机器学习学术速递[6.25]

AI 总结：本文揭示循环语言模型中密集交叉熵损失仅控制读出变量，忽略隐藏状态尺度，导致尺度失控；提出尺度可见读出、显式范数惩罚或尺度移除循环的修复方法。

链接：https://arxiv.org/abs/2606.24898

机构：Virginia Tech（弗吉尼亚理工大学）

作者：Rituraj Sharma, Tu Vu

英文摘要：Looped language models turn hidden states into runtime state: each state is decoded for prediction and fed back into future computation. This creates a basic supervision question: which state variables does cross-entropy actually control? We show that dense per-loop cross-entropy controls the variables exposed by the readout, not every variable active in the recurrent transition. Hidden-state scale gives a concrete failure mode. Scale-invariant readouts such as RMSNorm and LayerNorm hide radial scale from the immediate cross-entropy loss, while pre-norm residual recurrence continues to carry and update that same scale. Thus per-loop loss can make early exits usable without controlling recurrent scale. In 44M and 129M looped transformers without inter-loop normalization, per-loop cross-entropy through RMSNorm readouts still drives final hidden-state norms into the thousands or tens of thousands. Scale-visible readouts and explicit norm penalties keep norms in the tens, and scale-removing recurrence is the complementary architectural fix. The resulting design rule is simple: dense supervision trains exits; recurrent scale control requires either making scale visible to a loss or removing it from the loop. Consistent with this rule, scale-controlled variants achieve lower perplexity at matched inference-depth operating points in our variable-depth benchmarks.

AI 总结：通过激活扰动实验，发现LLMs的残差流激活对沿特征方向（对比对构造的“纯”方向）的扰动更鲁棒，且扰动效应满足p>2的Lp范数，表明存在特征特定的误差校正机制。

链接：https://arxiv.org/abs/2606.24964

作者：Francisco Ferreira da Silva, Stefan Heimersheim

英文摘要：Understanding the features of large language models (LLMs) is a central goal of interpretability. LLMs are commonly assumed to use superposition to represent more features than they have dimensions. They may not only represent features in superposition but also perform computation in superposition. Theory predicts that computing in superposition requires error correction that privileges feature directions over generic ones, but this prediction has not been tested empirically. We propose an empirical test of error correction in LLMs based on activation perturbations. Perturbing residual-stream activations, we find that they are robust to small perturbations--forming activation plateaus consistent with error correction--but less robust along candidate feature directions ("pure" directions, constructed from contrastive prompt pairs) than along mixtures of two such directions, indicating that the pure directions are privileged. We quantify this privilegedness by modeling the perturbation effect as a function of the $L^p$-norm of its decomposition into feature components. For $p=2$ the response is a quadratic form with at most as many nonzero eigenvalues as the residual-stream dimension, which cannot privilege the many feature directions superposition requires. $p>2$ lifts this constraint and is consistent with feature-specific error correction. We find $p>2$ for contrastive, MELBO, and SAE-decoder directions, and $p\approx2$ for random and PCA directions (controls). These results replicate across Gemma-2-9B, Qwen3-1.7B, Llama-3.1-8B, Mistral-7B-v0.3, Aya-Expanse-8B, and Yi-1.5-9B. We further validate our method on a toy model of error correction with known ground-truth features, recovering $p>2$ for true feature directions, degrading toward $2$ as we rotate away from them.

AI 总结：提出频域储层计算（FRESCO），通过全频域操作实现O(N)复杂度，解决回声状态网络（ESN）的二次瓶颈，在记忆基准、序列分类和多变量长时预测上达到最先进性能。

链接：https://arxiv.org/abs/2606.24969

作者：Klaus Schertler, Xiomara Runge, Andrea Ceni, David Kappel, Claudio Gallicchio

英文摘要： While the quadratic sequence-length bottleneck of transformers has fueled a resurgence in recurrent models, effectively capturing complex dynamics requires architectures that balance efficient training with highly expressive latent states. Echo State Networks (ESNs) offer a compelling approach by utilizing fixed recurrent weights to circumvent backpropagation through time, enabling a closed-form training solution. However, achieving the expressivity needed for complex tasks demands large reservoirs, exposing an $\mathcal{O}(N^2)$ state-update bottleneck that prevents ESNs from matching the scale of contemporary recurrent models. To address this limitation, we introduce Frequency Domain Reservoir Computing (FRESCO), an ESN architecture operating entirely in the frequency domain while avoiding domain-shift overheads to achieve $\mathcal{O}(N)$ complexity for dense, non-linear recurrent updates. By employing a novel dimensional zero-padding input embedding, a packed \FDh readout, and a natively applied frequency-domain non-linearity, FRESCO drastically reduces computational costs and energy consumption of training and inference. Furthermore, FRESCO matches the state-of-the-art predictive performance on memory benchmarks, sequential classification, and multivariate long-horizon forecasting, offering a scalable path forward for dense recurrent architectures.

AI 总结：本文研究累积正交变换（如Householder反射或SO(2)旋转）在注意力机制中产生长度外推能力的原理，证明其通过有限步后去相干性抑制远距离token，并指出其最终会退化，而旋转值可扩展有效范围。

链接：https://arxiv.org/abs/2606.24975

机构：A Carrot, Inc.（A Carrot公司）

作者：Mahesh Godavarti

英文摘要：PaTH Attention showed that replacing RoPE's position-indexed rotations with accumulated data-dependent Householder reflections yields strong length extrapolation, though performance degrades at extreme context lengths. We ask whether this depends on Householder-specific structure or reflects a general property of accumulated transformations along source-to-query paths. We study a simpler variant keeping RoPE's block-diagonal SO(2) rotations but replacing position-indexed angles with accumulated token-dependent ones. It shows the same pattern: improved extrapolation then degradation at long contexts. We prove the result extends to accumulated orthogonal transformations satisfying certain regularity conditions: their products become incoherent after finitely many steps, suppressing attention to distant tokens. Accumulated rotations of queries and keys create a finite mixing window independent of context length; per-token suppression learned in training transfers unchanged to any evaluation length, and high-dimensional concentration produces a score gap suppressing far tokens while near-route transport preserves the target signal. Conversely, a lower bound shows accumulated rotations must eventually degrade: as the far set grows, no rotations preserve the near signal without explicit far-mass control. For SO(2) rotations, rotating values too makes residual far contributions combine incoherently, extending the range. Controlled experiments support these predictions: random accumulated rotations substantially improve extrapolation over RoPE, learned token-dependent rotations maintain near-training-length perplexity far beyond the training context, and rotating values helps over queries and keys alone. Rotation-only models still degrade at extreme lengths, while ALiBi stays length-stable, consistent with the need for far-mass control.

AI 总结：研究小型语言模型在闭环中执行图算法的能力，发现结构算法可适应可靠，但加权算法对误差累积敏感，强预测不保证可靠执行。

链接：https://arxiv.org/abs/2606.24980

机构：NASK National Research Institute（NASK国家研究所）

作者：Michal Podstawski

英文摘要：Small language models offer an efficient alternative to large-scale systems, but their ability to execute structured algorithms over multiple dependent decisions remains poorly understood. We study graph algorithm execution as a closed-loop prediction problem in which a model repeatedly selects the next action from the current graph and algorithmic state. Our evaluation framework covers several classical graph procedures, multiple synthetic graph families, and disjoint training, validation, and test partitions. It assesses both local decision quality and global execution behaviour using step accuracy, exact rollout accuracy, constraint validity, partial solution quality, prefix survival, and intervention-based diagnostics. The results show that adaptation can produce reliable policies for structural procedures such as traversal and coloring, while weighted algorithms remain substantially more sensitive to error accumulation. More broadly, the findings demonstrate that strong next-step prediction does not necessarily translate into reliable autonomous execution and motivate evaluating algorithmic language models through complete closed-loop rollouts rather than isolated decisions.

AI 总结：提出内存高效等变变压器（MEET），通过线性内存缩放和几何特征改进，实现全原子肽的序列与结构协同设计，在生成质量、结合亲和力和多样性上超越现有方法。

链接：https://arxiv.org/abs/2606.25006

机构：Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）； Institute for AI Industry Research, Tsinghua University（清华大学人工智能产业研究院）； Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）； Department of Chemistry, Tsinghua University（清华大学化学系）

作者：Rui Jiao, Xiangzhe Kong, Yinjun Jia, Yijia Zhang, Ziyi Yang, Yang Liu, Jianzhu Ma

英文摘要：Target-specific peptide design requires sequence and structure co-design under full atom geometric constraints. Latent generative frameworks offer an effective route for this problem by compressing fine grained atomic structures into block level latent representations and performing conditional generation in a compact latent space. However, the scalability of such systems depends heavily on the geometric backbone used throughout their encoding, decoding, and denoising components. We introduce MEET (Memory Efficient Equivariant Transformer), an E(3) equivariant backbone for scalable atomistic peptide modeling. MEET maintains coupled invariant scalar and equivariant vector feature streams, while reformulating geometric computation around memory efficient attention. It initializes vector features through global coordinate aggregation, incorporates pairwise distances through augmented query and key dot products, and injects covalent bond information through sparse bond adaptation. Integrated into a VAE and latent diffusion pipeline for full atom peptide generation, \model{} achieves linear memory scaling with atom count and improves generation quality over existing peptide design methods. Experiments on large scale AFDB derived datasets further show that the proposed backbone supports systematic model and data scaling, leading to better binding affinity, physical validity, and sample diversity.

AI 总结：研究发现，transformer模型的下游能力（如上下文学习）在训练过程中随机涌现，较大模型平均更早获得，且涌现对应于任务相关注意力模式的突然学习。

链接：https://arxiv.org/abs/2606.25010

机构：New York University（纽约大学）

作者：Vatsal Baherwani, Zixi Chen, Shikai Qiu, Andrew Gordon Wilson, Pavel Izmailov

英文摘要：Neural scaling laws for transformer language models predict smooth improvements in pretraining loss with increasing parameters, but downstream capabilities such as in-context learning are known to emerge abruptly past a certain model scale. In this paper, we show that emergent capabilities arise stochastically throughout training, with larger models acquiring them earlier on average. We demonstrate that the emergence of capabilities such as pattern completion and indirect object identification corresponds to the abrupt learning of task-relevant attention patterns. To isolate this phenomenon, we train transformer models on synthetic linear map and cellular automata datasets, and we show that the difficulty of learning attention patterns depends on context length and pattern sparsity. Moreover, scaling the number of attention heads improves learning efficiency on our synthetic tasks, while increasing the head dimension yields diminishing returns past a minimum capacity. We additionally investigate architectures with alternative attention mechanisms, showing that MLP-Mixer outperforms a transformer on linear map tasks with complex attention patterns. Our findings provide a mechanistic insight into emergence, showing that downstream capabilities arise abruptly due to the intrinsic difficulty of learning sparse attention patterns in transformer models.

AI 总结：通过因果测试发现，前沿MoE模型Command A+中仅阿拉伯语专家族表现出稳健的模块化，其他专家族的模块化依赖测量方式，表明基于消融的模块化结论需谨慎。

链接：https://arxiv.org/abs/2606.25092

机构：Transformer Lab

作者：Tony Salomone, Deep Gandhi, Ali Asaria

英文摘要：Sparse Mixture-of-Experts (MoE) models route each token to a few of many experts, inviting the hypothesis that experts form functional modules tied to capabilities or languages. We test this causally on Command A+, a frontier open-weights MoE (218B total / 25B active; 128 experts, 8 active, +1 shared). We build a routing-mass atlas, pre-register six family-to-axis hypotheses before any intervention, and ablate each family at inference time against a size-matched random-expert null, measuring whether it selectively breaks its own axis (worst off-target effect at most one third of on-target). Crucially, we test the same families under four metrics and a held-out, independent-corpus run with bootstrap confidence intervals. Our finding is cautionary: robust functional modularity is rare and measurement-dependent. Of six pre-registered families, only one, the Arabic-language family, is a clean selective module that survives an independent corpus and a conservative statistical bar (1/6; a more permissive pre-registered point rule admits 3/6, but that count is threshold-sensitive). Every other family has a real causal effect yet fails selectivity, and its apparent modularity flips with the measurement: with the corpus, the metric, and the statistical bar. A positive control on Qwen3-30B-A3B recovers its published disjoint structure, confirming the method detects modularity when present. The verdict reproduces on the un-quantized BF16 model, ruling out a 4-bit quantization artifact. We conclude that ablation-based modularity verdicts are not safe unless the corpus, metric, and statistical bar are controlled. We release the atlas and ablation data.

AI 总结：提出ATMA混合卷积-注意力架构，通过极坐标注意力三通道分解和门控-增量递归压缩记忆，解决长上下文语言建模中注意力稀释和性能崩溃问题，实现训练长度32倍外推下90%以上检索准确率和单调递减困惑度。

链接：https://arxiv.org/abs/2606.25156

机构：Kreasof AI

作者：Habibullah Akbar

英文摘要：Modern large language models based on softmax scaled-dot-product attention are constrained by their training sequence length: as the key-value sequence grows, softmax probability mass can dilute across a wider distribution, inducing activation shift and long-context performance collapse. Moreover, long-context language modeling faces a structural tension: a sliding-window attention core maintains a bounded local representation and low perplexity but is blind to long-range dependencies, while full-context attention preserves global recall but suffers from out-of-distribution perplexity explosion. To resolve these limitations, we introduce ATMA, a hybrid convolutional-attention architecture that integrates a novel three-channel attention mechanism. ATMA factorizes the attention mixing step into: (1) a count-blind, unit-vector direction channel, (2) a bounded magnitude channel driven by the participation ratio of effective matches over an extreme-value-corrected null sink, and (3) a long-term recurrent compression memory optimized via a gated-delta fast-weights rule. Neither the Polar Attention core nor the recurrent memory is sufficient alone; their combination enables monotonic perplexity reduction and high-fidelity long-range retrieval simultaneously. We evaluate ATMA using a 100-run factorial ablation sweep, demonstrating that the combined Polar + memory model maintains induction needle-in-a-haystack retrieval accuracy above 90% out to 64K tokens (32 times the training length of 2K) while its document perplexity improves monotonically, outperforming softmax-based memory baselines which collapse at extreme context lengths. Code: this https URL

AI 总结：提出未来分解网络（FDN），通过分类实现可解释预测，揭示潜在活动模式，并以更低的存储和运行成本达到与最先进方法相当的预测精度。

链接：https://arxiv.org/abs/2606.25201

作者：Nicholas Majeske, Ariful Azad

英文摘要：Spatiotemporal systems comprise a collection of spatially distributed yet interdependent entities each generating unique dynamic signals. Highly sophisticated methods have been proposed in recent years delivering state-of-the-art (SOTA) forecasts but few have focused on interpretability. To address this, we propose the Future Decomposition Network (FDN), a novel forecast model capable of (a) providing interpretable predictions through classification (b) revealing latent activity patterns in the target time-series and (c) delivering forecasts competitive with SOTA methods at a fraction of their memory and runtime cost. We conduct comprehensive analyses on FDN for multiple datasets from hydrologic, traffic, and energy systems, demonstrating its improved accuracy and interpretability.

AI 总结：本文提出将上下文学习扩展到终身设置是AI代理持续学习的实用方案，并论证需要参数化注意力机制来在固定硬件预算下理解终身上下文。

链接：https://arxiv.org/abs/2606.25342

机构：UC San Diego（加州大学圣地亚哥分校）

作者：Luke McDermott, Robert W. Heath jr., Rahul Parhi

英文摘要：Lifelong continual learning remains an obstacle on the path to human-like intelligence. Modern transformers show sparks of intelligence with in-context learning. The quadratic nature of attention, however, prohibits transformers from performing this process on arbitrarily long sequences. In this work, we argue that extending in-context learning to lifelong settings is a practical solution for continual learning in AI agents. In particular, we argue that \emph{parametric forms of attention} are needed to understand a lifetime of context with transformers on a fixed hardware budget. These attention mechanisms learn the relationship between keys and their associated values at test-time with parametric regression. Our generalization of parametric approaches (linear attention, state-space models, fast weight programmers, and test-time training layers) contrasts with nonparametric counterparts like softmax attention. They replace the ever-growing key-value cache with an online-trainable neural network, maintaining a constant memory footprint. We highlight how parametric attention currently fall short of lifelong learning due to limited memory capacity or costly online updates. To address these issues, we pose a set of open questions with novel insights to guide the field toward long-horizon agents.

AI 总结：针对脑电解码中信号低信噪比和现有黎曼方法依赖特定度量的局限，提出基于Bures-Wasserstein度量的黎曼自注意力网络及其可推广版本GBWAtt，在三个数据集上验证了鲁棒性和有效性。

链接：https://arxiv.org/abs/2606.25456

作者：Shaocheng Jin, Tao Zhou, Rui Wang, Ziheng Chen, Xiaoqing Luo, Xiaojun Wu, Josef Kittler

英文摘要：Brain-Computer Interface (BCI) based on electroencephalography (EEG) enables direct interaction between the brain and external environments and has significant applications in assistive technologies, medical rehabilitation, and entertainment. Recently, EEG decoding methods based on Symmetric Positive Definite (SPD) learning have demonstrated superior performance. However, these methods typically employ basic network architectures and do not explicitly capture local relationships between EEG signals. This limitation is problematic for EEG signals due to their inherently low Signal-to-Noise Ratio (SNR). Moreover, most existing Riemannian manifold-based methods are restricted to specific metrics. The most widely used is the Affine-Invariant Metric (AIM). However, it has a quadratic dependency on the SPD matrices and cannot handle ill-conditioned SPD matrices, which hinders the effectiveness of networks. In contrast, the Bures-Wasserstein Metric (BWM) exhibits linear dependence on SPD matrices and demonstrates superior performance for ill conditioning. To overcome these challenges, we propose a Riemannian self-attention network based on the BWM. Additionally, the recently introduced power-deformed generalized Bures-Wasserstein metric reveals a nonlinear relationship between SPD matrices and matrix power deformation. This metric provides a more nuanced representation of the geometric structure of the SPD manifold. Consequently, we extend our model to a learnable version. For simplicity, we refer to it as GBWAtt. Experimental results on three EEG benchmarking datasets validate the robustness and effectiveness of our proposed method. The code is available at this https URL.

AI 总结：提出序数交叉熵（OCE）框架，通过序数代价矩阵扩展标准交叉熵，以处理医疗应用中标签的序数结构和非对称误分类代价，实现更平滑的优化和更好的序数一致性。

链接：https://arxiv.org/abs/2606.25769

机构：Intuit

作者：Tal Dvora, Rotem Haba, Gonen Singer

英文摘要：In many prediction problems in medical applications, target labels exhibit an inherent ordinal structure, where class ordering reflects clinically meaningful severity levels. The cost associated with misclassification is often non-uniform and asymmetric, as errors between distant ordinal categories may have substantially more severe consequences than errors between adjacent ones, and overestimating disease severity may have different clinical implications than underestimating it. Traditional loss functions such as multi-class cross-entropy treat all misclassifications equally and fail to incorporate this ordering information. Recent advances in ordinal regression aim to address this limitation by integrating rank-based structures into deep learning models. In this work, we introduce the \textbf{Ordinal Cross-Entropy (OCE)} framework, a general and architecture-independent approach for learning from ordinal data. The proposed method extends the standard cross-entropy formulation to account for misclassification severity through an ordinal cost matrix while preserving the probabilistic interpretation and optimization benefits of the conventional loss. We provide a theoretical analysis of the OCE gradient behavior and show that it yields smoother optimization dynamics and improved ordinal consistency. Experiments on benchmark datasets show that our method achieves lower prediction error costs and better calibration compared to existing state-of-the-art ordinal approaches, establishing OCE as a simple yet effective solution for ordinal regression in deep neural networks.

AI 总结：提出幅度-方向（MD）解耦方法，将权重分解为固定范数的方向和可学习的幅度增益，以独立学习率更新，消除权重衰减和预热需求，在Adam和Muon优化器上均提升性能。

链接：https://arxiv.org/abs/2606.25971

机构：Machine Learning and Optimization Lab, EPFL（EPFL机器学习与优化实验室）

作者：Alexander Hägele, Alejandro Hernández-Cano, Atli Kosson, Martin Jaggi

英文摘要： Modern neural network training relies on optimizers such as Adam and Muon which act on each weight matrix as a single object. Yet every weight matrix carries two distinct quantities -- a \emph{magnitude} and a \emph{direction} -- and all optimizers stepping in the matrix as a whole couple their dynamics: the directional change from an update depends on the current magnitude, while the magnitude drifts as a byproduct of learning the direction, so neither is governed directly by the learning rate. Typical training therefore leans on surrounding recipes such as weight decay and warmup to keep learning stable at scale, though these regulate the coupling only indirectly; other recent methods instead constrain the weight to a fixed-norm sphere, but add no learnable magnitude, leaving scale control to normalization layers alone. We propose \emph{Magnitude--Direction (MD) Decoupling}, an optimizer modification that factorizes each weight into a fixed-norm direction on a hypersphere and learnable per-row and per-column magnitude gains, updated at separate learning rates, all while the model still sees a single fused weight tensor. The method is agnostic to the base optimizer and removes the need for weight decay and warmup. Across both Adam and Muon, MD Decoupling improves on well-tuned baselines, transfers the optimal LR across model width without retuning, and continues to help at scale on large Mixture-of-Experts (MoE) models. Treating magnitude and direction as separately controlled quantities thus yields more predictable training dynamics and a simple, broadly applicable improvement to modern optimizers.

AI 总结：提出Tensorion优化器，将Muon的约束优化从矩阵扩展到高阶张量，通过线性最小化预言机在张量范数球上实现，实验表明在张量视觉任务上比Adam和现有张量感知方法收敛更稳定。

链接：https://arxiv.org/abs/2606.25975

机构：MTML-LAB（MTML实验室）

作者：Vladimir Bogachev, Vladimir Aletov, Alexander Molozhavenko, Sergei Kudriashov, Maxim Rakhuba

英文摘要：Common first-order optimizers, such as Adam, implicitly treat each parameter block as an unstructured vector, which disregards the multilinear weight structure present in many modern machine learning models. Recent work has shown that exploiting matrix structure can improve optimization dynamics. A notable example is Muon, which performs steepest descent under the spectral norm constraint. We take the next step and introduce Tensorion, a tensor-aware optimizer that extends Muon's constrained optimization perspective from matrices to higher-order tensors. Tensorion is built around a linear minimization oracle (LMO) over a tensor norm ball. The norm is carefully chosen to balance two objectives: tightly bounding the tensor spectral norm, while still keeping the LMO tractable. This LMO becomes computable because it reduces to operations on adaptively selected unfolding matrices. Notably, when restricted to order-2 tensors (i.e., matrices), Tensorion recovers Muon exactly. Experiments on tensor-based computer vision problems suggest that Tensorion can offer improved convergence behavior and more stable gradient updates compared with Adam-based and existing tensor-aware baselines in the evaluated settings.

AI 总结：本文发现在线自蒸馏虽提升pass@1准确率，但会降低输出多样性并导致pass@k曲线平坦，通过理论分析揭示了其放大概率差距的机制，并在路径规划与科学问答任务中验证了该问题。

链接：https://arxiv.org/abs/2606.26091

作者：Andrei Liviu Nicolicioiu, Mohammad Pezeshki, Aaron Courville

英文摘要：On-policy self-distillation achieves strong pass@1 accuracy by using a single model as both teacher and student, with the teacher conditioned on a correct demonstration to provide dense token-level feedback. We show that this could come at a hidden cost: rollout diversity decreases and pass@k curves flatten (i.e., generating more rollouts fails to improve accuracy). We trace this to compounding biases in the design of self-distillation with sampled demonstrations. The teacher scores each student rollout while conditioned on a sampled correct rollout, channeling its feedback through the model's own biases. We theoretically analyze the optimal self-distillation policy and show that it tilts the base distribution by a pointwise conditional mutual information score between the student's rollout and the correct rollout used as context. Unlike the ideal optimal on-policy reinforcement learning (RL), which preserves probability ratios among equally correct rollouts, self-distillation can amplify existing probability gaps, concentrating mass on already-dominant modes. On a controlled graph path-finding task and science question-answering benchmarks, self-distilled models match or exceed RL on average performance but exhibit substantially lower functional and semantic diversity, failing on out-of-distribution settings that require diverse strategies.

AI 总结：研究全息简化表示（HRR）在知识图谱零样本组合查询中的表现，发现即使单跳检索准确，组合仍失败，瓶颈在于叠加记忆的检索容量和干扰效应。

链接：https://arxiv.org/abs/2606.24948

作者：Randhir Kumar

英文摘要：Knowledge graph embedding (KGE) models predict single-hop links well but have no mechanism for zero-shot compositional queries: multi-hop questions whose relation chains never appeared during training. Holographic Reduced Representations (HRR), which bind and unbind symbols via circular convolution, are a theoretically attractive candidate, since binding is approximately invertible and associative. We test whether this promise holds. We study two holographic memory variants, real-valued HRR and phase-only Fourier HRR (FHRR), each with a modern Hopfield cleanup, on FB15k-237 over five seeds. Four findings follow. First, both are competitive single-hop retrievers (filtered MRR 0.358 +/- 0.002 for HRR, 0.350 +/- 0.021 for FHRR). Second, neither composes zero-shot: accuracy stays at chance across all cleanup temperatures. Third, the main contribution, we localise the failure mechanistically. A hop-1 probe shows the memory recovers the correct intermediate entity with high fidelity (MRR 0.896 +/- 0.002 for HRR), yet composition still fails even with a verified-correct intermediate. A second probe shows why: posing the ground-truth second-hop fact as a standalone atomic query, bypassing composition entirely, already recovers it at only 0.26 to 0.48x average atomic accuracy, uniformly across relation fan-out. The bottleneck is not the bind-unbind algebra or the cleanup; it is that facts compositional chains pass through are intrinsically harder for the superposed memory to retrieve, a capacity and interference effect present already at a single hop. Fourth, we prove (Lemma 4.1) that FHRR's softmax cleanup is not phase-equivariant, compounding the primary failure on the minority of chains where hop-1 itself errs. Fixing zero-shot composition requires improving retrieval capacity under superposition, not just redesigning the cleanup.

