBM），通过传播参数导数监督敏感性，在多个随机系统中提升干预响应预测精度，并降低决策跟踪误差。

链接：https://arxiv.org/abs/2610.02906

机构：University of Michigan（密歇根大学）

作者：Jowaria Khan, Elizabeth Bondi-Kelly

英文摘要：Predicting how stochastic systems respond to changes in viscosity, reaction rates, or external forces requires costly simulations, motivating reusable learned models. Yet matching observed outcome distributions does not ensure accurate intervention responses. We introduce Tangent Schrödinger Bridge Matching (Tangent-SBM), which learns stochastic transports from endpoint observations and mechanistic sensitivities. It propagates parameter derivatives alongside trajectories and supervises them against supplied targets. For average-response targets, single-rollout squared error also penalizes response variability; our objective uses two independent rollouts to match the mean without this additional penalty. We establish conditions under which sensitivity accuracy bounds finite-change prediction error and decision regret. Across Gaussian, stochastic double-well, PDEBench reaction--diffusion, and stochastic Navier--Stokes systems, Tangent-SBM improves sensitivity and finite-change prediction over matched conditional-bridge baselines while maintaining comparable endpoint and distributional accuracy. Controls examine target correctness, response objectives, and simulator-budget allocation. To test decision usefulness, we evaluate calibrated viscosity selection in Navier--Stokes: Tangent-SBM reduces tracking error relative to taking no action on every evaluated task.

AI 总结：本文通过莫比乌斯反演分解残差网络输出，发现其交互高阶主导且随输入变化，证明密集残差网络隐式实现软路由，无需显式路由器或稀疏执行。

链接：https://arxiv.org/abs/2610.02907

机构：Fudan University（复旦大学）； University of Washington（华盛顿大学）； Tongji University（同济大学）； Shandong University（山东大学）； Datacanvas

作者：Liang Yan, Siying Chen, Kaijie Chen, Bo Li, Jinghao Zhang, Mu Miao

英文摘要：Residual networks execute every block for every input, yet their functional contributions need not be input independent. We formulate a trained ResNet as a set function over binary residual-branch masks and apply Möbius inversion to decompose its output exactly into individual residual corrections and higher-order interactions. For smooth residual stacks, we show that each fixed $k$-way interaction scales as $\mathcal{O}(\lambda^k)$ under residual scaling. Exhaustive analysis of ImageNet-pretrained ResNet-18 and ResNet-34 reveals that interaction mass peaks at orders five and ten, respectively, rather than at low orders. Reducing the residual scale shifts both spectra toward lower orders, but also changes model predictions. The interaction coefficients are concentrated in magnitude but not hard sparse, and prediction-preserving sparsity weakens with depth. Crucially, the dominant interactions vary across inputs and predicted classes around a shared global core, while their overall complexity changes little with sample difficulty. These results show that dense ResNets implement an implicit form of soft routing: every block is executed, but different inputs rely on different residual interaction experts. Routing can therefore emerge at the level of functional contribution without an explicit router or sparse execution.

AI 总结：提出Dirac互连神经单元（DINEs），通过微分代数方程和Dirac结构同时识别组件互连与特性，实现无需约简的模块化发现，支持子系统隔离组合及部分可观测系统，超越现有方法。

链接：https://arxiv.org/abs/2610.02960

机构：Hokkaido University（北海道大学）； Kyushu University（九州大学）； RIKEN（理化学研究所）； Waseda University（早稻田大学）

作者：Reiho Li, Razmik Arman Khosrovian, Takaharu Yaguchi, Hiroaki Yoshimura, Takashi Matsubara

英文摘要：Deep learning has shown remarkable success in the data-driven modeling of dynamical systems. Much of its success is attributed not to the flexibility of neural networks but to inductive biases based on physical prior knowledge, such as energy conservation and symplecticity. However, existing methods do not fully exploit the fact that real-world physical systems are interconnections of components. Some methods require the interconnection to be known a priori, while others assume the system to be reducible to an ordinary differential equation (ODE) and learn only the reduced ODE, discarding the algebraic constraints imposed by the interconnection. Here, we propose Dirac-interconnected neural elements (DINEs), a neural network model that represents a physical system as a differential-algebraic equation (DAE), whose algebraic constraints are given by a Dirac structure in kernel representation. With DINEs, we simultaneously identify from data the interconnection among the components as a Dirac structure and learn the characteristics of the components as neural networks. This allows us to keep the learned subsystems in unreduced form and isolate or compose them to make a new system without retraining. Moreover, DINEs can handle partially observable systems. Experimental results demonstrate these capabilities on physical systems beyond the reach of existing methods.

