机器学习学术速递[7.3]

AI 总结：提出M-QCDNet，将Q矩阵作为结构先验嵌入神经网络，通过带L2惩罚的损失函数平衡预测性能与结构对齐，实现可解释的认知诊断。

链接：https://arxiv.org/abs/2607.01278

作者：Yiyao Yang

英文摘要：The research proposes a multilayer Q-matrix-embedded neural network for cognitive diagnosis (M-QCDNet), which integrates the structural interpretability of cognitive diagnostic models (CDMs) with the deep learning neural network (NN). M-QCDNet structures the item-skill relationship using the Q-matrix as a structural prior, ensuring latent mastery profiles remain interpretable and consistent with cognitive theory, followed by the proposed loss function with an L2 penalty to penalize skills not aligned with the Q-matrix and to balance predictive performance and structural alignment. Corresponding evaluation matrices, the interpretable alignment-based metrics that quantify the degree to which predicted skill activations correspond to item-level skills, were further developed. M-QCDNet offers practical benefits for classroom practice, enabling early detection of learning difficulties and supporting mastery-based interventions. By embedding diagnostic validity into model design, M-QCDNet bridges psychometric transparency and neural flexibility, advancing interpretable, fair, and actionable AI for cognitive diagnostics.

AI 总结：提出SpinGTP方法，通过从标量函数推广到自旋加权球谐函数，在保持渐近效率的同时恢复Gaunt张量积缺失的反对称路径，实现完整且可扩展的E(3)-等变网络，在手性材料和非中心对称几何任务中表现优异。

链接：https://arxiv.org/abs/2607.01408

机构：Department of Computer Science and Engineering, Texas A&M University（德克萨斯农工大学计算机科学与工程系）； Lambda, Inc.（Lambda公司）； Department of Materials Science and Engineering, Texas A&M University（德克萨斯农工大学材料科学与工程系）； Department of Electrical and Computer Engineering, Texas A&M University（德克萨斯农工大学电气与计算机工程系）； Department of Physics and Astronomy, Texas A&M University（德克萨斯农工大学物理与天文学系）； Department of Mechanical Engineering, Texas A&M University（德克萨斯农工大学机械工程系）

作者：Chenxing Liang, Yuchao Lin, Andrii Kryvenko, Wendi Yu, Chuan Li, Jianwen Xie, Xiaofeng Qian, Shuiwang Ji

英文摘要：$\mathrm{E}(3)$-equivariant networks are promising for 3D atomistic system modeling, yet their scalability is limited by the $O(L^6)$ complexity of the Clebsch-Gordan Tensor Product (CGTP). The recently proposed Gaunt Tensor Product (GTP) reduces the complexity but is unable to capture the antisymmetric paths, resulting in incomplete expressivity. In this work, we present SpinGTP, an approach to overcome the GTP incompleteness by generalizing from scalar functions to Spin-Weighted Spherical Harmonics (SWSH). By relying on the algebraic properties of SWSH, SpinGTP recovers the missing antisymmetric interactions while maintaining the asymptotic efficiency of GTP. It also allows for a more expressive equivariant basis that naturally accounts for the parity-odd components of tensor products. We evaluate SpinGTP across diverse benchmarks, including Tetris, 3BPA, SPICE-MACE-OFF, and OC20. Our results show that SpinGTP achieves accuracies comparable to full CGTP. Notably, by explicitly capturing antisymmetric paths, SpinGTP exhibits superior performance in tasks involving chiral materials and non-centrosymmetric geometries. This work provides a complete, scalable, and mathematically rigorous path toward high-order equivariance in large-scale 3D atomistic system simulations.

AI 总结：提出GRS-KAN混合架构，将R函数集成到KAN中，通过可微逻辑运算编码几何约束，在回归任务中相比标准KAN测试RMSE降低高达67%，并提升可解释性。

链接：https://arxiv.org/abs/2607.01449

机构：Imperial College London（帝国理工学院）

作者：Sergei Kucherenko, Nilay Shah

英文摘要： We propose a novel hybrid neural architecture, the Geometry-aware R-Structured Kolmogorov-Arnold Network (GRS-KAN), which integrates this http URL 's R-functions into the Kolmogorov-Arnold Network (KAN) framework. The proposed approach combines two complementary modeling mechanisms: smooth nonlinear structure is learned by KAN branches, while known geometric or logical constraints are encoded analytically using differentiable R-functions. This enables explicit representation of discontinuities, feasible regions, and implicit geometric boundaries within a trainable neural architecture. The framework implements differentiable logical operations through R-conjunctions and R-disjunctions, allowing complex geometric supports to be represented analytically and incorporated directly into regression models. Several GRS-KAN variants are introduced, including additive, multiplicative, and agnostic branch-weighted architectures. The method is demonstrated on regression problems involving discontinuities with circular and rectangular supports. Numerical experiments show that explicit geometric encoding substantially improves predictive accuracy and boundary localization compared with standard KANs. In the considered benchmarks, geometry-aware GRS-KAN models reduce test RMSE by up to 67% while simultaneously improving interpretability through explicit analytical representation of the learned geometric structure. The agnostic variant further demonstrates the ability to automatically determine whether geometric priors are beneficial for a given learning task.

AI 总结：针对递归记忆智能体在长上下文中性能退化问题，提出多头递归记忆（MHM）框架，通过分阶段选择-更新策略隔离记忆头，显著提升记忆保持率和端到端准确性。

链接：https://arxiv.org/abs/2607.01523

机构：Department of Computer Science, University of Wisconsin-Madison（威斯康星大学麦迪逊分校计算机科学系）

作者：Jiatong Li, Samuel Yeh, Sharon Li

英文摘要：Recurrent memory agents extend LLMs to arbitrarily long contexts by iteratively consolidating input into a fixed-size memory window. Despite their scalability, these agents exhibit a well-documented reliability problem: end-to-end performance degrades systematically as context length grows. We diagnose this failure by decomposing performance into two factors--memory capture and memory retention--and quantitatively confirm that retention is the dominant bottleneck. Retention collapses because existing designs maintain memory as a monolithic text block, forcing every update to risk overwriting previously retained content. Motivated by this diagnosis, we propose Multi-Head Recurrent Memory (MHM), a general, training-free framework that partitions memory into independent heads governed by a stage-wise select-then-update strategy. At each step, exactly one head is selected for update while the remaining heads are structurally shielded from overwriting, shifting the burden of retention from model behavior to architectural design. As a lightweight instantiation, we introduce Least-Recently-Updated MHM (MHM-LRU), which guarantees uniform head utilization with zero additional token overhead. Extensive experiments on long-context benchmarks show that MHM-LRU substantially improves both retention and end-to-end accuracy across the 100K--1M token range, where baselines degrade sharply. On RULER-HQA at 896K tokens, MHM-LRU improves the memory retention rate from less than 30% to 73.96%. These gains generalize across model families, scales, and task types, positioning architectural optimization as a practical and cost-efficient path toward reliable long-context recurrent memory.

AI 总结：提出将模型合并视为概率推断问题，基于专家乘积框架，通过柯西分布捕获重尾残差，提升多任务合并性能。

链接：https://arxiv.org/abs/2607.01689

机构：Washington State University（华盛顿州立大学）； Hanoi University of Science and Technology（河内科技大学）

作者：Long Minh Bui, Tuan Anh Le Van, Tung Phi Duc, Phi Le Nguyen, Jana Doppa, Trong Nghia Hoang

英文摘要：Model merging aims to combine existing single-task solutions into a multi-task solution without additional data-driven fine-tuning.~Most existing approaches achieve this using geometric properties of local solution spaces. However, such geometric views provide limited guidance for scoring how statistically useful each task-specific update direction is across tasks during merging. To address this, we formulate model merging from a new perspective of probabilistic inference under a product-of-experts (PoE) scenario where each single-task solution defines an energy-based expert model (EBM) over the merged parameters. We show that several existing model merging methods arise as special cases of our framework under energy designs that impose implicit Gaussian assumptions on directional residuals between merged and task-specific models. Empirically, we find that these residuals are often heavy-tailed which exposes a mismatch with the imposed light-tailed Gaussian structures. We address this with a heavy-tailed PoE design based on Cauchy experts, which better captures the observed residual behavior while admitting a provably convergent inference procedure. Experiments across multiple tasks and architectures show significant improvements over state-of-the-arts baselines. Our code is available at this https URL.

AI 总结：提出频移物理信息极限学习机（FS-PIELM），通过平移权重分布均值而非缩放方差来缓解谱偏差，在七个基准问题上相比现有方法精度提升1至近5个数量级。

链接：https://arxiv.org/abs/2607.01694

机构：School of Mathematics and Statistics, Northwestern Polytechnical University（西北工业大学数学与统计学院）； College of Science, Shijiazhuang University（石家庄学院理学院）； Department of Engineering Mechanics, Northwestern Polytechnical University（西北工业大学工程力学系）； Department of Aeronautical Engineering, Northwestern Polytechnical University（西北工业大学航空工程系）； MIIT Key Laboratory of Dynamics and Control of Complex Systems, Northwestern Polytechnical University（西北工业大学工信部复杂系统动力学与控制重点实验室）

作者：Xiong Xiong, Ruonan Zhai, Zheng Zeng, Sheng Zhou, Rongchun Hu, Zichen Deng

英文摘要：Solving partial differential equations (PDEs) with high-frequency solutions remains a central challenge in physics-informed machine learning due to spectral bias -- the tendency of neural networks to learn low-frequency components preferentially. This paper proposes a Frequency Shift Physics-Informed Extreme Learning Machine (FS-PIELM) framework that addresses this limitation through an additive mechanism for weight initialization. Rather than multiplying random weights by a scaling factor, the method translates the mean of the Gaussian weight distribution while keeping the variance fixed at unity, thereby avoiding the variance amplification inherent in scaling-based methods. Two variants are developed: FS-PIELM-L assigns independent frequency magnitudes to individual neurons, while FS-PIELM-G groups neurons for improved robustness. Theoretical analysis shows that the frequency variance under the proposed framework remains bounded and approaches unity regardless of target frequency, in contrast to the quadratic growth of conventional approaches. The method preserves the computational efficiency of extreme learning machines, requiring only a single linear solve. Experiments on seven benchmark problems spanning six equation types -- Helmholtz, wave, Poisson, Klein-Gordon, heat, and advection-diffusion -- on both regular and complex geometries show that the linear variant achieves the best accuracy in six of seven cases, with improvements of one to nearly five orders of magnitude over existing PIELM variants. The code and data accompanying this manuscript will be made publicly available at this https URL.

AI 总结：针对单调神经网络在建模累积条件强度函数时的结构缺陷，提出单调交替样条框架，通过分离插值与外推组件提升表示能力与计算效率，在合成和真实数据集上取得更优性能。

链接：https://arxiv.org/abs/2607.01752

机构：Hong Kong University of Science and Technology（香港科技大学）； Alibaba Cloud（阿里云）； Center for Applied Statistics and School of Statistics, Renmin University of China（中国人民大学应用统计中心与统计学院）

作者：Cheng Wan, Quyu Kong, Feng Zhou

英文摘要：Temporal point processes (TPPs) have widespread applications across various domains. Compared to modeling the conditional intensity of a TPP, modeling its cumulative conditional intensity function (CCIF) improves computational efficiency and eliminates numerical approximation errors. However, current CCIF parameterizations uniformly rely on Monotone Neural Networks (MNNs), which we identify as suffering from three structural deadlocks--convexity restrictions, saturation limits, and violations of CCIF modeling requirements--that fundamentally restrict their representational capacity for complex temporal dynamics. To resolve these bottlenecks, this paper proposes a novel framework called Monotone Alternating Splines (MAS). By leveraging distinct interpolation and extrapolation components, MAS provides a flexible and efficient framework for modeling CCIFs. Theoretically, MAS's interpolation provides strong fitting accuracy, while its extrapolation supports robust generalization, reducing the irreducible approximation gaps of MNNs. Extensive experiments show that MAS achieves superior performance on both synthetic and real-world datasets.