AI 总结：针对古希腊字母在数百年书写变异中的表示学习，提出相似性加权监督对比损失和空缺驱动增强方案，实现鲁棒且可解释的字符嵌入。

链接：https://arxiv.org/abs/2606.24984

机构：Athens University of Economics and Business（雅典经济与商业大学）； Archimedes, Athena Research Center（阿基米德，雅典娜研究中心）； Department of Computer and Systems Sciences, Stockholm University（斯德哥尔摩大学计算机与系统科学系）； Università degli Studi di Torino（都灵大学）； University of Basel（巴塞尔大学）； Democritus University of Thrace（德谟克利特大学）； Computer Vision Center (CVC) - Barcelona（巴塞罗那计算机视觉中心）； Julius-Maximilians-Universität Würzburg（维尔茨堡大学）

作者：John Pavlopoulos, Spyros Barbakos, Lavinia Ferretti, Dionysis Voulgarakis, Asimina Paparrigopoulou, Maria Konstantinidou, Giuseppe De Gregorio, Isabelle Marthot-Santaniello, Paraskevi Platanou, Holger Essler

英文摘要：Learning representations that remain robust across centuries of variation in handwriting is a key challenge in diachronic representation learning. Taking one of the longest continuously used writing systems, ancient Greek, as a case study, we introduce three datasets for diachronic representation learning: Hell-Char, a curated training set spanning the 3rd-1st centuries BCE, and two evaluation sets, PaLit-Char (2nd-5th c. CE) and Med-Char (9th-14th c. CE). To address the challenges of symbolic variation, scarce data, and systematic degradation, we propose: a similarity-weighted supervised contrastive loss that biases embeddings using dynamically estimated inter-class similarities, and a lacuna-driven augmentation scheme that simulates realistic manuscript corruptions. Trained with these strategies, both a lightweight CNN and a pretrained ResNet achieve strong recognition performance and produce embeddings that more coherently separate character classes than PCA or generic pretrained models. These embeddings enable clustering, identification of stylistic subgroups, and construction of prototype images that visualize diachronic evolution and transitional letterforms. Our results demonstrate that respecting intrinsic inter-letter relationships and augmenting with domain-informed corruptions yield robust, interpretable representations, offering a transferable paradigm for representation learning under scarce, temporally evolving, and noisy conditions. Code and data available at: this https URL.

AI 总结：通过稀疏自编码器、自然语言概念和视觉特征分解地理隐式神经表示的位置嵌入，揭示其编码的可解释地理结构。

链接：https://arxiv.org/abs/2606.24997

机构：University of Colorado Boulder（科罗拉多大学博尔德分校）； Technical University of Munich（慕尼黑工业大学）； Munich Center for Machine Learning（慕尼黑机器学习中心）

作者：Livia Betti, Sebastian Ricke, Ivica Obadic, Adam J. Stewart, Esther Rolf

英文摘要：Geographic implicit neural representations (INRs) learn to map any coordinate on Earth to a location embedding, implicitly encoding geospatial data into the weights of a neural network. Location embeddings are widely used off the shelf as general-purpose geospatial representations, yet users lack principled tools to audit what geographic or semantic information these embeddings capture. In this work, we analyze the information content of geographic INRs through their location embeddings. We decompose these embeddings into human-interpretable features$\unicode{x2014}$namely, (i) sparse latent concepts, (ii) natural language concepts, and (iii) visual features. The latent concept embeddings are learned using sparse autoencoders. To recover natural language concepts, we apply sparse linear concept embeddings (SpLiCE) over a predefined geospatial dictionary. Finally, visual features are extracted using saliency maps derived from CLIP Surgery. We show that location embeddings can be decomposed into human-interpretable representations while retaining high reconstruction capability, revealing interpretable geographic structures such as forests, deserts, and urban features. Across methods, sparse decompositions expose systematic differences in encoded information, ranging from urban structures to broader biome and climate signals, and pretraining-space saliency maps further highlight complementary features such as roads and landmarks. We hope this work provides a first step toward interpretable geospatial representations.

AI 总结：提出PRIOR框架，通过log2缩放级别和逐级预测器替代掩码排序，在对比学习和图像重建中实现有序表示，提升全预算性能并支持离散/量化设置。

链接：https://arxiv.org/abs/2606.25232

机构：Neuro-Cognitive Modeling Group, University of Tübingen（神经认知建模组，图宾根大学）

作者：Erik Ayari, Manuel Traub, Martin V. Butz

英文摘要：Ordered bottlenecks aim to provide utility at flexible budgets by assigning coarse information to early tokens and task-relevant detail to later ones. Prior work, including tail dropping (TD), typically enforces ordering by means of a masking-based ordering pressure (MBOP): Late tokens are masked more frequently than early tokens and are therefore encouraged to store less essential fine details. We introduce predictive residual inference for ordered representations (PRIOR), a framework designed to address inherent weaknesses of MBOP. MBOP is prone to weak late-token utility because it lacks an explicit refinement objective and uses gradient exposure as a proxy for importance. Furthermore, representations may become particularly brittle in optimization-sensitive settings, such as when using discrete or quantized token representations. PRIOR replaces activation-rate control with log2-scaled levels and level-wise predictors. These predictors separate already explained from unexplained information, focusing each level on residual error. We compare PRIOR against MBOP-TD and independent tail-biased dropout (MBOP-ITD) in contrastive learning and image reconstruction tasks. Unlike the baselines, PRIOR learns well-ordered representations across experiments: low budgets provide coarse descriptors, while high budgets add refinements. Simultaneously, full-budget performance with PRIOR is higher in all but one experimental setting, where performance remains comparable. MBOP baselines are severely limited in discrete and quantized settings, while PRIOR approaches the performance of continuous counterparts. Taken together, these findings establish PRIOR as an effective framework for ordered representation learning.

AI 总结：提出监督强化学习框架，先通过监督学习预训练策略，再经离线与在线微调，实现分布式能源高效协调，显著提升成本效益。

链接：https://arxiv.org/abs/2606.24947

机构：National Natural Science Foundation of China（国家自然科学基金）； Research Grants Council of the Hong Kong SAR（香港研究资助局）； Advanced Research + Invention Agency (ARIA)（高级研究与发明机构）； Engineering and Physical Sciences Research Council (EPSRC)（工程与物理科学研究理事会）

作者：Haoyuan Deng, Yihong Zhou, Thomas Morstyn, Yi Wang

英文摘要：The increasing integration of distributed energy resources (DERs) is crucial for power system decarbonization, yet unlocking DERs' flexibility is challenged by their inherent uncertainties and modelling complexity. As traditional optimization methods struggle with such uncertainty and complexity of DERs, reinforcement learning (RL) has emerged as a promising alternative for DER management. However, standard RL methods suffer from sample inefficiency and sub-optimality when trained from scratch. Inspired by the training paradigms in large language models, this paper proposes a Supervised Reinforcement Learning (SRL) framework for learning DER coordination policies. This framework first pre-trains a policy on demonstration data in a supervised-learning fashion, which is then further fine-tuned using RL. Furthermore, we propose a two-step fine-tuning process: offline fine-tuning for enhancing policy performance and online fine-tuning for adapting it to the real-world dynamics. Experiments demonstrate that RL implementations based on the proposed framework significantly outperform all benchmarks, achieving high cost efficiency even under low-quality demonstration data.

AI 总结：提出LDM-v0，一个在大规模异构强化学习环境上离线预训练的Transformer策略，通过监督下一动作预测实现多任务学习，在约1000个环境中达到与独立训练策略相当的性能。

链接：https://arxiv.org/abs/2606.24962

作者：Thibaut Kulak

英文摘要：Recent progress in large-scale sequence modeling has shown that a single model can learn useful representations across highly diverse data distributions. Inspired by these advances, we investigate whether a unified transformer policy can be trained across large collections of heterogeneous reinforcement learning environments. We introduce LDM-v0, a Large Decision Model trained offline on trajectories collected from thousands of environments spanning multiple domains and modalities. LDM-v0 is a multi-task, multi-modal transformer policy conditioned on histories of observations, actions, rewards, and termination signals, and trained through supervised next-action prediction over offline trajectories. We describe the environment infrastructure, automated data generation pipeline, model architecture, and training methodology used to build LDM-v0, and evaluate its performance across diverse environments. We show that a single pretrained model matches the performance of independently trained task-specific reference policies on approximately 1,000 environments including robotics, autonomous driving, inventory management, cybersecurity, trading, and video games. These results demonstrate the feasibility of large-scale offline pretraining across heterogeneous reinforcement learning environments using a single transformer policy.

AI 总结：提出两种将预测不确定性融入强化学习的方法，使化学语言模型更稳健地探索化学空间，在保持分子得分的同时将真实命中率从0.5提升至0.75。

链接：https://arxiv.org/abs/2606.24990

作者：Borja Medina, Jon Paul Janet

英文摘要：Reinforcement Learning (RL) has become a powerful paradigm for de novo molecular design, enabling Chemical Language Models (CLMs) to navigate and explore the chemical space while optimizing specific desired properties. However, the existing RL frameworks treat all scoring functions as deterministic oracles, neglecting the inherent uncertainty attached to the predictions of the different molecular properties. This can lead to the exploration of highly-uncertain regions of the chemical space, focusing on the generation of highly scored molecules which are poorly supported by the training data. This can destabilize the optimization process, yielding predictions that are far from their true values. We propose and compare two complementary ways of incorporating predictive uncertainty into RL. In the first one, uncertainty is treated as an additional optimization objective and incorporated along with the rest of the scoring functions, allowing the policy to trade off exploitation against reliability. Secondly, uncertainty is used to modulate policy updates, reducing the influence of molecules whose properties lie far outside the scoring function confidence domain. Both approaches were evaluated across three different settings: (i) a controlled model system, in which the prediction error is modeled as a Gaussian distribution, with a variance proportional to the distance to the training data; and two real-world tasks, making use of (ii) ChemProp models and (iii) a Conformal Prediction wrapper applied to a Random forest classifier. We show that uncertainty-aware RL enables CLMs to explore chemical space more robustly by favoring lower-uncertainty regions. This leads to more reliable hit discovery without compromising molecular score, increasing the true hit rate by 0.25 (from 0.5 to 0.75), and nearly doubling the total number of true hits.

AI 总结：提出ExTra框架，通过新颖性奖励和熵引导前缀再生增强GRPO，在数学推理基准上提升pass@1约5%、pass@16约7%。

链接：https://arxiv.org/abs/2606.24994

机构：National University of Singapore（新加坡国立大学）； SAP

作者：Wenyang Hu, Junxiang Jia, Zhen Shu, Daniel Dahlmeier, See-Kiong Ng, Bryan Kian Hsiang Low

英文摘要： Reinforcement Learning with Verifiable Rewards (RLVR) for language-model reasoning can fail at both extremes of task difficulty: easy prompts often produce all-correct, low-diversity rollout groups with little gradient signal, while hard prompts can produce all-incorrect groups with no positive reward. We introduce ExTra (Exploratory Trajectory Optimization), a GRPO-compatible framework that extracts exploration signals from the model's own rollouts. ExTra combines two mechanisms: (i) a novelty reward that adds embedding-based diversity bonuses after GRPO normalization, rewarding diverse correct solutions; and (ii) entropy-guided prefix regeneration, which scores partial trajectories using entropy signals and continues exploration from promising intermediate steps. Across six mathematical reasoning benchmarks, ExTra improves Qwen3-1.7B over GRPO by about +5 points on pass@1 and +7 points on pass@16, showing that trajectory-level exploration signals can improve both single-sample accuracy and inference-time coverage.

AI 总结：提出Geo-Strat-RL合成环境，通过可验证奖励的强化学习（RLVR）训练视觉语言模型进行地质事件重建，并证明从地层图学到的推理可迁移至合成地震数据。

链接：https://arxiv.org/abs/2606.25000

作者：Lukas Mosser

英文摘要：To evaluate whether vision-language models can reason about geological histories, it is necessary to construct observations for which the underlying process history is known. Furthermore, reasoning over geological histories is not just a question of recognizing visual patterns, but also of understanding temporal and structural relationships that may be only indirectly visible or highly ambiguous. When ground-truth event histories are not uniquely identifiable or are unavailable, it remains an open challenge to teach models capable of visual reasoning to produce valid geological reconstructions that are consistent with both observed evidence and geological principles. We therefore investigate whether defining a verifiable geological reasoning task can improve geological event reconstruction across observation domains through reinforcement learning with verifiable rewards (RLVR). To this end, we present Geo-Strat-RL, a synthetic environment that generates stratigraphic observations and compact visible-evidence event histories. The environment combines a geological generator with an executable verifier that scores chronology, event identity, deposition, and structural relationships. We show that RLVR improves geological reconstruction in vision-language models (VLMs), increasing geological content scores on held out stratigraphic diagrams. We further evaluate the same held-out geological histories in a synthetic seismic observation domain by converting the generated scenes into acoustic-impedance-derived amplitude sections. In this controlled paired-renderer setting, we present evidence that geological reasoning learned from stratigraphic diagram-domain RLVR training transfers to synthetic seismic representations without seismic-specific training examples, supporting the hypothesis that RLVR can teach reusable geological reasoning concepts across related observation formats.

AI 总结：针对平均奖励设置下的约束多目标强化学习，提出基于MLMC的原对偶自然演员-评论家算法，控制标量化目标、约束评估和演员-评论家估计中的偏置，实现最优全局收敛和约束违反率。

链接：https://arxiv.org/abs/2606.25012

机构：Indian Institute of Science, Bengaluru, India（印度科学研究所，班加罗尔，印度）； Purdue University, USA（普渡大学，美国）

作者：Ankur Naskar, Swetha Ganesh, Vaneet Aggarwal

英文摘要：Many reinforcement learning (RL) problems in the infinite-horizon average-reward setting require optimizing multiple conflicting objectives while satisfying multiple safety constraints. A common approach is concave scalarization, where the agent maximizes a utility $ f(J^\pi_{r_1}, \ldots, J^\pi_{r_M}) $ subject to a scalarized constraint $ g(J^\pi_{c_1}, \ldots, J^\pi_{c_N}) \ge 0 $, where $J^\pi_{r_m}$ and $J^\pi_{c_n}$ denote the average-reward and cost under policy $\pi$. However, the nonlinearity of $f$ and $g$ introduces bias in policy-gradient and actor-critic methods, since gradients must be evaluated using noisy estimates of $J^\pi,$ and $ \mathbb{E}[\partial f(J^\pi)] \neq \partial f(\mathbb{E}[J^\pi]),$ and this bias propagates through both primal and dual updates. We propose an MLMC-based primal-dual Natural Actor-Critic algorithm for average-reward MDPs that controls bias in scalarized objectives, constraint evaluation, and actor-critic estimation without requiring mixing-time knowledge. We show that the algorithm achieves optimal global convergence and constraint-violation rates of $ \tilde{O}(1/\sqrt{T}) $. To our knowledge, this is the first result establishing optimal convergence for concave scalarized multi-objective RL in the average-reward setting, both with and without constraints, and the first to do so without mixing-time information even in the absence of scalarization.

AI 总结：提出GCT-MARL框架，利用多视图图对比学习和自适应加权对齐损失，结合两阶段训练协议，实现跨不同规模和组成群体的高效迁移，显著加速目标任务收敛。

链接：https://arxiv.org/abs/2606.25073

作者：Animesh Animesh, Satheesh K Perepu, Kaushik Dey

英文摘要：In cooperative multi-agent reinforcement learning (MARL), from a deployment perspective, it is challenging and expensive to train agents from scratch for each new environment or task. In this work, we propose GCT-MARL, a transfer learning framework that builds on the multi-view graph contrastive backbone of MAIL and augments it with a per-view, adaptively weighted alignment loss and a two-phase training protocol specifically designed for transfer across populations of varying sizes and compositions. We empirically demonstrate that the proposed framework markedly accelerates convergence on the target task relative to from-scratch training, in both homogeneous (within-faction, varying N) and heterogeneous (cross-faction and mixed unit-type) transfer scenarios. Furthermore, we show that the framework naturally supports continual learning by sequentially chaining the two-phase transfer protocol across a series of related tasks. Overall, this work provides a unified approach to mitigating key limitations in current MARL transfer methods with new insights at both methodological and empirical levels.

AI 总结：研究奖励设计如何影响自动驾驶强化学习代理的内部注意力模式，发现奖励内容直接决定编码器优先关注的场景元素，且连续碰撞时间惩罚会形成学习性警觉先验。

链接：https://arxiv.org/abs/2606.25127

机构：National School of Artificial Intelligence (ENSIA)（国家人工智能学院）； Cosys-Grettia, Univ Gustave Eiffel（古斯塔夫·埃菲尔大学Cosys-Grettia实验室）

作者： Mohamed Benabdelouahad, Ahmed Djalal Hacini, Nadir Farhi, Aissa Boulmerka

英文摘要：We investigate how reward design shapes the internal attention patterns of reinforcement learning agents trained for autonomous driving. Using three Perceiver-based agents that share identical architectures and training data but differ only in their reward configurations$\unicode{x2014}$ranging from basic violation penalties to continuous proximity penalties$\unicode{x2014}$we analyze cross-attention allocation across 50 real-world scenarios from the Waymo Open Motion Dataset. A central methodological finding is that naïve pooling of timesteps across episodes substantially underestimates the attention$\unicode{x2013}$risk relationship; within-episode correlation with Fisher z-transform aggregation is the appropriate statistic and reveals a robustly positive link between collision risk and agent-directed attention. Building on this validated methodology, we demonstrate two reward-conditioned effects: agents trained with navigation rewards allocate up to $2.0\times$ more attention to GPS-path tokens than those trained with additional proximity penalties$\unicode{x2014}$and $4.7\times$ more than agents with no navigation incentive$\unicode{x2014}$revealing that reward content directly determines which scene elements the encoder prioritizes, and continuous time-to-collision penalties create a $\textit{learned vigilance prior}$$\unicode{x2014}$elevated resting agent surveillance maintained throughout collision-free phases. In several scenarios, the complete-reward and minimal-reward models exhibit opposite attention$\unicode{x2013}$risk correlation directions, demonstrating that reward design can qualitatively reverse attentional strategy rather than merely modulating its magnitude. These results suggest that attention analysis is a practical diagnostic for verifying that a reward function produces the intended representational behaviour in safety-critical RL systems.

AI 总结：提出UC-Search，一种模型无关的测试时包装器，通过可行性自动机与风险调整搜索，解决延迟约束时间序列控制中的不确定性决策问题，在多个基准上优于现有方法。

链接：https://arxiv.org/abs/2606.25274

作者：Xibai Wang

英文摘要：Time-series models are usually scored as forecasters, yet deployed systems often require delayed decisions under uncertainty and hard feasibility constraints. UC-Search is a model-agnostic test-time wrapper: a backbone emits forecasts or action scores, a feasibility automaton rolls candidate paths forward, and bounded search returns the first action of a risk-adjusted feasible trajectory. We instantiate UC-Beam and a UCT-style UC-MCTS diagnostic, using epistemic, aleatoric, and propagated uncertainty mainly as path-risk terms. A myopic-collapse/separation theorem states when search reduces to one-step risk-greedy and when delayed feasible-set coupling can create non-myopic value. Primary evidence comes from a predeclared public $9$-family, $33$-series delayed-control suite with six held-out starts per series: UC-Pareto is positive versus validation-selected CEM, MPPI, and risk-aware random at the normalized threshold ($+3.1675/+2.3328/+2.5038$), and remains positive in a compute-matched audit ($+2.8466/+2.7418/+2.7429$). ETT/LTSF delayed-inventory validation supports the same compute-frontier claim. A 48-series raw M4 standard periodic-review lost-sales inventory audit is positive versus the strongest classic base-stock control ($+13556.7547$), CEM ($+64900.2207$), and risk-random ($+52881.6042$), while MPPI remains family-mixed. FI-2010, official-forecast adapters, SB3/FQI controls, direction/capacity/intervention checks, and synthetic mechanism tests are reported as boundary or mechanism evidence rather than broad dominance claims.

AI 总结：针对多智能体强化学习价值分解方法在任务迁移中可塑性下降的问题，提出KNIFE方法，通过替换停滞神经元为包含冻结知识、重初始化活跃和补偿三个组件的复合单元，恢复学习能力并保持已有知识。

链接：https://arxiv.org/abs/2606.25335

机构：Fujian Key Laboratory of Urban Intelligent Sensing and Computing, School of Informatics, Xiamen University (XMU)（福建省城市智能感知与计算重点实验室，厦门大学信息学院）； Key Laboratory of Multimedia Trusted Perception and Efficient Computing, XMU（多媒体可信感知与高效计算重点实验室，厦门大学）

作者：Zhengzhu Liu, Zeming Gao, Haoyuan Qin, Jiawei Hu, Junhao Wu, Miao Zhu, Haipeng Zhang, Chennan Ma, Siqi Shen, Cheng Wang

英文摘要：Multi-Agent Reinforcement Learning (MARL) value factorization methods can suffer from a loss of plasticity, gradually failing to adapt when transferring to new task instances. We trace this issue to stagnant neurons, units whose gradient updates become negligibly small relative to their weights, thereby hindering learning. While existing plasticity injection methods exist, they prove ineffective for such neurons. To address this, we propose Knowledge-retentive Neuron-level PlastIcity Focusing InjEction (KNIFE), a novel method that directly targets stagnant neurons. KNIFE replaces each stagnant neuron with a composite unit comprising three specialized components: a frozen knowledge neuron to preserve acquired knowledge, a re-initialized active neuron to restore learning capacity, and a compensation neuron to ensure the combined output matches the original, thus maintaining previous learned cooperation knowledge. Extensive experiments on SMACv2, predator-prey, and matrix games demonstrate that KNIFE significantly outperforms state-of-the-art plasticity injection methods.

AI 总结：提出统一框架，通过局部一步系统动态描述组成性地定义行为语义，证明行为结构在抽象与具体系统间的安全迁移，并构建具有可靠性保证的定量度量。

链接：https://arxiv.org/abs/2606.25357

作者：Yivan Zhang, Ziyan Luo, Manuel Baltieri

英文摘要：State abstraction plays a key role in scaling reinforcement learning to complex but structured systems. In studying such systems, a wide range of behavioral structures have been studied in reinforcement learning, including value functions, invariants, bisimulation relations, and behavioral metrics. However, a general principle for determining what structures are provably preserved under state abstraction is still lacking. In this paper, we present a unified framework for defining and analyzing behavioral structures in reinforcement learning. Our framework provides a compositional way to specify behavioral semantics based on local, one-step descriptions of system dynamics. Using this framework, we establish results showing how behavioral structures can be safely transferred between abstract and concrete systems. We further show how to construct quantitative metrics from logical behavioral semantics with soundness guarantees. Together, these results provide a principled foundation for reasoning about behaviors under state abstraction in reinforcement learning and offer reusable definition and proof principles for a broad class of behavioral structures in reinforcement learning.

AI 总结：将有限域上多项式的最小算术电路发现建模为强化学习问题，提出FactorLibrary存储可分解子表达式作为子目标，使用PPO+MCTS的top-down方法在复杂度8以内达到91.8%的成功率。

链接：https://arxiv.org/abs/2606.25394

作者：Rohan Pandey, Michael Ruofan Zeng, Weikun K. Zhang, Kaijie Jin, Naomi Morato, Archit Ganapule, Bhaumik Mehta, Jarod Alper

英文摘要：Finding minimal arithmetic circuits for polynomials over finite fields is a combinatorially hard problem central to algebraic complexity theory. We formulate it as a reinforcement learning problem in two directions, bottom-up and top-down. To address the challenge of a fast-growing combinatorial search space, we introduce FactorLibrary, which stores factorizable subexpressions that serve as reusable subgoals across training episodes. We trained a bottom-up agent with Gumbel-PPO-MCTS and two top-down agents with PPO+MCTS and SAC. The PPO+MCTS top-down agent exhibited the most stable performance, finding certified optimal circuits up to complexity $8$ with a success rate of $91.8\%$.