AI 总结：Sentry提出条件性暴露失败知识的故障管理层，在测试时检索外部剧本指导恢复并验证，显著优于运行时干预和上下文演进基线。

链接：https://arxiv.org/abs/2610.02994

机构：Stanford University（斯坦福大学）

作者：Changxiu Ji, Amy Lu, Qizheng Zhang, Kunle Olukotun

英文摘要： LLM agents often fail mid-task due to invalid tool calls, repeated actions, or poorly grounded reasoning, and learning from these failures is a path to reliability. We find that how failure knowledge reaches the agent matters as much as what it contains. Failure lessons are conditional: kept in the agent's context, they misfire when their failure is absent, and removing them from an evolving playbook improves performance. Runtime interventions, in contrast, act only when a failure occurs but do not learn from their repairs. We argue that failure knowledge is conditional knowledge and should be conditionally exposed, and instantiate this principle in Sentry, a failure-management layer that runs alongside the agent. When Sentry detects a failure, it retrieves matching lessons from an external playbook to guide recovery, verifies without access to task rewards whether the agent recovered, and stores a new lesson only if it did; the full playbook never enters the agent's context. Across multiple agentic benchmarks, Sentry outperforms the strongest runtime-intervention baseline on every benchmark, by 37\% on average, and the strongest context-evolution baseline by 39\% on the two benchmarks where both are evaluated; combining Sentry with context evolution yields further gains. Learned lessons transfer to held-out tasks, and controlled experiments show that exposing the full playbook to the agent lowers performance even when relevant lessons remain available on demand.

AI 总结：针对神经数据跨会话泛化失败的问题，提出基于行为事件分割群体状态的语义标记化方法TWS，无需神经元或会话嵌入，在跨物种迁移中优于每神经元基础模型。

链接：https://arxiv.org/abs/2610.03001

机构：Seoul National University（首尔大学）

作者：Sangyoon Bae, Jiook Cha

英文摘要：Extracellular electrophysiology records a different set of neurons in every session. Neural foundation models embed each neuron and each session into their tokens, so every new session is an input they have never seen, and they fail to generalize to it. A tokenizer for new sessions needs a unit that every session shares and that carries behavior. Population activity offers such a unit. It evolves on a low-dimensional manifold that persists across neuronal turnover and across animals once sessions are aligned. This manifold changes regime at task events such as stimulus onset and movement onset. Within each regime the population occupies a state, the part of the manifold it spans between two events, and each state carries its own behavioral meaning. We propose Tokenization with States (TWS), which segments each trial, one repetition of the task, at these events and converts every state into tokens of population geometry, with no neuron or session embedding. On held-out International Brain Laboratory (IBL) sessions, TWS decodes movement even from regime boundaries that carry no information about the target, while a per-neuron foundation model pretrained on those sessions decodes at chance. Frozen after training on mice alone, TWS transfers to macaques and Utah arrays with only a linear probe. On reach direction, a target that its boundaries do not define, it achieves a Matthews correlation of 0.23, where the event time alone achieves $0.01$. For cross-session generalization, the token matters more than the model on top.

AI 总结：针对多模态学习中的模态不平衡问题，提出功能空间引导的多模态优化（FGMO），通过功能进展估计和功能响应控制实现跨模态协调优化，并在多个基准上验证有效性。

链接：https://arxiv.org/abs/2610.03035

作者：Zhongjing Gu, Fengqiang Wan, Yiming Cui, Yufa Feng, Yang Yang

英文摘要：Multimodal learning often suffers from modality imbalance, where the joint optimization process is dominated by a single modality. Existing methods typically estimate modality imbalance from score disparities derived from prediction uncertainty or optimization statistics. However, due to distinct prediction uncertainty and learning dynamics across modalities, direct comparison of such scores may misinterpret intrinsic modality differences as progress gaps, leading to biased imbalance estimation. In this paper, we propose Function-Space Guided Multimodal Optimization (FGMO), which leverages a function-space progress signal to assess modality-wise optimization progress and coordinate optimization across modalities to alleviate modality imbalance. Specifically, we introduce Functional Progress Estimation (FPE) to measure each modality's update-induced function-space response and calibrate it against a loss-aligned unimodal reference, producing a comparable progress signal. Based on this signal, Functional Response Control (FRC) redistributes modality-level function-space budgets and realizes the target responses through tensor-wise learning-rate adjustment. Theoretical analysis establishes a one-step target-contraction property of FRC under bounded controller-state mismatch, and extensive experiments demonstrate the effectiveness of FGMO across multiple multimodal benchmarks.