AI 总结：提出自门控注意力（SGA），通过共享可学习矩阵和输入相关残差分量实现线性复杂度，在保持预测性能的同时提升推理效率。

链接：https://arxiv.org/abs/2607.02344

作者：Dezheng Wang, Tong Chen, Wei Yuan, Congyan Chen, Shihua Li, Hongzhi Yin

英文摘要：Transformer architectures have shown strong potential in time series forecasting, where multi-head self-attention is widely used to capture temporal dependencies across historical timestamps. However, standard self-attention has quadratic time and memory complexity with respect to the look-back length. This cost may limit its use in resource-constrained or high-throughput forecasting systems, where fast and memory-efficient inference is important. Through qualitative and quantitative analyses, we observe that self-attention maps in time series forecasting often contain redundant patterns across different timestamps. This phenomenon can be related to the repeated temporal patterns and relatively stable temporal correlations in many real-world time series. Motivated by this observation, we propose Self-Gating Attention (SGA), a plug-and-play attention mechanism that represents the attention score with a shared learnable matrix and an input-dependent residual component. The shared matrix captures common attention patterns, while the residual component captures input-dependent variations. In this way, SGA avoids the query and key projections used in standard attention score computation, leading to linear time and score-matrix memory complexity with respect to the look-back length. We integrate SGA into several forecasting backbones and compare it with standard self-attention and lightweight attention variants on nine publicly available real-world datasets covering electricity, finance, weather, medical monitoring, human activity, and climate records. The results show that SGA improves inference efficiency on public benchmarks while maintaining competitive forecasting performance against state-of-the-art attention mechanisms. These benchmark results provide deployment-oriented evidence.

AI 总结：针对时间序列中罕见极端事件预测难题，提出Exformer框架，通过包含局部、步长和极端三个稀疏分量的极端自适应注意力机制，显式建模正常与极端事件的时间依赖，在四个水文数据集上实现更优的3天预测性能。

链接：https://arxiv.org/abs/2607.02437

机构：Department of Computer Science, Missouri State University（密苏里州立大学计算机科学系）

作者：Sanjeev Shrestha, Hui Liu, Yifan Zhang

英文摘要：Time series forecasting remains challenging when the underlying data contain rare but critical extreme events. This issue is particularly important in hydrologic forecasting, where streamflow distributions are often highly skewed and extreme peaks can have substantial impacts on flood monitoring, water resource management, and early warning systems. Although Transformer-based forecasting models have achieved strong performance by modeling long-range temporal dependencies, they typically treat all time points uniformly and may therefore underrepresent rare extreme patterns. In this paper, we propose the Extreme-Adaptive Transformer (Exformer), a forecasting framework designed to explicitly model temporal dependencies involving both normal and extreme events. Exformer introduces an extreme-adaptive attention mechanism composed of three sparse components: Local, Stride, and Extreme. The Local and Stride components capture short-term and periodic temporal dependencies, respectively, while the Extreme component selectively models event-aware dependencies between normal and extreme streamflow patterns. Experiments on four real-world hydrologic streamflow datasets show that Exformer achieves superior 3-day forecasting performance compared with state-of-the-art baselines. Our findings demonstrate that explicitly incorporating extreme-aware attention improves the forecasting capacity of Transformer models on imbalanced time series with rare but consequential events.

AI 总结：提出模糊函数编程范式，通过Program-as-Weights方法将自然语言规范编译为轻量可执行神经工件，在保持性能的同时大幅降低推理成本。

链接：https://arxiv.org/abs/2607.02512

机构：University of Waterloo（滑铁卢大学）； Cornell University（康奈尔大学）； Harvard University（哈佛大学）

作者：Wentao Zhang, Liliana Hotsko, Woojeong Kim, Pengyu Nie, Stuart Shieber, Yuntian Deng

英文摘要： Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repairing malformed JSON, or ranking search results by intent, and are increasingly outsourced to large language model APIs at the cost of locality, reproducibility, and price. We propose fuzzy-function programming: compiling such a function from a natural-language specification into a compact, locally-executable neural artifact. We instantiate this paradigm with Program-as-Weights (PAW), in which a 4B compiler trained on FuzzyBench, a 10M-example dataset we release, emits parameter-efficient adapters for a frozen, lightweight interpreter. A 0.6B Qwen3 interpreter executing PAW programs matches the performance of direct prompting of Qwen3-32B, while using roughly one fiftieth of the inference memory and running at 30 tokens/s on a MacBook M3. PAW reframes the foundation model from a per-input problem solver into a tool builder: invoked once per function definition, it produces a small reusable artifact whose subsequent calls per function application are cheap and offline.

AI 总结：研究两人零和不完美信息博弈中策略表示（嵌入）的学习问题，提出数据集构建、表示学习方法和下游评估任务，在Kuhn和Leduc扑克上验证了学习嵌入中包含有用行为表示。

链接：https://arxiv.org/abs/2607.01498

作者：Kevin Wang, Kevin Yang, Arjun Prakash, Amy Greenwald

英文摘要：We investigate the problem of learning useful policy representations (embeddings) in two-player zero-sum imperfect-information games. We make three contributions: First, we introduce methods of creating datasets of policies for a given game. Second, we propose methods to learn policy representations. Third, we introduce downstream tasks to evaluate the effectiveness of such representations. We evaluate each dataset method, embedding method, and downstream task on Kuhn and Leduc Poker. Although our methods are very basic, we demonstrate that useful behavioral representations are present in the learned embeddings. To our knowledge, this work is among the first to systematically compare self-supervised learning techniques for learning policy representations in games. Our code is available at this https URL for others to extend.

AI 总结：提出有限滞后算子几何，通过源-后继对估计条件传输律，导出传输张量和循环量，证明仿射协方差与分离性，揭示循环网络架构差异。

链接：https://arxiv.org/abs/2607.01746

机构：University of Washington（华盛顿大学）

作者：Kanishka Reddy

英文摘要：Recurrent representations are trajectories, but representation geometry is often measured from static snapshots. We develop finite-lag operator geometry for recurrent hidden states from observed source-successor pairs $(X_t,X_{t+\Delta})$. The primitive is the conditional transport law $Q_\Delta(dy\mid x)$, estimated by a dense Gaussian source-smoothing operator. From this directed finite-lag law we derive a source-centered transport tensor $G_\Delta$, which decomposes exactly into conditional spread and coherent displacement, and an antisymmetric coordinate circulation $W_\Delta^\rho$, which summarizes directed lagged flow. We prove affine covariance with explicit metric dependence of scalar summaries, dense estimator stability on bounded trajectory clouds, and a finite-lag separation result showing that source-centered transport detects deterministic recurrent motion not recorded by infinitesimal carre-du-champ geometry. A linear-Gaussian closed form calibrates the quantities in terms of the update $A_\Delta$, source covariance, and innovation covariance. Controlled experiments validate the decomposition, circulation, covariance, and stability predictions. In performance matched repeat-copy networks, the framework reveals architecture dependent differences in total transport scale and coherent displacement trace, while coherent displacement fraction is metric and resolution dependent.

AI 总结：提出角色感知神经凸散度头，通过源/目标角色投影和输入凸神经Bregman散度实现非对称表示学习，在语义和本体基准上提升方向性准确率。

链接：https://arxiv.org/abs/2607.01762

机构：School of Mathematics and Statistics, Chongqing Technology and Business University（重庆工商大学数学与统计学院）； Chongqing Key Laboratory of Statistical Intelligent Computing and Monitoring, Chongqing Technology and Business University（重庆工商大学统计智能计算与监测重庆市重点实验室）； School of Food Science, Chongqing Technology and Business University（重庆工商大学食品科学与工程学院）； Faculty of Electrical Engineering and Information Technology, TU Dortmund University（多特蒙德工业大学电气工程与信息技术学院）

作者：He Huang, Lu Shen, Yunfeng Huang, Li Qi

英文摘要：Many representation learning problems involve directed relations, such as lexical entailment, sentence entailment, ontology hierarchy, and citation links. Standard Euclidean, cosine, and Mahalanobis heads are symmetric, while generic neural scorers can model directionality but provide limited geometric structure. This paper proposes a role-aware neural convex divergence head for asymmetric representation learning. The head applies source- and target-role projections before evaluating an input-convex neural Bregman divergence, yielding a nonnegative structured score in the role-projected space. We characterize its projected-space identity, source-role convexity, directional-gap decomposition, and Hessian-based local curvature. Experiments on lexical, sentence, ontology, and directed graph benchmarks compare symmetric distances, unstructured asymmetric scorers, order/hyperbolic baselines, plain ICNN-Bregman heads, and the proposed role-aware variant. Across ten random seeds on the main semantic and ontology benchmarks, role-aware projections consistently improve directional accuracy over plain ICNN-Bregman heads while preserving zero observed negative divergence rate. The results also identify a boundary case: on large fixed-feature citation prediction, specialized symmetric or hyperbolic baselines remain stronger in ranking accuracy. Overall, the proposed head is best understood as a structured and interpretable plug-in distance module for tasks where directional relations matter.

AI 总结：通过探测78种分子子结构，系统研究了预训练和微调对化学语言模型分子结构感知能力的影响，发现预训练提升上层结构意识，微调增强任务相关子结构表征。

链接：https://arxiv.org/abs/2607.02140

作者：Anna Karnysheva, Dietrich Klakow, Ji-Ung Lee

英文摘要：Chemical language models (CLMs) are trained with linearized representations such as SMILES, yet it remains unclear which chemically meaningful substructures they encode. To foster a better understanding of CLMs, we conduct a systematic study and probe for 78 molecular substructures across eight pre-trained and six randomly initialized models. We furthermore study how fine-tuning on chemical downstream tasks affects the learned representations of molecular substructures. Our results show that pre-training generally improves molecular structure awareness of CLMs, particularly in the upper layers. Moreover, randomly initialized models already encode ring structures well in the first layer. Our analysis on two chemical downstream tasks further reveals that, interestingly, fine-tuning affects task-relevant molecular substructures more than others, indicating that the changes in the representations follow chemical theory.

AI 总结：本文理论分析分布式自监督学习在非IID数据下的鲁棒性，发现掩码图像建模比对比学习更鲁棒，且联邦学习与去中心化学习鲁棒性相当，并提出MAR损失验证理论。

链接：https://arxiv.org/abs/2607.02447

机构：School of Electrical and Computer Engineering, The University of Sydney（悉尼大学电气与计算机工程学院）； Northwestern Polytechnical University（西北工业大学）

作者：Xuanyu Chen, Nan Yang, Shuai Wang, Dong Yuan

英文摘要：Recent research has introduced distributed self-supervised learning (D-SSL) approaches to leverage vast amounts of unlabeled decentralized data. However, D-SSL faces the critical challenge of data heterogeneity, and there is limited theoretical understanding of how different D-SSL frameworks respond to this challenge. To fill this gap, we present a rigorous theoretical analysis of the robustness of D-SSL frameworks under non-IID (non-independent and identically distributed) settings. Our results show that pre-training with Masked Image Modeling (MIM) is inherently more robust to heterogeneous data than Contrastive Learning (CL), and that the robustness of decentralized SSL increases with average network connectivity, implying that federated learning (FL) is no less robust than decentralized learning (DecL). These findings provide a solid theoretical foundation for guiding the design of future D-SSL algorithms. To further illustrate the practical implications of our theory, we introduce MAR loss, a refinement of the MIM objective with local-to-global alignment regularization. Extensive experiments across model architectures and distributed settings validate our theoretical insights, and additionally confirm the effectiveness of MAR loss as an application of our analysis.

AI 总结：研究四种执行环境（单容器、托管沙箱、Kubernetes编排容器、云虚拟机）在编码智能体RL中的冷启动延迟和工人工时差异，发现优化执行基础设施可显著提升训练效率。

链接：https://arxiv.org/abs/2607.01415

机构：Daytona

作者：Daniel Thi Graviet, Lovre Pesut, Ivan Dagelic, Vedran Jukic, Ivan Burazin

英文摘要：Coding-agent reinforcement learning treats execution infrastructure as a background implementation detail, despite relying on large numbers of interactive software rollouts. This is a missed opportunity: measuring infrastructure overhead can reveal practical efficiency gains for RL post-training, where small per-rollout savings compound at scale. We present a comparative study of four execution substrates: single containers, hosted sandboxes, Kubernetes-orchestrated containers, and cloud virtual machines. We find up to $110\times$ variation in cold-start latency and a $1.8\times$ spread in projected worker-hours for one million 150-step trajectories. Our results suggest that future coding-agent RL systems should optimize execution substrates as part of the training system itself, not merely as deployment plumbing.

AI 总结：提出FADE方法，通过动态调整优势函数的正负和难度权重，解决RL训练不稳定和多样性崩溃问题，在7B和32B模型上分别提前20k和2k步达到最佳pass@1。

链接：https://arxiv.org/abs/2607.01490

机构：FAIR at Meta（Meta FAIR）； Inria, Ecole Normale Supérieure（法国国家信息与自动化研究所，巴黎高等师范学院）； University of California, San Diego（加利福尼亚大学圣迭戈分校）

作者：Juliette Decugis, Sean O'Brien, Francis Bach, Gabriel Synnaeve, Taco Cohen

英文摘要：Reinforcement learning post-training dramatically improves LLM reasoning, but suffers from training instability and diversity collapse. Advantage functions offer an appealing fix: they reshape the training objective, reweight which rollouts drive learning, and are trivial to implement. Yet a proliferation of methods makes it unclear which advantage to use and when. We cut through the confusion with a unifying framework that decomposes any advantage into its positive and negative gradient mass along two orthogonal axes. On the sign axis, imbalanced updates collapse either entropy or weight geometry. On the difficulty axis, hard-problem focus sharpens signal but costs sample size. Both trade-offs shift during training: exploration favors balance and hard focus; exploitation favors suppression and medium focus. This motivates FADE (Focal Advantage with Dynamic Entropy), a self-adapting advantage that reads training dynamics to schedule the gradient weight automatically. FADE reaches peak pass@1 20k steps earlier than the best static baseline at the 7B scale and 2k steps earlier at the 32B, while achieving the best accuracy-diversity trade-off across all pass@k on LiveCodeBench and AIME.