AI 总结：提出单次 rollout 近端策略优化（SR-PPO），利用每个提示的一次 rollout 训练 token 级信用评判器，通过 Pass@k 成功概率提供更选择性学习信号，避免重复采样并改善信用分配。

链接：https://arxiv.org/abs/2606.25451

机构：University of Alberta（阿尔伯塔大学）； BIGAI（北京通用人工智能研究院）； University of Toronto（多伦多大学）； McGill University, Mila（麦吉尔大学，米拉）； Nvidia Research（英伟达研究院）； Amii（阿尔伯塔机器智能研究所）； CIFAR AI Chair（CIFAR人工智能教席）

作者：Fengdi Che, Yang Liu, Lei Yu, Meng Cao, Tong Che, Rupam Mahmood, Dale Schuurmans

英文摘要：Estimating token-level advantages in reinforcement learning (RL) for language models remains challenging because scaling up episodic experience collection is expensive. The difficulty intensifies for baseline advantage estimation methods, where repeated sampling causes trajectories to diverge into substantially different reasoning prefixes. In this context, RL algorithms such as GRPO prove limited: an outcome reward is too sparse to be attributed to specific actions like intermediate steps, and comparisons across sampled traces are non-trivial because they are heterogeneous. To mitigate both the computational cost of repeated sampling and the difficulty of credit assignment, we study single-rollout proximal policy optimization (SR-PPO) featuring token-level credit assignment in RL for language models. Instead of estimating advantages by normalizing episodic returns within the candidate group, we train a calibrated token-level credit critic using Monte Carlo outcomes from one rollout per prompt. Specifically, we use the critic to predict the Pass@k success probability at the prompt prefix, which is derived from a Pass@1 attempt. This choice yields a more selective learning signal than Pass@1: it discounts easily solved prefixes while prioritizing hard ones whose success probability remains marginal. We show that as $k$ increases, Pass@k converges to a reachability indicator, reflecting whether a prefix can lead to at least one successful continuation. In an explicit state graph, the limit ($k \rightarrow \infty$) can be computed in $O(|V|+|E|)$ time, offering a promising surrogate for direct credit assignment without the need to sample contrastive traces. As an initial validation, SR-PPO exhibits stable learning dynamics, along with consistent gains in Pass@128 success rates on mathematical reasoning benchmarks such as HMMT26 and AIME24.

AI 总结：针对合作多智能体强化学习中顺序更新导致优势函数方差指数级增长的问题，提出裁剪目标控制优势波动上限，实现亚线性收敛到ε-纳什均衡，并在三个基准测试中优于基线方法。

链接：https://arxiv.org/abs/2606.25526

作者：Bang Giang Le, Viet Cuong Ta

英文摘要：Cooperative multi-agent reinforcement learning assumes each agent shares the same reward function and can be trained effectively using the Trust Region framework of single-agent. Instead of relying on other agents' actions, the independent actors setting considers each agent to act based only on its local information, thus having more flexible applications. However, in the sequential update framework, it is required to re-estimate the joint advantage function after each individual agent's policy step. Despite the practical success of importance sampling, the updated advantage function suffers from exponentially high variance problems, which likely result in unstable convergence. In this work, we first analyze the high variance advantage both empirically and theoretically. To overcome this limitation, we introduce a clipping objective to control the upper bounds of the advantage fluctuation in sequential updates. With the proposed objective, we provide a monotonic bound with sub-linear convergence to $\epsilon$-Nash Equilibria. We further derive two new practical algorithms using our clipping objective. The experiment results on three popular multi-agent reinforcement learning benchmarks show that our proposed method outperforms the tested baselines in most environments. By carefully analyzing different training settings, our proposed method is highlighted with both stable convergence properties and the desired low advantage variance estimation. For reproducibility purposes, our source code is publicly available at this https URL.

AI 总结：本文提出诊断驱动的张力管理框架，通过三种功能角色表征离线先验知识如何重塑在线优化，并展示跨领域证据，解决先验知识有效性随部署变化的问题。

链接：https://arxiv.org/abs/2606.25527

机构：Nanyang Technical University（南洋理工大学）； University of Oxford（牛津大学）

作者：Guozheng Ma, Lu Li, Zilin Wang, Pierre-Luc Bacon, Dacheng Tao

英文摘要： Online reinforcement learning (RL) agents increasingly depend on knowledge acquired offline to achieve practical efficiency. Originally studied in offline-to-online RL, this paradigm now spans foundation model post-training and embodied intelligence, with prior types expanding from offline datasets and pre-trained policies to increasingly diverse knowledge sources such as multimodal foundation models and generative world models. Offline priors have become central to how deep RL is developed and deployed. However, this reliance introduces a challenge that the prevailing benchmark-driven paradigm cannot resolve: because prior validity varies across deployments and shifts during training, no single approach to managing it is universally optimal, and benchmark rankings offer limited guidance for real-world deployments. Rather than pursuing universal solutions, we argue that the field should shift to diagnosis-driven tension management, in which deployment-specific evidence guides how the learner relates to its priors throughout training, enabling both flexible and adaptive deployment. We support this position with a framework characterizing how priors reshape online optimization through three functional roles, controlled experiments demonstrating help-or-hurt reversals, cross-domain evidence from foundation model post-training to embodied intelligence, and engagement with five substantive counterarguments.

AI 总结：研究结构化MDP中最优策略的几何特性，提出基于边界的策略近似方法，直接学习策略区域，并通过策略损失分解解释误差集中在无差异边界附近。实验表明该方法在策略误差、价值差距、误差衰减和稳定性上优于强化学习基线。

链接：https://arxiv.org/abs/2606.25593

作者：Fredy Pokou (CRIStAL)

英文摘要：We study optimal-policy geometry in structured Markov decision processes. While approximate dynamic programming and reinforcement learning typically approximate high-dimensional value functions, we show that optimal policies induce simpler decision tessellations. We propose boundary-based policy approximations that learn policy regions directly. A policy-loss decomposition links performance degradation to action margins and explains why errors concentrate near indifference boundaries. Inventory control and queue admission experiments show lower policy error, smaller value gaps, faster error decay, and stability than reinforcement learning baselines.

AI 总结：研究将参数高效微调方法（如LoRA）迁移至机器人强化学习，通过PPO算法微调基线模型构建多任务策略库，实现内存占用降低20-160倍，存储节省90-95%，且成功率无显著差异。

链接：https://arxiv.org/abs/2606.25700

作者：Samuel Valland Lyngset, Tor Viljen Raanaas, Gard Sveipe, Eirik Møller Nilsen, Jim Torresen, Kai Olav Ellefsen, Tobias Lømo

英文摘要：When fine-tuning Large Language Models (LLMs), there has been success in minimizing both memory usage and computation with Parameter-Efficient Fine-Tuning (PEFT), like Low Rank Adaptation (LoRA). In this article, we have explored whether this approach is transferable to the world of robotics and Reinforcement Learning (RL), allowing learning with reduced memory usage and improved computational performance. Specifically, we focused on a version of multi-task robotics, where a library of specialist policies are created. In such a library memory efficiency is especially important. We used a Proximal Policy Optimization (PPO) algorithm and fine-tuned a baseline model to different tasks using LoRA. Our results demonstrate that, depending on the hyperparameters, LoRA can minimize memory usage by a factor of 20-160 compared to full fine-tuning of all layers. This implies a 90-95% storage saving when deploying a library of many (10-50) specialized policies, which can be the differentiating factor between being able to store the entire library in memory or having to use swap-memory in an applied robotics setting. At the same time, our results indicate that there is no significant difference in the success-rate between full fine-tuning and LoRA fine-tuning for the selected tasks.

AI 总结：针对稀疏奖励下VLA模型在线自适应困难，提出ROAD-VLA框架，通过优势引导的自蒸馏在动作空间构建近端教师，将稀疏奖励转化为密集token级监督，并在7个机器人操作环境中优于PPO。

链接：https://arxiv.org/abs/2606.25800

机构：Air Force Research Laboratory（空军研究实验室）

作者：Kejing Wang, Toan Nguyen, Minh Hoang Nguyen, Simon Khan, Flora D. Salim

英文摘要：Effective online adaptation of vision-language-action (VLA) models remains challenging, as sparse rewards provide weak supervision for high-dimensional autoregressive action policies. Although self-distillation can in principle provide denser training signals, we find that text-based privileged teachers conditioned on demonstrations, retrieved experiences, or high-level plans are ineffective for VLA adaptation, exposing a modality gap between symbolic guidance and low-level robot actions. We propose ROAD-VLA, an advantage-guided self-distillation framework that constructs a proximal teacher directly in action space by perturbing action-token logits with calibrated advantage estimates. This converts sparse rewards into dense token-level supervision while keeping the teacher close to the current policy. We further derive a policy-improvement lower bound under calibrated advantages and accurate teacher matching. Across seven robotic manipulation environments with in-distribution and out-of-distribution shifts, ROADVLA outperforms PPO in nearly all settings, demonstrating robust online VLA adaptation.

AI 总结：提出MiniOpt强化学习框架，通过“推理-建模-求解”范式，结合层次化奖励函数OptReward和优化导向策略优化，使3B参数模型在多种优化问题上达到强泛化，且训练资源需求低。

链接：https://arxiv.org/abs/2606.25832

机构：East China Normal University（华东师范大学）； AntGroup（蚂蚁集团）； Southern University of Science and Technology（南方科技大学）； Nanjing University（南京大学）

作者：Ke Zhao, Zixiang Di, Hong Qian, Xiang Shu, Yaolin Wen, Qitao Shi, Bingdong Li, Xingyu Lu, Xiangfeng Wang, Jun Zhou, Ke Tang, Yang Yu

英文摘要： Achieving strong optimization generalization across diverse optimization problems while requiring limited training resources remains a challenging problem for optimization-oriented large language models (LLMs). Existing approaches typically rely on large-scale supervised datasets, costly reasoning annotations, and expensive intermediate step verification, resulting in substantial training overhead. To address these challenges, we propose MiniOpt, a reinforcement learning framework that learns to solve optimization problems through an "reasoning-to-model-and-solve" paradigm. MiniOpt decomposes optimization reasoning into structured optimization modeling and executable solver generation. Building upon this paradigm, we introduce OptReward, a reward function with hierarchical score structure that jointly evaluates formulation and solution, enabling effective policy learning without expert demonstrations. We further develop an optimization-oriented policy optimization strategy that improves exploration efficiency and stabilizes reinforcement learning for compact models. Extensive experiments show that MiniOpt-3B exhibits strong optimization generalization across various optimization types, problem scenarios, and task domains. For models with fewer than 10B parameters, MiniOpt series achieves the highest average solving accuracy (SA). For models with more than 10B parameters, MiniOpt still shows competitive performance. These results suggest that optimization-oriented reward design and reinforcement learning provide an effective pathway for developing compact optimization-specialized language models with strong optimization generalization capabilities. The code is available at this https URL.

AI 总结：针对基于组的强化学习中语义一致的中间步骤因轨迹成败获得相反信用的问题，提出无价值奖励塑造方法SCPO，通过从组内成功兄弟步骤恢复信用，在ALFWorld和WebShop上达到93.7%和74.8%的成功率。

链接：https://arxiv.org/abs/2606.25852

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

作者：Peng Xu, Sijia Chen, Junzhuo Li, Xuming Hu

英文摘要：Group-based reinforcement learning effectively post-trains LLM agents for long-horizon, sparse-reward tasks by deriving step-level credit from trajectory outcomes. However, this ties a step's credit to its rollout's final outcome: semantically near-identical intermediate steps receive opposite credit depending on whether their trajectory eventually succeeded or failed. Such semantic credit inconsistency sends conflicting gradients to similar actions and wastes the partially-correct progress inside failed rollouts. Motivated by this, we propose Semantic Consistency Policy Optimization (SCPO), a value-free reward-shaping method that mitigates this inconsistency by recovering step-level credit from successful siblings in the same rollout group. Concretely, SCPO scores each failed step against a successful sibling and adds positive step-level credit for new progress along that sibling. On ALFWorld and WebShop, SCPO matches or exceeds strong group-based baselines, reaching 93.7+/-4.1 percent success on ALFWorld and 74.8+/-2.0 percent on WebShop at 1.5B parameters, with gains concentrated on the hardest multi-step tasks.

AI 总结：针对数字孪生模型在有限容量下优化一步预测误差可能导致策略排序次优的问题，提出决策导向训练范式$\text{DT}^2$，通过拟合Q评估和保留策略排序的损失函数，提升策略排序质量并降低决策遗憾。

链接：https://arxiv.org/abs/2606.25923

作者：Harry Amad, Mihaela van der Schaar

英文摘要：A digital twin (DT) is a virtual model of a real-world system that can assist decision-making by simulating scenarios induced by different policies. However, typical machine learning-based DTs do not optimise for this use case. We prove that, when model capacity is limited, training DTs to minimise one-step transition errors can produce suboptimal models for ranking sets of policies according to a reward function. We further show that this holds empirically, even with expressive model classes. To address this, we introduce $\text{DT}^2$, a decision-targeted DT training paradigm. Firstly, $\text{DT}^2$ uses fitted Q-evaluation to estimate values of candidate policies from offline data. A DT is then trained to generate rollouts that preserve pairwise policy rankings derived from these proxy ground-truth values with an architecture-agnostic loss function. We empirically demonstrate the efficacy of our method across a range of settings and architectures. $\text{DT}^2$ consistently improves policy ranking and reduces decision regret during policy selection relative to conventional DT training, both for policies used during training and for unseen policies, while maintaining a good level of raw simulation fidelity.

AI 总结：提出进展优势概念，利用强化学习后训练中的隐式优势函数作为无标注、领域无关的步骤级评分，在测试时扩展、不确定性量化和失败归因中超越专用奖励模型。

链接：https://arxiv.org/abs/2606.26080

机构：University of Wisconsin–Madison（威斯康星大学麦迪逊分校）； Argonne National Laboratory（阿贡国家实验室）

作者：Changdae Oh, Wendi Li, Seongheon Park, Samuel Yeh, Tanwi Mallick, Sharon Li

英文摘要：Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult: long-horizon interactions, irreversible actions, and stochastic environment feedback make both human annotation and Monte Carlo estimation infeasible at scale. In this work, we show that reinforcement learning (RL) post-training already provides the ingredients for effective step-level scoring, eliminating the need for dedicated reward model training altogether. Concretely, we derive an implicit advantage under a general stochastic Markov decision process, which we term progress advantage -- log-probability ratio between the RL-trained policy and its reference policy exactly recovers the optimal advantage function. This formulation makes the resulting signal annotation-free, domain-agnostic, and available as a byproduct of the standard RL post-training pipeline. We validate the effectiveness of the progress advantage across three different applications: test-time scaling, uncertainty quantification, and failure attribution on five benchmarks and four model families. Across all settings, it consistently outperforms confidence-based baselines and, despite requiring no task-specific training, surpasses dedicated trained reward models. We complement these results with deeper analyses on characteristics of progress advantage, offering practical guidance for adoption in real-world agentic systems.

AI 总结：提出潜在块扩散时间点过程（LBDTPP），通过潜在空间中的块级自回归和块内高斯扩散，实现可变长度、高质量的事件序列生成，理论证明可减少误差累积，实验优于现有方法。

链接：https://arxiv.org/abs/2606.24982

机构：Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）； Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）； Department of Data Science, City University of Hong Kong（香港城市大学数据科学系）； Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）

作者：Shuai Zhang, Yancheng Chen, Chuan Zhou, Yang Liu, Xixun Lin, Xiangyu Zhao, Jun Zhu, Zhi-Ming Ma

英文摘要：Modeling and sampling from the underlying distribution of asynchronous event sequences are crucial in various real-world applications, including social networks, medical diagnosis, and financial transactions. Existing autoregressive methods suffer from error accumulation during multi-step generation, while non-autoregressive diffusion methods are typically limited to fixed-length output sequences. In this paper, we propose Latent Block-Diffusion Temporal Point Processes (LBDTPP), a novel semi-autoregressive TPP framework that introduces a latent block diffusion mechanism for high-quality and variable-length event sequence generation. The core idea is to define an autoregressive probability distribution over event blocks in latent space and perform Gaussian diffusion within each block. By sequentially generating blocks while simultaneously sampling events in each block, LBDTPP preserves the length flexibility of autoregressive TPPs and inherits the parallel high-quality generation capability of diffusion models. Theoretically, we derive Wasserstein error bounds showing that, under suitable local approximation and prefix-stability assumptions, block-wise generation can reduce error accumulation compared with event-wise autoregressive generation. Extensive experiments on six real-world benchmark datasets demonstrate that LBDTPP outperforms state-of-the-art TPP baselines in both unconditional and conditional generation tasks. Further empirical analyses verify the benefits of latent-space diffusion and block-wise generation, and reveal the trade-off between generation quality and block size. Our code is available at this https URL.

AI 总结：提出熵传输下降（ETD），一种基于粒子变分推断方法，通过熵正则化最优传输实现全局协调，避免高维方差坍塌和多模态模式坍塌，无需评分函数。

链接：https://arxiv.org/abs/2606.25265

作者：Vincent Pacelli, Akash Ratheesh, Evangelos Theodorou

英文摘要：Particle-based variational inference (ParVI) methods approximate an intractable target distribution by evolving an ensemble of interacting samples. Existing approaches rely predominantly on kernel-based repulsion (e.g., SVGD), which suffers from variance collapse in high dimensions and mode collapse on multimodal targets -- pathologies caused by the absence of global transport structure. We introduce entropic transport descent (ETD), a ParVI family that frames each particle update as an entropy-regularized optimal transport problem. Derived from the JKO proximal scheme by lifting to the space of couplings and relaxing via the KL chain rule, each ETD iteration reduces to a Sinkhorn computation. The resulting transport plan provides global coordination, guiding each particle to nearby high-density proposals and naturally preserving multimodal structure. ETD can operate entirely score-free, requiring only pointwise evaluations of the unnormalized target density. Experiments on variance-collapse diagnostics, Bayesian logistic regression, neural networks, and molecular Boltzmann distributions show that ETD matches or outperforms SVGD, AGF-SVGD, and SGLD, with the largest gains in high-dimensional and multimodal settings.

AI 总结：研究变分深度高斯过程的后验坍缩问题，发现线性先验均值函数的优势源于改善初始化时的优化条件，提出零先验均值的替代初始化方法，避免后验坍缩并提升稳定性。

链接：https://arxiv.org/abs/2606.25882

作者：Francisco Javier Sáez-Maldonado, Juan Maroñas, Daniel Hernández-Lobato

英文摘要：DGPs are probabilistic models with remarkable prediction performance that concatenate GPs across several layers. Exact inference in DGPs is intractable, and variational inference is often used to approximate the posterior with a parametric distribution tuned by minimizing the Kullback-Leibler divergence. Moreover, finding a good VI approximation is challenging. In particular, a problem of VI is posterior collapse, where VI converges to a variational posterior that matches the prior. In variational DGPs, this implies explaining the data as noise. This work studies posterior collapse in DGPs and identifies its connection to the DSVI algorithm and the widely used linear prior mean function employed in all but the last layer. We show that the benefit of the linear prior mean does not arise from avoiding the non-injective pathology in very deep DGPs, as previously believed, but from improving the conditioning of the optimization problem at initialization. Thus, we propose an alternative initialization of a zero prior mean DGP that mimics a DGP with a linear prior mean at initialization. This enables successful training of DGPs without imposing optimization-driven constraints on the prior, allowing to choose the prior based on modeling assumptions rather than optimization convenience. Our analysis considers three common parameterizations of DGPs and shows that not all of them benefit from a linear prior mean. We also explain why a whitened parameterization of the \DGP provides more stable convergence, something often assumed from experience, but lacking a rigorous analysis. Furthermore, we show that this stability is also beneficial to avoid the posterior collapse problem. Extensive experiments validate our findings: the proposed initialization prevents posterior collapse, improves stability, and achieves performance comparable to (and sometimes better than) DGPs with a linear prior mean.

AI 总结：提出将变分自编码器作为神经网络层集成，并设计新训练策略，分析其性能。

链接：https://arxiv.org/abs/2606.25900

作者：Gananath R

英文摘要： Variational Autoencoders (VAEs) belong to a family of autoencoders with probabilistic properties, making them well suited for generating data by producing a smooth and continuous latent space. Despite being introduced over a decade ago, the method continues to be widely adopted in both research and industry for diverse applications. While VAEs are typically used as standalone models, this paper introduces a novel approach to integrate them as a neural network layer. Furthermore, a new training strategy is proposed for models incorporating these layers, and their performance is thoroughly analyzed.

AI 总结：提出退化蒸馏器方法，通过估计和展平Fisher信息矩阵，自动符号化检测并解决物理模型中的退化参数组合，降低神经后验估计所需的模拟预算。

链接：https://arxiv.org/abs/2606.23838

机构：Department of Applied Mathematics and Theoretical Physics, University of Cambridge（剑桥大学应用数学与理论物理系）； Imperial Centre for Inference and Cosmology (ICIC), Imperial College London（伦敦帝国理工学院帝国推理与宇宙学中心）； Astrophysics, University of Oxford（牛津大学天体物理学系）； CNRS & Sorbonne Université, Institut d’Astrophysique de Paris (IAP)（法国国家科学研究中心与索邦大学巴黎天体物理研究所）； Department of Physics and Astronomy, University College London（伦敦大学学院物理与天文学系）； Department of Physics & King’s Institute for Artificial Intelligence, King’s College London（伦敦国王学院物理系与国王人工智能研究所）； Department of Physics and Astronomy, Johns Hopkins University（约翰霍普金斯大学物理与天文学系）； Department of Applied Mathematics and Statistics, Johns Hopkins University（约翰霍普金斯大学应用数学与统计学系）

作者：T. Lucas Makinen, Deaglan J. Bartlett, Niall Jeffrey, Benjamin D. Wandelt

英文摘要：When two or more parameters or labels produce similar data, they are degenerate, or hard to distinguish. Degeneracies render both label prediction and inverse problems difficult, since both machine learning algorithms and probabilistic samplers rely on the distinguishability of data and its gradients with respect to parameters. However, identifying degeneracies in physical models or real-world datasets can be elucidating about the choice of model or the underlying process that produces the data. We present the degeneracy distillery, a method that (1) detects and (2) resolves degenerate parameter combinations (a) automatically and (b) symbolically, from parameter-data (or parameter-simulation) pairs alone, through estimation and flattening of the Fisher information matrix. By exploring the information geometry of the likelihood, we characterize degeneracies as an intrinsic property of the physical model, requiring no realised data observation. We demonstrate our approach on a range of synthetic and real-world problems, discovering symbolic coordinate transformations that identify the combinations of parameters of a model which yield independent effects on the data. The resulting coordinates flatten the Fisher information in expectation globally, in contrast to posterior-based methods that flatten only at a single point, and substantially reduce the simulation budget required for downstream neural posterior estimation. In test cases we require up to $10\times$ fewer simulations for posterior estimation at matched validation calibration whilst simultaneously gaining physical insight on the system.

AI 总结：本文通过复杂动力系统视角，论证神经网络学习本质上是复杂系统，并指出训练复杂性的三个关键属性（对权重初始化的敏感性、梯度优化中的反馈、对训练数据的敏感性）各自如何导致学习不透明性，且这些属性可能不可约。

链接：https://arxiv.org/abs/2606.24953

机构：Heidelberger Akademie der Wissenschaften（海德堡科学院）； Universität Tübingen, Cluster of Excellence: Machine Learning – New Perspectives for Science（图宾根大学，卓越集群：机器学习——科学新视角）

作者：Joachim Stein, Eric Raidl

英文摘要：Machine learning (ML) algorithms are known to be opaque. We do not know the reasons for their predictions. The learning process leading to the prediction function is also opaque. We do not fully understand the time evolution of the weight values of neural nets (NN) and related dynamical phenomena. While prediction opacity is widely studied, learning opacity remains largely underexplored. This article studies learning opacity trough the lens of complex dynamical systems. We argue that NN learning is essentially a complex system and that learning opacity is due to dynamical complexity and the epistemological challenges that arise from it. We identify three key properties of training complexity -- sensitivity to weight initialization, feedback in gradient based optimization, and sensitivity to the training data -- and show how each contributes to learning opacity. As these properties are fundamental to the learning process damping or eliminating them would fundamentally alter how ML systems learn. Some sources of opacity in ML may hence be irreducible.

AI 总结：提出层次贝叶斯框架，通过共享种群分布建模多个稀疏、含噪、不规则采样数据集，结合ODE求解器和梯度MCMC实现高效后验推断，提升预测性能。

链接：https://arxiv.org/abs/2606.24966

机构：SUPSI, Dalle Molle Institute for Artificial Intelligence (IDSIA USI-SUPSI), Lugano, Switzerland（瑞士南方应用科技大学，达勒莫尔人工智能研究所（IDSIA USI-SUPSI），卢加诺，瑞士）

作者：Cristian Brugnara, Lea Multerer, Marco Forgione, Laura Azzimonti

英文摘要：Estimating parameters of dynamical systems from sparse, noisy, and irregularly sampled data is often severely ill-conditioned. When multiple related datasets are available, they provide additional information if the shared structure and variability are properly modeled. We propose a hierarchical Bayesian framework for probabilistic meta-learning in dynamical systems, modeling dataset-specific parameters as draws from a shared population distribution. A numerical ODE solver is embedded within gradient-based MCMC to enable efficient posterior inference of the shared population and dataset-specific parameter distribution. Experiments show improved predictive performance over unpooled methods, highlighting the potential for data-efficient system identification in settings with sparse data.