AI 总结：WebFovea通过强化模型与浏览器间harness的四个关键阶段并设置护栏，将真实网站视觉Web智能体的隐藏集分数从31.0提升至57.0，获挑战赛第二名。

链接：https://arxiv.org/abs/2610.03036

作者：Jiangang Han

英文摘要：We present WebFovea, a vision-based web agent that placed 2nd in the WebRetriever Challenge 2026 with a final score of 57.0 out of 100. The challenge evaluates agents end to end on Protocol III of the WebRetriever benchmark ( arXiv:2607.06118 ): starting from an entry URL on a live website, the agent must operate the site's own interface and return a verifiable answer. A capable multimodal large language model (LLM) is necessary for this, but not sufficient. The model's decisions reach the browser through the harness, the code between the model and the page. At every step, four things must go right: the model's reply must be parsed into the intended action, the action must take effect on the page, the result must be reported back accurately, and the model must be shown the information it needs. On real websites, many of the failures we observed occurred at one of these four stages rather than in the model's reasoning. A coordinate-space mismatch placed every click at 3/4 of its intended coordinates; actions on native dropdowns, inside iframes, and in text boxes failed silently; and self-generated chat-template tokens contaminated 4.9% of task episodes. WebFovea hardens each stage and surrounds the loop with guardrails that keep the agent within the rules and its budget. The four-stage view does not depend on the model, although some individual fixes do. Because we used the same model in all four submissions, the rise of our official hidden-set score from 31.0 to 57.0 reflects changes to the harness, up to run-to-run variance on live sites. We describe the design, the evidence for each component (including negative results), a failure analysis, the limitations, and a roadmap that includes routing different steps to different models.

AI 总结：本研究通过数据归因方法，发现合成预训练数据中跨表信息的预测必要性促使关系模型学习关系机制，RelDiff因外键链接增益最大而表现最佳，干预实验验证了其因果作用。

链接：https://arxiv.org/abs/2610.03057

机构：Lexsi Labs

作者：Shivam Dubey, Mohamed Bouadi, Nassim Bouarour, Varun Kulkarni, Aditya Tanna, Vinay Kumar Sankarapu

英文摘要：Relational foundation models are increasingly pretrained on synthetic databases, yet downstream benchmarks reveal little about why one synthetic corpus produces a better model than another. In particular, strong performance may arise from realistic row-level statistics without the model ever learning to use relational structure. We study this as a data-attribution problem: which property of synthetic pretraining data induces relational computation? Using four Relational Transformer checkpoints trained with the same architecture, initialization, objective, and compute budget on corpora produced by four relational data generators, we trace a measurable property of the data to learned computation and downstream behavior. We hypothesize that relational mechanisms emerge when cross-table information is predictively necessary for the masked-cell pretraining objective. RelDiff exhibits by far the largest predictive gain from foreign-key-linked parents, and its corresponding model is uniquely sensitive to foreign-key interventions on unseen databases. This dependence survives a random-initialization control, grows monotonically with the fraction of corrupted links, and localizes to a serial cross-table pathway. Finally, disrupting the same mechanism during downstream inference removes RelDiff's advantage on relational tasks while leaving structure-insensitive models nearly unchanged. These results connect a property of synthetic training data to a learned mechanism and, through intervention, to downstream behavior.

AI 总结：Zephon提出一种支持在线有状态管道的基础模型数据加载器，通过拓扑无关通道和序列化排序实现弹性确定性，并高效恢复检查点，在文本和视觉-语言任务上达到有竞争力吞吐量。

链接：https://arxiv.org/abs/2610.03087

机构：DatologyAI； ETH Zürich（苏黎世联邦理工学院）； ITU Copenhagen（哥本哈根IT大学）； Stanford University（斯坦福大学）； Arcee AI； CMU（卡内基梅隆大学）

作者：Maximilian Böther, Josh Wills, Ties Robroek, Sonnet Xu, Paul Burstein, Daniel Zayas, Cody Blakeney, Siddharth Joshi, Haoli Yin, Rishabh Adiga, Haakon Mongstad, Luke Merrick, Pratyush Maini, Ari Morcos, Matthew Leavitt, Ana Klimovic, Bogdan Gaza

英文摘要：Deterministic data loading is important for foundation model development: model researchers need confidence that differences they observe across costly ablations are caused by the parameter they changed rather than non-determinism in the training data sequence. The data loader must provide elastic determinism, i.e., a deterministic sequence of global training data batches despite changes to the GPU topology across runs (e.g., due to GPU scarcity), frequent checkpoint-resume cycles, and different data processing execution backends. Achieving this is difficult because modern foundation model data pipelines tokenize, pack, and mix samples online, introducing stateful n-to-m transformations that break sample indexing. Existing data loaders largely assume indexable 1-to-1 pipelines, and the common workaround of offline materialization is expensive and, for some modalities such as video, infeasible. We present Zephon, a data loader for foundation models that supports online, stateful pipelines while providing elastic determinism and efficient resumption from checkpoints. It partitions the global stream into topology-independent lanes, serializes ordering decisions while parallelizing stateless work on interchangeable backends, and checkpoints only bounded in-flight state so recovery cost does not grow with training progress. We evaluate Zephon on text and vision-language workloads and show that it achieves competitive throughput while providing a combination of guarantees that no existing loader offers for online, stateful pipelines.