AI 总结：提出一套基于最优控制理论的结构化验证时诊断指标，用于从离线检查点中预测潜在世界模型的闭环性能，其中复合奖励可观测性分数（CROF）在LunarLander任务上有效选择检查点，显著提升MPC和基于模型的强化学习性能。

链接：https://arxiv.org/abs/2607.01736

作者：Nikolai Smolyanskiy

英文摘要：We study how to predict the downstream closed-loop performance of a learned latent world model from validation-time diagnostics alone. Choosing the right checkpoint from a world-model training run is difficult: validation loss and multi-step prediction RMSE keep improving long after closed-loop performance has collapsed. We present a suite of structural validation-time diagnostics drawn from optimal-control theory and apply them to Gymnasium's LunarLander v3, which features shaped rewards. We train an RSSM [5, 4] world model on it and treat per checkpoint CEM-MPC return as the oracle for closed-loop quality. By evaluating 40 metrics against this oracle, we find that the strongest single predictor is the Reward Observability Fraction (ROF), which measures the reward predictor's dependence on the observable subspace. We combine ROF with three structural regularizers into a single-number offline checkpoint selection score, the Composite Reward Observability Fraction (CROF). The CROF-selected world model trains a model-based A2C policy that beats a fairly evaluated model-free A2C baseline by ~24.5 return points while using ~65x fewer real-environment interactions, and the same world model also drives a strong zero-shot CEM-MPC policy. Code and data: this https URL.

AI 总结：提出动态学习支撑集上下界的方法，联合优化支撑集与分类表示，理论证明其比固定支撑集更紧的MSE上界，实验匹配或优于HL-Gauss算法。

链接：https://arxiv.org/abs/2607.01880

作者：Jen-Yen Chang, Takayuki Osa, Tatsuya Harada

英文摘要：Value functions are an essential component in actor-critic based deep reinforcement learning (RL). Conventionally, these functions are trained as a regression task by minimising the mean squared error (MSE) relative to bootstrapped target values. Meanwhile, in distributional RL, a distribution of returns is modelled based on the distributional Bellman operator. This work investigates the Gaussian Histogram Loss (HL-Gauss), a recent approach that reframes value estimation as classification by encoding each scalar Bellman target as a Gaussian-smoothed categorical target. Despite its potential, applying histogram-based losses to RL presents inherent challenges, most notably the requirement to pre-define a fixed support interval, which is often complicated by the non-stationary and stochastic nature of target values typically found in RL tasks. In this work, we propose an approach that dynamically learns the lower and upper bounds of the support instead of assigning them beforehand. We derive an objective that jointly learns these bounds whilst learning the categorical representation of the scalar values, and we show that this objective forms an upper bound on the mean-squared Bellman error. Our theoretical analysis further shows that this bound is tighter than that of non-learned supports of HL-Gauss. Empirically, the proposed objective enables stable adaptation of the support interval and matches HL-Gauss-based actor-critic algorithms on most continuous-control tasks whilst improving on a subset, without requiring a pre-specified support interval.

AI 总结：提出Rank-Then-Act框架，利用视觉语言模型从专家视频中学习进度排序器，通过斯皮尔曼等级相关奖励函数实现无环境奖励的策略学习，在离散和连续控制任务中达到或超越现有方法。

链接：https://arxiv.org/abs/2607.01897

机构：T-Tech

作者：Yuriy Maksyuta, George Bredis, Ruslan Rakhimov, Daniil Gavrilov

英文摘要：We introduce Rank-Then-Act (RTA), a framework for learning control policies from expert video demonstrations without environment rewards. RTA trains a Vision-Language Model (VLM) offline as a progress-based ordinal scorer, using a Group Relative Policy Optimization (GRPO) objective over shuffled frame sequences, which forces the model to recover temporal ordering from visual semantics rather than trivial time cues. Importantly, instead of using the scorer directly as a scalar reward model, we propose a correlation-based reward function for reinforcement learning: at each interaction window, we compute the Spearman rank correlation between predicted progress rankings and true temporal indices, yielding a bounded, scale-invariant learning signal. This design decouples reward learning from absolute calibration and enables stable transfer across tasks and environments. We evaluate RTA on discrete control benchmarks (PyBoy: Catrap, Kirby) and continuous control tasks (PointMaze, MetaWorld). RTA consistently matches or outperforms prior video-based reward learning methods and rank-based baselines, while demonstrating strong cross-task reuse of a single pretrained progress scorer. Our results suggest that correlation-structured supervision over video-derived ordinal signals is sufficient for policy learning, offering a scalable alternative to explicit reward design.

AI 总结：本文证明在离线强化学习中，过度悲观不会阻碍上下文MDP中的最优泛化，关键在于悲观结构是否尊重最优解的对称性，并据此提出数据增强应通过策略提取中的一致性损失来应用。

链接：https://arxiv.org/abs/2607.02288

作者：Max Weltevrede, Matthijs T.J. Spaan, Wendelin Böhmer

英文摘要：While pessimism counteracts overestimation bias in offline reinforcement learning (RL), being overly conservative has been associated with hindering certain forms of generalization. However, in this paper we demonstrate that being overly pessimistic does not inherently prevent optimal generalization in contextual MDPs (CMDPs). Instead, we argue successful generalization depends not on the amount of pessimism, but whether the pessimistic structure respects the underlying symmetries of the optimal solution. We prove that a mildly pessimistic, non-symmetric value function can generalize worse than an overly pessimistic, symmetric one. In offline RL, the structure of the pessimism is determined by the structure of the dataset coverage. As such, enforcing a symmetric value function can be non-trivial, and might require techniques such as data augmentation (DA). Inspired by our theoretical results, we argue that DA can best be applied through a consistency loss during policy extraction, rather than the common practice of (regular) offline training on an augmented dataset. This is empirically validated using IQL and CQL on a rotationally symmetric reacher environment.

AI 总结：将变分能量最小化视为优势策略梯度问题，提出近端波函数优化（PWO）算法，通过裁剪概率比和相位增量实现稳定优化，在自旋系统中优于现有方法，并首次优化了15亿参数的NQS模型。

链接：https://arxiv.org/abs/2607.02292

机构：Mila Quebec AI Institute, Université de Montréal（Mila 魁北克人工智能研究所，蒙特利尔大学）； QuTech and Kavli Institute of Nanoscience, Delft University of Technology（QuTech 与卡夫利纳米科学研究所，代尔夫特理工大学）； CIFAR AI Chair（CIFAR 人工智能主席）

作者：Juan Agustín Duque, Sergio García Heredia, Vinicius Hernandes, Eliška Greplová, Thomas Spriggs, Aaron Courville, Anna Dawid

英文摘要：Neural quantum states (NQS) provide a flexible and scalable framework for approximating quantum many-body wavefunctions. Among NQS parameterizations, autoregressive models are especially attractive because they enable exact, independent sampling from the Born distribution, avoiding the autocorrelation and mixing issues of Markov chain methods. Yet their optimization remains comparatively underexplored: Adam is a scalable method but ignores function space geometry, while stochastic reconfiguration is principled but costly and numerically fragile in large models. To address this gap, we show that variational energy minimization can be viewed as an advantage policy-gradient problem over the Born distribution, motivating trust-region optimization for NQS training. We introduce Proximal Wavefunction Optimization (PWO), a principled trust-region algorithm that clips probability-ratio changes in the amplitude channel and phase increments in the phase channel. PWO avoids explicit matrix inversion, reuses samples across multiple updates, and combines the scalability of first-order optimization with theoretical guarantees. Across Ising and frustrated $J_1$-$J_2$ one- and two-dimensional spin systems, PWO improves stability and wall-clock convergence over Adam, minSR, and SPRING. Finally, we fine-tune a $1.5$B-parameter RWKV-7 model, demonstrating NQS optimization at a scale over three orders of magnitude beyond prior work.

AI 总结：提出DecompRL算法，通过强化学习将问题分解为可复用的子函数，重组模块生成候选解，将GPU瓶颈转移至CPU评估，在LiveCodeBench和CodeContests上超越标准RL基线。

链接：https://arxiv.org/abs/2607.02390

作者：Juliette Decugis, Fabian Gloeckle, Francis Bach, Taco Cohen, Gabriel Synnaeve

英文摘要：How can Large Language Models (LLMs) solve problems they currently cannot? Repeated sampling scales test-time compute but GPU cost grows linearly with attempts, while reinforcement learning (RL) with verifiable rewards improves single-attempt accuracy at the expense of sample diversity. Both strategies ultimately fail when the base policy has near-zero probability of producing a correct solution: no amount of sampling or gradient signal can overcome a search space that is simply too large. We take a different approach: rather than sampling harder, we make the task easier by decomposing problems into smaller, independently solvable sub-functions whose implementations can be recombined. Since off-the-shelf models are not trained for this modular generation, we introduce DecompRL, an RL algorithm that explicitly learns to decompose and implement hierarchical code structures. Recombining $k$ implementations of $n$ modules yields up to $k^{n}$ candidate solutions, shifting the bottleneck from GPU inference to cheap CPU evaluation and cutting GPU token cost by $\sim$50$\times$. On LiveCodeBench and CodeContests (Qwen~2.5~7B, Code World Model~32B), DecompRL outperforms standard and diversity-optimized RL baselines beyond $10^5$ tokens per problem, solving problems that standard generation cannot reach.

AI 总结：提出DemoPSD框架，通过选择性采纳教师指导，平衡学生从教师学习和保持自身推理能力，解决特权信息泄露和探索抑制问题，在科学推理任务上优于现有方法。

链接：https://arxiv.org/abs/2607.02502

机构：City University of Hong Kong（香港城市大学）； Tsinghua University（清华大学）； Shenzhen University of Advanced Technology（深圳理工大学）； Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））

作者：Yunhe Li, Hao Shi, Wenhao Liu, Mengzhe Ruan, Hanxu Hou, Zhongxiang Dai, Shuang Qiu, Linqi Song

英文摘要：On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason, where a single model acts as both the teacher and the student with different levels of information access. However, recent studies have found that the teacher's dense token-level supervision, conditioned on privileged information, can lead to overfitting to in-domain patterns, suppress exploration, and hurt cross-domain generalization, while also introducing a more fundamental issue: *privileged information leakage*, where the student encodes answer-dependent shortcuts that are unavailable at test time. We introduce **DemoPSD**, a novel framework that resolves such problems through the idea of *selective adoption of teacher guidance*. Instead of fitting the full teacher distribution, DemoPSD steers the student toward a *reverse-KL barycenter target*, a weighted geometric combination of the teacher and student distributions, that naturally balances learning from the teacher with preserving the student's own reasoning capacity. We measure the difference between their distributions and use such a discrepancy to adaptively control the blending at each token position. We provably show that DemoPSD achieves **(1)** *leakage attenuation*, i.e., effective mitigation of privileged information leakage; and **(2)** *exploration preservation*, i.e., preservation of exploration capacity under dense token-level distillation. Extensive experiments on SciKnowEval across four scientific fields show that DemoPSD outperforms both GRPO and SDPO while maintaining higher training entropy and robustly generalizing to out-of-distribution GPQA benchmarks.

AI 总结：从采样视角出发，以证明为导向介绍扩散模型，涵盖经典采样动力学到现代扩散采样器、误差分析及推理时控制。

链接：https://arxiv.org/abs/2607.01693

机构：Duke University（杜克大学）

作者：Jianfeng Lu

英文摘要： These notes give a proof-oriented introduction to diffusion models from the viewpoint of sampling, tracing a single arc from classical sampling dynamics to modern diffusion samplers, their error analysis, and inference-time control. Throughout, the material is layered into core definitions and identities proved in full, representative estimates proved under simplifying assumptions, and research-level theorems stated with a proof roadmap. The intended audience is beginning graduate students with a background in probability but no prior exposure to stochastic differential equations, stochastic numerics, or diffusion models.