AI 总结：研究马尔可夫采样下线性TD(0)的Polyak-Ruppert平均，提出依赖混合时间的单一步长，无需曲率参数先验知识，实现无投影下自动有界，同时获得鲁棒和快速收敛速率。

链接：https://arxiv.org/abs/2606.24981

机构：King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）

作者：Wei-Cheng Lee, Francesco Orabona

英文摘要：We study linear TD(0) under Markovian sampling, where data are generated along a single trajectory. We provide high-probability guarantees for a plain unprojected TD(0) algorithm with Polyak-Ruppert (PR) averaging, using a single stepsize schedule $\eta_t \propto \frac{1}{\tau_{\mathrm{mix}}\log(t)\sqrt{t}}$ that depends on the mixing time but requires no prior knowledge of the curvature parameter $\omega$. Our first result shows that such a choice of the stepsize guarantees that the TD(0) iterates are automatically and uniformly bounded with high probability, without projections and without any stability argument based on $\omega$. Building on this result, we establish a simultaneous high-probability convergence guarantee for the PR average: the same stepsize yields both a robust curvature-free $\widetilde{\mathcal{O}}\!\left(\frac{\tau_{\mathrm{mix}}}{\sqrt{T}}\right)$ rate and a fast curvature-dependent $\widetilde{\mathcal{O}}\!\left(\frac{\tau_{\mathrm{mix}}^2}{\omega T}\right)$rate, with the bound taking the minimum of the two. The core technical ingredient is a Poisson-equation toolkit for geometrically mixing Markov chains, which decomposes Markov noise into a martingale term plus a controlled remainder and enables a new self-bounding inductive argument for pathwise stability.

AI 总结：本文论证神经缩放定律中的幂律指数由通用机制固定，而系数对数据和架构细节敏感，理解系数是近期性能提升的关键。

链接：https://arxiv.org/abs/2606.25008

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

作者：Yizhou Liu, Jeff Gore

英文摘要：Neural scaling laws describe how pre-training loss decays as power laws with training time, model size, and compute. This position paper argues that the exponents of these power laws are fixed by generic mechanisms: a one-third time scaling due to the strong nonlinearity of Softmax, an inverse width scaling due to representational superposition, and an inverse depth scaling due to ensemble averaging of Transformer layers. These mechanisms are robust to a wide range of data structures and architectural details, placing current large language models in a universality class with fixed exponents. The coefficients, however, are expected to be sensitive to data and architecture details, and directly determine practical quantities such as the optimal model shape and the compute-optimal frontier. We therefore argue that understanding the coefficients is the key to near-term performance improvements, and that a closer examination of the current universality class may reveal pathways to better universality classes.

AI 总结：针对返回迭代平均而非最终迭代的语言模型，提出PACE方法，通过最优控制理论优化平均估计器，在二次模型中证明其能显著降低均方误差，并在1-2B参数LM微调和GPT-2预训练中优于AdamW。

链接：https://arxiv.org/abs/2606.25086

作者：Kwok Chun Au, Adam Block

英文摘要：Many modern Language Model (LM) pipelines return an averaged model, such as an exponential moving average of the training iterates, rather than the final iterate itself. This raises a fundamental question: given that we will return an iterate average, how should we change training to improve the performance of this average? We study this question by formulating optimizer design for the iterate-average estimator as an optimal-control problem. In a continuous-time stochastic quadratic model, we solve for the control strategy that minimizes the error of the returned average subject to a penalty on the size of the intervention. A practical approximation to this controller yields PACE, a lightweight wrapper around AdamW that pulls the live weights toward their exponential moving average with a clipped, per-coordinate control strength. We prove that a stylized version of PACE converges at the standard stochastic convex optimization rate, up to a factor depending on the averaging rule, while in the quadratic setting it can strictly improve the limiting squared error of the iterate-average estimator and can do so by an arbitrarily large factor on some instances. Empirically, our results suggest that PACE improves over AdamW and EMA-evaluated AdamW in supervised fine-tuning of 1-2B parameter LMs and in GPT-2 pretraining on FineWeb for a wide range of learning rates, decay schedules, and other hyperparameters.

AI 总结：研究有限标注下利用固定黑盒预测器进行非参数回归的问题，发现风险在临界半径处发生相变，并提出安全残差估计器以避免负迁移，达到极小化最优。

链接：https://arxiv.org/abs/2606.25743

作者：Yan Zhou

英文摘要：Foundation models are often used as fixed black-box predictors for downstream tasks with limited labeled data, but their predictions may be biased and unsafe to trust blindly. We study this setting through black-box assisted nonparametric regression: a learner observes labeled samples and can query a fixed predictor $f_0$, while the target $f^*$ is close to $f_0$ in $L_2(P_X)$ up to an unknown radius $\delta$. We give a finite-sample minimax characterization showing a phase transition at $\delta_c(n) \asymp n^{-\beta/(2\beta+d)}$, with leading risk $\min\{\delta^2, n^{-2\beta/(2\beta+d)}\}$. We then analyze a Safe Residual Estimator: it learns a correction around $f_0$, initializes the residual head at zero so the initial predictor equals $f_0$, and uses holdout selection to revert to $f_0$ when the learned correction is not supported by validation data. Here, "safe" means avoiding negative transfer, i.e., performing worse than the black-box predictor alone. The estimator matches the leading minimax term up to an additive validation-selection cost. Synthetic regression experiments verify the predicted phase transition, while CIFAR-100 with CLIP and AG News with Qwen3-8B provide practice-facing evidence that the same residual-correction tradeoff is useful beyond the formal squared-loss regression setting.

AI 总结：将进化策略、共识优化和积分优化统一为理论框架，通过引入混合优化器控制平坦偏好和模态，在连续控制和语言模型合并任务中提升性能与鲁棒性。

链接：https://arxiv.org/abs/2606.25761

作者：Johannes Ackermann, Stefano Peluchetti

英文摘要：When gradient information is unavailable, black-box optimization (BBO) methods provide a practical alternative. While Evolution Strategies (ES), Consensus-Based Optimization (CBO), Optimization via Integration (OVI), and related methods have each been studied independently, their connections remain underexplored. We unify these approaches within a common theoretical framework, revealing that they differ primarily in two design choices: fitness aggregation (controlling sharpness preference) and consensus scope (controlling modality). Leveraging these insights, we introduce hybrid optimizers that interpolate between existing methods. Our ES-OVI hybrid allows explicit control over the preference for flat minima, enabling a trade-off between performance and robustness in continuous control tasks. Our CBO-OVI hybrids combine the higher-dimensional efficiency of parametric methods with the multimodal capabilities of particle-based approaches, achieving competitive results on language model merging under limited evaluation budgets. We validate our methods on standard BBO benchmarks and higher-dimensional locomotion tasks, demonstrating that the hybrid methods can outperform their constituent algorithms.

AI 总结：本文揭示变分蒙特卡洛（VMC）中局部能量和梯度估计子的重尾特性，提出基于裁剪的PS-Clip-VMC算法，证明其在弱矩条件下的收敛性，实验表明比标准方法更稳健。

链接：https://arxiv.org/abs/2606.26009

机构：Faculty of Mathematics, University of Vienna（维也纳大学数学学院）； RICAM, Austrian Academy of Sciences（奥地利科学院里卡姆研究所）

作者：Philipp Grohs, Davide Nobile

英文摘要：Variational Monte Carlo (VMC) is a central algorithm in electronic structure theory and has gained renewed importance through modern neural-network ansätze such as FermiNet. At its core, VMC seeks ground states by minimizing the Rayleigh quotient by stochastic optimization. In this work, we show that the resulting stochastic optimization problem is intrinsically governed by the nodal geometry of the underlying wave function. More precisely, we establish that properties of the nodal set determine the integrability of the local energy and gradient estimators that drive VMC. For broad and practically relevant ansatz classes, including Slater-Jastrow wave functions with variable-exponent Slater-type orbitals, we prove that these estimators are generically heavy-tailed and fail to admit higher moments. At the same time, for general analytic ansätze, we prove weak moment bounds for the relevant estimators and identify precise low-moment regimes, showing how generic and degenerate nodal structures lead to different integrability thresholds. Building on this analysis, we introduce a new robust variant of VMC $\unicode{x2013}$ coined PS-Clip-VMC $\unicode{x2013}$ which is based on clipping both the local energy and the gradient random variable. We prove that PS-Clip-VMC converges both in expectation and with high probability in the weak moment regime of VMC. Preliminary experiments for training FermiNet on Atoms with up to 18 electrons suggest that PS-Clip-VMC is significantly more robust than standard methods.

AI 总结：提出一种在部署设备上直接进行轻量级神经架构搜索的方法，以优化传感器实时数据分析，在人机接口中实现个性化适应，并在两个数据集上验证了其优于现有技术。

链接：https://arxiv.org/abs/2606.24900

作者：Andrea Mattia Garavagno, Edoardo Ragusa, Paolo Gastaldo, Antonio Frisoli, Claudio Loconsole

英文摘要：This paper proposes a new approach to near-sensor computing, in which a lightweight Neural Architecture Search (NAS) is performed directly on the deployment device to find the best tiny neural architecture for analyzing the real-time data acquired through sensors. This new adaptation capability can be particularly useful in the case of human-machine interfaces for which the neural network analyzing the biometrical data can be re-designed each time the user changes, after a guided data collection procedure, fighting the typical data variations between individuals on a new level. To implement the proposed approach a new NAS has been designed and then validated on the Italian Sign Language dataset (ISL), a collection of surface electromyography (sEMG) signals of the signs of the Italian alphabet, using several embedded systems. Moreover, further validation on the Case Western Reserve University dataset (CWRU), a benchmark for intelligent fault diagnosis, is presented to suggest another possible application of the proposed approach. When run on a Raspberry Pi 4, the proposed NAS performs beyond the state of the art proposing a tiny neural architecture having 0.63 times less RAM occupancy and 5.96 percentage points of more accuracy in the case of the ISL dataset; and 0.44 times less RAM occupancy and 0.2 percentage points of more accuracy in the case of the CWRU dataset.

AI 总结：研究剪枝LLM注意力层对解释忠实性和置信度校准的影响，发现尽管准确率保持，但忠实性和校准度常下降，表明模型置信度、可解释性与准确性之间存在错位。

链接：https://arxiv.org/abs/2606.24970

作者：Pietro Tropeano, Maria Maistro, Tuukka Ruotsalo, Christina Lioma

英文摘要：Pruning Large Language Models (LLMs) reduces memory and inference costs by removing parts of the network, producing smaller models that retain most of their accuracy. As attention layers are the most resource-intensive parts of LLMs, pruning them is a promising compression strategy. Prior work shows that up to 33% of attention layers can be pruned with minimal accuracy loss. Nevertheless, the impact of attention pruning on model interpretability, specifically faithfulness and confidence calibration, remains unstudied. To address this gap, we study how pruning attention layers affects explanation faithfulness and confidence calibration across five LLMs and eight datasets. While the pruned models often maintain high accuracy, we find that their faithfulness and calibration often degrade. Notably, faithfulness and calibration can fluctuate significantly, even when accuracy remains stable, highlighting a misalignment between model confidence, interpretability, and accuracy. Our findings suggest that layer pruning can affect LLMs' interpretability and reliability in ways not captured by accuracy and efficiency measures alone. We recommend including explainability and calibration metrics when evaluating pruned models.

AI 总结：提出ADOWIP框架，通过决策损失优先级门控在反馈到达时选择性更新，在有限预算下降低决策损失，并在公共数据集上验证有效性。

链接：https://arxiv.org/abs/2606.25068

作者：Xibai Wang

英文摘要：Online time-series forecasters receive labels only after horizon-dependent delays, while every adaptation step spends limited compute. We study when an online learner should update, not how to adapt at every opportunity, and introduce ADOWIP: a residual-adapter framework with sealed delay queues, exact budget accounting, and auditable update telemetry. Its main scheduler is an observed decision-loss priority gate that updates only after feedback is revealed, when downstream loss, optionally penalized by prediction MSE, exceeds a calibrated empirical quantile and budget remains. We prove hard-budget feasibility, projected-OGD regret for a convex linear accepted-update subproblem, and stability plus conditional finite-sample gate-selection statements. On public ETT capacity-planning tasks, a frozen calibration/evaluation split selects a gate that lowers held-out decision loss against always, fixed-period, and drift-triggered exact-update baselines under matched compute. Secondary threshold/load-index ETT suites are mixed: 33 of 41 selected contrasts clear the stricter cross-artifact Holm family, and the 8 nonpassing rows are explicitly excluded from primary claims. The same protocol improves an external UCI Bike capacity proxy with 20/0 held-out wins, and a fixed gate passes three full-year Capital Bikeshare station-rebalancing contrasts. Probe-based and finance experiments remain negative, delimiting the current scope of decision-prioritized adaptation.

AI 总结：提出ASAP框架，通过智能体集成多种优化器并利用系统级优化（前缀稳定提示、推测并行、自适应调优）减少端到端挂钟时间，在多样HPO任务中优于基线。

链接：https://arxiv.org/abs/2606.25207

机构：University of Notre Dame（圣母大学）

作者：Taicheng Guo, Haomin Zhuang, Kehan Guo, Yujun Zhou, Nitesh V. Chawla, Olaf Wiest, Xiangliang Zhang

英文摘要：Hyperparameter Optimization (HPO) is essential for maximizing machine learning model performance, and its core challenge is sample efficiency: finding strong configurations within a limited budget. Because every HPO tool relies on a surrogate prior that imparts its own inductive bias, individual tools struggle once problems become sufficiently diverse and drift from these priors. Motivated by the reasoning and generalization capabilities of LLMs, recent work has explored using LLMs for HPO and reports improved per-iteration performance. Yet these methods share two limitations with a common origin: they use the LLM as a single-tool replacement evaluated by iteration count. (i) Deployed in place of prior tools, the LLM is itself constrained by its pretraining objective to one family of inductive-biased proposals; this single-source setup still fails to handle the full diversity of problems. (ii) Per-iteration evaluation ignores that, in real runs, LLM inference or tool execution is paid serially on top of model evaluation every round, so iteration-count gains do not translate into end-to-end wall-clock gains. We present ASAP, an agent-system co-design that addresses both limitations. On the agent side, ASAP uses the LLM to integrate a diverse pool of inductive-biased optimizers and to select among their proposals each round. On the system side, ASAP re-architects the loop to reduce end-to-end wall-clock while preserving regret quality: a prefix-stable prompt maximizes KV-cache reuse across rounds; speculation parallelism hides the remaining LLM and tool latency under model evaluation via a relative-error accept test; and a Self-Tuner adapts the speculation threshold from execution logs off the critical path. Extensive experiments on diverse modern HPO tasks show that ASAP consistently outperforms baselines, underscoring the value of tool integration and agent-system co-design.

AI 总结：提出弹性后训练稀疏性（EPTS）框架，通过单次优化生成单一弹性模型，支持多种稀疏度配置，解决传统方法需为每个稀疏度单独优化的效率问题。

链接：https://arxiv.org/abs/2606.25285

作者：Ke Xu, Jiaqi Wan, Wenhao Hu, Han Pu, Xiaoyun Wang

英文摘要：Post-Training Sparsity (PTS) has emerged as a crucial paradigm for compressing Large Language Models to facilitate efficient deployment on resource-constrained devices. However, existing PTS methodologies are typically confined to Single-Sparsity optimization, necessitating a separate, time-consuming optimization session for each specific sparsity level. This rigid paradigm significantly hinders flexible deployment across diverse hardware scenarios, as adapting to a new sparsity requirement mandates a complete re-optimization process. To address these limitations, we propose Elastic Post-Training Sparsity (EPTS), a unified Multi-Sparsity framework that produces a single elastic model capable of maintaining robust performance across diverse sparsity configurations through a one-shot optimization process. Specifically, we design a Multi-Sparsity Hierarchy LoRA (MS-HiLoRA) mechanism that facilitates knowledge inheritance from low- to high-sparsity groups, effectively mitigating the competition for parameter reconstruction. Furthermore, we introduce a Multi-Sparsity Feature Mixer (MSFM), which significantly enhances the model's adaptability to pruning perturbations by dynamically fusing feature representations of varying sparsity granularities. Extensive experiments on LLaMA and OPT families demonstrate that EPTS achieves competitive performance compared to state-of-the-art methods like SparseGPT and Wanda, while offering significant efficiency gains by enabling multi-scenario deployment from a single optimization. our source code is available at this https URL.

AI 总结：提出一种数据节俭的机器遗忘方法DFMU，通过单次前向和后向传播计算模型计算块的重要性分数，基于知识保留剪枝实现快速收敛，仅需13%数据样本即可达到比现有方法高40%的保留准确率，平均处理时间快88%。

链接：https://arxiv.org/abs/2606.25410

作者：Sajith U, Prateek Keserwani

英文摘要：Machine unlearning is an emerging domain that ensures the safe removal of elements (includes concepts, attributes, entity and class) from the trained model along with least drop in model performance. The domain of machine unlearning brings its own indigenous challenges since the removal of pre-trained elements from model will always degrade the model performance on remaining elements. The existing methods basically rely on retraining for removal of elements from the pre-trained model, which is compute extensive. In this work, we propose a machine unlearning method which helps to reduce the computational requirement for faster retain-dataset accuracy convergence which also does not require extensive retraining of the pre-trained model. The proposed method, Data-Frugal Machine Unlearning (DFMU) requires only a single forward and backward pass for computing the importance score of various computational blocks of a model. The importance score computation is based on knowledge preserving pruning which helps to converge faster and requires far less data as compared to the existing methods. Experimentally, it achieves 40% more retain-accuracy with just 13% of data samples in comparison with SOTA method on various public datasets and also averages 88% faster processing time for forgetting a given class.

AI 总结：本文提出通过预训练数据策展诱导视觉语言模型输出简洁答案，从而降低推理成本，在保持精度的同时实现35倍成本优势。

链接：https://arxiv.org/abs/2606.25432

机构：DatologyAI

作者：DatologyAI: Matthew L. Leavitt, Siddharth Joshi, Haoli Yin, Rishabh Adiga, Haakon Mongstad, Alvin Deng, David Schwab, Bogdan Gaza, Ari Morcos

英文摘要：Inference efficiency is typically pursued by shrinking the model: distillation, pruning, quantization, and sparse routing each lower per-token cost while treating token count as fixed. But output length has been inflating, and it is precisely the component the standard toolkit leaves untouched. Here, we argue that brevity is the missing inference-efficiency lever, and that pretraining data curation is a practical way to pull it: a model trained on concise, correct data learns to answer in fewer tokens; i.e. it has a lower Cost-of-Pass. We apply our VLM curation pipeline to the MAmmoTH-VL single-image subset, and compare models trained on our curated data, the standard MAmmoTH-VL data, and external open-weight frontier VLMs. On a controlled 20-evaluation set and 14 VLMs at 1B-4B activated parameters, we hold output length fixed with a per-model regression, separating brevity from quality, and price models in FLOPs per correct answer. Curation buys a 35x Cost-of-Pass advantage over the most verbose 4B comparator (Qwen3.5-4B) within $\sim$1 pp of accuracy (0.41 vs 14.58 TFLOPs per correct answer; 0.691 vs 0.704 mean accuracy). Curation also buys a +17.55-percentage-point matched-length accuracy gain over the uncurated baseline that grows with model scale (from +16.7 pp at 1B to +21.2 pp at 4B). This brevity improvement concedes no quality: generic verbosity buys no accuracy at any capability or scale, and the window where reasoning-structured verbosity still earns its tokens shrinks from 4 of 8 capability groups at 2B to 1 of 8 at 4B. Per example, the concise model even reaches correct answers the verbose reasoning model misses, marking reasoning as a distinct curation target rather than something brevity gives up. Inference efficiency in this regime is a tokens-per-correct problem, and brevity is the lever that targets it directly.

AI 总结：提出IF-Beta框架，结合影响函数与可学习Beta分布采样策略，通过双层优化实现高效数据剪枝，在减少数据和计算量的同时提升蒸馏性能。

链接：https://arxiv.org/abs/2606.25488

机构：School of Data Science, Fudan University（复旦大学数据科学学院）； Faculty of Engineering, The Chinese University of Hong Kong（香港中文大学工程学院）； College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院）； School of Computer Engineering and Science, Shanghai University（上海大学计算机工程与科学学院）

作者：Yifan Wu, Yiqi Wang, Xichen Ye, Wenjing Yan, Xiaoqiang Li, Cheng Jin, Xiangyu Yue, Weizhong Zhang

英文摘要：Knowledge Distillation (KD) is widely used to obtain compact models for efficient inference in resource-constrained environments. Yet the computational overhead of the distillation process itself is often overlooked, raising the question of whether a better student model can be obtained with less data and less compute via data pruning. However, existing data pruning methods are not designed for KD: some introduce substantial overhead, such as obtaining training dynamics through retraining, while others rely on heuristic selection rules that fail to capture what KD actually requires, often resulting in suboptimal subsets. To address these issues, we propose IF-Beta, an efficient data pruning framework that combines influence functions with a learnable sampling policy. Empirically, we first demonstrate that influence functions can serve as an effective and efficient estimator of sample impact in KD settings, where only a pretrained teacher is available. Building on this, our sampling policy is specifically parameterized by a Beta distribution, whose highly flexible two-parameter family allows the policy to adapt to diverse pruning regimes rather than being tied to fixed heuristic forms. Next, we formulate KD pruning as optimizing this policy through a bilevel objective, where the inner loop operates in the teacher feature space with a KD-aligned objective, enabling fast proxy training, while the outer loop updates the policy parameters to maximize distillation performance. This design ensures that IF-Beta is both computationally efficient and inherently aligned with the goals of KD. Extensive experiments on CIFAR-10/100 and ImageNet show that IF-Beta consistently outperforms other baselines across a wide range of pruning ratios. Remarkably, IF-Beta enables students trained on less data and less compute to surpass the performance of students distilled on the full dataset.

AI 总结：提出HiReLC框架，通过层次强化学习实现深度神经网络的联合量化和结构化剪枝，利用Fisher信息引导的集成投票协调全局预算分配，在Vision Transformer和CNN上实现5.99-6.72倍压缩比，精度损失可控。

链接：https://arxiv.org/abs/2606.26002

机构：National School of Artificial Intelligence (ENSIA)（国立人工智能学院（ENSIA））； Cosys-Grettia, Univ Gustave Eiffel（古斯塔夫·埃菲尔大学 Cosys-Grettia 实验室）

作者：Kamar Hibatallah Baghdadi, Kawther Guoual Belhamidi, Sara Belhadj, Aissa Boulmerka, Nadir Farhi

英文摘要： We present HiReLC, a hierarchical ensemble-reinforcement learning framework for automated joint quantization and structured pruning of deep neural networks. The framework decomposes the compression search across two levels of abstraction: low-level agents (LLAs) operate independently per block, selecting per-kernel configurations over a multi-discrete action space spanning bitwidth, pruning keep-ratio, quantization type, and granularity, while high-level agents (HLAs) coordinate global budget allocation via ensemble voting guided by Fisher Information-based sensitivity estimates. To mitigate the computational cost of policy evaluation, an iterative active learning loop interleaves surrogate-guided RL optimization with post-compression fine-tuning, using a lightweight MLP surrogate to amortize expensive evaluations and a logit-MSE proxy during cold-start. The surrogate is used for reward shaping rather than as a replacement for final post-compression evaluation. The controller is architecture-agnostic by design, with a modular layer abstraction decoupling the RL environment from the underlying network topology. Experiments across Vision Transformer and CNN benchmarks demonstrate effective parameter-storage compression ratios of 5.99 - 6.72$\times$ with a 3.83 % gain in one setting and 0.55 - 5.62 % accuracy drops elsewhere, supporting hierarchical policy decomposition and sensitivity-aware guidance as practical design choices for joint neural network compression.

AI 总结：针对联邦拆分学习中的通信瓶颈，提出联合优化激活压缩与同步间隔的框架，通过延迟驱动调度器在仿真和树莓派部署中验证，在保持预测质量的同时显著降低通信负载和运行时抖动。

链接：https://arxiv.org/abs/2606.25003

作者：Wenjie Ding, Yi Sin Lin, Jiale Liu, Baoyi Liu, Guanghua Liu, Zhuolu Li, Suleiman Sabo, Chuadhry Mujeeb Ahmed, Aydin Abadi, Rehmat Ullah, Rajiv Ranjan

英文摘要：Federated split learning (FSL) enables collaborative training across bandwidth-constrained IoT devices, but repeated activation and gradient exchange creates a communication bot-tleneck. Prior work optimises either activation compression or synchronisation frequency in isolation. This paper presents an FSL framework for IoT rainfall prediction that jointly regulates activation compression and the synchronisation interval \r{ho} via a latency driven scheduler on a server with per client EMA smoothing. The system is evaluated on hourly ERA5 data from 11 weather stations through a 17 scenario simulation matrix and a four scenario Raspberry Pi deployment over a real wide-area link. The simulation matrix validates scheduler switching across low, high, and mixed latency profiles, while the Pi deployment validates the high latency endpoint selected by the same policy. AUPRC varies only slightly across configurations (0.6381-0.6484 in simulation; within 0.011 on Pi), indicating that aggressive quantisation and sparser aggregation do not materially degrade predictive quality in this setting. On Pi, the selected endpoint (int8 with rho=3) achieves an 87% reduction in activation upload payload and a 54% reduction in synchronisation traffic relative to the float32 baseline, while reducing runtime jitter from +/-688 s to +/-10 s.