AI 总结：ULTRADISCOVERY通过2×2设计分离表征开放与证据分散需求，发现现有模型在开放表征下无法引入新实体或重写变量，且难以做出精确跨域预测，揭示溯因探索的核心困难在于将证据组合为可迁移表征。

链接：https://arxiv.org/abs/2610.03092

作者：Weihan Li, Tianshi Zheng, Yangqiu Song, Ginny Y. Wong, Simon See

英文摘要：Scientific discovery often begins when scattered clues call for a new way of describing the world. Such abductive exploration can require constructing the representation in which an explanation is stated, when the world is epistemically open, and composing evidence scattered across contexts, when it is structurally interconnected. Existing benchmarks rarely separate these two demands or control them independently. We introduce ULTRADISCOVERY, an interactive world of five domains in which an agent revises an initially successful theory and predicts the outcome of an unseen cross-domain intervention. A $2 \times 2$ design leaves the representation open or discloses it, and leaves the evidence distributed or aligns it, with the latent dynamics fixed. With the representation open, agents across eleven models often retract the axiom they were taught, and none introduces the unobserved entity or rewrites the variables that a replacement requires. Disclosure triples intervention requests and adds about one of the eighteen findings the world affords, and alignment adds less. Two vendor-harness systems carry discovery into more domains, and one of them rewrites the variables in Open episodes. No system makes the exact prediction within 200 paid actions. At larger budgets one exact prediction appears with both aids, while every Open episode remains inexact. The results locate the difficulty in the step from accumulating evidence to composing it into a representation that transfers.

AI 总结：LS-AR通过双通道架构将连续目标引导与离散令牌解码解耦，在长程检索和规划任务中显著提升性能与效率，并增强对提示注入的防御。

链接：https://arxiv.org/abs/2610.03093

机构：University College London（伦敦大学学院）

作者：Anubha Gupta, Eduardo Pignatelli

英文摘要： Standard autoregressive (AR) models process high-level task instructions, state history, and transient tokens within a single shared sequence of tokens. Consequently, they lack the architectural mechanisms needed to isolate macro-objectives from context noise. To overcome this single-channel limitation, we introduce Latent-Steered Autoregressive (LS-AR), a dual-channel architecture that decouples continuous goal steering from discrete token decoding via FiLM conditioning. We evaluate a Static Goal Encoder (P_0) for persistent macro-objective retention across long rollouts and a Dynamic State Tracker (P_t) for recurrent latent updates during generation. On long-horizon retrieval past context limits (H=1024, W=500), LS-AR (Static) achieves 100% target recall where parameter-matched baselines collapse (0%), while increasing throughput by ~35% and cutting peak VRAM by 52.8%. In Blocksworld planning under forced perturbations (k=1), LS-AR (Dynamic) sustains an 89.0% completion rate vs. 71.0% for the baseline, though zero-shot entity scaling (N -> N+1) exposes single-vector capacity limits (0%). Finally, dual-channel authority analysis shows that text goal dropout establishes latent-dominant control, offering structural defence against text prompt injection while introducing a latent vector attack surface.

AI 总结：本文实证研究深度神经网络宽度与容错性的权衡，发现结构化剪枝虽增加单次推理故障敏感性，但缩短执行时间可抵消风险，实现节能降延迟且不损可靠性，为空间AI系统设计提供指导。

链接：https://arxiv.org/abs/2610.03117

机构：Magics Technologies； KU Leuven（鲁汶大学）； Flanders Make

作者：Toon Vinck, Naïn Jonckers, Jaro De Roose, Jeffrey Prinzie, Peter Karsmakers

英文摘要：Deep Neural Networks (DNNs) inherently exhibit a degree of robustness to bit-level faults due to their distributed representation of information. As a model increases in width, this information becomes more dispersed, theoretically reducing the impact of any single bit fault. In this paper, we empirically investigate the relationship between model width and robustness to Single Event Upsets (SEUs). We conduct a comprehensive experiment in which baseline models undergo iterative structured pruning to reduce their width while preserving task performance as much as possible. At each pruning stage, we run a targeted fault-injection campaign to evaluate the model's performance under simulated bit-flip scenarios. Our results show that, although structured pruning increases per-inference sensitivity to faults by reducing redundancy, this effect is effectively counterbalanced by shorter execution time, which lowers the probability of encountering an SEU. These findings suggest that structured pruning can yield significant energy and latency savings without compromising overall reliability, providing useful guidance for designing robust AI systems for space applications.