AI 总结：提出Set Diffusion模型，通过将似然参数化为灵活位置和长度的令牌集，并设计集因果扩散架构，支持任意顺序解码和KV缓存更新，在数学推理、摘要和无条件生成上优于先前的扩散语言模型。

链接：https://arxiv.org/abs/2607.01775

作者：Marianne Arriola, Volodymyr Kuleshov

英文摘要：Discrete diffusion models have steadily improved in quality relative to autoregressive (AR) models. However, these models are normally constrained to fixed-length generation and do not support key-value (KV) caching. Block diffusion partially bridges diffusion and AR by generating token blocks left-to-right, but its fixed-size sequential blocks limit decoding flexibility and parallelism. Here, we present a new class of language models, set diffusion, comprised of (i) a likelihood parameterization that factorizes over flexible-position, flexible-length token sets and (ii) a set-causal diffusion architecture that supports KV cache updates after every inference step. By factorizing over token sets instead of fixed-size blocks, tokens can be decoded in arbitrarily-ordered sets, including sliding-window sets, enabling faster inference and support for any-order decoding. Set diffusion achieves better speed-quality tradeoffs on mathematical reasoning, summarization, and unconditional generation compared to prior diffusion language models while offering stronger infilling performance than block diffusion. We provide the code, along with the model weights and blog post on the project page: this https URL

AI 总结：提出Decomposer框架，通过两阶段方法（合成数据微调+强化学习优化）将符号音乐反编译为可读、可编辑的程序，在MIDI重建保真度和代码可读性上优于基线。

链接：https://arxiv.org/abs/2607.01849

作者：Yewon Kim, Apurva Gandhi, David Chung, Graham Neubig, Chris Donahue

英文摘要：Musical performance involves executing a set of high-level musical instructions, yet recovering those instructions from the performance is a challenging inverse problem. We present Decomposer, a post-training framework for symbolic music decompilation: the task of recovering executable, editable music programs from symbolic music. We instantiate the task as MIDI-to-Strudel decompilation, where the model takes symbolic MIDI as input and produces a program in Strudel, a music programming language, that reconstructs the input when executed. The task poses two challenges: Strudel is a low-resource language with little naturally paired MIDI-code data, and optimizing faithful reconstruction of MIDI alone can collapse to unreadable note-by-note transliteration. We address these challenges in two stages. First, we construct Strudel-Synth, a synthetic corpus of paired Strudel programs and rendered MIDI, and use it for supervised fine-tuning. Second, we refine the model with reinforcement learning on unpaired MIDI, optimizing rewards for both MIDI reconstruction faithfulness and code readability. Our evaluation across synthetic and real-world MIDI benchmarks shows that Decomposer achieves substantially higher MIDI reconstruction faithfulness than closed-source LLMs while producing more readable and diverse code than the heuristic converter.

AI 总结：提出基于种群的多目标进化训练策略，将半监督GAN的判别器学习建模为多目标优化问题，通过帕累托支配排序探索分类精度与真假判别之间的权衡，提升训练鲁棒性和分类准确率。

链接：https://arxiv.org/abs/2607.01907

作者：Francisco Sedeño, Francisco Chicano, Jamal Toutouh

英文摘要：Semi-supervised generative adversarial networks (SSL-GANs) can exploit large unlabeled datasets while retaining a classifier in the discriminator, but their training is often unstable. This paper proposes a population-based evolutionary training strategy in which discriminator learning is formulated as a multi-objective optimization problem. Instead of aggregating the supervised and unsupervised components of the SSL objective into a single scalar loss, the method maintains a population of discriminators ranked by Pareto dominance, enabling the exploration of different trade-offs between classification accuracy and real/fake discrimination. This formulation aims to improve both roles of SSL-GANs: learning accurate classifiers and training generators capable of producing realistic samples. We analyze several variants, including an elitist strategy and a mono-objective ablation, to assess the role of multi-objective selection. Experiments on MNIST with limited labels show improved training robustness compared to SSL-GAN and CE-SSL-GAN state-of-the-art baselines, while the elitist variant consistently achieves the highest classification accuracy.

AI 总结：提出自适应重参数化时间 (ART) 方法，将扩散采样的时间步分配建模为连续时间控制问题，并通过强化学习求解，以自适应学习采样时间表，提升样本质量。

链接：https://arxiv.org/abs/2607.02137

机构：Department of Applied Mathematics, The Hong Kong Polytechnic University（香港理工大学应用数学系）； Department of Industrial Engineering and Operations Research, Columbia University（哥伦比亚大学工业工程与运筹学系）； Data Science Institute, Columbia University（哥伦比亚大学数据科学研究所）

作者：Yilie Huang, Wenpin Tang, Xun Yu Zhou

英文摘要： We study timestep allocation for score-based diffusion sampling, where a learned reverse-time dynamics is discretized on a finite grid. Uniform and hand-crafted schedules are standard choices, but they rely on fixed prescriptions and can therefore be suboptimal. To address this limitation, we propose Adaptive Reparameterized Time (ART), a continuous-time control formulation that learns a time change by treating the speed of the sampling clock as the control, so that a uniform grid on the learned clock induces adaptive timesteps in the original diffusion time. Based on a leading-order Euler error surrogate, ART provides a principled objective for allocating timesteps along the sampling trajectory. To solve this deterministic control problem, we introduce ART-RL, an auxiliary randomized formulation with Gaussian policies that turns schedule learning into a continuous-time reinforcement learning problem. We prove that the randomized ART-RL formulation is equivalent to ART at the optimizer level, in the sense that its optimal Gaussian policy recovers the optimal ART time-warping rate through its mean. We further establish policy evaluation and policy improvement characterizations and derive trajectory-based moment identities that yield implementable actor--critic updates for learning the schedule. Across experiments ranging from controlled low-dimensional settings to image generation, ART-RL can be plugged into existing diffusion samplers by changing only the timestep grid, consistently improving sample quality over strong baseline schedules at matched budgets while leaving the rest of the sampling pipeline unchanged. The learned schedules also exhibit broad generalization, transferring without retraining across sampling budgets, datasets, solvers, pipelines, and representation spaces.

AI 总结：提出分布级奖励框架，通过子集替换策略高效估计奖励并优化模型合并系数，解决样本级奖励导致的模式崩溃和视觉异常问题，在SiT和EDM2上显著提升FID-50K。

链接：https://arxiv.org/abs/2607.02291

作者：Ruihang Li, Mengde Xu, Shuyang Gu, Leigang Qu, Fuli Feng, Han Hu, Wenjie Wang

英文摘要：Conventional reinforcement learning strategies for visual generation typically employ sample-wise reward functions, yet this practice frequently results in reward hacking that degrades image diversity and introduces visual anomalies. To address these limitations, we present a novel framework that finetunes generative models using distribution-wise rewards, ensuring better alignment with real-world data distributions. Unlike rewards that evaluate samples individually, distribution-wise reward accounts for the data distribution of the samples, mitigating the mode collapse problem that occurs when all samples optimize towards the same direction independently. To overcome the prohibitive computational cost of estimating these rewards, we introduce a subset-replace strategy that efficiently provides reward signals by updating only a small subset of a generated reference set. Additionally, we apply RL to optimize post-hoc model merging coefficients, potentially mitigating the train-inference inconsistency caused by introducing stochastic differential equation (SDE) in regular RL practices. Extensive experiments show our approach significantly improves FID-50K across various base models, from 8.30 to 5.77 for SiT and from 3.74 to 3.52 for EDM2. Qualitative evaluation also confirms that our method enhances perceptual quality while preserving sample diversity.

AI 总结：本文提出统一的理论框架，从逼近、优化、泛化等经典基础到过参数化、鲁棒性、生成建模、Transformer、上下文学习、缩放定律、可解释性、对齐和涌现等当代机制，系统梳理深度学习理论。

链接：https://arxiv.org/abs/2607.01311

作者：Zhilin Zhao

英文摘要：Deep learning has outgrown any single mathematical explanation. From Approximation to Emergence develops a unified, proof-oriented account of modern deep learning theory, tracing a path from the classical foundations of approximation, optimization, and generalization to the contemporary mechanisms of overparameterization, robustness, generative modeling, transformers, in-context learning, scaling laws, interpretability, alignment, and emergence. Rather than presenting isolated results, the book organizes a broad literature into a coherent research narrative: each theory is examined through the object it controls, the assumptions that make it valid, and the phenomena it leaves unexplained. Written for researchers, graduate students, and mathematically trained practitioners, this monograph offers a rigorous map of deep learning theory as it stands today: powerful, incomplete, and increasingly centered on the question of how learned mechanisms arise from scale, data, architecture, and training.

AI 总结：发现嵌入表和LM头的梯度几何特性，提出轻量优化器Ember，在微调、强化学习和预训练中提升帕累托前沿，仅需KB级优化器状态。

链接：https://arxiv.org/abs/2607.01455

作者：Kathan Shah

英文摘要：Language models learn continuous programs over discrete symbols, with the embedding table and LM-head acting as the read/write interface between them. We show that this interface has gradient geometry distinct from dense hidden weights which can be exploited to improve the Pareto frontier across supervised finetuning, RL, and pretraining, while only utilizing kilobytes of optimizer state. We introduce Ember, a lightweight optimizer for embedding and LM-head matrices that utilizes O(V + D) VRAM, instead of Adam's O(2VD), and forgoes the need to shard both token table optimizer states. We provide empirical evidence that Ember scales effectively across batch size and parameter count. We show that the optimization trajectory of tokens can be well described by a simple 1D ray, counter to the popular belief that neural net parameters navigate a heavily nonconvex landscape. We provide a principled view on the surprisingly narrow space of optimizers that suffice for Transformer training. Finally, we open-source our distributed Ember implementation that merges cleanly with existing ZeRO/FSDP setups to support further research at this https URL

AI 总结：针对带压缩通信的分布式在线凸优化，首次提出两种基于跟随正则化领导者的算法，在完整信息和赌博机设置下分别匹配或显著改进现有遗憾界与通信成本。

链接：https://arxiv.org/abs/2607.01665

机构： School of Software Technology, Zhejiang University（浙江大学软件学院）； State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全全国重点实验室）

作者：Hao Zhou, Xiaoyu Wang, Chang Yao, Mingli Song, Yuanyu Wan

英文摘要：Decentralized online convex optimization (D-OCO) is a popular framework for distributed applications with streaming data. To tackle the communication bottleneck, previous studies have investigated D-OCO with compressed communication and proposed several algorithms that are variants of online gradient descent (OGD). However, for D-OCO with exact communication, the best existing algorithms are variants of follow-the-regularized-leader (FTRL). In this paper, for the first time, we propose two FTRL-type algorithms for D-OCO with compressed communication. Compared with OGD-type algorithms, our algorithms are more elegant in both algorithmic design and theoretical analysis. The key insight is that the dual update mechanism of FTRL allows us to make a simple application of the technique for average consensus with communication compression. More specifically, our first algorithm considers the full-information setting, and can match the existing regret bounds. Our second algorithm is designed for the bandit setting, and can significantly improve both the regret bounds and communication costs of existing algorithms.

AI 总结：研究高斯位置模型下岭正则化对数密度比估计，通过变分与谱方法推导高维渐近等价，比较两者风险并分析核范数惩罚的特征学习。

链接：https://arxiv.org/abs/2607.01895

作者：Francis Bach (SIERRA)

英文摘要：We study ridge-regularized log-density-ratio estimation in the Gaussian location model with a common covariance matrix. By affine invariance, the model is written as q $\sim$ N(0, I), p $\sim$ N($\Delta$, I), with linear features, where $\Delta$ is a mean vector. The variational estimator is the empirical Kullback-Leibler (KL) log-normalized fit with a squared L2-penalty on its nonconstant coefficient, and the spectral estimator recently introduced in [1] replaces a single variational problem by a continuum of ridge-regularized least-squares problems. We derive high-dimensional deterministic asymptotic equivalents when the numbers of observations and dimension tend to infinity with fixed ratios. The regularized variational limit is characterized by a scalar entropy minimization problem derived from the convex-Gaussian-min-max theorem (CGMT), while the regularized spectral limit follows from deterministic equivalents for resolvents of weighted sums of two independent Gaussian sample covariance matrices. We use these formulas to compare population risks, with experiments focused on fixed-signal aspect-ratio sweeps and optimized regularization. Our conclusion is that with many observations, under the criteria and asymptotic regimes analyzed here, the well-specified variational estimator has the smaller risk, while with fewer observations, the spectral estimator is favored because its covariance-based construction has lower variance. We also study how a nuclear penalty can be used and partially analyzed to perform feature learning.