AI 总结：首次系统评估图神经网络在电路设计中的梯度泄露攻击风险，发现GAT加剧泄露而GIN更具鲁棒性，并分析了现有防御技术的局限性。

链接：https://arxiv.org/abs/2606.25589

作者：Rupesh Raj Karn, Johann Knechtel, Ozgur Sinanoglu

英文摘要：As graph neural networks (GNNs) become standard tools for critical tasks in circuit design and analysis, their security and privacy risks require careful attention. Here, we present the first comprehensive evaluation of gradient leakage attacks (GLAs) on GNNs in circuit-design and hardware-security tasks, a practical threat that has been largely overlooked. We assess state-of-the-art (SOTA) GNNs, including GraphSAGE, GCN, GIN, and GAT, trained on standard netlist benchmarks (ISCAS'85, EPFL, and TrustHub), for their fundamental vulnerability to GLAs. We find that GLAs can expose sensitive information, such as gate types and distinctive properties of hardware Trojans, which may assist adversaries in analyzing logic locking schemes or evading Trojan detection mechanisms. Our analysis shows that these risks are influenced by architectural features, with attention mechanisms (GAT) exacerbating leakage, while injective aggregation (GIN) provides comparatively stronger resilience. We further evaluate several SOTA defense techniques, including differential privacy, gradient clipping, secure aggregation, model compression with quantization, and adversarial training. We find that these techniques improve resilience only in specific settings and can also compromise model performance. Overall, our work provides key insights toward privacy-preserving GNNs and highlights the need for more robust and efficient defenses. We release our full methodology and artifacts.

AI 总结：提出TL++框架，通过虚拟批次恢复中心化小批量梯度行为，采用基础模式（交换切割层激活和梯度）和安全模式（秘密共享切割层张量），在CIFAR-10和PubMedQA上超过联邦学习和分割学习基线，通信量降低13.1倍。

链接：https://arxiv.org/abs/2606.25627

机构：Neouly； Hongik University（弘益大学）

作者：Erdenebileg Batbaatar, Young Yoon

英文摘要： Distributed intelligent systems increasingly need to train across data silos without centralizing raw data. Federated learning keeps data local but can suffer under heterogeneous partitions and requires repeated full-model exchange. Split learning reduces communication through cut-layer activations, but standard protocols generally do not recover centralized mini-batch gradient behavior and may expose activations and gradients in plaintext. We present TL++, a two-mode traversal-learning framework that constructs virtual batches across nodes to recover centralized mini-batch gradient behavior under explicit synchronization assumptions. Base mode exchanges cut-layer activations and gradients rather than full models. Secure mode secret-shares each cut-layer activation and gradient between an orchestrator and a non-colluding helper, preventing either server from observing plaintext cut-layer tensors. This protection is limited to a semi-honest two-server setting; labels and loss-related outputs remain visible to the orchestrator. In the lightweight secure path evaluated here, exactness requires a linear or affine server path, while nonlinear operations require nonlinear MPC or approximation. We formalize TL++, analyze communication and computation costs, and evaluate it against federated and split-learning baselines on CIFAR-10 and BioGPT/PubMedQA using full fine-tuning and LoRA. On CIFAR-10, TL++ base cut 1 and exact secure cut 3 achieve accuracies of 91.41% (SD 0.19) and 90.93% (SD 0.17), respectively, exceeding the strongest measured non-TL++ baseline by more than 12 percentage points. TL++ base cut 1 also reduces per-step communication by 13.1-fold relative to full-model synchronization. PubMedQA results similarly favor TL++. Overall, TL++ approaches centralized-training performance while reducing communication and providing activation-level secret sharing.

AI 总结：研究物理世界模型中守恒律在潜表示学习后的可认证性，提出一种通过解码物理不变量并分解模型缺陷来预计算认证视界的方法，实验表明硬规范辛结构在已知相坐标中表现最佳，但软约束在潜表示设置中更鲁棒。

链接：https://arxiv.org/abs/2606.24945

机构：Department of Mathematics, Stony Brook University（石溪大学数学系）

作者：Hongbo Wang

英文摘要：We ask a representation-learning question about physical world models: when does a conservation law remain certifiable after a model learns a latent representation? A certified horizon bounds -- in advance, from measurable model defects -- how many steps a rollout provably stays on a physical invariant's level set. The key design choice is what is certified: not a learned latent Hamiltonian or a learned scalar witness (a model can conserve either while drifting in true energy), but the decoded physical invariant obtained by decoding the latent state and evaluating the known invariant. Around this object we derive shell-horizon certificates whose budget decomposes into representation, readout, and latent-dynamics defects, with a monotone alignment bridge through which a soft learned witness yields a certified horizon for the decoded invariant, and test them across state, learned-lift, and pixel observations on conservative systems. Conservation certificates can survive learned representation, but not all geometric priors survive equally: hard canonical symplectic structure yields the longest horizons in known phase coordinates yet does not cross a learned chart, whereas a controlled-Lipschitz-aligned soft invariant survives in the learned-representation settings we test; pixel certification is recovered on a readout-stable sub-tube; and the Kepler problem exposes a geometric boundary. The central object is therefore not a latent Hamiltonian, but a decoded physical invariant whose robustness to representation learning can be measured, certified, and falsified.

AI 总结：针对具有已知群对称性的潜在世界模型，提出一种共形校准的信任视界认证方法，利用等变性实现轨道常数认证，实验验证了其保守性和非空性。

链接：https://arxiv.org/abs/2606.24946

机构：Department of Mathematics, Stony Brook University（石溪大学数学系）

作者：Hongbo Wang

英文摘要：Learned world models are useful only over horizons on which their rollout error remains controlled. We study trust-horizon certification for latent world models with known group symmetries. Given a one-step latent residual and a finite-time expansion estimate, we form a raw horizon curve and calibrate it with a split-conformal multiplicative factor. On the reproducible audit set, the conformal factor is $\gamma_\alpha=1.0$: the raw certificate is already conservative under the audit protocol. Across 50 stable audits, we observe zero anti-conservative violations, corresponding to an exact-binomial 95% upper bound of 5.8% on the violation rate. Our main structural result is that exact equivariance transports a calibrated trust-horizon curve over the group orbit: when the environment dynamics, encoder, predictor, action transform, and latent metric satisfy the stated equivariance/invariance conditions, rollout errors and trust horizons are orbit-constant. Empirically, the implemented models exhibit small orbit-transport residuals, with median 1.1% and maximum 4.1% over 14 orbit audits. The certificate is also non-vacuous (median certified-to-measured horizon ratio 0.67). A certificate-level calibration-cost study shows two complementary regimes. On a symmetric 2D substrate, equivariant, plain, and augmented models are all orbit-valid from a single calibration sector -- no separation, because the substrate already makes non-equivariant baselines approximately orbit-robust. A 3D yaw audit shows the other regime: the equivariant model obtains a one-sector safe and non-vacuous orbit-valid certificate, while healthy non-equivariant baselines pay violation, slack, sharpness, or additional-sector cost. The certificate is a conservative, distributional audit rather than a global reachability guarantee, and certificate-guided subgoal spacing is not confirmed in the current 3D CEM-MPC behavior layer.

AI 总结：提出用谱熵量化可解释性技术引入的信号噪声，并在心电图心律失常分类中验证其有效性。

链接：https://arxiv.org/abs/2606.24974

作者：David A. Kelly, Nathan Blake

英文摘要：Explainability techniques are used to assess the output of various deep learning models. This is especially true in healthcare, where models need to be trusted and decisions justified. Explainability (XAI) tools use heuristics which often add signal noise to the explanation "core". It is not always obvious what is signal from the model and what is noise from the XAI. We propose the use of spectral entropy as a measure of noise in XAI output. We demonstrate its usefulness in the context of classifying arrhythmias in an ECG dataset with different post hoc explainability techniques.

AI 总结：研究评估多传感器融合在牛姿势分类中的鲁棒性，发现跨年评估性能大幅下降（F1从0.94降至0.49），表明常用评估高估实际性能，融合可能降低而非提升鲁棒性。

链接：https://arxiv.org/abs/2606.24986

机构：Institute of Computer Science, University of Potsdam（波茨坦大学计算机科学研究所）； Department of Sensors and Modelling, Leibniz Institute for Agricultural Engineering and Bioeconomy - ATB（莱布尼茨农业工程与生物经济研究所传感器与建模系）； Department of Data Science in Bioeconomy, Leibniz Institute for Agricultural Engineering and Bioeconomy - ATB（莱布尼茨农业工程与生物经济研究所生物经济数据科学系）

作者： Leutrim Uka, Severino Pinto, Gundula Hoffmann, Marina M.-C. Höhne

英文摘要：Automated cattle posture-classification systems frequently report near-perfect accuracy, yet their robustness under realistic deployment conditions remains largely unknown. In particular, it is unclear whether multimodal sensor fusion improves generalisation or leads models to rely on context-specific signals that fail under distribution shift. Here, we evaluate the robustness of automated posture classification (lying versus standing) using collar accelerometers, rumen-bolus sensors, and environmental measurements collected from a pasture-based beef cattle herd across two consecutive years (2024-2025). XGBoost served as the primary model, with Logistic Regression, Random Forest, and Long Short-Term Memory networks evaluated as comparative baselines. Model robustness was assessed under progressively more stringent evaluation protocols, ranging from conventional random train-test splits to leave-one-animal-out validation and cross-year evaluation on an independent cohort of previously unseen animals recorded one year later. While multimodal models achieved strong within-year performance (macro-F1 0.94), the performance declined substantially under cross-year evaluation (macro-F1 0.49). Explainability analysis revealed persistent reliance on rumen-bolus activity and environmental variables even when predictive performance deteriorated. Distribution-shift diagnostics further confirmed substantial differences in feature distributions between recording years. Our findings demonstrate that commonly used evaluation protocols can substantially overestimate real-world performance and that multimodal sensor fusion may reduce, rather than improve, robustness under temporal distribution shift. More broadly, the results highlight that benchmark accuracy alone is insufficient to assess deployment readiness and underscore the need for robustness-centred evaluation in livestock-monitoring research.

AI 总结：本研究通过引入基准测试，评估表格基础模型在六个人类肠道微生物组数据集上对三种生物启发式扰动（去除高丰度类群、稀疏化、零值注入）的鲁棒性，发现即使保留判别性特征，模型性能仍下降，零值注入破坏性最大。

链接：https://arxiv.org/abs/2606.24995

机构：IRD, Sorbonne Université, Unité de Modélisation Mathématique et Informatique des Systèmes Complexes (UMMISCO)（法国发展研究所、索邦大学、复杂系统数学建模与信息学单元）； Inria, CNRS, I3S, Université Côte d’Azur（法国国家信息与自动化研究所、法国国家科学研究中心、信息系统与软件工程实验室、蔚蓝海岸大学）； INSERM, Nutrition et Obésités（法国国家健康与医学研究院、营养与肥胖症）； Approches Systémiques, NutriOmique, AP-HP, Hôpital Pitié-Salpêtrière（系统方法、营养组学、巴黎公立医院集团、皮提耶-萨勒佩特里医院）

作者：Giulia Perciballi, Ahmad Fall, Federica Granese, Edi Prifti, Jean-Daniel Zucker

英文摘要：Tabular foundation models (TFMs) achieve strong performance on microbiome abundance data, yet their robustness under realistic distribution shift remains poorly characterized. We introduce a benchmark that evaluates the robustness of TFMs to biologically inspired perturbations across six gut microbiome datasets spanning four disease contexts. In this in-context learning setting, models receive unperturbed support sets as context and are evaluated on perturbed query samples. To isolate robustness beyond "shortcut" features, we preserve the most discriminative taxa and apply three controlled perturbation strategies: (i) removal of high-abundance (uninformative) taxa, (ii) sparsification via increased zero-inflation, and (iii) zero-imputation via spurious non-zero injections. Our results show that protecting discriminative features is insufficient to guarantee stability under support-query shift: across datasets, all perturbations degrade model performance, with zero-imputation consistently the most harmful, indicating that corrupting global feature structure can break generalization even when key taxa are retained. Sparsification disproportionately affects TFMs relative to a classical random forest baseline, suggesting greater sensitivity to zero-inflation-type shifts. The code is publicly available at: this https URL.

AI 总结：本文通过重训练一致性表示遗忘框架，揭示当前机器遗忘评估中输出级遗忘可能高估遗忘效果，实际存在结构化残留。

链接：https://arxiv.org/abs/2606.25001

机构：Universiti Malaya（马来亚大学）； VinUniversity

作者：Teresa Pui Yee Yong, Win Kent Ong, Chee Seng Chan

英文摘要：Machine unlearning (MU) is commonly judged by output forgetting, such as low forget-set accuracy or reduced logit-level membership inference. But if output-level success can coexist with retraining-inconsistent residuals in representation space, what kind of forgetting are current evaluations actually certifying? We study this question through retraining-consistent representation forgetting, using the retrained model (i.e., trained from scratch without the forget data) as an operational reference for correct forgetting. Across multiple unlearning methods, datasets, and models, our theoretical analysis and empirical results show that standard output-level evaluation can systematically overestimate the success of unlearning. Under this stronger lens, current methods often appear forgotten at the output layer while exhibiting a structured mismatch relative to retraining. They partially align with retraining on forget samples, remain more inconsistent on retain samples, and leave residual discrepancy concentrated along retraining-related directions rather than diffuse in representation space. This structured mismatch is characterized by forget/retain asymmetry, directional mismatch, and concentrated residuals along retraining-related directions. These results suggest that current MU is often evaluated for apparent forgetting rather than retraining-consistent forgetting. More broadly, retraining reveals what output forgetting hides.

AI 总结：提出定向锐度指标，高效可靠地指示泛化性能，比现有指标更相关且更可靠地识别泛化差的模型，并支持零知识证明认证。

链接：https://arxiv.org/abs/2606.25004

机构：Northwestern University（西北大学）； Google（谷歌）； University College London（伦敦大学学院）

作者：Gefei Tan, Adria Gascon, Sarah Meiklejohn, Mariana Raykova

英文摘要： In machine learning, model certification has been identified as an important method for gaining assurance about a model's trustworthiness and quality. A model's quality is largely determined by its ability to generalize, i.e., to perform well on data beyond what it was trained on. It is not possible to certify generalization directly, however, as it depends on unknown data and is not directly measurable. Proxies such as test accuracy can be misleading when the training process is perturbed (intentionally or accidentally), and metrics such as sharpness -- which has an empirically supported link to generalization -- are computationally expensive and can also serve as unreliable signals when training deviates from a prescribed procedure. In this work, we propose directional sharpness, a metric designed to efficiently and reliably indicate generalization despite potential training deviations. We provide empirical and analytical evidence that directional sharpness (1) correlates more strongly with generalization than existing metrics and (2) identifies models with poor generalization more reliably than existing metrics. Furthermore, directional sharpness is efficiently computable in model auditing settings, where the verifier has access to training data, and via zero-knowledge proofs that certify quality without revealing training data.

AI 总结：研究发现前沿推理模型的安全性行为并非真正基于思考，早期令牌即可预测拒绝/顺从结果，思考过程更像前缀补全而非审慎修订。

链接：https://arxiv.org/abs/2606.25013

作者：Narutatsu Ri, Abhishek Panigrahi, Sanjeev Arora

英文摘要：Today's reasoning models use thinking tokens to attain stronger performance on benchmarks than their instruction-tuned counterparts. It is also generally believed that this more "deliberative" mode should improve alignment and safety, by providing the model a safe space to consider whether its planned answer to a request violates its safety principles. We present evidence that this intuition is not always correct. Across frontier open-weight reasoning models spanning GPT-OSS, Qwen, Olmo, and Phi families, we find that the eventual refusal/compliance outcome is already strongly predictable via a trained head on the first token's hidden representation ($0.84$-$0.95$ AUROC and $\sim88\%$ balanced accuracy for predicting refusal/compliance) before any visible thinking. The thinking process turns out to be more akin to prefix completion than to deliberative revision, with the final outcome rarely changing after the first $\sim20\%$ of thinking, despite giving the appearance of deliberation at the text level ($\sim74\%$ of text-level deliberations occur when the response distribution is already locked to one refusal/compliance side). We also find that existing inference-time and training-based safety interventions, despite being motivated by the goal of inducing deliberation, largely shift model behavior toward over-refusal while suppressing already-scarce deliberation signals. Our results suggest that safety behavior in current reasoning models is much less deliberative than commonly assumed, and highlight the need for methods that induce real safety deliberation.

AI 总结：提出典型接受不变性筛查（TAIS），通过行为等价性测试验证零温度下推测解码是否泄露安全风险，实验表明在vLLM堆栈中无安全差异。

链接：https://arxiv.org/abs/2606.25097

机构：Independent Researcher（独立研究员）

作者：Sahil Kadadekar

英文摘要：Speculative decoding accelerates inference by letting a draft model propose tokens for a target model to verify, raising a concrete safety question: at temperature zero, can draft-side behavior leak into safety-scored outputs? We answer with Typical-Acceptance Invariance Screen (TAIS), a behavioral-equivalence screen that pairs target-only and speculative outputs on the same safety battery and requires byte-identity evidence, TOST equivalence at +/-3pp, and per-task Cohen's h below a calibrated null cutoff of |h| < 0.1. Applied to a 16,783-sample confirmatory core plus 44,066 matched expansion samples (fp16/bf16 execution, canonical and DPO-adversarial drafts, GPTQ-4bit drafts, two seeds, and four safety benchmarks), the tested temperature-zero vLLM stacks show no detectable safety divergence under TAIS. The largest absolute Cohen's h on matched target-only versus speculative refusal is 0.024, roughly an order of magnitude below the conventional trivial-effect floor; 25 of 27 per-task TOST contrasts pass at the +/-3pp margin (the two non-pass contrasts are capability-domain Wald-CI edge cases at identical ceiling rates, not genuine non-equivalence); the DPO-adversarial draft produces byte-identical output to the canonical draft across 4,006 samples; and bf16 changes 36%-53% of output bytes without moving any per-task safety rate outside equivalence. A separate 4,006-sample 70B production-scale probe, which lacks a matched 70B target-only arm and is therefore not counted as a TAIS pass, produces AdvBench refusal 0.839 over 700 AdvBench completions with 95% Wilson CI [0.809, 0.864]. We make no claim about sampling temperatures, untested frameworks, untested model families, or tree-speculation variants such as EAGLE and Medusa.

AI 总结：本文揭示物理信息神经网络（PINNs）在编码物理参数错误时，即使训练损失很低，解也可能严重偏离真实解，并提出一种无需重训的后验防御方法，通过扫描残差损失最小值恢复真实参数。

链接：https://arxiv.org/abs/2606.25151

作者：David McShannon, Nicholas Dietrich

英文摘要：Physics-informed neural networks (PINNs) embed governing equations in their loss function, enabling mesh-free solutions to partial differential equations. Low training loss is treated as evidence that the learned solution is physically correct. This paper shows that assumption breaks down when encoded physics are incorrect. By perturbing PDE parameters before training, a setting we describe as physics parameter poisoning or parameter misspecification, we produce models that train to low loss but give incorrect answers; we treat the perturbation schedule as sensitivity analysis rather than only as a security threat, and none of our claims requires an adversary. Achieving low residual loss does not discriminate accurate from inaccurate solutions: poisoned models reach losses at or below the clean baseline yet differ by large margins, so driving the residual down is not evidence of physical accuracy. Across three PDE systems (Burgers equation, Navier-Stokes cavity, and convection-diffusion), poisoned models match or beat the clean-model training loss while their solutions differ by up to 71% in the fixed sweep and up to 128% under adversarial search; at Cavity Re=400 the poisoned loss falls below the clean baseline. We define a detection difficulty ratio R (solution error divided by training loss) to summarize how invisible the corruption is, though cross-PDE comparison is complicated by differences in loss scale. We test six candidate defenses, none of which reliably detects corruption across all regimes. We propose a post-hoc defense: sweeping the PDE residual loss across parameter values without retraining. The loss minimum recovers the true training parameter without external data, and generalizes across all three PDE systems. The effect holds across five network architectures (8.7K to 133K parameters), is bidirectional, and is confirmed across multiple random seeds.

AI 总结：针对多模态回归中现有不确定性量化方法效率低或假设过强的问题，提出基于变分贝叶斯推断的统一框架，将分位数回归和分类恢复模型转化为解析ELBO和闭式预测密度，实现高效准确的不确定性量化，在三个大规模基准上超越现有方法。

链接：https://arxiv.org/abs/2606.25188

机构：Google（谷歌）； Google DeepMind（谷歌 DeepMind）

作者：Kun Jin, James Harrison, Jiawei Li, Sihan Liu, Jiayi Liu, Randolph Linderman, Yuening Li, Arnab Bhadury, Sourabh Prakash Bansod, Liang Liu, Jasper Snoek

英文摘要：Efficient uncertainty quantification (UQ) is essential for trustworthy large-scale learning. Existing UQ methods for regression tasks mainly operate under the assumption that the conditional label marginal satisfies single-peak parametric models, e.g., Gaussians, where the negative log-likelihood function simplifies to the mean square error. However, such single-peak assumptions fail in regression tasks featuring multi-modal distributions. On the other hand, semi-parametric methods which achieve strong regression performance for multi-modal distributions often lack efficient quantification on their prediction variances. In this work, we extend UQ techniques based on Variational Bayesian Inference (VBI) to two widely used semi-parametric regression models that yield histogram-like reconstructions of the conditional label densities: Quantile Regression (QR) and Classification Restoration (CR). Our approach introduces a unified, distribution-agnostic framework that simultaneously achieves accurate estimation of complex conditional distributions and highly efficient UQ. Theoretically, our method is grounded in novel formulations of QR and CR within the VBI framework, yielding analytic Evidence Lower Bounds (ELBO) to streamline training and a closed-form or analytically approximated predictive density for efficient inference. Empirically, we evaluate our methods on three large-scale regression benchmarks with multi-modal label distributions. Our framework outperforms state-of-the-art multi-modal regression baselines, and even matches predictive performance of computationally expensive ensemble models. Furthermore, by leveraging epistemic uncertainty estimation, our approach enables highly data-efficient active learning strategies.

AI 总结：提出一个两步基线协议，通过读取思维链生成假设并编辑环境测试假设，以区分模型行为是出于恶意意图还是良性原因，并在六个环境中验证了该方法。

链接：https://arxiv.org/abs/2606.26071

作者：Aditya Singh, Gerson Kroiz, Senthooran Rajamanoharan, Neel Nanda

英文摘要：A central goal of safety research is determining whether a model is misaligned. Prior work has largely focused on detecting concerning behavior. But behavior alone does not establish misalignment: a concerning action can arise from benign causes such as confusion. This motivates model forensics: investigating whether the action was driven by malign intent. In this paper, we propose a baseline protocol for model forensics consisting of two steps, iterated as needed. First, we read the chain of thought (CoT) to generate hypotheses about what drives model behavior. Second, we make edits to the prompt or environment to test these hypotheses. While the CoT is not always faithful, it is a rich source of unsupervised insight that can guide the collection of more rigorous evidence. To evaluate our protocol, we create a suite of six agentic environments where models exhibit concerning behavior, and apply it to each. We establish that Kimi K2 Thinking takes shortcuts due to a genuine disposition towards low-effort actions, by showing this hypothesis successfully predicts its behavior. Through counterfactual experiments, we show DeepSeek R1 deceives out of a desire to be consistent with a previous instance of itself. Our methods nonetheless leave significant room for refinement. For example, when we test whether Kimi K2 Thinking believes it is violating user intent, we find no evidence of such a belief, but without positive controls we cannot confirm our tests would detect it. Overall, we find our simple protocol provides a strong baseline that we hope future work will improve upon. More broadly, our work is a concrete step in developing the growing field of model forensics.

AI 总结：提出DCQ-GNN，利用凸-凹二次滤波器组实现高效谱选择性，通过节点自适应门控融合，在异/同配图上达到竞争性能且对结构扰动鲁棒。

链接：https://arxiv.org/abs/2606.24956

机构：School of Computing and Artificial Intelligence, Guangzhou Xinhua University（广州新华学院计算机与人工智能学院）； School of Statistics and Data Science, Guangdong University of Finance and Economics（广东财经大学统计与数据科学学院）

作者：Ranhui Yan, Jia Cai, Mengzhu Chen, Haodong Yang

英文摘要：Spectral graph neural networks (GNNs) interpret message passing as frequency-selective filtering. While low-order spectral filters are efficient, their limited selectivity often leads to weak attenuation outside the passband, whereas high-order alternatives introduce optimization challenges. We propose DCQ-GNN, a spectral GNN based on a compact bank of adaptive convex--concave quadratic filters. By restricting the filter order to two while explicitly exploiting complementary curvature, DCQ-GNN improves spectral selectivity as quantified by Dirichlet energy and entropy measures without resorting to high-order polynomial expansions. The model fuses filter outputs through a node-adaptive gating mechanism to enable node-wise structure-aware spectral selection. We provide a formal spectral analysis grounded in Dirichlet energy attenuation, von Neumann entropy, and curvature polarity, and derive explicit characterizations of filter behavior across varying levels of homophily and structural perturbations. Extensive benchmarks on 10 datasets show that DCQ-GNN ties for the top average rank (3.0) on heterophilic graphs and obtains the second-best rank (4.2) on homophilic graphs, remaining competitive with representative high-order polynomial spectral filters. Furthermore, under strong structural perturbations, DCQ-GNN exhibits substantially smaller performance degradation compared to both first-order and high-order baselines. These results demonstrate that curvature-aware quadratic banks provide a robust and efficient alternative to high-order spectral models while preserving optimization stability and computational efficiency.