AI 总结：本文提出一种基于任务向量方差的统计量来预测大型语言模型合并崩溃，并引入PRISM操作符通过软阈值修复破坏性合并，实验验证了其有效性。

链接：https://arxiv.org/abs/2610.03199

机构：Korea University（高丽大学）； Yonsei University Mirae Campus（延世大学未来校区）； Konkuk University（建国大学）

作者：Jungseob Lee, Seungyoon Lee, Sugyeong Eo, Hyeonseok Moon, Jaehyung Seo, Heuiseok Lim

英文摘要：Large language models fine-tuned from a shared base can be merged by averaging their task vectors, but some merges collapse far below the base model, and common merge operators give no warning before evaluation. We show that one statistic of the specialists' task vectors both predicts this collapse and calibrates its repair. The power that averaging removes equals the variance of the task vectors across specialists, our measure of interference. Under a working noise model, the disturbance that a merge injects grows with the merge coefficient and with interference, yielding a pre-merge score. In our experiments on twenty-two merge configurations from four model families, only destructive merges exceed a threshold on this score. We find that statistics of sign conflict between specialists, a common target of existing merge operators, are anti-predictive. We then predicted the outcomes of fourteen merges before evaluating them, and twelve predictions were correct, including the destructive outcome of a specialist pair pushed past the threshold by continued pretraining. To address this collapse, we introduce PRISM, an operator that averages the task vectors first and then soft-thresholds each layer at a level set by the layer's interference. Without data or tuning, PRISM keeps all five destructive merges above the threshold within evaluation noise of the base model, where plain averaging falls at least 14.4 points below it or collapses entirely. We apply PRISM only above the threshold and keep the plain average for merges below it, which include all fifteen harmless ones. Code is available at this https URL.

AI 总结：本文提出eKSVD，将核奇异值分解扩展至多数据源，通过联合非线性特征学习与神经网络显式映射，实现对非对称核的高效处理，实验验证其优于Mercer核方法。

链接：https://arxiv.org/abs/2610.03216

机构：KU Leuven（鲁汶大学）

作者：Xinjie Zeng, Qinghua Tao, Johan Suykens

英文摘要：Kernel Singular Value Decomposition (KSVD) learns a pair of singular vectors w.r.t. an asymmetric kernel matrix, which can be induced by two data sources, e.g., the queries and keys in self-attention or the rows and columns of a given matrix. In this work, we extend KSVD to multiple data sources, namely eKSVD, which conducts joint nonlinear feature learning upon asymmetric kernels. In the primal formulation, the projections associated with each data source are jointly learned to capture maximal information, while incorporating pair-wise couplings. With the Lagrangian and its Karush-Kuhn-Tucker (KKT) conditions, the optimization in the dual leads to a generalization of the shifted eigenvalue problem in Lanczos decomposition theorem of KSVD. Further, a covariance-based framework is derived together with using neural networks (NNs) for explicit feature mappings, complementary to the kernel-based interpretation and optimization. Numerical experiments verify the effectiveness of our eKSVD compared to methods based on Mercer kernels for tackling multiple data sources, and our innovation of deploying NNs demonstrates great flexibility for kernel methods.

AI 总结：本研究通过分析拼接与原生多模态架构的MLLMs，揭示两种不同的融合路径，为多模态融合提供机制性视角及架构感知诊断方法。

链接：https://arxiv.org/abs/2610.03289

机构：Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）

作者：Hebao Zhu, Dongxia Wu

英文摘要：Multimodal Large Language Models (MLLMs) achieve strong performance across vision-language tasks, yet the internal mechanisms by which visual and textual information are fused across layers remain insufficiently understood. We investigate representative MLLMs from two architectural paradigms: concatenation architectures and native multimodal architectures. We conduct three progressively connected analyses: alignment decoupling identifies which modality changes, attention routing and entropy characterize how cross-modal information is distributed, and intrinsic dimensionality examines how fusion reshapes feature spaces. Separately, we perform causal intervention experiments as a validation of the resulting interpretation. As a supplementary analysis, we use visual CKA to examine the Platonic Representation Hypothesis. Together, these analyses reveal two distinct fusion pathways: concatenation models follow a text-first, vision-later pathway, whereas native models exhibit earlier visual-textual co-adaptation and feature-space reorganization. This work provides a mechanistic perspective for understanding multimodal fusion and supports architecture-aware diagnostics of multimodal representations.