AI 总结：针对低不稳定性复杂度的线性动力系统，提出一种在线预测算法，参数复杂度为Õ(k)，实现亚线性遗憾，内存适应内在复杂度而非全状态维度。

链接：https://arxiv.org/abs/2607.02050

作者：Yuval Ran-Milo, Angelos Assos, Elad Hazan

英文摘要：Motivated by the challenge of stabilizing a general unknown linear dynamical system (LDS) from observations, we study the natural prerequisite of online prediction. Our goal is to achieve sublinear regret with a memory footprint that adapts to the intrinsic complexity of the dynamics rather than the full hidden -- state dimension. We focus on the practically central regime of systems with low instability complexity -- eigenvalues outside the real stable interval that do not decay rapidly, together with non-semisimple modes-potentially embedded in an otherwise stable real spectrum of much higher dimension; we write $k$ for this count. This regime is the primary setting in which stabilization is plausible: we show that many systems with high instability complexity cannot be stabilized without exponentially large controls. Thus, prediction is meaningful for stabilization precisely when the instability complexity is small. Within this regime, we introduce a unified online algorithm that handles every LDS (including non-diagonalizable systems with complex or exploding modes) with a learnable parameter count of $\widetilde{O}(k)$. Finally, we prove a lower bound showing that $k$ is a valid complexity measure: any filter-based predictor needs at least $k$ filters. Experiments corroborate our theory: on a high-dimensional system, our predictor sharply outperforms prior methods at an equal parameter budget.

AI 总结：提出DSGNAR二阶优化框架，通过双草图高斯-牛顿和自适应正则化步长控制，解决PINN训练中的病态损失景观问题，在多个基准问题上实现前所未有的精度和速度。

链接：https://arxiv.org/abs/2607.02194

作者：Joseph Webb, Sadok Jerad, Coralia Cartis

英文摘要：Physics-informed neural networks (PINNs) have emerged as a promising route to solve partial differential equations, yet they have struggled to reach the precision of classical solvers. The obstacle is increasingly understood to be one of optimisation, owing to the severely ill-conditioned loss landscape. We present $\textbf{DSGNAR}$: Doubly-Sketched Gauss-Newton with Adaptive Ratio, a scalable second-order optimisation framework that confronts this ill-conditioning and, in doing so, obtains unprecedented accuracy and speed. $\textbf{DSGNAR}$ couples a doubly-sketched Gauss-Newton model with a novel strategy that carefully controls both regularisation and step length. Across a suite of problems spanning nonlinear, chaotic, multi-scale, high-dimensional, and Navier-Stokes, the framework greatly improves on the state of the art: able to attain relative $\ell_2$ errors as low as $3\times10^{-16}$ in double precision, improve contemporary results by five orders of magnitude on the canonical Burgers' equation, and as much as eight orders on a high-dimensional Poisson problem, while remaining markedly faster. We further show that, in single precision, solutions at the limit of round-off error can be obtained very quickly: Burgers' equation to $\ell_2^{\text{rel}} = 4.75 \times 10^{-7}$ in under ten seconds. The framework is also robust to the choice of architecture, arithmetic precision, and initial hyperparameters. The code is available at this https URL

AI 总结：研究奖励和消耗量连续分布的在线资源分配问题，提出基于样本路径的边际策略，在退化情况下实现次线性遗憾。

链接：https://arxiv.org/abs/2607.02196

作者：Jiawei Zhang

英文摘要：We study online resource allocation when both rewards and consumption sizes may be continuously distributed. Requests arrive sequentially and must be accepted or rejected irrevocably under fixed resource capacities. Each request belongs to one of finitely many observable types; conditional on an observable request type, both the reward and the scalar size are random, and the realized size scales a fixed type-specific resource-consumption vector. The model allows the deterministic fluid relaxation to be degenerate. We show that additive regret is governed by the size-weighted mass of requests whose value-to-size ratios lie near the active acceptance cutoffs. We formalize this quantity through an active weighted-mass exponent p. When p > 1, this cutoff mass is thin, and the problem is genuinely hard: every online policy must incur regret of order at least $T^{1/2 - 1/(2p)}$, and this holds for every p > 1. A sample-path marginal policy matches this lower bound up to polylogarithmic factors; and when p = 1, so that the mass grows linearly near the cutoff, it attains $O((\log T)^2)$ regret. For example, if the size and the value-to-size ratio are independent and uniformly distributed, then p = 1; if instead the size and the reward are independent and uniformly distributed, then p = 2. Thus the policy achieves $o(\sqrt{T})$ regret throughout this regularity class without any fluid non-degeneracy assumption, allowing both primal degeneracy and dual non-uniqueness.

AI 总结：本文实现并系统比较了Muon、SOAP及混合SOAP-Muon等矩阵结构化优化器，用于训练NequIP和Allegro MLIP模型，发现这些优化器在收敛速度和最终精度上显著优于Adam，尤其在部分力监督下改进更为明显。

链接：https://arxiv.org/abs/2607.02499

作者：Gil Harari, Yoel Zimmermann, Ola Tangen Kulseng, Laura Zichi, Chuin Wei Tan, Marc L. Descoteaux, Boris Kozinsky

英文摘要：Machine learning interatomic potentials (MLIPs) have become a hallmark of AI for scientific simulation. While efforts on new architectures and datasets have led to increasingly accurate and general models, the choice of optimizer for training has largely remained unexplored, defaulting to Adam and its variants in the community. Here, we implement and systematically compare a class of recently proposed matrix-structured optimizers, including Muon, SOAP, and the hybrid SOAP-Muon, for training NequIP and Allegro MLIP models. We find that these optimizers can substantially outperform Adam in both convergence speed and final accuracy. SOAP and SOAP-Muon emerge as robust and consistently strong methods, while Muon only provides partial gains relative to Adam. The improvements are particularly pronounced under partial force supervision. Our results indicate that optimizer choice is an overlooked yet impactful design axis for MLIPs.

AI 总结：研究通过结构化专家剪枝降低混合专家模型部署成本，评估剪枝对生物医学领域实用性与事实可靠性的影响，发现适度剪枝保持领域内性能但极端剪枝增加幻觉风险。

链接：https://arxiv.org/abs/2607.01444

机构：University of Sheffield（谢菲尔德大学）； AstraZeneca（阿斯利康）； University of Exeter（埃克塞特大学）； Federal University of Rio Grande do Norte（北里奥格兰德联邦大学）

作者：Atsuki Yamaguchi, Szymon Palucha, Léo Bijar, Aline Villavicencio, Nikolaos Aletras

英文摘要：Mixture-of-Experts (MoE) models offer inference speedups via selective activation but impose substantial memory requirements because the whole network must remain loaded. Structured expert pruning is a practical approach for reducing deployment costs in resource-constrained settings. However, prior studies primarily evaluate benchmark utility, leaving the effect of pruning on factual reliability underexplored, particularly in high-stakes domains such as biomedicine. In this paper, we investigate how domain-specific expert pruning affects both utility and reliability. We assess four MoE models, six pruning methods, and multiple pruning ratios across generation and classification tasks under in-domain (biomedical) and cross-domain settings. Results reveal that moderate pruning preserves in-domain utility without immediate reliability decline, although hallucination risks increase at extreme pruning ratios. When shifting to the general domain, both utility and reliability degrade rapidly. These findings indicate that safe compression depends heavily on the task and domain. Evaluating pruned MoE models solely on utility is inadequate for high-stakes deployment without reliability assessment.

AI 总结：针对长序列Transformer推理中KV缓存压缩的瓶颈，本文通过最小化最大风险理论，揭示了缓存内在可压缩性决定准确压缩的边界，并设计出在因果掩码下达到最优风险的实用算法，在LongBench上取得良好效果。

链接：https://arxiv.org/abs/2607.01520

机构：RWTH Aachen University（亚琛工业大学）； Stanford University（斯坦福大学）

作者：Lukas Haverbeck, Carmen Amo Alonso, Andres Felipe Posada-Moreno, Sebastian Trimpe, Marco Pavone

英文摘要： Transformer inference on long sequences is expensive because softmax attention repeatedly reads from a large KV cache. The prevalent approach to this bottleneck is KV cache compression, which replaces the full cache with a compact summary. Despite its practical importance, the design of such summaries is largely driven by empirical experimentation. On the theoretical side, existing results show that KV cache compression can be impossible in the worst case, but offer little systematic guidance for designing algorithms in regimes where accurate compression is possible. We bridge this gap by characterizing the minimax risk of KV cache compression in terms of the intrinsic compressibility of a cache, revealing when and how accurate compression is possible. These results yield novel design principles for KV cache compression under causal masking that map efficiently to prefill and autoregressive decoding while achieving minimax-optimal risk. We instantiate these principles in a practical algorithm and report promising performance on LongBench in targeted experiments. Overall, our results provide a principled avenue for practical KV cache compression with theoretical guarantees.

AI 总结：提出DeadPool，利用非关键路径内存检查点和通信器重建协议实现零开销热替换，在无故障时无额外开销，故障时40秒内恢复，支持高达512 GPU和65B参数模型。

链接：https://arxiv.org/abs/2607.01646

作者：Haotian Xie, Junlin Chen, Mingkai Zheng, Lishan Yang, Zhao Zhang

英文摘要：State-of-the-art large language model (LLM) training takes tens of thousands of graphics processing units (GPUs) for months and encounters failures across the software and hardware stack. Existing fault-tolerance mechanisms either impose non-trivial overhead during failure-free execution or suffer from prolonged recovery latency, particularly under scenarios where a small subset of compute nodes experience permanent failures. %The tradeoff between failure-free overhead and recovery latency forms a space forms a Pareto frontier We present DeadPool to simultaneously address both optimization objectives. DeadPool incorporates a fault-tolerance mechanism that restores LLM training via hot-swapping, namely by replacing failed nodes with spare nodes without terminating the complete job. The hot-swapping of DeadPool is enabled by two ideas: First, it exploits an off-critical-path in-memory checkpointing mechanism for spatial redundancy. Second, it introduces a communicator reconstruction protocol that replaces failed nodes with spare nodes at runtime. DeadPool efficiently overlaps the in-memory checkpointing with computation, thus introducing zero overhead during error-free execution. Upon permanent node failures, DeadPool can rebuild memory states with minimal recomputation by leveraging in-memory checkpoints. We evaluate DeadPool across scales (up to 512 NVIDIA A100 GPUs) and LLMs (up to 65B parameters), and observe zero checkpoint overhead with hot-swapping recovery completing in under 40 seconds. These results show that DeadPool simultaneously achieves both zero-overhead error-free execution and extremely low recovery cost.

AI 总结：提出SCAPE分布式优化器，利用AdamS的一阶矩稳定性实现高稀疏度通信，通过基于一阶矩的掩码生成、分片并行和延迟掩码策略，在90%-99%稀疏度下保持模型质量，并减少端到端训练时间达43.3%。

链接：https://arxiv.org/abs/2607.01678

机构：Rutgers University（罗格斯大学）

作者：Mingkai Zheng, Junlin Chen, Haotian Xie, Zhao Zhang

英文摘要：Communication increasingly dominates the cost of Large Language Model (LLM) pre-training, especially under data-parallel and sharded training schemes, where gradient synchronization and parameter reconstruction overhead increase with model size and system scale. Existing communication-reduction methods either sparsify raw gradients, which can be unstable for modern Adam-style optimizers at high sparsity, or quantize communication, whose savings are fundamentally bounded by bit width and often incur additional runtime overhead. We present SCAPE, a communication-efficient distributed optimizer for LLM training that exploits the stability of AdamS's first-moment to enable aggressive sparsification without loss of LLM quality. Instead of constructing masks from raw gradients, SCAPE derives them from first-moment-based statistics, partitions mask generation across workers to align with optimizer sharding, and delays mask usage by one step so that mask synchronization can overlap with computation. SCAPE also reconstructs the quantities required for second-moment updates from a single synchronized sparse buffer, avoiding an additional collective. We implement SCAPE in Megatron-LM and evaluate its convergence by pre-training GPT-345M on OpenWebText and Llama-500M on SlimPajama-6B using 32 NVIDIA GH200 GPUs on TACC Vista. In both models, SCAPE preserves training stability, validation loss, and downstream task accuracy under 90\% and 99\% sparsity. For Llama-500M, SCAPE reduces end-to-end pre-training wall-clock time by up to 43.3\% while maintaining model quality comparable to dense AdamW and AdamS. For Llama-1.8B, SCAPE achieves up to 3.26$\times$ speedup per step compared to dense AdamS.