AI 总结：提出SIES框架，结合显式动力学与局部智能体，学习可泛化的局部交互规则，实现图上的可控同步控制与异配图表示学习。

链接：https://arxiv.org/abs/2606.24958

机构：Zhejiang University（浙江大学）； Huzhou Institute of Zhejiang University（浙江大学湖州研究院）； National University of Singapore（新加坡国立大学）

作者：Ji Chen, Song Chen, Chengzhang Gong, Li Fan, Chao Xu

英文摘要：Collective behavior arises when locally interacting units produce coordinated global organization, from synchronization in dynamical systems to task-relevant information flow on graphs. The central challenge is not only to explain how collective behavior emerges, but to design local interaction rules that can produce desired global organization and generalize across graphs, dynamics and this http URL address this challenge, we introduce the Swarm-Inspired Emergent Synchronizer (SIES), a graph-dynamical framework that learns generalizable local-interaction laws for controllable collective organization. Each node is an agent-like dynamical unit with a state and task cue, and signed source-target-conditioned attention acts as an adaptive coupling term inside an explicit evolution model. Therefore, SIES combines an explicit dynamical engine with local agent intelligence, similar to biological swarms. For synchronization control, SIES learns a generalizable coupling operator that produces prescribed synchronization patterns for CDSs across untrained network scales, target phase relations, and intrinsic node dynamics without retraining. The learned operator also reaches gait-related modes faster than three oscillator baselines and generalizes synchronization-driven locomotion to simulated multi-legged robots of different scales and a physical hexapod after leg disablement. For graph representation learning, SIES applies the same signed interaction principle to message passing and achieves the highest performance among the compared methods on heterophilous node-classification benchmarks. Together, these results position SIES as a generalizable and learnable graph-dynamical interaction framework with promise for synchronization control, adaptive robot coordination, and heterophilous graph representation learning.

AI 总结：提出有向超图信号处理（DHGSP）框架，利用张量t-SVD定义邻接张量和有向超图傅里叶变换，在交通网络去噪任务中优于矩阵和未定向张量基线。

链接：https://arxiv.org/abs/2606.25112

机构：University of Delaware（特拉华大学）； University of Kentucky（肯塔基大学）； Institute for Financial Services Analytics（金融服务分析研究所）

作者：Carlos Mundo-Levano, Nicolás Bello, Daniel L. Lau, Gonzalo R. Arce

英文摘要：We introduce Directed Hypergraph Signal Processing (DHGSP), a unified framework that extends graph signal processing to accommodate both higher-order (polyadic) and asymmetric (directional) relationships simultaneously. Using the tensor singular value decomposition (t-SVD) within the t-product algebra, we define a novel adjacency tensor for directed hypergraphs, a topologically faithful shift operator, and a lossless Directed Hypergraph Fourier Transform (t-DHGFT). Experiments on real traffic networks demonstrate that DHGSP outperforms matrix-based (graph and digraph) and undirected tensor-based (hypergraph) baselines in denoising tasks.

AI 总结：提出通信启发的图位置编码(CIPE)，利用节点间通信性定义注意力兼容的几何结构，通过维度对齐实现高效Transformer训练，在七个基准上平均提升35.5%。

链接：https://arxiv.org/abs/2606.25293

机构：Division of Mathematical Sciences, School of Physical and Mathematical Sciences, Nanyang Technological University（南洋理工大学物理与数学科学学院数学科学部）； School of Computing, University of Kent（肯特大学计算机学院）； Department of Computer Science and Technology, University of Cambridge（剑桥大学计算机科学与技术系）

作者：Yipeng Zhang, Zhongtian Sun, Pietro Liò, Kelin Xia

英文摘要：Positional encodings (PEs) are essential for Transformers. Yet designing effective PEs for non-Euclidean graphs remains challenging. Such encodings should ideally induce an Attention-Compatible Geometry for self-attention: not merely describing graph structure, but defining a geometry whose inner products reflect meaningful structural relatedness. To realize this geometry, we propose Communicability-Inspired Positional Encoding (CIPE), built from communicability, a measure between pairs of nodes that aggregates contributions from paths of all lengths. By construction, CIPE inner products recover communicability, converting global multi-path connectivity into an attention-ready similarity geometry. For practical Transformer training, we introduce dimensionality alignment, mapping graph-size-dependent CIPE representations to prescribed dimensions while faithfully preserving the induced geometry. Empirically, CIPE improves structure-agnostic Transformers by 35.5% on average across seven benchmarks, outperforming representative PEs; it also consistently improves structure-biased graph Transformers, where competing PEs often yield only marginal benefits. These results position CIPE as a principled framework for attention-compatible graph positional encodings.

AI 总结：从生态系统视角重新定义工业级LLM持续学习为闭环更新与发布问题，识别三大挑战，提出五项生命周期设计原则，并评估其成熟度与部署蓝图。

链接：https://arxiv.org/abs/2606.24901

机构：Huawei Technologies Co., Ltd.（华为技术有限公司）； Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）； Renmin University of China（中国人民大学）

作者：Hao Jiang, Enneng Yang, Guojie Zhu, Yibin Chen, Yunkun Xu, Zifu Kou, Jiayi Li, Chong Chen, Zhao Cao, Li Shen

英文摘要： Continual learning capability is critical for Industrial LLMs, as deployed models must be continuously updated to meet evolving requirements and environments, rather than repeatedly retrained from scratch. However, most existing research focuses on improvements on static benchmarks, failing to capture real industrial needs. In this survey, we reformulate Industrial Continual Learning (ICL) for LLMs as a closed-loop update-and-release problem in a versioned ecosystem, where updates propagate hierarchically to industrial, application-specific models and LLM-powered applications, with capability inheritance and transfer across versions and model families. From this ecosystem perspective, we identify three core challenges: repeated adaptation erodes model plasticity, foundation-model upgrades break capability inheritance, and long-term sustainability is constrained by deployment requirements. We then organize the technical landscape of ICL around five lifecycle design principles: preserving plasticity headroom, treating upgrades as capability transfer, enabling trustworthy continual reinforcement learning, making training recipes self-optimizing, and building accountability as a base layer for long-term iteration. For each principle, we synthesize representative technical directions. Finally, we evaluate the maturity of each principle and its technical components via an evidence-based lens, identify key gaps hindering real-world deployment, and outline a practical ICL deployment blueprint and a pathway for feeding industrial realities back into academic research.

AI 总结：针对实际能源市场中功率预测模型面临的数据非平稳性和操作约束，提出连续功率预测范式，将预测视为持续学习问题，系统评估六种代表性持续学习方法，证明其能自适应分布漂移、积累知识并缓解灾难性遗忘。

链接：https://arxiv.org/abs/2606.24955

机构：University of Kassel（卡塞尔大学）

作者：Yujiang He, Frederic Uhrweiller, Bernhard Sick

英文摘要：Power forecasting models deployed in real-world energy markets must operate under nonstationary conditions, where data distributions continually evolve due to weather variability, infrastructure upgrades, and changing consumption behaviors. In practice, these models face strict operational constraints: historical data may be limited or unavailable for repeated retraining, and uninterrupted long-term service is often required. This paper addresses these challenges by proposing the paradigm of Continuous Power Forecasting, which views power forecasting as a continual learning problem rather than a static offline task. Based on an adaptive continual learning framework for regression, we systematically investigate the practical effectiveness of six representative continual learning approaches from three methodological categories. These approaches are evaluated under different realistic assumptions regarding data accessibility and update policies. Experimental validation on real-world power datasets demonstrates that continual learning enables forecasting models to self-adapt to distributional drift, accumulate knowledge over time, and mitigate catastrophic forgetting without relying on large-scale historical data storage. Beyond performance gains, our study provides practical insights into the stability and adaptation behaviors of different continual learning approaches under realistic operational constraints. Overall, this work illustrates how continual learning can be pragmatically integrated into industrial power forecasting pipelines, offering a scalable and sustainable solution for long-term deployment in dynamic environments.

AI 总结：提出李括号对偶性分数预测序列学习中的源域顺序，通过李括号锦标赛实现O(N log N)排序，在指令微调和DPO中达到高准确率。

链接：https://arxiv.org/abs/2606.24993

作者：John Sweeney

英文摘要：Sequential learning is order-dependent: from Pile-style next-token domain adaptation to instruction-SFT and DPO, N candidate sources induce N! possible curricula. We show that the local order effect is governed by a computable geometric quantity, the Lie-bracket commutator of gradient update fields, yielding a pairwise score for whether A->B or B->A is better for a target domain. The pairwise bracket primitive also defines a Lie-Bracket Tournament: with a shared theta_0 target-gradient reference, Hessian symmetry gives Borda/row-sum scores from one Hessian-vector product per source, O(N) dot products, and an O(N log N) sort, without materializing the O(N^2) edge matrix. Empirically, the planner reaches 98.1%/98.9% pairwise accuracy at k=1 for instruction-SFT/DPO, remains at 73.1%/72.2% at k=20, and preserves the original pretraining-domain evidence with 82.4-92.0% accuracy across four LLMs and 91.1% on diffusion. At curriculum scale, it recovers the best of all 3! schedules in 87.5% of trials, ranks 85 Stack programming-language source domains for a Python target in the 99th sampled percentile, and reaches the 99.0-99.6th sampled percentile on 56 MMLU subjects, sharply above the reported descending gradient-norm baseline. These results reframe sequential learning as a geometric tournament problem: commutators provide both local pairwise order information and a scalable primitive for many-domain schedules.

AI 总结：提出净价值每字节评分机制，在设备端智能体内存中权衡价值与危害，实现预算约束下的记忆保留、共享与信任决策，降低内存和上行带宽并防御注入攻击。

链接：https://arxiv.org/abs/2606.25115

机构：Apple（苹果）； Google（谷歌）； Microsoft（微软）； Meta； Alibaba（阿里巴巴）

作者：Beining Wu, Zihao Ding, Jun Huang, Yanxiao Zhao

英文摘要：On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights. This memory is hard-bounded and exposed: it consumes RAM and energy, reaches peers through a thin uplink, and becomes an attack surface because it is writable by what the agent reads. Existing systems each cover one part of this problem: agentic memories grow without a budget, on-device methods keep entries by success alone, and poisoning is studied mainly as an attack rather than as a memory-governance problem. We propose \sys{}, a single net-value-per-byte score that governs an agent's experience-memory lifecycle. The main idea is to let the budget act as the curator: each entry is scored as value minus harm, per byte, so one ruler decides what to keep, share, and trust. \sys{} makes three decisions: (1) \textbf{KEEP} evicts low-value bytes under the RAM and energy budget; (2) \textbf{SHARE} sends an insight only when its value exceeds its uplink cost; and (3) \textbf{TRUST} gates a peer entry by provenance. On language-model-agent task-drift benchmarks and a real heterogeneous Jetson testbed with two robot-arm nodes and a hub, \sys{} reduces memory by $2.7\times$ and uplink by $2.4\times$, drives injection success from 0.75 to zero, and raises accuracy on cases corrupted by poison or stale memory. Curating by net value reduces footprint, energy, uplink, and injection success together without reducing accuracy. In this setting, forgetting by net value improves the agent rather than weakening it.

AI 总结：针对准确率度量灾难性遗忘的局限性，提出六种基于softmax的连续度量（真实标签排名、预测置信度、分布散度），在CIFAR-100上揭示准确率无法捕捉的遗忘内部结构，并用于缓解遗忘，如作为损失权重或采样准则。

链接：https://arxiv.org/abs/2606.25165

机构：German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））； RPTU University Kaiserslautern-Landau（凯泽斯劳滕-兰道大学）； Hochschule Karlsruhe University of Applied Sciences（卡尔斯鲁厄应用技术大学）

作者：Ahmed Anwar, Andreas Wagner, Federico Raue, Tobias Nauen, Andreas Dengel

英文摘要：Accuracy degradation is the standard metric for Catastrophic Forgetting (CF), however, it records only whether forgetting occurred or not. It saturates at the extremes and collapses discretely at task boundaries, hiding the internal structure of what is being forgotten. We introduce six softmax-derived metrics spanning true-label rank (TLR), predictive confidence, and distributional divergence that characterize forgetting continuously, each normalized to [0, 1] with no modification to training. On CIFAR-100, these metrics carry information where accuracy does not: at 0% accuracy, the Confusion Margin spans an IQR of [0.32, 0.50] across classes that accuracy treats identically. We demonstrate that this richer signal is actionable in mitigating catastrophic forgetting. Per-sample metric scores used as loss weights reduce forgetting by 1.3 percentage points over uniform experience replay (ER) on CIFAR-100. Furthermore, the slope of a metric over a small window provides a stable sampling criterion: at a small-window size (e.g. 3 epochs), accuracy-trend degrades to 34.79% (std. = 2.32) while log-TLR achieves 41.07% (std. = 0.57). This gap is structural since reliable small-window trend estimation requires a continuous signal. On TinyImageNet, log-TLR trend sampling reduces forgetting by 7.7 percentage points over the ER baseline.

AI 总结：提出POLAR框架，利用预训练预测模型作为信念状态编码器，解耦表示学习与策略学习，在贝叶斯实验设计、贝叶斯优化和主动学习中实现高效自适应数据获取。

链接：https://arxiv.org/abs/2606.25197

机构：ELLIS Institute Finland（芬兰ELLIS研究所）； Department of Computer Science, Aalto University, Finland（芬兰阿尔托大学计算机科学系）； Department of Computer Science, University of Helsinki, Finland（芬兰赫尔辛基大学计算机科学系）； Department of Computer Science, University of Manchester, UK（英国曼彻斯特大学计算机科学系）； Department of Statistics, University of Oxford, UK（英国牛津大学统计系）

作者：Daolang Huang, Zhuoyue Huang, Conor Hassan, Luigi Acerbi, Samuel Kaski, Tom Rainforth

英文摘要：Learning effective policies for adaptive data acquisition remains challenging: posterior-based methods rely on surrogate models and posterior approximations that can be misspecified or biased, while direct policy-learning methods map from historical observations and fail to exploit available model representations, making learning harder. We introduce policy learning with belief representations (POLAR), based on the insight that optimal data acquisition depends on the observation history only through a sufficient belief state. Specifically, POLAR decouples representation learning from policy learning by leveraging pretrained predictive foundation models as belief-state encoders, training a policy head on top of their representations. This yields a simple, unified amortised policy learning framework for Bayesian experimental design, Bayesian optimisation, and active learning, differing only in the task-specific utility used to train the policy. Empirically, we find that POLAR outperforms state-of-the-art amortised methods across diverse tasks while requiring far fewer training samples, demonstrating a significant step in the scalability and efficiency of amortised data acquisition.

AI 总结：提出几何锚定传输框架，通过分析几何锚定和拓扑感知演化约束，在训练阶段内嵌特征传输，解决无样本类增量学习中的各向异性漂移问题。

链接：https://arxiv.org/abs/2606.25347

机构：Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology（罗切斯特理工学院切斯特·F·卡尔森成像科学中心）

作者：Hongye Xu, Bartosz Krawczyk

英文摘要：Exemplar-free class-incremental learning (EFCIL) requires stable decision boundaries within a shifting feature space. While maintaining class-conditional Gaussian statistics provides a principled classification strategy, these parametric summaries remain sensitive to anisotropic representation drift. Existing methods often transport these statistics across tasks using a decoupled, post-hoc paradigm: optimizing a backbone without explicit geometric constraints can distort the legacy manifold, limiting the precision of retroactive alignment. In this paper, we formulate feature transport as an endogenous training constraint rather than a separate post-task step, presenting the Geometry-Anchored Transport Framework. First, we derive an Analytic Geometric Anchor via Mahalanobis-aligned regression to mitigate macroscopic anisotropic drift. Second, we introduce a Topology-Aware Evolution objective that regularizes localized manifold degradation while calibrating a residual network against the analytic prior. By coupling manifold evolution with transport constraints during the primary training phase, our framework mitigates evaluation errors without requiring decoupled fine-tuning. Experiments across CIFAR-100, TinyImageNet, and ImageNet-100 demonstrate that the proposed framework consistently improves upon existing post-hoc alternatives under strict exemplar-free constraints.

AI 总结：研究将马具（工具集成脚手架）作为可控设计维度，分析其对后训练的影响，发现马具感知的后训练能提升分布内和分布外性能。

链接：https://arxiv.org/abs/2606.25447

机构：Graduate School of Artificial Intelligence, POSTECH（浦项科技大学人工智能研究生院）； Department of Computer Science and Engineering, POSTECH（浦项科技大学计算机科学与工程系）

作者：Kyungmin Kim, Youngbin Choi, Seoyeon Lee, Suhyeon Jun, Dongwoo Kim, Sangdon Park

英文摘要： Tool-integrated LLM agents are often wrapped within a harness: the scaffolding that determines which tools are exposed, how they are described, and what auxiliary information accompanies each per-step observation. While agents are routinely post-trained, this scaffolding is typically treated as a fixed engineering detail, with design effort limited to the training-free regime. Moreover, existing post-training algorithms assume a static environment, even though tool environments and tasks often shift upon deployment. To address this gap, we extend $\texttt{ALFWorld}$ (i) to treat the harness as a controllable design dimension and (ii) to support evaluation under task and tool environment shifts. Building on this, we systematically analyze how the harness design influences post-training in both in-distribution and out-of-distribution (OOD) settings. We empirically show that harness-aware post-training not only improves in-distribution performance but also enables agents to robustly adapt to OOD settings. Under a harness with minimal design effort, post-training suffers a drastic performance drop under stronger tool environment shifts, further highlighting the importance of harness-aware post-training under such shifts.

AI 总结：针对域泛化中全局不变性限制表示空间的问题，提出子集共享不变性，通过专家混合架构学习路由条件不变性，提升域外泛化性能。

链接：https://arxiv.org/abs/2606.25665

机构：VinUniversity

作者：Tien-Hung Nguyen, Tien-Dat Tran, M.-Duong Nguyen, Kok-Seng Wong

英文摘要：Domain generalization (DG) aims to learn a model from one or more source domains that generalizes to an unseen target domain without accessing target data during training. A common approach enforces invariance of representations across all source domains, assuming predictive structure is globally shared. However, we demonstrate that enforcing invariance across more domains gradually restricts the feasible representation space, discarding transferable predictive factors that are not universally shared. To address this limitation, we propose subset-shared invariance, where predictive structure is assumed stable only within domain subsets. We implement this principle with a mixture-of-experts architecture, where each expert aligns the specific domains it serves and a routing mechanism composes subset-invariant components for prediction. This creates a routing-conditioned invariance, jointly learned with the representation. To facilitate effective decomposition, we develop training objectives that encourage selective alignment, confident and balanced routing, and diverse expert specialization. Experiments on DomainBed benchmarks demonstrate improved out-of-domain generalization and greater robustness under increasing domain heterogeneity. Our results suggest that DG should move beyond enforcing a single global invariance and instead model invariance through partially shared structure across domain subsets.

AI 总结：提出饱和指数S(K)作为二元少样本分类中标注停止准则，理论证明其与协方差估计集中度及线性判别稳定性相关，实验验证其与边际精度增益正相关，并划分探索、过渡、饱和三阶段。

链接：https://arxiv.org/abs/2606.24903

作者：Arnav Gupta

英文摘要：Deciding when to stop collecting labeled examples is a fundamental but undertheorized problem in applied machine learning. The saturation index $S(K) = \operatorname{erank}(\widehat{\Sigma}_W^{(K)}) / K$ measures the ratio of the effective rank of the pooled within-class sample covariance to the shot count; we prove it falls below a threshold precisely when the covariance estimator is well-concentrated around the population covariance and the linear discriminant has stabilized. The index is computable in $O(d^3)$ time from support features alone, requiring no test labels or trained classifier. Evaluated across $N = 246$ doubling-pair observations from seventeen binary tasks and six datasets, sixteen of seventeen tasks have a positive within-task Spearman correlation between $S(K)$ and marginal accuracy gain (median $\rho = 0.811$). The pooled Spearman correlation is $\rho = 0.548$ ($p = 1.1 \times 10^{-20}$, $N = 246$). A three-phase diagram (exploration, transition, saturation) with mean marginal gains of $3.48\%$, $2.40\%$, and $0.82\%$ is supported by all pairwise significance tests ($p \leq 0.008$). As a binary stopping rule, the index achieves AUC $= 0.752$, providing meaningful probabilistic guidance for annotation decisions. Asymptotic effective rank and peak accuracy show no significant monotone relationship across tasks (Spearman $r_s = 0.380$, $p = 0.133$, $N = 17$). A small saturation index paired with low accuracy diagnoses representational inadequacy. All results are for binary classification with a fixed linear classifier; extensions to $N$-way settings and pretrained backbone representations are discussed as future work.

AI 总结：针对金融决策中价格、基本面、宏观和文本四信号联合评估的缺失，构建了涵盖4426只美股、七个任务、1130个宏观事件的基准，评估19种方法，揭示上下文特征的重要性。

链接：https://arxiv.org/abs/2606.24950

机构：KAIST（韩国科学技术院）

作者：Patara Trirat, Jin Myung Kwak, Jay Heo, Heejun Lee, Sung Ju Hwang

英文摘要：Financial decision-making is contextual: forecasting prices, valuing companies, and assessing event exposure weigh price history, accounting fundamentals, macroeconomic regime, and contemporaneous text. A benchmark over these four signals is hard to build because finance violates four assumptions of time-series evaluation: text must be gated by its publication date to prevent look-ahead, quarterly fundamentals are reported with a one- to ninety-day lag, filing text is partly redundant with the numerical statement fields it accompanies, and macroeconomic regimes leak across calendar splits. No public benchmark addresses all four signals jointly. MacroLens covers 4,416 U.S. small- and micro-cap equities over 2021-2026. Seven tasks share one point-in-time panel of prices, 46.8M XBRL accounting facts, 53 macroeconomic series, 295,860 SEC filings, and 215,882 news articles, plus a scenario layer of 1,130 macroeconomic events across 49 types automatically detected and rendered as natural language. Tasks span contextual forecasting, public and private valuation, statement generation from fundamentals and descriptions, scenario-conditioned returns, and real-estate valuation. We evaluate 19 methods across six families spanning naive heuristics through time-series foundation models, fine-tuned LLM-based time-series models, and zero-shot large language models (LLMs), plus a five-step feature-context ablation on two frontier LLMs and a gradient-boosted baseline. MacroLens is released at this https URL.

AI 总结：针对序数分类中的不确定性量化，提出基于排序概率得分的共形预测方法，自动生成中位数居中的连续预测集，在宽度与序数错误覆盖间取得平衡。

链接：https://arxiv.org/abs/2606.24959

机构：BMW Group（宝马集团）； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）； German Centre for Artificial Intelligence (DFKI, DSA)（德国人工智能研究中心）

作者：Stefan Haas, Luca Killmaier, Alireza Javanmardi, Eyke Hüllermeier

英文摘要：Ordinal classification (OC) arises in high-stakes domains such as medicine and finance, where uncertainty quantification must account for the severity of ordinal errors. Conformal prediction (CP) provides distribution-free prediction sets with marginal coverage guarantees; however, its practical effectiveness depends critically on the choice of nonconformity function. We introduce a CP method for ordinal classification based on the ranked probability score (RPS), a proper scoring rule defined over cumulative predictive distributions. Although it reflects ordinal risk quite naturally, it has largely been neglected in conformal ordinal prediction (COP). When used as a measure of nonconformity, RPS yields median-centered contiguous prediction sets by construction. The method is model-agnostic, supports both assessed and grouped ordered categorical outcomes, and permits efficient implementation compared to greedy interval selection procedures. Across multiple ordinal image and tabular datasets, RPS-based CP produces contiguous prediction sets and strikes a favorable balance between prediction set width and the magnitude of ordinal miscoverage relative to existing CP methods.

AI 总结：提出一种故障关闭认证协议，通过统计检验和部署反转条件，确保预测排行榜冠军在指定决策接口下可部署行动，避免因摩擦导致的次优部署。

链接：https://arxiv.org/abs/2606.24996

机构：Chungbuk National University（忠北大学）

作者：Geumyoung Kim

英文摘要：Forecasting leaderboards rank models by predictive quality, but their winners are often read as deployment-ready top-1 advice. That reading can fail when forecasts are passed through a fixed decision interface, such as an alert threshold, a top-k budget, or a switching-cost policy. We study when a forecast-side winner can be certified as deployment-actionable for a specified interface and deployed utility. We introduce a fail-closed certification protocol whose gates are sufficient evidential conditions for a strong claim: a friction-caused, non-tie, statistically supported, and recurrent deployment-side reversal. Traffic-Hourly provides a certified anchor: winners agree at zero friction, but positive switching friction makes the forecast winner deployed-suboptimal. A locked native audit tests overclaiming: across 22 verified candidates and 362 full-grid cells, 155 apparent forecast/deployment winner inversions are blocked before certification. The contribution is not a new forecaster, metric, or universal utility, but a conservative protocol for deciding when forecasting leaderboard winners should be read as deployment-actionable top-1 advice.

AI 总结：研究重复数据对语言模型的影响，通过无重复缩放定律量化计算等效损失，发现重复次数存在最坏点，且该点随模型规模呈幂律增长。

链接：https://arxiv.org/abs/2606.24998

机构：Stanford Computer Science（斯坦福大学计算机科学系）； Stanford Statistics（斯坦福大学统计学系）； Tel Aviv University（特拉维夫大学）； IMC Trading

作者：Jessica Chudnovsky, Joshua Kazdan, Noam Levi, Rylan Schaeffer, Yegor Denisov-Blanch, Bo He, Mehmet Donmez, Sanmi Koyejo, David Donoho

英文摘要：Language models are running out of high-quality training data, and even aggressively deduplicated corpora retain some amount of repetition. Earlier controlled studies predated Chinchilla-style scaling laws and could only measure the cost of repetition indirectly. We revisit repetition in the Chinchilla era, using a fitted no-repetition scaling law to report Compute-Equivalent Gain and Compute-Equivalent Loss. We show that under this modernized paradigm, repetition damage is systematic in three ways. First, holding compute allocated to repeated data constant, eval loss peaks at an intermediate repeat count $\Rep$; repeating a moderately sized subset a moderate number of times damages performance more than repeating a large subset a few times or a small subset many times. Second, the location of this peak is well-fit by a power law in model size; this scaling law reveals that the most damaging number of repeated data grows more quickly than compute. Finally, when repeated documents consume 10\% of the FLOPs budget in a controlled exact-document repetition setting, the compute-equivalent loss can be large: on FineWeb-Edu-Dedup, the most damaging repeat count for a Qwen3-style 344M-parameter model at $\OT=1$ matches the loss of a no-repetition run using 67% of the FLOPs. We demonstrate that these phenomena are not language-model-specific, and can be analytically understood in a simple statistical model: a misspecified linear regression with verbatim duplicates reproduces the same qualitative loss peak, quantifying how such peaks can arise from a statistical tradeoff between memorization and generalization. Our findings add precision to the study of duplication in language models, allowing practitioners to quantify the wasted compute incurred by the presence and repeat structure of duplicates in pretraining corpora.