AI 总结：针对 Muon 优化器，提出有限时间训练损失保证，证明在充分宽两层 ReLU 网络上，五步调优 Newton--Schulz 正交化与动量累积结合，以高概率达到任意目标损失，且无需精确正交化。

链接：https://arxiv.org/abs/2610.03306

机构：Indian Institute of Technology Delhi（印度理工学院德里分校）； Robert Bosch GmbH（罗伯特·博世有限公司）

作者：Amartya Roy, Souvik Chakraborty

英文摘要：Existing convergence analyses of Muon either assume exact orthogonalization or analyze classical Newton--Schulz polynomials, and guarantee only stationarity, so it is unresolved what Muon's five tuned Newton--Schulz steps preserve and whether that suffices to reach a prescribed neural-network training loss. We establish a finite-time training guarantee that accounts for both momentum accumulation before orthogonalization and the tuned finite-step update. For full-batch training of a sufficiently wide two-layer ReLU network with fixed random output weights and a positive-definite limiting neural tangent kernel, we prove that Muon reaches any target empirical squared loss $\varepsilon>0$ with high probability over initialization. For every momentum parameter $\mu\in[0,1)$, a target-dependent constant learning rate proportional to $(1-\mu)\sqrt{\varepsilon}$ yields a hitting-time bound of $O((1-\mu)^{-1}\varepsilon^{-1/2})$, with other problem parameters fixed. The sufficient width is independent of both target accuracy and momentum. The analysis shows that the tuned Newton--Schulz map preserves alignment with the momentum buffer while bounding the update's spectral norm. Control of gradient variation near initialization transfers this alignment to the current gradient, ensuring descent until the target is reached without requiring exact orthogonalization. Numerical experiments support these mechanisms at widths below the sufficient theoretical threshold: gradient-update alignment remains above the analytical reference, and all 30 runs across six widths and five student initializations on a fixed teacher-student dataset reach the target loss while maintaining kernel positivity.

AI 总结：SCAD通过结构化信用分配与局部蒸馏，结合终端奖励和教师指导，提升长时程智能体的规划与执行，在文本和多模态任务上分别提升4.48和4.19个百分点。

链接：https://arxiv.org/abs/2610.03372

机构：Beijing University of Posts and Telecommunications（北京邮电大学）； Tsinghua University（清华大学）； Nanyang Technological University, Singapore（新加坡南洋理工大学）

作者：Shangyang Wu, Shuai Zhao, Ziyue Zhu, Jinyang Wu, Anh Tuan Luu, Haoran Luo

英文摘要：Training long-horizon agents to solve complex tasks requires effective supervision over extended interaction sequences. However, sparse terminal rewards obscure intermediate contributions, while on-policy distillation can lose informative teacher guidance as student-generated histories grow. To address this problem, we introduce SCAD, which organizes interactions into planning and bounded subtask execution, distills execution in local contexts, and refines planning credit through cross-rollout subtask prefix trees, with planning receiving full terminal credit and execution receiving positive terminal credit and teacher guidance. Across all evaluated benchmarks, SCAD improves macro-average accuracy over the strongest training baseline by 4.48 percentage points for text tasks and 4.19 points for multimodal tasks. SCAD effectively combines outcome-based credit assignment with teacher-guided distillation to improve planning and execution in long-horizon agents.

AI 总结：本研究提出OptiSelect框架，理论证明优化器预条件器影响数据选择增益，实验表明AdamW评分几何最优，为LLM预训练中优化器与数据选择协同设计提供指导。

链接：https://arxiv.org/abs/2610.03432

机构：EPFL（洛桑联邦理工学院）

作者：Simin Fan, Alireza Abdollahpoorrostam, Martin Jaggi

英文摘要： Online data selection has demonstrated substantial efficiency gains for LLM pretraining by training on the most valuable candidates within each batch. Since a candidate's value is realized through its effective model update, principled selection should account for the optimizer step, which reshapes the raw gradient before it updates model parameters. We formalize this optimizer-aware selection paradigm as OptiSelect and present the first systematic study of how the optimizer shapes data selection. Our theory establishes a selection gain principle in which the advantage of online selection is governed by the discriminability of the optimizer-induced utility scores. We prove that sign-based and polar-tangential preconditioners of Lion and Muon would suffer from a discriminability collapse which caps attainable gains from OptiSelect, whereas diagonal-adaptive optimizers such as AdamW and Sophia admit strictly better upper bounds. The proposed principle also yields a quantitative derivation of the optimal candidate oversampling ratio. Pretraining experiments on 124M and 720M models are consistent with our theoretical analysis and show that AdamW's diagonal-adaptive scoring geometry remains the strongest scoring geometry even with Muon as optimizer. We further demonstrate that OptiSelect retains its benefits under data rephrasing, a technique used in modern data processing pipelines. Our findings provide theoretical foundations and practical guidance for co-designing optimizers and data selection in LLM pretraining.