AI 总结：提出EPnG框架，基于路由器门控概率动态分配LoRA容量，剪枝低效专家并扩展重要专家，在固定参数预算下超越LoRA，性能媲美全微调。

链接：https://arxiv.org/abs/2607.01789

机构：Ulsan National Institute of Science & Technology (UNIST)（蔚山科学技术院）

作者：Ahin Lee, Sehyun Yun, Taesik Gong

英文摘要：Mixture-of-Experts (MoE) models scale efficiently but remain costly to adapt due to redundant experts and uniform parameter allocation. Existing parameter-efficient fine-tuning (PEFT) methods such as LoRA ignore MoE routing dynamics, leading to suboptimal resource use. We propose EPnG, an adaptive prune-and-grow framework that reallocates LoRA capacity based on expert importance derived from router gate probabilities. EPnG prunes under-utilized experts and expands high-importance experts via rank growth with orthogonal initialization, while maintaining a fixed parameter budget. Across OLMoE and Qwen1.5-MoE, EPnG consistently outperforms LoRA under the same budget and achieves performance comparable to full fine-tuning while updating only 0.55%-0.72% of parameters (up to 140x-180x fewer). These results demonstrate that aligning PEFT with MoE routing yields a more effective and scalable fine-tuning strategy.

AI 总结：提出Expander SAEs，利用左d-正则扩展器掩码支持解码器和编码器，仅学习dn个解码器值，在保持稀疏编码问题不变的情况下大幅降低存储和计算成本，实验表明在多种模型上实现了存储-保真度前沿。

链接：https://arxiv.org/abs/2607.01799

作者：Rodrigo Mendoza-Smith

英文摘要： Sparse autoencoders (SAEs) decompose internal activations of neural networks into sparse linear combinations of learned features by fitting an overcomplete dictionary $\mathbf{W}\in\mathbb{R}^{m\times n}$ with $m

AI 总结：提出kNNGuard，一种利用现成LLM激活空间的无需训练护栏，通过多层kNN融合激活和嵌入空间分数，在多个领域达到与微调方法相当或更优的F1，且速度更快。

链接：https://arxiv.org/abs/2607.02072

作者：Mahmoud Abdelfattah, Hamid Nasiri, Peter Garraghan

英文摘要：Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts. Existing guardrails predominately rely on fine-tuning to build classifiers, which often suffer from low generalization and high inference latency. We present kNNGuard, a training-free guardrail that utilizes the activation space of an off-the-shelf LLM. Given a small bank of 50 safe and unsafe prompts, kNNGuard extracts hidden activations and performs multi-layer kNN fusing activation-space and embedding-space scores for classification. Across six domains spanning topical and security prompts, kNNGuard achieves competitive or superior F1 compared to fine-tuned state-of-the-art guardrails while running 2.7x faster than the best comparable guardrail, and 10x faster than a fine-tuned safety classifier without gradient updates or fine-tuning. Domain adaptation requires only updating the labeled bank, which can be constructed in under 10 seconds and several orders of magnitude faster than established guardrails. We also analyze the impact of system prompts, layer selection, and integration into production LLM pipelines as a configurable, low-latency guardrail.

AI 总结：提出NeuFS框架，利用神经元激活模式从模型内部动态选择最具价值的少样本示例，提升大语言模型在专业领域的适应性和性能。

链接：https://arxiv.org/abs/2607.02423

作者：Zhuowei Chen, Liwei Chen, Christian Schunn, Raquel Coelho, Xiang Lorraine Li

英文摘要：Active Few-Shot Learning (AFSL) adapts LLMs to specialized domains by identifying the most valuable unlabeled samples for annotation and use as few-shot demonstrations, effectively reducing human annotation costs while promoting high performance. However, existing methods typically rely on output-level signals for sample identification, such as predictive entropy or semantic similarities with test-time data based on external embeddings, which often overlook models' internal dynamics, which could pinpoint specific knowledge gaps. To bridge this gap, we propose NeuFS, a Neuron-Aware Active Few-Shot Learning framework that shifts the selection paradigm from output-level proxies to models' internal dynamics. NeuFS utilizes neuron activation patterns to represent sample directly, and includes a dual-criteria selection strategy that: (1) ensures few-shot sample diversity with neuron patterns for broader example coverage, while (2) prioritizing on identifying informative and challenging few-shot samples LLMs tend to hallucinate by quantifying neuron consensus. Experiments on three datasets demonstrate that NeuFS excels in both reasoning and text classification tasks, outperforming existing AFSL baselines. Ablation studies further highlight that internal neuron activations provide a more principled and effective selection signal than external embeddings, validating the superiority of the proposed NeuFS.

AI 总结：提出Neuron-OPSD框架，利用神经元激活指导训练数据选择和教师上下文构建，通过在线策略蒸馏实现无标注自蒸馏，提升领域内性能并保持跨领域泛化。

链接：https://arxiv.org/abs/2607.02460

机构：University of Pittsburgh（匹兹堡大学）

作者：Zhuowei Chen, Xiang Lorraine Li

英文摘要：Post-training large language models (LLMs) without real-world interaction feedback or human-labeled supervision remains challenging, particularly in specialized domains where expert annotations are costly to obtain. Recent annotation-free self-evolution methods address this by using the model's own outputs as supervision signals, constructing a teacher via additional context and aggregating predictions across multiple rollouts through majority voting to produce pseudo-labels. However, these approaches are not without drawbacks: SFT- and GRPO-based variants suffer out-of-domain performance degradation, while reward-based on-policy RL inflates calibration error. In this paper, we propose Neuron On-Policy Self-Distillation (Neuron-OPSD), a data-centric framework for annotation-free self-distillation that leverages internal neuron activations to guide both training-data selection and teacher context construction. The model is then trained via on-policy distillation from the teacher distribution, requiring no ground-truth labels at any stage. Across specialized-domain benchmarks, Neuron-OPSD improves in-domain task performance while preserving cross-domain generalization and mitigating calibration collapse over prior annotation-free baselines. This framework is particularly relevant to settings where online interaction or external supervision is costly or infeasible, and is conceptually distinct from offline RL approaches that rely on logged, reward-labeled trajectories.

AI 总结：提出FedCGNM客户端优化器，通过类分组归一化动量平衡梯度幅度并降低噪声，结合FedHOO算法高效优化重采样率，在长尾数据集上优于基线方法。

链接：https://arxiv.org/abs/2607.01474

作者：Haemin Park, Diego Klabjan, Martin W. Braun, Xiuqi Li, Balakrishnan Ananthanarayanan

英文摘要：Class imbalance poses a critical challenge in federated learning (FL), where underrepresented classes suffer from poor predictive performance yet cannot be addressed by standard centralized techniques due to privacy and heterogeneity constraints. We propose FedCGNM (Federated Class-Grouped Normalized Momentum), a client-side optimizer in FL that partitions classes into a small number of groups based on minimum within-group variance, maintains a momentum per group, normalizes each group momentum to unit length, and uses the summation of the normalized group momentums as an update direction. This design both equalizes gradient magnitude across majority and minority groups and mitigates the noise inherent in rare-class gradients. We further provide a theoretical convergence analysis explicitly accounting for time-varying resampling-rates. Additionally, to efficiently optimize these rates in small-client regimes, we introduce FedHOO, an X-armed-bandit (XAB) based algorithm that exploits federated parallelism that evaluates many combinations of two candidate rates per client at linear cost. Empirical evaluation on four public long-tailed benchmarks and a proprietary chip-defect dataset demonstrates that FedCGNM consistently outperforms baselines, with FedHOO yielding further gains in small-scale federations.

AI 总结：本文研究分布式学习中拜占庭鲁棒性、本地差分隐私与泛化误差之间的关系，发现隐私对泛化的影响是非单调的：强隐私下增加隐私降低泛化误差，弱隐私下则相反。

链接：https://arxiv.org/abs/2607.01492

作者：Thomas Boudou, Batiste Le Bars, Nirupam Gupta, Aurélien Bellet

英文摘要：Recent work has established a fundamental trilemma between Byzantine robustness, local differential privacy (LDP), and optimization error in distributed learning. We show that this trilemma does not universally extend to generalization error, but instead depends critically on the privacy regime. Specifically, in the high-noise regime (strong privacy), we prove that increasing privacy reduces the generalization error, i.e., there is no tension between robustness and privacy. In the low-noise regime (weaker privacy), however, the tension between robustness and privacy reappears and increasing privacy indeed degrades generalization. Our theory explains this surprising non-monotonic behavior of the generalization error via matching lower and upper bounds on the algorithmic stability of Byzantine-robust distributed learning under LDP constraints. We corroborate and further analyze these theoretical findings with empirical evaluations.

AI 总结：提出一种模型无关的分布式学习框架，结合隐私增强编码计算与鲁棒聚合及验证技术，同时抵御联邦和去中心化学习中的隐私泄露与恶意攻击。

链接：https://arxiv.org/abs/2607.02187

作者：Xavier Martínez-Luaña, Alba Gude-Santos, Manuel Fernández-Veiga, Rebeca P. Díaz-Redondo

英文摘要：Distributed machine learning enables collaborative model training without centralizing data, but it also exposes learning processes to privacy leakage and malicious manipulation. Existing defenses typically address these threats in isolation and are often tailored to specific learning paradigms or model architectures, limiting their applicability in realistic deployments. In particular, federated learning and decentralized learning exhibit distinct adversarial surfaces that are rarely addressed within a unified framework. In this paper, we present a model-agnostic framework for adversary-resistant distributed learning that jointly addresses privacy preservation and malicious behavior across both federated and decentralized settings. Our approach combines paradigm-specific defense mechanisms with GPBACC, a privacy-enhancing coded computing technique applicable to arbitrary machine learning models. For federated learning, we integrate robust aggregation strategies to mitigate the impact of malicious participants, while for decentralized learning we employ approximate decode-and-compare and group testing techniques to enable lightweight verification and adversary isolation without relying on a trusted aggregator. Crucially, we evaluate the proposed framework through an explicit, attack-driven analysis. We implement representative privacy attacks and malicious behaviors, and empirically demonstrate that the combination of GPBACC with robust aggregation and verification mechanisms significantly reduces privacy leakage and improves resilience against active adversaries. These results suggest that privacy-enhancing coded computing, when combined with appropriate adversary-resistance strategies, provides a practical and deployable foundation for secure distributed machine learning.

AI 总结：提出QFedAgent混合量子-经典个性化联邦学习框架，通过变分量子电路融合模块减少参数开销，在非独立同分布多模态数据上实现97.7%准确率。

链接：https://arxiv.org/abs/2607.02426

作者：Quoc Bao Phan, Tuy Tan Nguyen

英文摘要：Federated learning (FL) enables collaborative model training across distributed devices without sharing raw data, making it suitable for privacy-sensitive robotic sensing applications. However, multi-agent systems generate heterogeneous and non-independent and identically distributed (non-IID) multimodal sensor streams that degrade conventional FL algorithms, while classical fusion modules introduce substantial parameter overhead and communication cost. This paper proposes QFedAgent, a hybrid quantum-classical personalized FL framework for multi-agent activity recognition. The approach integrates a variational quantum circuit fusion module that models accelerometer--gyroscope interactions through quantum state encoding and entanglement, requiring only 72 quantum rotation parameters versus 33K in classical multi-layer perceptron-based fusion, achieving approximately 10x total parameter reduction. Experiments on the OPPORTUNITY dataset under subject-based non-IID partitions demonstrate 97.7% mean test accuracy, confirming that parameter-efficient quantum fusion remains competitive with conventional federated baselines.

AI 总结：研究编程示例系统中对抗性示例损坏的鲁棒性，提出版本空间分区聚合（VPA）防御方法，实验表明低裕度任务易受攻击，VPA仅在语义分区投票裕度存在时有效。

链接：https://arxiv.org/abs/2607.01280

作者：Yuan Si, Jialu Zhang

英文摘要：Programming-by-example systems infer programs from a small set of input-output examples. Robust PBE work usually models wrong examples as samples from a stochastic noise process and then minimizes an expected or empirical loss. This paper studies a different failure mode: an adversary who sees the synthesizer and chooses the examples whose corruption most damages the returned program. We formalize fixed-set worst-case corruption for finite PBE version spaces, implement exact-within-bounded-pool and heuristic corruption searches for a string-transformation DSL, and introduce version-space partition aggregation (VPA), a defense that synthesizes on disjoint example groups and votes by semantic signatures. The central claim is deliberately bounded and partly negative: low-margin PBE tasks have an adversarial robustness dimension that random-typo and noisy-PBE evaluations miss, while semantic partition aggregation helps only when the clean semantics keep a partition vote margin, which often fails on realistic tasks. Evidence from curated/generated DSL tasks, accepted public SyGuS PBE_SLIA slices, SYNTRA Playgol v2, and noisy-PBE objective baselines supports that boundary. One curated edit flips all 8 spike tasks while 200-trial typo, DSL-pool, and distance-matched random controls succeed on 10.3%, 11.0%, and 16.7%; generated margin-1 rows flip under budget 1 yet VPA recovers them; on public SyGuS the vote margin is near one, so an adaptive attacker drives VPA accuracy to zero; accepted public SyGuS slices move across exact-within-pool budget boundaries; and Playgol shows positive paired-bootstrap gaps against typo and same-pool random controls on the 141 accepted rows. A small exact-output prompt harness over 20 controlled margin-1 tasks shows the same qualitative clean-to-attacked pattern across local and API models, while it is treated as a scope check, not a broad LLM benchmark.