AI 总结：提出首个基于事件相机的眼动数据集EveLoad，通过N-back引导注视范式收集20名受试者的六等级认知负荷数据，并建立基准，利用时空事件编码框架实现96.36%的个体识别准确率。

链接：https://arxiv.org/abs/2606.25177

机构：Leiden Institute of Advanced Computer Science (LIACS), Leiden University（莱顿大学莱顿高级计算机科学研究所（LIACS））

作者：Guorui Lu, Shaohua Guan, Zhen Xu, Qinyu Chen

英文摘要： Cognitive workload monitoring is important for adaptive rehabilitation and assistive interfaces, where task difficulty, pacing, and feedback should be adjusted according to the user's cognitive state to avoid overload and under-challenge. Emerging extended reality and robot-assisted rehabilitation environments provide controllable training tasks, but they require unobtrusive sensing methods that can capture rapid ocular dynamics during interaction. Existing eye-movement-based cognitive workload recognition methods mainly rely on frame-based eye trackers, which often suffer from limited temporal resolution and degraded robustness under rapid eye movements. In contrast, event cameras provide microsecond-level temporal resolution, high dynamic range and low latency, making them suitable for capturing fine-grained ocular dynamics. Many previous studies rely on free-viewing or similar paradigms, where gaze locations can vary across tasks. As a result, models may learn associations between gaze-location distributions and cognitive workload, rather than workload-related eye movement characteristics themselves. In this work, we introduce EveLoad, which, to the best of our knowledge, is the first event-based eye-movement dataset with graded cognitive workload annotations, collected from 20 healthy participants under spatially constrained and task-driven conditions using a controlled N-back-guided fixation paradigm. Based on this dataset, we establish a benchmark for cognitive workload recognition with six workload levels and propose a learning framework that encodes spatiotemporal event representations. Experimental results show that our approach achieves an average subject-specific accuracy of 96.36% and 96.13% under mixed random split evaluation. These results suggest that event-based eye movements may provide a useful sensing pathway for future workload-aware rehabilitation.

AI 总结：针对现有评估指标忽略预测信号结构特性（如振荡、相位对齐）的问题，提出拓扑驱动的TopoCast框架，通过Takens嵌入和持续同调提取拓扑保真度度量，并引入主导周期重叠指标形成局部拓扑保真度评分，揭示传统评估忽略的失败模式。

链接：https://arxiv.org/abs/2606.25439

机构：University of Moratuwa（莫拉图瓦大学）

作者：Sandeepa Weerasekara, Sandareka Wickramanayake

英文摘要：Deep learning-based models have achieved state-of-the-art performance in Time Series Forecasting (TSF), yet their evaluation remains dominated by pointwise error metrics such as Mean Squared Error (MSE), which quantify numerical accuracy but overlook structural properties of the forecast signal, including recurrent dynamics, oscillatory behavior, and phase alignment. As a result, forecasts exhibiting over-smoothing, phase shifts, or frequency distortions may achieve favorable error scores despite substantial structural degradation. To address this limitation, we propose TopoCast, a topology-driven framework for evaluating structural fidelity in TSF. TopoCast reconstructs phase-space representations of forecast and ground-truth sequences using Takens delay embedding and applies persistent homology to characterize their intrinsic dynamics. We derive four complementary topological fidelity measures from persistence diagrams and aggregate them into a Topological Fidelity Score (TFS). We further introduce dominant cycle overlap, a novel metric that maps persistent topological features to the temporal domain to assess whether dominant oscillatory patterns occur at the correct time points. Combined with TFS, this yields the Localized Topological Fidelity Score (LTFS), a phase-aware measure that captures temporal localization errors invisible to existing evaluation metrics. Experiments on five Transformer architectures across three real-world benchmark datasets demonstrate that models with similar forecasting errors can exhibit markedly different structural fidelity profiles, revealing failure modes overlooked by conventional evaluation and highlighting the value of topology-aware forecast assessment.

AI 总结：提出泛化谱框架，通过构建从精确回忆到跨语言实现转移等不同转移距离的测试变体，揭示算法从单个样本泛化到其他样本的程度，并应用于竞争编程任务评估不同学习范式。

链接：https://arxiv.org/abs/2606.25450

机构：ByteDance Seed（字节跳动Seed）； Hong Kong University of Science and Technology（香港科技大学）； Princeton University（普林斯顿大学）； University of Oxford（牛津大学）

作者：Jinghan Zhang, Zerui Cheng, Shiqi Chen, Ge Zhang, Wenhao Huang, Jiashuo Liu, Junxian He, Tianle Cai

英文摘要：Traditional evaluations measure a learning algorithm's final performance on an i.i.d. test set, reducing learning to a single aggregate score. This approach obscures a fundamental question: to what extent does learning from a specific example generalize to others? Such per-sample generalization, akin to learning by analogy in human cognition, captures how far the knowledge extracted from one example can transfer, yet remains invisible to standard benchmarks. We introduce the Generalization Spectrum, an evaluation framework designed to expose this hidden dimension. For each training example, we construct a controlled suite of test variants arranged by increasing transfer distance, from exact recall to implementation transfer across languages, context transfer under complete narrative re-framing, category-matched in-domain problems, and an unpaired baseline. By tracking performance across these distances, we reveal not just whether an algorithm learns, but how far that learning extends. We instantiate this framework on competitive programming, using a selection-and-synthesis pipeline seeded with recent problems to mitigate contamination. We first compare three canonical learning paradigms under matched memorization. RL converts memorization into near-transfer more efficiently than SFT-family baselines, while ICL exhibits strong but correspondence-dependent transfer. We then use the Spectrum to diagnose within-family variants. The resulting profiles show that local gains need not expand the generalization radius: abstractions and hints mainly lift local transfer, RFT preserves a stronger far-transfer tail than reference SFT, and self-distillation or hint-assisted RL can reduce far transfer even when local transfer or optimization improves.

AI 总结：提出跨机制基准Argus，评估27种后验不确定性量化方法在4个VLM代理和4个数据集上的表现，发现UQ排名在固定模型内跨数据集稳定，但跨模型类别和接口时下降，隐藏状态和密度方法最稳定。

链接：https://arxiv.org/abs/2606.25760

机构：University of Illinois Chicago（伊利诺伊大学芝加哥分校）； Intel Labs（英特尔实验室）； Capital One AI Labs（Capital One AI实验室）

作者：Divake Kumar, Sina Tayebati, Devashri Naik, Amanda Sofie Rios, Nilesh Ahuja, Omesh Tickoo, Ranganath Krishnan, Amit Ranjan Trivedi

英文摘要： Computer-use agents turn vision-language model (VLM) predictions into executable GUI clicks, so reliable uncertainty estimates are essential for rejection, calibration, miss-severity ranking, and spatial safety regions. Yet evidence on post-hoc uncertainty quantification (UQ) for these agents is fragmented across isolated model and dataset pairs, leaving it unclear whether UQ rankings stay stable when the agent, benchmark, or observable interface changes. We present Argus, a cross-regime benchmark for post-hoc UQ in single-step executable GUI grounding: a 27-method open-weight matrix over 4 VLM agents and 4 datasets, plus an 8-method closed-source matrix across 3 frontier vendors where logits, hidden states, and attention maps are unavailable. Evaluated methods span logit-based scores, sampling and consistency measures, hidden-state and density estimators (Mahalanobis, SAPLMA), attention-based scores, P(True) and verbalised-confidence prompting, and split-conformal prediction. The main finding is selective transfer: UQ rankings are stable across datasets for a fixed model, but degrade across model classes and observable interfaces. Hidden-state and density methods are the most stable open-weight family, while CoCoA-1MCA, Focus, sampling-based scores, and verbalised self-assessment win in specific regimes. Within-model ranking transfer is strong (Spearman rho up to 0.969), but cross-tier transfer to closed-source vendors averages only +0.08, so closed-source UQ should be reranked on the target rather than extrapolated. Conformal click regions show score-level discrimination is not enough for deployment: locally weighted disks shrink radii by 40-60% when the plug-in UQ is calibrated, but coverage degrades under calibration-test or interface mismatch. We release per-item records, calibration/test splits, UQ scores, and analysis scripts for regime-aware UQ selection in GUI agents.

AI 总结：提出一种基于高斯混合模型的患者增强方法，在嵌入空间生成逼真患者，解决医学多实例学习中的数据稀缺问题，在跨数据集迁移、低数据和非图像任务中提升性能。

链接：https://arxiv.org/abs/2606.25770

机构：Computational Health Center & Helmholtz AI, Helmholtz Munich（计算健康中心与亥姆霍兹AI，亥姆霍兹慕尼黑）； Computer Aided Medical Procedures, Technical University of Munich（计算机辅助医疗程序，慕尼黑工业大学）； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）； Department of Medicine III, Ludwig Maximilian University Hospital（路德维希·马克西米利安大学医院第三内科）； Department of Physics, Ludwig-Maximilians-Universität München（慕尼黑路德维希-马克西米利安大学物理系）； DKTK, German Cancer Consortium, partner site Munich（德国癌症联盟DKTK，慕尼黑合作站点）

作者：Muhammed Furkan Dasdelen, Fatih Ozlugedik, Anastasia Litinetskaya, Nassir Navab, Carsten Marr, Ario Sadafi

英文摘要：Data scarcity is a major bottleneck in medical Multiple Instance Learning (MIL), especially for rare diseases or expensive modalities. We introduce a statistically grounded patient augmentation approach that generates realistic patients directly in embedding space. Using Gaussian Mixture Models as a probabilistic clustering approach on pooled instance embeddings from all patients, our method learns disease-specific "recipes"-statistical distributions of instances across unsupervised clusters. New patients are then generated by sampling embeddings from clusters based on learned recipes. Unlike existing methods that require examples from all categories, our method can generate patients offline by re-mixing pooled embeddings. Generated patients are further selected based on uncertainty quantification to improve MIL performance. We evaluate our method across three clinically relevant scarcity scenarios: (i) cross-dataset transfer, where an entirely missing "healthy" class is generated using statistics from an external cohort; (ii) low-data regimes, where class sizes are extremely limited; and (iii) small-cohort non-image tasks, including single-cell RNA-seq and flow cytometry. Across all experiments, our method improves performance over baseline, often outperforming other bag-mixing strategies. Notably, in the missing-class scenario, a performance comparable to full-dataset training is achieved, demonstrating its potential for rare disease diagnostic and privacy-preserving patient augmentation. The code is available at this https URL

AI 总结：发现语言模型在预训练中学习规则后会自动遗忘，规则存亡由训练数据中支持频率决定，且遗忘不可逆。

链接：https://arxiv.org/abs/2606.26050

作者：Juliana Li, Diya Sreedhar

英文摘要：Midway through an ordinary pretraining run, a small language model learns the pronoun-gender rule: cued with a girl's name ("Sue cried because"), it resolves the next pronoun to she, generalizing to held-out probes (0.94 by step 925). By step 3,500 the same model scores near zero on the same probes, although the rule's evidence is still in the training data. We call this within-run reversal natural ungrokking: the corpus decides, with no trace in the loss curve, which learned rules a model keeps. Which rules survive is predictable from one corpus statistic: how often the training stream shows the rule winning. Across un-intervened runs (two corpora, three budgets, three seeds), support frequency decides a rule's fate; the data-to-parameter ratio only modulates how deeply a doomed rule falls. The same emerge-then-collapse dynamics appear in public Pythia checkpoints, collapse depth ordered by model scale as predicted. The forgetting is a displacement: a competing surface pattern out-competes the rule, and the log-probability margin between them crosses zero within 100 training steps of the behavioral collapse. Control over this fate is asymmetric: the same edit that destroys a rule on demand cannot restore it. Flipping support to counter-evidence in place kills the rule with monotone dose-response in two unrelated rules; but injecting support back, even to 450 times the level that naturally sustains it, buys no recovery. Every confirmatory threshold and prediction was pre-registered before the data it governed was read.

AI 总结：提出RevengeBench基准，通过行为轨迹和可控实验逆向工程LLM生成的策略代码，验证恢复质量在34-72%之间，并能提升下游对战胜率。

链接：https://arxiv.org/abs/2606.26094

机构：Tübingen AI Center（图宾根人工智能中心）

作者：Babak Rahmani, Sebastian Dziadzio, Joschka Strüber, Sergio Hernández-Gutiérrez, Matthias Bethge

英文摘要：For most of scientific history, researchers studying behavior could only infer hidden mechanisms from outward actions: an inverse problem that becomes more tractable when observation is augmented by targeted intervention. We pose a computational analogue: given only behavioral traces of an agent in a game environment, can a learner reconstruct the underlying decision program as executable code, and how much does this reconstruction improve with the ability to design controlled experiments? We introduce RevengeBench, a benchmark of 75 LLM generated, Elo-calibrated policies across five game environments, drawn from CodeClash tournament trajectories. The learner observes the hidden target policy play against sampled opponents and designs behavioral probes in the form of custom opponent policies that elicit informative behavior. It then submits an executable hypothesis, which is evaluated using continuous action-distance metrics. We further validate that recovered code carries informative signal in downstream player-versus-player tournaments. Across twelve frontier LLMs, recovery quality varies substantially (34 to 72% of initial distance closed), with reconstructed policies yielding measurable competitive advantage, particularly for weaker models that otherwise struggle to design effective counter-strategies. Our benchmark positions behavioral recovery of programmatic policies as a tractable inverse problem in code-space, opening a path to opponent modeling, policy interpretability, and the broader question of inferring latent mechanisms from observations.

AI 总结：本研究通过符号嵌入量子算法的案例，展示了人机协同发现如何将模糊研究直觉转化为具体问题、可行路线和定理族，其中AI辅助探索（包括AIM系统）在路线扩展、方案比较和框架收敛中发挥关键作用，而人类保留最终科学判断。

链接：https://arxiv.org/abs/2606.24899

作者：Yanqiao Wang, Jin-Peng Liu, Peng Li, Yang Liu

英文摘要：AI-assisted mathematics is often evaluated on solving predefined problems. In practice, however, many important advances begin earlier, when a vague research intuition is transformed into a concrete problem, a promising route, and a theorem family worth proving. This report studies that stage through a case study that led to sign-embedding quantum algorithms for matrix equations and matrix functions, foundational primitives in quantum linear algebra and operator-output quantum algorithms. The project began with a human-originated intuition that rational approximation is especially effective for jump-type functions such as the sign function, and might therefore serve as a design principle for quantum algorithms. Rather than merely assisting after the problem was fixed, AI-assisted exploration, including workflows later integrated into the agentic AI-mathematician system AIM, played a key role in expanding this intuition into a route map, comparing candidate formulations, and converging toward sign embedding as the central framework. AIM then helped connect a known matrix-sign identity to wider classes of matrix equations and matrix functions, and drafted proof and complexity calculations. The decisive scientific judgments remained human: selecting which human-AI-expanded routes were worth pursuing, rejecting a Cayley-trapezoidal approximation when its validity required a hidden condition, and refining the Sylvester implementation from a coarse quadratic-gap query route to the final factorized and scaled analysis. The report argues that human-AI co-discovery workflows, with systems such as AIM as important components, are most valuable not as standalone theorem provers, but as research partners for problem formation, connection discovery, derivation, and skeptical review inside a human-gated research loop.

AI 总结：针对数据稀缺下振动监测的故障诊断问题，提出基于强化学习的数字孪生自适应对齐方法，通过策略网络为不同故障类型生成特定仿射变换，平衡特征间隙与类间可分性，在三个数据集上验证了有效性。

链接：https://arxiv.org/abs/2606.24954

作者：Jinghan Wang, Yanjun Chen, Wei Zhang, Wentao Wu, Tianchen Liu, Gaoliang Peng

英文摘要：Vibration-based health monitoring of rotating machinery requires reliable fault diagnosis under operational data constraints, yet condition assessment remains challenged by structural scarcity of fault events and heterogeneous sim-to-real gaps in digital twin-generated signals. Each fault type generates impulses with distinct periodicity, amplitude modulation, and spectral character, making feature-space discrepancies fundamentally heterogeneous across fault classes. Existing domain adaptation methods apply a class-agnostic global transformation that cannot close all fault-specific gaps without distorting inter-class separability, while uniform source-target mixing introduces distributional noise into the data-abundant Normal class. These limitations stem from treating a sequential, state-dependent alignment problem as a one-shot optimization. Each corrective transformation simultaneously reshapes all class distributions, creating state dependencies that static gradient descent cannot resolve. We formulate feature alignment as a continuous-action Markov decision process solved via Proximal Policy Optimization, where the learned policy issues fault-type-specific affine corrections responsive to the current feature-space configuration, with a dual-objective reward balancing gap minimization against separability preservation. An asymmetry-aware strategy reserves real data for the Normal class while augmenting fault classes with policy-aligned simulated samples. Validation across XJTU-SY, CWRU, and a self-built slewing bearing testbed confirms the dominant gain from reinforcement learning-driven alignment, and cross-equipment linear probing achieves 92.8% without encoder retraining, demonstrating transferable monitoring capability.

AI 总结：提出xAARA引擎，利用动态贝叶斯网络和熵门控融合多模态模型，为中风康复提供带校准不确定性和解释的ARAT评估，实现高准确率并减少不确定性。

链接：https://arxiv.org/abs/2606.24960

作者：Tamim Ahmed, Thanassis Rikakis

英文摘要：Tailoring stroke rehabilitation requires assessing how movements are organized, not merely if they succeed. Currently, this assessment is a rate-limiting bottleneck. Instruments like the Action Research Arm Test (ARAT) compress rich behavioral observations into single ordinal endpoints, discarding the movement-quality details that distinguish recovery from compensation. Automated alternatives typically chase accuracy on noisy, single-observer labels to output opaque scores - a technology-centric approach that rarely reaches clinical practice. To address this, we present xAARA: an engine designed to augment rather than replace clinical judgment. From multi-view video, xAARA returns ARAT assessments with calibrated uncertainty and explanations across task, movement-phase, and movement-quality levels. Treating clinical scoring as an ill-posed inference problem, xAARA composes 692 calibrated multimodal models via a Dynamic Bayesian Network with entropy-based gating. It qualifies results against clinical validity rules and defers low-confidence cases. In 105 stroke survivors (788 exercises), xAARA achieved 94.2% task accuracy (Cohen's kappa=0.934) and 81.3% movement-phase accuracy (kappa=0.727), reducing predictive uncertainty by 96.1% compared to single-clinician scoring. For subjective cases, it matched at least one rater 100% of the time and never returned out-of-range scores. Four independent clinicians validated the assessments and indicated willingness to adopt the system. We argue that principled uncertainty quantification and clinician-aligned explainability are the critical bridges moving automated assessment from technical demonstration to a deployable clinical tool.

AI 总结： 研究通过句子嵌入将地质描述注入达西流反演求解器，发现文本条件使重建误差降低81%，主要来自类别级约束，而句子嵌入相比离散标签提升训练稳定性并支持开放词汇输入。

链接：https://arxiv.org/abs/2606.24967

机构：Department of Civil and Environmental Engineering, Tohoku University（东北大学土木与环境工程系）

作者：Taiga Saito, Yu Otake, Daijiro Mizutani, Sopheakpolin Mom

英文摘要：In ill-posed inverse problems, the recovered solution depends as much on the prior as on the data, yet much of the engineering knowledge that could serve as that prior is recorded qualitatively rather than in formal mathematical form. Here we test whether sentence embeddings can act as an inference-time interface for injecting geological descriptions into a learned Darcy-flow inverse solver. Across six synthetic geological classes and an exploratory transfer to a benchmark reservoir model (SPE10), we vary only the conditioning representation and find that text conditioning reduces reconstruction error by 81 % relative to a no-text counterfactual. Most of this gain comes from a categorical, class-level constraint whose value concentrates where the hydraulic head leaves the conductivity field underdetermined, while within-class geometric detail is secondary and pattern-dependent. Compared with a discrete class label, sentence embeddings add little dense-observation accuracy but improve training stability and enable paraphrase-based sensitivity analysis and open-vocabulary inputs. These results show that language priors can serve as an engineering-informatics interface for injecting geological knowledge into learned inverse solvers, while clarifying when they help and what signal they actually carry.

AI 总结：研究类不平衡与类重叠耦合时，深度学习软件缺陷预测模型的训练动力学模式，提出交互感知实验协议和模式分类法。

链接：https://arxiv.org/abs/2606.24968

作者：Emmanuel Charleson Dapaah, Philip Makedonski, Jens Grabowski

英文摘要：Context: Software defect prediction supports maintenance decisions such as testing prioritization, release-risk assessment, and quality monitoring. However, metric-based SDP datasets often contain coupled data-quality issues, especially class imbalance and class overlap. Prior work has mainly measured their impact through endpoint performance, while recent evidence suggests that such issues may also appear in neural training dynamics (gradients, weights, biases, error trajectories). However, these studies examine issues in isolation, leaving open how internal neural network training patterns manifest when data quality issues are coupled. Objective: We investigate how training-dynamics patterns from class imbalance, overlap, and their coupling can be characterized under interaction-aware conditions in deep learning-based SDP. Method: We conduct a controlled intervention study on class-level UBD datasets, training a fixed MLP under imbalance-only, overlap-only, and joint conditions across five seeds. Training dynamics are logged per epoch; fidelity is monitored via coupling ratios. Patterns are characterized using effect sizes, trajectories, sensitivity analyses, and rule-based classification. Expected contribution: The study will produce an interaction-aware empirical protocol and a candidate taxonomy of training-dynamics patterns for coupled data-quality issues in metric-based SDP.

AI 总结：提出基于混淆矩阵的动态图构建方法和混合损失函数，利用五种GNN模型进行多站点PM预测，GraphSage表现最佳，并通过GNNExplainer和PGExplainer增强可解释性。

链接：https://arxiv.org/abs/2606.24978

机构：University of Science and Technology of Oran-Mohamed Boudiaf (USTO-MB)（奥兰科技大学-穆罕默德·布迪亚夫）； King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）

作者：Abdelkader Dairi, Fouzi Harrou, Ying Sun

英文摘要：Accurate particulate matter (PM) prediction is crucial for mitigating air pollution. Graph Neural Networks (GNNs) effectively model spatiotemporal dependencies, but predefined graphs limit adaptability, and some datasets complicate learning. This study introduces a graph construction method based on a confusion matrix from a supervised learning process to dynamically capture inter-class relationships. Additionally, a hybrid loss function that combines energy distance and Huber loss is applied to address the vanishing gradient problem and improve learning stability. The approach is evaluated using air pollution data from the University of Utah AirU Pollution Monitoring Network in Salt Lake City, UT, with five GNN models: Graph Convolutional Networks (GCNs), Simple Graph Convolutional Networks (SGConv), Graph Isomorphism Networks (GINs), Graph Attention Networks (GATs), and GraphSage. The experimental results of single- and multistep predictions confirm that GraphSage achieves the highest accuracy in predicting the concentrations of PM${1}$, PM${10}$, and PM$_{2.5}$ over different time horizons. Furthermore, {\color{black} GNNExplainer (Graph Neural Network Explainer) and PGExplainer (Probabilistic Graph Explainer)} are applied to interpret feature importance and graph structure, ensuring model transparency. Results show improved prediction accuracy, with GNN models outperforming traditional machine learning \textcolor{black}{and deep learning models (i.e., Prophet, Long short-term memory, Gated recurrent units} in air pollution forecasting.

AI 总结：针对城市巡检中通信可靠性的挑战，提出基于信道知识图（CKM）的轨迹规划框架，利用扩散模型构建CKM并采用全局到局部图注意力网络软演员-评论家算法优化路径，提升轨迹效率与通信可靠性。

链接：https://arxiv.org/abs/2606.24979

作者：Yang Xiaomeng, Jia Ziye, Zhu Qiuming, Wu Qihui

英文摘要： Unmanned aerial vehicles (UAVs) are increasingly employed in urban inspection tasks, where reliable communication is critical but challenging due to the severe spatial channel heterogeneity. To address the issue, in this paper, we focus on the communication-aware path planning for multi-UAV tasks, and propose a channel knowledge map (CKM)-driven trajectory planning framework which integrates the channel modeling and trajectory decision-making. Specifically, we apply the diffusion model to construct a time-accumulated CKM and achieve the accurate perception with low flight overhead, which leverages the sparse observation data to reconstruct the high-fidelity global channel quality distribution. Based on the CKM, we propose a global-to-local graph attention network soft actor-critic algorithm. The graph attention network optimizes the complex combinatorial node ordering problem, generating an optimal and communication-aware sequence for the inspection targets. Subsequently, the soft actor-critic algorithm performs continuous action control to ensure the smoothness of the flight path and dynamically avoid communication attenuation areas. Simulation results demonstrate that the proposed method effectively guides UAVs through high-quality channel regions without dependence on real-time channel feedback, significantly improving both the trajectory efficiency and communication reliability.