AI 总结：本文证明在解码时策略组合中，Metropolis-Hastings 校正方法在任意 rollout 预算下均优于重要性重采样，并给出改进下界与渐近误差分析，实验验证其有效性。

链接：https://arxiv.org/abs/2610.03480

作者：Alexey Kurennoy, Ramil Yarullin, Fergal Reid

英文摘要：Post-training a large language model (LLM) often requires exploring trade-offs between multiple rewards, but retraining for each trade-off is expensive. Decoding-time policy composition allows these trade-offs to be adjusted by combining reward-specific policies at inference time. This composition targets a weighted product of the policies' probabilities over complete responses, but standard implementations combine their next-token probabilities, generally introducing sampling bias. We analyze a known iterative correction based on independence Metropolis-Hastings (MH). Our main result shows that, for every rollout budget, MH produces an output distribution at least as close to the target as sampling-importance-resampling (SIR) with the same budget, as measured by every convex f-divergence. We also derive a lower bound on MH's improvement over the uncorrected decoder in a consensus objective measuring agreement with the supplied policies. We further characterize the correction's sampling error in two asymptotic regimes: when the reward-specific policies approach agreement, and when the log ratio between target and uncorrected-decoder probabilities fluctuates increasingly widely, as can happen for long responses. We complement our analysis with experiments in enumerable and LLM-scale settings.

AI 总结：本研究提出认证机制性编辑，通过可靠界传播在连续输入区域上可证明地移除技能并保留另一技能，并证明有限黑盒测试无法认证移除，适用于小型标准架构网络。

链接：https://arxiv.org/abs/2610.03502

机构：American International University-Bangladesh (AIUB)（美国国际大学孟加拉分校（AIUB））

作者：Md Sazid Uddin, Md. Khairul Alam Mazumder, M. F. Mridha

英文摘要：Mechanistic edits (ablations, weight edits, activation steering) are the standard tools for unlearning a harmful capability from a neural network while preserving useful ones. Current approaches validate their effects only by testing, which can never cover an entire continuous region of inputs. Prior work at the interpretability-verification boundary certifies descriptions of a model: what a circuit computes, or whether it faithfully explains the whole. We instead certify the behavioral effect of an edit: that disabling a circuit removes one skill and provably preserves another, for every input in a region; a feature non-interference guarantee in the information-flow-security sense. We demonstrate such certified edits from toy ReLU networks up to a standard softmax + LayerNorm transformer, proving removal and preservation over continuous embedding-space regions and reaching roughly 9x the input-perturbation dimension an exact solver can handle by switching to sound bound propagation. Furthermore, we prove that no finite deterministic black-box test can certify removal, exhibiting an edit that passes exhaustive testing yet provably fails on a survivor pocket that can be made arbitrarily small. Guarantees hold on small, standard-architecture networks and, like any removal claim, presuppose that the target skill admits a decidable specification, a property which real-world harms may not have.

AI 总结：针对聚变材料辐照后显微分析中人工处理无法扩展的问题，提出一种在Galaxy环境中实现的可复现自动化工作流，可从SEM图像识别裂纹并量化损伤，无需参数调整，并在稀疏数据集上验证，为后续预测与模拟提供标准化输入。

链接：https://arxiv.org/abs/2610.03505

机构：Oak Ridge National Laboratory（橡树岭国家实验室）

作者：Rinkle Juneja, Viktor Reshniak, Richard K. Archibald, John W. Duggan, Gregory R. Watson, Cory D. Hauck, Gary M. Staebler

英文摘要：Post-exposure microscopy is central to qualification of fusion materials. However, manual analysis does not scale to the volume, heterogeneity, and multiresolution character of modern fusion-materials campaigns. To address this challenge, we present a reproducible workflow, implemented in the Galaxy scientific workflow environment, for automated crack identification and quantitative damage assessment from scanning electron microscopy images. The workflow processes SEM images and experimental metadata to identify cracks, quantify damage, and retain the intermediate products and processing history needed for reproducibility. Outputs include crack masks, skeletonized crack networks, quality-control visualizations, and scalar damage descriptors. The method is designed to operate without image-specific parameter tuning across tungsten grades, microstructures, magnifications, and damage states. We demonstrate the workflow on a sparse electron-beam thermal-shock dataset containing 418 images from 114 experiments spanning five tungsten grades and three microstructural states. We define a crack-density descriptor, which provides standardized inputs for downstream machine-learning prediction and physics-based crack simulation. These predictive components are exposed in the same Galaxy environment and are intentionally treated here as extensible workflow modules. The principal contribution is therefore an end-to-end, shareable, and computationally portable workflow that links experimental characterization, automated image analysis, preliminary damage prediction, and simulation-guided data acquisition for fusion-materials research.