AI 总结：提出一种基于认证世界模型的感知时钟，通过漂移感知的截止时间规则决定主动感知时机，在合成基准和3D VN-JEPA模型上验证了有效性。

链接：https://arxiv.org/abs/2607.01537

作者：Hongbo Wang

英文摘要：Certified world models estimate how long their predictions remain valid. We turn this validity horizon into an operational sensing clock: a rule for when an agent should stop coasting and re-sense. Starting from an audited equivariant world model, we derive a deadline for no-sensing intervals and show that deployable deadlines in learned world models must be drift-aware: on-manifold Lyapunov rates alone overestimate coasting validity, while calibrated native rollout-drift envelopes carry the deployed guarantee. On a frozen 3D VN-JEPA model, the resulting clock controls held-out interval-simultaneous certificate violation across seeds and data shards. In a cue-conditioned theorem-bed (a synthetic bench where all schedulers share the exact model, isolating the scheduling rule), the clock remains valid on the deployment distribution and substantially reduces eventful-tail violations relative to exact-mixture expected-belief scheduling at matched sensing budget. We also report limits: in the short-horizon frozen VN-JEPA regime, empirical conformal horizons match the deployed clock on validity and budget, and a partial-reset exploration finds no clean budget-matched advantage for the spectral term. Thus the contribution is a certified sensing-clock primitive and drift-aware deployment method, not a claim that spectral clocks empirically dominate all non-spectral schedulers.

AI 总结：提出分子扰动框架，通过控制图编辑距离生成结构变体，揭示分子LLMs对微小结构变化敏感，局部信任区域狭窄；上下文调优可部分缓解脆弱性。

链接：https://arxiv.org/abs/2607.01800

机构：The Hong Kong Polytechnic University（香港理工大学）； National University of Singapore（新加坡国立大学）； Shanghai AI Lab（上海人工智能实验室）； Fudan University（复旦大学）

作者：Jiatong Li, Weida Wang, Changmeng Zheng, Shufei Zhang, Yatao Bian, Xiao-yong Wei, Qing Li

英文摘要：Large Language Models (LLMs) have recently shown promise in molecular discovery, yet a gap remains between their probabilistic nature over discrete sequential tokens and the rigid topological constraints of chemical space. This raises the question of whether molecular LLMs can generalize beyond the local neighborhoods induced by their sequence-based representations. To systematically investigate this question, we introduce a Molecular Perturbation framework that generates syntax-valid structural variants of training molecules under controlled Graph Edit Distance (GED) to probe the manifold regularity of molecular LLMs. Our analysis shows that even a single edit can cause substantial performance drops on common molecular tasks, revealing a narrow local trust region and fragile sensitivity to structural changes. Since similar molecules tend to exhibit similar properties, In-Context Tuning (ICT), which anchors predictions on structurally similar molecules, offers a natural way to mitigate such fragility. Our experiments also examine whether ICT confers robustness under controlled structural perturbations, and the results suggest that it can partially expand the local trust region and offer a promising direction for stabilizing molecular LLMs against structural variation.

AI 总结：研究众包事实核查系统中矩阵分解桥接机制对协调操纵的脆弱性，发现通过少于10个评分即可操纵低质量笔记达到共识阈值，并提出了缓解措施。

链接：https://arxiv.org/abs/2607.01824

作者：Nikil Roashan Selvam, Jay Baxter, Sophie Hilgard, Brad Miller, Keith Coleman, Ellen Vitercik, Sanmi Koyejo

英文摘要： Crowdsourced fact-checking systems have been adopted by major social media companies such as X, Meta, TikTok and Google with the aim of combating misleading information at scale without relying on centralized editorial control. These systems have been developed around a common underlying concept: a bridging mechanism that identifies notes flagging misleading information when they receive support from people with different perspectives rather than simple majority support. To our knowledge the only publicly disclosed bridging algorithms deployed for fact-checking are based on matrix factorization, as deployed by both X and Meta, augmented with additional components addressing abuse, targeted manipulation, and contributor brigades. This work examines the core matrix factorization portion of these systems, presenting theoretical and empirical evaluations of the degree to which coordinated users could vote strategically by leveraging the latent representations to fabricate the appearance of synthetic consensus within the bridging mechanism. Using historic production data, we find that up to 10.7% of lower quality notes could be manipulated above consensus thresholds using less than 10 ratings. We complement these findings with a theoretical analysis, revealing counterintuitively that rating a note as "Not Helpful" can increase its helpfulness score, as well as a cost model quantifying manipulation effort. We have developed and deployed mitigations within X's Community Notes algorithm to address synthetic consensus.

AI 总结：提出DALorRA，一种变分贝叶斯稀疏框架，通过随机掩码低秩适应中的秩维度实现模型容量正则化和校准，在不牺牲推理精度下提升LLM校准性能。

链接：https://arxiv.org/abs/2607.02182

作者：Jijie Zhang, Zhe Ren, Quan Zhang, Dandan Guo

英文摘要：Large language models (LLMs) exhibit remarkable reasoning capabilities, but their task-specific fine-tuning is notoriously plagued by overconfidence, severely hindering trustworthy deployment. We propose Data-Adaptive Lower-Rank Adaptation (DALorRA), a simple and effective variational Bayesian sparse framework that shifts the paradigm of uncertainty quantification from the dense parameter space to the lightweight rank level of low-rank adaptation (LoRA). With the insight that LoRA essentially aggregates multiple rank-one components that may provide superfluous model capacity, DALorRA imposes stochastic masking on rank dimensions, enabling Bayesian regularization of model capacity during training and ensemble-like calibration during inference. Extensive experiments demonstrate DALorRA's excellent calibration of LLMs without compromising reasoning accuracy.

AI 总结：提出X-LogSMask，一种可解释的多头对数结构掩码，将对称归一化图拓扑直接注入注意力logits，使标准Transformer无需修改架构即可有效处理图数据，在20个基准测试中13个达到最优。

链接：https://arxiv.org/abs/2607.01553

作者：Leyan Li, Rennong Yang, Zhenxing Zhang, Liping Hu

英文摘要：Transformers have become general-purpose architectures, but their all-to-all self-attention is poorly matched to graph data, whose interactions are sparse, structured and multi-scale. Existing Graph Transformers address this mismatch through structural encodings, hybrid message-passing modules or learned attention constraints, often introducing additional complexity and limited interpretability. Here we introduce X-LogSMask, an explainable multi-head logarithmic structural mask that injects symmetrically normalized graph topology directly into attention logits. The logarithmic transform converts structural connectivity into a topology-aware gating signal, suppressing unsupported node interactions while preserving feature-dependent attention. By assigning different powers of the normalized adjacency matrix to different attention heads, X-LogSMask gives each head a defined structural radius and supports multi-hop information propagation within a single layer. We further show that a standard Transformer encoder can be interpreted as one-step message passing on a complete graph, motivating X-LogSMask as a topology-constrained alternative to unrestricted self-attention. Across 20 node-, edge- and graph-level benchmarks, Transformers equipped with X-LogSMask achieve state-of-the-art performance on 13 datasets and remain competitive in a lightweight one-layer configuration. These results show that simple, interpretable structural masks can make self-attention an effective graph-learning operator without changing the Transformer architecture. The code is available at this https URL.

AI 总结：提出MKGR框架，结合区域感知蛋白质序列编码与四个生物医学知识图谱，通过桥接重建目标和成对门控模块，在冷启动场景下显著提升PPI预测性能。

链接：https://arxiv.org/abs/2607.01627

机构：College of Computer and Information Science, Southwest University（西南大学计算机与信息科学学院）

作者：Wenbo Zhang

英文摘要：Accurate protein-protein interaction (PPI) prediction is central to functional genomics, disease mechanism discovery, and drug development. A difficult setting arises when candidate interactions include proteins that have no observed PPI edges during training, where models relying on network topology alone often lose useful context. This paper presents \method, a multimodal representation framework for cold-start PPI prediction. \method\ combines region-aware protein sequence encoding with four protein-centered biomedical knowledge graphs, including protein-drug, protein-disease, protein-miRNA, and protein-lncRNA associations. The sequence branch extracts contextual representations from structurally informed sequence regions, while graph attention encoders learn modality-specific protein embeddings from sparse biomedical associations. A bridge reconstruction objective regularizes graph learning by recovering shared protein-entity associations, and a pair-level gating module adaptively integrates sequence and graph evidence for each candidate protein pair. Experiments on two benchmark datasets under novel-old and novel-novel cold-start settings show that \method\ consistently outperforms competitive sequence, network, and knowledge-graph baselines across ACC, F1, AUC, AUPR, and MCC.

AI 总结：提出动态神经图编码器（DNG-Encoder），通过动态图表示神经网络参数并保留推理的时序特性，在INR分类任务上比现有方法提升约10%准确率。

链接：https://arxiv.org/abs/2607.02166

作者： Di Wu, Huan Liu, Zhixiang Chi, Yuanhao Yu, Konstantinos N. Plataniotis, Yang Wang

英文摘要：The rapid advancements in using neural networks as implicit data representations have attracted significant interest in developing machine learning methods that analyze and process the weight spaces of other neural networks. However, efficiently handling these highdimensional weight spaces remains challenging. Existing methods often overlook the sequential nature of layer-by-layer processing in neural network inference. In this work, we propose a novel approach using dynamic graphs to represent neural network parameters, capturing the temporal dynamics of inference. Our Dynamic Neural Graph Encoder (DNG-Encoder) processes these graphs, preserving the sequential nature of neural processing. Additionally, we also leverage DNG-Encoder to develop INR2JLS (Implicit Neural Representation to Joint Latent Space) for facilitate downstream applications, such as classifying Implicit Neural Representations (INRs). Our approach demonstrates significant improvements across multiple tasks, surpassing the state-of-the-art INR classification accuracy by approximately 10% on the CIFAR-100-INR.

AI 总结：研究通过自蒸馏策略优化（SDPO）发现，同策略自蒸馏在持续后训练中会加剧遗忘甚至崩溃，而GRPO等强化学习方法更保守地保留先前能力，表明密集自蒸馏并非默认的稳定器。

链接：https://arxiv.org/abs/2607.01763

作者：Meng Wang, Haohan Zhao, Wenzhuo Liu, Lu Yang, Geng Liu, Haiyang Guo, Guo-Sen Xie, Gaofeng Meng, Hongbin Liu, Fei Zhu

英文摘要：Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities. Recent work suggests that on-policy learning can mitigate forgetting, with on-policy self-distillation emerging as a particularly attractive approach. In this work, we revisit this optimistic view through self-distillation policy optimization (SDPO). Our experiments show that SDPO can accelerate in-domain specialization when teacher signals are stable and well aligned, but it struggles to generalize to out-of-distribution scenarios. In continual post-training, SDPO exhibits stronger forgetting and can even collapse, whereas on-policy reinforcement learning methods such as GRPO adapt more conservatively and better preserve prior capabilities. Further analyses reveal that denser self-distillation induces larger drift in both parameter space and response space, and can amplify high-frequency formatting artifacts through a self-reinforcing teacher--student loop. These findings suggest that on-policy data alone is insufficient for continual learning. Dense self-distillation can accelerate specialization when teacher targets are stable and token-level supervision is reliable, but it should not be treated as a default stabilizer for continual post-training. Our code is available at this https URL.

AI 总结：本研究系统刻画了多探针网格算法在数据集大小N和维度d上的缩放行为，发现其在GloVe嵌入上具有恒定的维度缩放指数，优于图、树和分区方法，且索引成本更低。

链接：https://arxiv.org/abs/2607.01283

机构：University of California, Berkeley（加州大学伯克利分校）； University of Toronto, St. George（多伦多大学圣乔治校区）； Independent Researcher（独立研究员）； University of Waterloo（滑铁卢大学）

作者：Matthew J Liu, Wei Hang Zheng, Vidhan Purohit, Siqi Xie, Chieh-En Li, Jerry Li, Noah Flynn

英文摘要：Grid-based approaches to approximate nearest neighbor (ANN) search have been absent from modern scaling analyses. We present a systematic characterization of a multiprobe grid algorithm with respect to dataset size $N$ and dimensionality $d$. Our experiments reveal a previously unreported $d$-scaling crossover on the GloVe embedding family, in which multiprobe grid search maintains an approximately constant dimensional scaling exponent while other graph-, tree-, and partitioning-based methods exhibit degrading throughput. The advantage comes with near-linear query scaling in $N$, but also with lower indexing cost than competing ANN methods. Our results suggest that grid-based methods such as multiprobe grid may be competitive in rebuild-heavy or high-dimensional settings where indexing cost and dimensional robustness dictate performance. More broadly, recent work has formalized self-attention as an ANN operation. Thus, the $N$- and $d$-scaling properties of ANN algorithms may guide cost analysis of efficient transformer architectures. Code is available at: this https URL.