AI 总结：针对可穿戴压力检测中个体差异大的问题，提出基于检索增强的轻量级个性化方法，利用冻结的基础模型从用户历史中检索相似模式生成紧凑嵌入，在WESAD数据集上准确率提升3.92%，宏F1提升4.76%，接近监督微调性能且无需标签数据。

链接：https://arxiv.org/abs/2606.24985

机构：Institut des Systèmes Intelligents et de Robotique（智能系统与机器人研究所）； Sorbonne University（索邦大学）

作者：Louis Simon, Mohamed Chetouani

英文摘要：Personalization in wearable-based stress detection remains challenging due to substantial inter-individual variability in physiological and behavioral responses. While traditional approaches rely on user-specific fine-tuning or costly self-supervised pre-training on large datasets, we propose a lightweight alternative based on retrieval-augmented personalization. Our method leverages frozen, out-of-domain foundation models to retrieve similar patterns from a target user's history and encode them into a compact personalized embedding that modulates representations extracted by a lightweight transformer network. We evaluate our approach on the WESAD stress detection dataset with N=15 users, comprising wrist-worn physiological (EDA, BVP, temperature) and activity (accelerometer) signals, and report gains of +3.92\% in accuracy and +4.76\% in macro F1-score over a non-personalized transformer baseline, approaching supervised fine-tuning performance without requiring any labeled user data. We further show that temporal retrieval, where only prior user samples are available, achieves performance close to full intra-user retrieval, demonstrating robustness to limited user history. Finally, we explore personalization in a cross-dataset retrieval setting, leveraging embeddings from the K-Emocon dataset to personalize representations for stress detection on the WESAD dataset.

AI 总结：提出低成本高阶奇异值分解（lcHOSVD），一种基于张量的稀疏传感重建框架，用于高维环境场重建，在保持多维结构的同时降低计算成本，在城市流动和空气质量数据中仅用1-4%空间位置实现低误差重建。

链接：https://arxiv.org/abs/2606.24989

机构：ETSI Aeronáutica y del Espacio, Universidad Politécnica de Madrid（马德里理工大学航空与航天工程学院）； Ove Arup（奥雅纳）； Department of Aerospace Engineering, University of Michigan（密歇根大学航空航天工程系）

作者：Arindam Sengupta, Paul Jeanney, Ricardo Vinuesa, Jose Miguel Perez, Soledad Le Clainche

英文摘要：Urban flow and air-quality simulations generate high-dimensional datasets describing velocity and pollutant transport across multiple spatial, temporal, and physical-variable dimensions. Reconstructing these fields from sparse sensor measurements is a fundamental challenge in environmental monitoring, digital twins, forecasting, and data assimilation. Existing low-cost reconstruction approaches are commonly based on matrix decompositions, which require multidimensional datasets to be flattened into two-dimensional snapshot matrices, thereby discarding important structural information. This work introduces the low-cost High-Order Singular Value Decomposition (lcHOSVD), a novel tensor-based sparse-sensing reconstruction framework for high-dimensional environmental fields. To the authors' knowledge, this is the first methodology that combines sparse sensing and HOSVD for field reconstruction. Unlike matrix-based approaches, lcHOSVD preserves the natural tensor structure of the data, enabling the exploitation of correlations across spatial, temporal, and physical-variable dimensions while substantially reducing the computational requirements of conventional HOSVD. The methodology is applied to urban flow and air-quality datasets, where three-dimensional velocity and pollutant concentration fields are reconstructed using only 1-4% of the available spatial locations. While lcSVD provides larger computational speed-ups, lcHOSVD consistently achieves lower reconstruction errors in configurations characterized by strong multidimensional coupling and heterogeneous dynamics across dimensions. Additional sensor-anisotropy analyses demonstrate that the tensor formulation is significantly more robust to uneven sensor distributions, a common situation in practical environmental monitoring networks.

AI 总结：针对高维未知系数非线性PDE，提出基于零阶导数估计的无模型深度学习方法，通过模拟器生成数据并学习解及其导数，理论分析给出非渐近误差界和样本复杂度。

链接：https://arxiv.org/abs/2606.24999

作者：Yanwei Jia, Du Ouyang, Huyên Pham, Xun Yu Zhou

英文摘要：High-dimensional partial differential equations (PDEs) with unknown coefficients arise widely in scientific machine learning, including continuous-time reinforcement learning, yet solving them efficiently in a data-driven way remains challenging. Existing deep learning solvers often rely on repeated automatic differentiation to evaluate differential operators, which can cause instability and amplify derivative errors in high dimensions, while probabilistic methods based on stochastic representations require explicit knowledge of the data-generating dynamics and therefore do not apply to black-box environments. We introduce two types of simulators as data-generating mechanisms, and take a ``representing-then-learning" approach that learns the solutions and their derivatives under settings where the underlying PDE operators are accessible only through simulations and pointwise evaluations. Our representation of derivatives relies on the zeroth-order derivative (ZOD) estimators derived from perturbed Monte Carlo trajectories. This fully model-free approach generates targets for the gradient and Hessian networks using only function evaluations. We provide a statistical learning analysis of the proposed approach, including a bias--variance tradeoff for ZODs. Assuming a standard contraction property of the underlying operator, we establish a non-asymptotic error bound that decomposes the total error into discretization error, approximation error, statistical error, and ZOD bias. Crucially, we derive the sample complexity of the learned representations in (weighted) Sobolev space, characterizing the error up to second-order derivatives. Numerical experiments illustrate the competitive performance of the method in moderate and high dimensions.

AI 总结：提出无训练框架TRACER，通过闭环结构化推理，在几何、运动学和交互约束下迭代优化事件锚定运动假设，实现与人类专家工作流一致的可解释交通事故重建。

链接：https://arxiv.org/abs/2606.25002

作者：Yanchen Guan, Chengyue Wang, Bin Rao, Haicheng Liao, Jiaxun Zhang, Shang Gao, Chengzhong Xu, Zhenning Li

英文摘要：Traffic accident reconstruction is a forensic inverse problem that requires recovering physically consistent motion from sparse and heterogeneous evidence. Existing learning-based approaches predominantly optimize for semantic plausibility or visual realism, rather than quantitative agreement with measurable geometry and dynamics. Here, we present TRACER, a training-free framework that formulates reconstruction as a closed-loop structured inference process. Instead of directly generating dense trajectories, our framework constructs and iteratively refines event-anchored motion hypotheses under geometric, kinematic, and interaction constraints, guided by structured case memory and consistency-driven diagnosis. This design enables incremental, interpretable corrections when evidence is insufficient, making the accident reconstruction process more aligned with the workflow of human experts. Experiments on real-world accident data show that TRACER achieves improved geometric fidelity, velocity consistency, and collision accuracy over both data-driven and physics-based baselines.

AI 总结：提出多流欺诈Transformer（MSFT），通过独立编码交易、登录、风险等多事件流并融合表示，在千万用户数据集上AUROC达0.996，优于单流Transformer和XGBoost。

链接：https://arxiv.org/abs/2606.25007

作者：Mohammadamin Dashti Moghaddam, Nick Sciarrilli

英文摘要：Financial fraud detection in digital banking requires reasoning over multiple heterogeneous event streams -- transactions, login sessions, risk signals -- that individually appear benign but collectively reveal fraudulent patterns. We propose the Multi-Stream Fraud Transformer (MSFT), a unified architecture that encodes each event stream with independent Transformer encoders and fuses their representations through configurable mechanisms. We conduct a systematic ablation study comparing five fusion strategies: concatenation, gated fusion, time-aware positional encoding, cross-stream attention, and a full combination. On a large-scale dataset (10M users, 1.5% fraud rate) with 85M parameter models, we demonstrate that (1) sequence models significantly outperform gradient-boosted trees operating on aggregated features (0.74 vs. 0.99 AUROC), (2) per-stream encoding is essential -- a single-stream Transformer baseline with matched parameter budget reaches only 0.82 AUROC, an 18-point gap that confirms the multi-stream inductive bias is necessary, (3) time-aware positional encoding achieves the highest discrimination (0.9961 AUROC), (4) gated fusion yields the best precision (0.989) suitable for production deployment, and (5) the risk event stream provides the strongest individual signal contribution. We further validate on proprietary production data from a digital banking platform, showing over 22% relative AUROC improvement over the XGBoost baseline.

AI 总结：提出LLM-ACES框架，利用大语言模型引导的主动闭环搜索，联合优化符号假设构建与自适应数据采集，从数据中发现常微分方程，在122个系统上取得最低中位NMSE和高达52.4%的符号准确率。

链接：https://arxiv.org/abs/2606.25039

机构：Virginia Tech（弗吉尼亚理工大学）

作者：Nikhil Abhyankar, Sha Li, Sanchit Kabra, Naren Ramakrishnan, Yulia Gel, Chandan K. Reddy

英文摘要：Recovering governing Ordinary Differential Equations (ODEs) from data is a central challenge in modeling dynamical systems across scientific domains. Existing approaches cast discovery as a static inference problem over fixed datasets, assuming that the observed trajectories are sufficiently informative. However, dynamical systems evolve over large state spaces, and limited data can make multiple equations observationally indistinguishable, leading to identifiability gaps and the recovery of incorrect governing equations. To address this, we introduce LLM-ACES, or LLM-guided Active Closed-loop Equation Search, a closed-loop framework that jointly optimizes symbolic hypothesis construction and adaptive data acquisition. In LLM-ACES, a large language model (LLM) proposes operator priors that partition the large search space into distinct regions, within which candidate equations are fit to the observed data. The disagreement among these candidates guides the acquisition of informative trajectories, creating a feedback loop that iteratively refines both the hypothesis space and the discovered dynamics. On 122 ODE systems spanning ODEBench and ODEBase, LLM-ACES achieves the lowest median NMSE, outperforming state-of-the-art baselines by several orders of magnitude while achieving a high symbolic accuracy of 46.2% and 52.4%, respectively. Our analysis further shows that LLM-ACES is sample-efficient, achieving better performance with one-tenth the data. Furthermore, LLM-ACES's feedback-driven data acquisition makes it robust to noise and recovers the correct symbolic structure, while baselines introduce spurious terms that fit the data locally but obscure the true governing relationships.

AI 总结：提出迭代能量Transformer（iEBT），通过嵌入多模态预测器并迭代更新目标向量，从Sentinel-1和Sentinel-2时序数据中联合反演土壤水分、叶面积指数和株高，在印度瓦拉纳西实测数据上取得高精度，并利用终端能量作为质量诊断指标。

链接：https://arxiv.org/abs/2606.25174

作者：Shubham Kumar Singh, Peilei Fan, Suraj A. Yadav, Rajendra Prasad, Prashant K Srivastava

英文摘要： Field-scale retrieval of surface soil moisture (SM), leaf area index (LAI), and plant height (PH) is essential for precision agriculture, yet it remains an ill-posed inverse problem. Concurrent variations in soil moisture and canopy density generate substantial ambiguities in radar backscatter and spectral responses, which reduces the effectiveness of traditional feedforward regression models in heterogeneous smallholder cropping systems. This study presents the Iterative Energy-Based Transformer (iEBT) for the joint retrieval of coupled soil-canopy states from Sentinel-1 C-band SAR and Sentinel-2 multispectral time series. Instead of direct regression, iEBT embeds multi-modal predictors within a shared sequence, produces an initial state estimate, and iteratively updates the target [SM, LAI, PH] vector through normalized gradient descent to minimize a learned scalar compatibility energy function. Using 700 quality-controlled field measurements from Varanasi, India, iEBT achieved the highest learned-model performance on the random test split, with a four-seed mean R^2 of 0.854 \pm 0.012 (R_SM^2 = 0.841, R_LAI^2 = 0.905, R_PH^2 = 0.821). WCM and PROSAIL were retained as physically interpretable SAR and optical reference models for comparison. Modality ablations confirmed that Sentinel-1 drives SM retrieval, while Sentinel-2 dominates LAI, whereas PH relies on combined structural-phenological signatures. Crucially, the model's terminal energy functions as an uncalibrated post-retrieval quality diagnostic; screening the 10% highest-energy samples markedly reduced target level root-mean-square errors. While leave-one-campaign-out validation highlights persistent cross-season domain shift challenges due to localized management variations, compatibility-guided multimodal fusion offers a structured self-diagnostic path toward reliable biophysical parameter estimation

AI 总结：提出基于神经算子的数据驱动框架，从稀疏纵向PET数据学习反应扩散动力学，预测淀粉样蛋白-β和tau蛋白时空演化，并优化个性化治疗策略。

链接：https://arxiv.org/abs/2606.25185

机构：Pennsylvania State University（宾夕法尼亚州立大学）； University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）

作者：Xiaofeng Xu, Tingting Dan, Zifan Zhou, Bin Li, Guorong Wu, Wenrui Hao

英文摘要：Accurately predicting the spatiotemporal evolution of amyloid-$\beta$ and tau proteins at the individual level is critical for improving the diagnosis and treatment of Alzheimer's disease. We consider the problem of constructing patient-specific digital twins that model the propagation of these biomarkers on the cortical surface using reaction--diffusion dynamics. A major challenge is that the underlying nonlinear aggregation mechanisms are unknown and must be inferred from sparse, noisy, and heterogeneous longitudinal PET imaging data. To address this, we develop a data-driven framework that learns biomarker dynamics directly from clinical observations. The approach combines operator learning with reduced-order representations to infer governing equations of disease progression from data. Using this framework, we achieve predictive accuracies of 87\% for amyloid-$\beta$ and 81\% for tau. Building on the learned dynamics, we further formulate a PDE-constrained optimal control problem to design personalized therapeutic strategies that regulate pathological protein propagation. By integrating data-driven dynamical modeling with treatment optimization, the proposed digital twin framework provides an interpretable and predictive platform for understanding disease progression and enabling precision interventions in neurodegenerative disorders.

AI 总结：提出混合CNN-LSTM入侵检测框架，结合CNN空间特征提取与LSTM时序建模，解决多步攻击时序建模不足、类不平衡和泛化性差问题，在CICIDS-2017和NSL-KDD上精度达98.2%以上，并实现低延迟实时推理。

链接：https://arxiv.org/abs/2606.25200

作者：Sajib Debnath, Remon Das

英文摘要：The accelerated digitalization of renewable energy smart grids through IoT sensors, AMI, and SCADA systems has significantly expanded the attack surface for sophisticated cyberattacks, FDI attacks that stealthily distort state estimation and DoS/DDoS attacks that flood communication channels. Current IDS, however, exhibit three inherent limitations: inadequate modeling of the temporal progression of multi-step attacks, degraded scalability under extremely skewed class distributions of standard benchmark datasets, and restricted generalization across heterogeneous network environments. In this study, we present a Hybrid CNN-LSTM IDS that jointly exploits CNN-based spatial feature extraction and LSTM-based temporal sequence modeling, enabling the detection of instantaneous volumetric anomalies and gradually evolving low and slow-attack campaigns in real time. The model was trained using a seven-step preprocessing workflow comprising missing-value imputation, min-max normalization, one-hot encoding, SMOTE class balancing, mutual-information feature selection, causal temporal sequence construction (T=10), and stratified partitioning. LSTM (96.1%), Random Forest (93.5%), SVM (91.2%) and KNN (89.7%); in NSL-KDD, it reaches 98.2% precision versus 96.4% (LSTM), 95.2% (CNN), 92.7% (Random Forest) and 90.8% (SVM), with margins of 2-9 percentage points in all measures. An ablation analysis identified SMOTE balancing as the most influential design choice (-3.7~pp F1 without it). The model achieves a real-time inference throughput of 27,800 flows/s on GPU and 0.082 ms/sample CPU latency in FP32,, with INT8 quantization providing an additional 3.1 x speedup at 0.3% accuracy loss, confirming deployment feasibility on resource-constrained IEDs with <128MB memory and establishing a deployable deep-learning framework for securing next-generation renewable energy smart grid infrastructure.

AI 总结：本文首次将逆强化学习应用于击键动力学，从帕金森病患者打字行为中恢复可解释的奖励函数，发现速度偏好权重与UPDRS-III严重程度显著相关。

链接：https://arxiv.org/abs/2606.25270

机构：Institute of Health Informatics, University College London（伦敦大学学院健康信息学研究所）

作者：Navin Bondade

英文摘要： Keystroke dynamics have been explored extensively as a passive digital biomarker for Parkinson's disease (PD), typically by extracting summary statistics from typing timing and training a classifier to discriminate PD from healthy controls. We instead apply inverse reinforcement learning (IRL) to keystroke data, modeling each keystroke as a discrete choice over typing speed and recovering, per subject, an interpretable reward function that explains their observed timing behavior. To our knowledge this is the first application of IRL to keystroke dynamics. On the public neuroQWERTY MIT-CSXPD dataset (85 subjects, 42 with PD), an initial four-parameter reward decomposition (speed, effort, smoothness, hand-alternation cost) was found to suffer severe feature collinearity between two terms ($r=1.000$ in typical contexts); we diagnose and correct this, yielding an identifiable three-parameter model. The recovered speed-preference weight correlates with UPDRS-III severity at $r=-0.607$ ($p<0.001$, $n=42$), replicates independently across two sub-cohorts, is stable across nine sensitivity configurations, and retains a statistically significant contribution beyond raw typing speed alone (incremental $R^2$ from 0.194 to 0.338, $p=0.006$). Two other recovered weights (consistency, hand-alternation) did not survive confound checks and are reported as negative results. We document two implementation bugs found during adversarial code review (session-boundary contamination, a rolling-window data leakage) and show the headline result is materially unchanged after fixing both. We discuss this result in the context of a literature where reported accuracies vary widely between studies (pooled AUC 0.85, I^2=94% in a 2022 meta-analysis), and argue that the validation process itself, not only the correlation coefficient, is part of the contribution.

AI 总结：提出CPTabKAN模型，通过概念编码、二阶多项式交互和傅里叶参数化TabKAN分类器，在睡眠EEG数据上实现MCI检测，F1达0.9038。

链接：https://arxiv.org/abs/2606.25434

机构：Computer Science Department, University of Kentucky（肯塔基大学计算机科学系）； Institute for Biomedical Informatics, University of Kentucky（肯塔基大学生物医学信息学研究所）

作者：Yosef Bernardus Wirian, Qiang Cheng

英文摘要：Early and scalable detection of mild cognitive impairment (MCI) remains an unresolved clinical challenge. Existing EEG-based screening approaches are constrained by handcrafted feature pipelines that discard neurophysiologically meaningful domain structure and deep learning classifiers that sacrifice interpretability for performance. No existing work unifies physiologically organized concept encoders, cross-concept interaction modeling, and nonlinear tabular classification in a sleep EEG-based MCI detection framework. This study proposes Concept-guided Polynomial-transformed Tabular learning using Kolmogorov-Arnold Network (CPTabKAN), which maps heterogeneous EEG-derived features into domain-informed concept representations, expands them via degree-2 polynomial transformation to expose first- and second-order interactions, and applies a Fourier-parameterized TabKAN classifier to learn nonlinear decision boundaries. CPTabKAN was evaluated on the Study of Osteoporotic Fractures cohort (372 subjects, overnight polysomnography), using 1,379 features organized into ten physiologically motivated concept groups. Under 10-fold cross-validation, CPTabKAN-Second Order achieved a weighted F1-score of 0.9038 (SD 0.034), outperforming GradientBoosting by 5.65 percentage points (t(9)=1.934,p=0.043, one-sided paired test), with advantages persisting under SMOTE-based balancing. Ablation analysis confirmed independent contributions from each component. Concept importance analysis revealed that power spectral density, multi-scale entropy, and Hjorth parameters dominated first-order weights, while cross-concept interactions involving Lempel-Ziv-Welch complexity, statistics, demographics, and slow oscillations exceeded all first-order scores. These results demonstrate that concept-structured, interaction-aware tabular learning surfaces physiologically coherent reasoning, supporting clinical trust.

AI 总结：本文从数据视角研究蜂窝负载预测，提出结合人口动态（潜在流量源数量及其移动性）与历史时间序列，在高速场景下预测误差降低约60%。

链接：https://arxiv.org/abs/2606.25709

机构：Academy of Finland（芬兰科学院）； Centre of Excellence in Randomness and Structures（随机性与结构卓越中心）； Aalto Science-IT project（阿尔托大学科学IT项目）

作者：Natalia Vesselinova, Pauliina Ilmonen

英文摘要：Mobile cellular load forecasting is native to network resource optimization and delivery of services with reliability, latency and quality guarantees. The mainstream of machine learning research in the area is focused primarily on developing powerful learning structures for improved prediction accuracy. The data used for forecasting traditionally belong to the cellular domain and at most contain exogenous information about the surroundings of the base stations. We approach the prediction task from the perspective of data as a vital component of any data learning process. We hypothesize that substantial improvements could be achieved when the data inform on the processes that create the cellular load. Specifically, we propose to characterize the population dynamics -- the potential number of cellular traffic sources and their mobility -- in addition to employing historical time series of mobile data traffic. We validate our hypothesis for the rarely examined highway scenario. Comprehensive experiments show forecasting improvements on the order of $60\%$ due to the use of these data alone.

AI 总结：提出一种基于梯度方法的极紫外掩模逆光刻技术，利用可微波导方法和波导神经算子作为端到端物理引擎，通过自动微分恢复掩模吸收体介电常数，实验验证了在多种材料下实现所需晶圆场。

链接：https://arxiv.org/abs/2606.25753

机构：University of Nizhny Novgorod（下诺夫哥罗德大学）

作者：Vasiliy A. Es'kin, Egor V. Ivanov

英文摘要：Gradient-based inverse lithography technology~(ILT) for extreme ultraviolet~(EUV) masks is presented. A novel framework treats the differentiable waveguide method and the recently proposed waveguide neural operator~(WGNO) as end-to-end physics engines, recovering the permittivity of the absorber of the mask through automatic differentiation of the full forward diffraction model. Numerical experiments on realistic 2D and 3D absorbers of the mask (TaBN, La, U) at $\lambda{=}11.2$~nm show that the considered ILT methods make it possible to obtain a mask structure that achieves the desired field on the wafer.

AI 总结：提出因果感知的生成框架OncoSynth，通过扩散序列建模协变量对治疗分配及治疗对生存的影响，在肺癌和乳腺癌队列中实现高保真合成，将群体和个体治疗效果估计误差分别降低66%和58%。

链接：https://arxiv.org/abs/2606.25762

机构：LMU Munich（慕尼黑大学）； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）； Department of Applied Mathematics and Theoretical Physics, University of Cambridge（剑桥大学应用数学与理论物理系）； Department of Public Health and Primary Care, University of Cambridge（剑桥大学公共卫生与初级保健系）； Cambridge Centre for AI in Medicine, University of Cambridge（剑桥大学剑桥医学人工智能中心）； The Alan Turing Institute（艾伦·图灵研究所）

作者： Octavia-Andreea Ciora, Julian Welzel, Dennis Frauen, Maresa Schröder, Marie Brockschmidt, Harry Amad, Thomas Callender, Mihaela van der Schaar, Stefan Feuerriegel

英文摘要：In oncology, access to patient-level data is often restricted. Synthetic data provides an alternative for analyzing treatment effectiveness, but existing methods for synthetic data generation fail to preserve the causal relationships between covariates, treatments, and outcomes, thereby leading to biased estimates of treatment effects. Here, we introduce OncoSynth, a generative, causally-aware machine learning framework designed to produce synthetic cohorts that enable accurate estimation of population- and patient-level treatment effects. OncoSynth uses a diffusion-based sequential approach to model how covariates influence treatment assignment and how treatment affects survival. We evaluate OncoSynth using large lung (N = 37,128) and breast cancer (N = 17,046) cohorts. Our results show that OncoSynth generates high-fidelity synthetic patient cohorts that preserve real-world patient, treatment, and outcome distributions. Notably, OncoSynth improves treatment effect estimation over existing approaches, by reducing population-level treatment effect error by up to 66%, and patient-level treatment effect error by up to 58%. Thereby, OncoSynth supports reliable evidence generation for precision oncology in settings where data sharing is restricted.

AI 总结：研究限价订单簿预测中的推理-计算前沿，发现幂律关系，并基于此提出延迟高效的FastBiNLOB架构，在低延迟下超越现有SOTA。

链接：https://arxiv.org/abs/2606.25986

机构：Independent Researcher（独立研究员）

作者：C. Evans Hedges

英文摘要：We study whether a scaling-law-style inference-compute frontier appears in limit order book prediction. Using FI-2010 and a suite of models ranging from small decision trees to neural LOB architectures, we find that the realized empirical frontier of predictive loss versus structural forward work is well summarized by a power law. In particular, with MLPLOB held out as an architecture family, a power-law fit to the low- and mid-compute non-MLPLOB frontier extrapolates across multiple orders of magnitude and attains $R^2=0.941$ on the excluded high-compute MLPLOB target frontier. A similar exercise in latency space gives substantially weaker results, showing that latency is not merely noisy compute. We use this gap to motivate FastBiNLOB, a dense axis-separable LOB mixer built from hardware-friendly temporal and feature mixing operations. In a five-seed experiment, FastBiNLOB exceeds the published $y_{10}$ and $y_{100}$ macro-F1 targets at notably lower latency than existing published SOTA architectures.