AI 总结：本文从熵视角研究蒸馏，证明前向KL膨胀学生熵，反向KL收缩熵，散度充当隐式熵正则化器，在自蒸馏中最佳超参数需补偿熵缩小。

链接：https://arxiv.org/abs/2610.03529

机构：Stanford University（斯坦福大学）

作者：Nicolas Zucchet, Scott W. Linderman

英文摘要： Distillation has become a core primitive of large language model training, but its properties are not yet well understood. We take an entropic perspective, studying how the entropy of the student depends on the data and the divergence that define the distillation objective. We prove that forward KL inflates the entropy of the student above that of the teacher. Since cross-entropy training is a special case, this yields an identity that we verify quantitatively in pretraining and supervised finetuning. Other divergences come with no such guarantee: reverse KL deflates entropy until the gap between student and teacher gets too large, and interpolating between the two changes entropy smoothly early in training but abruptly at convergence. The lower entropy of on-policy distillation comes from token-level reverse KL, not from on-policy sampling. The divergence therefore acts as an implicit entropy regularizer, whose role is clearest in self-distillation: as conditioning on privileged information deflates entropy, the divergence hyperparameters that work best are those that compensate for it.

AI 总结：本研究考察数学大语言模型在无外部标准时（子领域间翻译）的表征，引入盲队列工具度量改写对隐含假设的陈述，发现普遍性方向导致量化域不对称扩大，且能力不主导此现象。

链接：https://arxiv.org/abs/2610.03551

机构：Imperial College London（伦敦帝国理工学院）； Tsinghua University（清华大学）； University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

作者：Yanli Wang, Suijin Wang, Xiaopeng Yuan, Haohan Wang

英文摘要：Large language models (LLMs) have reached expert-level performance on competition mathematics largely through the volume of search placed around them: candidate solutions are sampled in quantity and retained only when an external criterion accepts them. Such a procedure improves the outcome that survives it while leaving untouched what the model represents. We examine that question where no external criterion exists: translating statements between the dialects of neighbouring subfields, where fidelity turns on the level of generality at which content is asserted. The source leaves that level implicit in its vocabulary, so a faithful translation must recover it from the relation between the theories. We introduce an instrument that codes truth, content and scope in separate blind queues, with a judge-free measure of whether a rewrite states the hypothesis implicit in its source, and establish its sensitivity with a planted-positive control. Across seven models from four families, translating towards the general framing widens the domain of quantification in 60.6% of rewrites and narrows it in none; translating towards the concrete framing narrows it in 28.3% and widens it in 0.3%. The hypothesis that would prevent it is stated in 21.6% of model rewrites and 4.2% of human statements. Capability does not govern the asymmetry: it appears in every model tested, and the most capable widens least. It replicates on the half of the benchmark held out by a pre-registered rule, and on statements written by mathematicians. Instructing a model to state every hypothesis it requires raises that rate but not its sensitivity to direction. We argue that these systems have acquired an object-level correspondence between subfield vocabularies without the constraint under which a translation between theories carries hypotheses to hypotheses.

AI 总结：提出免模拟的Double-Stitch方法，通过惩罚运动方程残差学习Wasserstein空间中的拉格朗日动力学，在多个数据集上优于或匹配现有方法，训练速度提升4-14倍。

链接：https://arxiv.org/abs/2610.03679

机构：Basis Research Institute（Basis研究院）； ETH Zurich（苏黎世联邦理工学院）； Helmholtz AI（亥姆霍兹人工智能）； MIT（麻省理工学院）； University of Toronto（多伦多大学）

作者：Fedor Sergeev, Markus Heinonen, Daniel Waxman, Tim Cooijmans, Ricardo Baptista, Dmitry Batenkov, Eli Bingham

英文摘要：The dynamics of cells, organisms, and fluids are often modeled as probability distributions evolving over time. Reconstructing and extrapolating this evolution from unpaired snapshots requires assumptions about the underlying process. Wasserstein gradient flows are a common choice, but they cannot describe conservative or periodic dynamics. Lagrangian mechanics in Wasserstein space covers both, but existing methods for learning it are simulation-based: they run a numerical solver at every training step, which makes training expensive. We propose Double-Stitch, a simulation-free method that learns these mechanics by penalizing the residual of the equation of motion along a learned population path. We derive this equation from a Clebsch variational principle that does not require gradient velocities, and show that the residual vanishes exactly when the equation holds. We test Double-Stitch on synthetic, single-cell and ocean vortex datasets and find that it matches or outperforms gradient-flow methods and simulation-based WLM on most tasks, while training $4$-$14$ times faster than WLM. We provide a JAX implementation of Double-Stitch at this https URL.