AI 总结：提出IonSense-QKG框架，通过添加量子相关元数据和量子就绪评分，帮助筛选适合混合量子-经典机器学习工作流的锂离子电池公开数据集。

链接：https://arxiv.org/abs/2607.01286

机构：Amrita School of Computing, Amrita Vishwa Vidyapeetham（阿姆里塔计算学院，阿姆里塔大学）

作者：Sakthi Prabhu Gunasekar, Prasanna Kumar Rangarajan

英文摘要： Public lithium-ion battery datasets are increasingly used for state-of-health estimation, remaining-useful-life prediction, anomaly detection, electrochemical diagnostics, second-life analytics, and battery safety research. However, these datasets vary substantially in chemistry, modality, scale, label quality, sequence structure, access status, and preprocessing complexity. These differences directly affect whether a dataset is feasible for near-term hybrid quantum-classical machine-learning workflows. This paper presents IonSense-QKG, a quantum-readiness metadata framework for lithium-ion battery dataset discovery. Starting from the EV-Battery-IonSense index, the proposed framework enriches public battery dataset records with quantum-relevant metadata, including task type, sensing modality, chemistry, label availability, sequence type, preprocessing requirements, candidate quantum encodings, estimated qubit range, and NISQ feasibility. A transparent Quantum Readiness Score is introduced to rank datasets as candidate resources for future hybrid quantum-classical battery benchmarks. The score is intended as a dataset-selection heuristic, not as evidence of quantum advantage. The framework demonstrates query-based discovery over enriched metadata to identify datasets suitable for compact quantum feature maps, quantum time-series workflows, limited-label anomaly detection, and future battery-health benchmarking. The released artifact includes metadata tables, scoring scripts, robustness checks, link-checking utilities, and SQL-style query examples. IonSense-QKG positions dataset selection as a data-management problem and provides a reproducible foundation for data-centric quantum battery analytics.

AI 总结：本研究系统比较了离散、连续和混合数值编码策略在合成算术任务和真实临床预测任务中的表现，发现混合令牌方法在精度与鲁棒性间取得最佳平衡，并提出基于数据集大小的经验幂律确定最优分箱数。

链接：https://arxiv.org/abs/2607.01391

作者：Maria Elkjær Montgomery, Christian Igel, Mikkel Odgaard, Martin Sillesen, Mads Nielsen

英文摘要：How do we encode numeric values in transformer-based sequence processing, particularly in electronic health record (EHR) data? We systematically compare discrete, continuous, and hybrid value encoding strategies using synthetic arithmetic tasks embedded within real-world EHR data, as well as real-world clinical prediction tasks. Our study reveals trade-offs between numeric precision, optimisation stability, and architectural flexibility. We find that approaches that explicitly model value-concept interactions perform best on precision-sensitive arithmetic tasks when architectural constraints permit. Hybrid token-based approaches that retain numeric values but apply binning prior to projection provide a more robust and broadly applicable alternative, with the optimal number of bins following a simple empirically derived power-law in dataset size. Across tasks, models consistently exhibit reliable "good enough" numeric computation rather than exact arithmetic, while clinical gains from incorporating laboratory values are task-dependent. This suggests that robustness and deployability often outweigh maximal numeric precision in practice, motivating hybrid token-based approaches as a practical default.

AI 总结：研究条件推理树和森林作为top-k特征排序方法，通过实验验证其性能，发现Bonferroni校正和自适应停止对运行时间影响显著，而森林特征采样可能遗漏重要特征。

链接：https://arxiv.org/abs/2607.01417

机构：Amazon Web Services（亚马逊云服务）

作者：Robert Milletich, Justin Downes, Steve Goley, Newel Hirst

英文摘要：Conditional inference trees (CIT) and conditional inference forests (CIF) reduce split-selection bias by testing features before choosing split thresholds, but repeated permutation tests and threshold searches can make these methods computationally expensive. We study CIT and CIF as top-$k$ feature-ranking methods for downstream prediction using real-data benchmarks, runtime ablations, and synthetic feature-recovery experiments. At a fixed node, if the features and permutation budget do not depend on the node responses, Bonferroni-corrected $+1$ Monte Carlo permutation $p$-values control nodewise rejection under the complete permutation null. CIF ranks 4th among 17 classification methods on 22 datasets and 3rd among 18 regression methods on 8 datasets. With Bonferroni correction held fixed, the CIF runtime ablations indicate that adaptive stopping and the number of thresholds searched have the largest measured effect on runtime: turning off adaptive stopping and using exact threshold search increase fitting time by 4.0--8.4$\times$ and 1.9--10.8$\times$, respectively, while downstream score changes are at most 0.011. Sparse high-$p$ simulations indicate that forest feature sampling can leave informative features out of many split decisions. Overall, the results support CIF as a top-$k$ feature-ranking method in the evaluated downstream prediction benchmarks.

AI 总结：提出一个包含模型大小、训练步数和批大小的三术语缩放定律，能正确恢复最优批大小缩放，且拟合所需训练运行次数更少。

链接：https://arxiv.org/abs/2607.01487

机构：Inria, École Normale Supérieure, PSL Research University（法国国家信息与自动化研究所，巴黎高等师范学院，巴黎文理研究大学）

作者：Fabian Schaipp

英文摘要：We propose a scaling law that takes into account model size and training data while explicitly splitting the latter into training steps and batch size (called three-term law). Fitting the proposed law on a large set of training runs, we find that it correctly recovers the scaling of the optimal batch size. Moreover, because it makes use of training runs with suboptimal batch size, our proposed law can be robustly fit with a significantly smaller amount of training runs. We further show that the three-term law can be used to derive scaling laws for suboptimal batch sizes, and that it matches previous empirical findings related to the critical batch size.

AI 总结：提出基于LLM进化的特征工程框架EFE，通过Python程序表示变换，利用数据集上下文和验证集性能反馈优化，在时间序列和表格预测任务中提升准确性和可解释性。

链接：https://arxiv.org/abs/2607.01548

机构：University of Michigan（密歇根大学）； Google Research（谷歌研究院）

作者：Ege Onur Taga, Yilin Zhuang, M. Emrullah Ildiz, Petros Mol, Abhimanyu Das, Karthik Duraisamy, Samet Oymak

英文摘要： Large language models are increasingly used as open-ended search operators in evolutionary optimization. We introduce Evolutionary Feature Engineering (EFE), a framework for using LLM-based evolution to discover preprocessing transformations for structured data. EFE represents transformations as Python programs with a standardized fit/transform interface, allowing them to be inserted directly into existing machine learning pipelines. During evolution, candidate programs are refined using dataset context, summary statistics, and downstream performance feedback on validation set. We instantiate EFE in two settings. For time-series forecasting, EFE-Time learns invertible, dataset-specific normalizations that improve off-the-shelf time-series foundation models. It reduces forecasting errors (MASE, WQL, MAE) 3% or more when averaged across datasets and improvements are as much as 19% on the COVID-Deaths dataset. Notably, these improvements occur with recent TSFMs such as Chronos-2. For tabular prediction, EFE-Tab evolves compact feature programs that add useful interpretable features and remove redundant ones, improving or matching existing LLM-based feature-engineering methods. We found EFE-Tab to be particularly effective on classical decision trees, where small sets of evolved features yield competitive accuracy while preserving interpretability. Overall, EFE demonstrates that LLM-based evolution can improve both accuracy and interpretability when automatically tackling structured data.

AI 总结：提出WARP框架，通过模型合并生成伪检查点，从权重空间几何特征恢复微调模型的训练数据域混合比例，在BERT和GPT-2上平均MAE分别低至0.046和0.104。

链接：https://arxiv.org/abs/2607.01686

机构：University of Wisconsin-Madison（威斯康星大学麦迪逊分校）

作者：Tzu-Heng Huang, Aditya Goyal, John Cooper, Frederic Sala

英文摘要：Foundation models are routinely released to the public, yet the data recipes used to train them -- such as domain mixture weights that determine how different sources are sampled -- are rarely disclosed. This creates an access asymmetry: researchers study the resulting models but lack visibility into the training distribution that produces them. Prior works for inferring training data, such as membership inference, detect at the level of individual samples and thus cannot characterize the global composition of the training corpus. We introduce WARP, a framework that recovers a fine-tuned model's training mixtures directly from its released weights. WARP interpolates between the base and fine-tuned models using model merging, generating pseudo-checkpoints that approximate the missing training trajectory and expose a geometric footprint of the training data in the weight space. From these simulated footprints, WARP extracts geometric features and maps them to domain proportions using either a parameter-free softmax readout or an MLP projector trained on synthetic mixtures. In controlled experiments with BERT and GPT-2, WARP recovers domain mixtures with an average MAE as low as 0.046 and 0.104 respectively, outperforming membership inference and a variant with access to the true training trajectory.

AI 总结：提出多角色评分标准生成框架(MRRG)，通过整合多个互补角色的评估标准，消除单一通用评估器的维度盲区，在偏好验证和强化学习奖励信号上均优于基线。

链接：https://arxiv.org/abs/2607.01830

机构：School of Data Science, The Chinese University of Hong Kong, Shenzhen, China（香港中文大学（深圳）数据科学学院）； LIGHTSPEED； Independent Researcher（独立研究员）

作者：Dazhi Fu, Jiuding Yang, Yiwen Guo, Jicong Fan

英文摘要：Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks. Rubric-based judges offer a transparent way to decompose such judgments into explicit evaluation criteria, but existing annotation-free rubric generators typically rely on a single generic evaluator. As a result, they may overlook important dimensions of human preference, a failure mode we term dimensional blind spots. To address this limitation, we propose Multi-Role Rubric Generation (MRRG), a training-free and reference-free framework that elicits evaluation criteria from multiple complementary roles and consolidates them into an auditable rubric-based scorer. This scorer can be used both to validate pairwise preferences and to provide rewards for GRPO-style Reinforcement Learning with Verifiable Rewards (RLVR). Experiments on preference validation benchmarks show that MRRG consistently outperforms single-role rubric generation baselines across multiple backbone models. Further RLVR experiments demonstrate that MRRG yields a stronger reward signal for improving open-ended generation.

AI 总结：提出统一无调优时间序列基础模型Zeus，通过多尺度Transformer和Multi-Objective Temporal Masking策略，在无需任务特定调优下实现多种分析任务的优异性能。

链接：https://arxiv.org/abs/2607.01918

作者：Yisong Fu, Zezhi Shao, Chengqing Yu, Yujie Li, Yongjun Xu, Xueqi Cheng, Fei Wang

英文摘要：We present Zeus, a unified tuning-free Time Series Foundation Model (TSFM) that delivers superior performance across diverse analysis tasks without any task-specific fine-tuning. Unlike prior studies that primarily focus on zero-shot forecasting but require task-specific tuning for other tasks, Zeus bridges this gap by addressing two fundamental challenges in multi-task generalization. First, to reconcile point-level granularity with long-sequence scalability, Zeus incorporates a multi-scale Transformer featuring point-wise tokenization and a U-shaped hierarchy, effectively balancing fine-grained fidelity with computational efficiency. Second, to accommodate varying inductive biases across different tasks, Zeus introduces Multi-Objective Temporal Masking (MOTM), a unified strategy that supports heterogeneous tasks (e.g., extrapolation, interpolation, and global abstraction) within a single framework. Extensive experiments across five representative tasks demonstrate that Zeus consistently achieves competitive results in tuning-free settings, underscoring its potential as a general-purpose TSFM.

AI 总结：揭示A/B测试可能比离线评估产生更高算法选择错误率的反直觉现象，提出通过引入假设中间算法并逐步估计性能差异来诱导正相关，从而减少关键选择错误。

链接：https://arxiv.org/abs/2607.01958

机构：Hakuhodo DY Holdings Inc.（博报堂DY控股公司）； Cornell University（康奈尔大学）

作者：Koki Konishi, Masataka Ushiku, Yuta Saito

英文摘要： A/B testing is the gold standard for selecting the better algorithm in online services. While offline evaluation has attracted attention as a safer alternative due to the high experimental costs and the potential risk of degrading user experience and revenue in A/B testing, it is widely recognized that the estimation accuracy of offline evaluation is substantially lower. As a result, final selection decisions are typically made through A/B testing. Contrary to this conventional view, we reveal a counterintuitive phenomenon in which A/B testing can produce a higher algorithm selection error rate than offline evaluation. This occurs because the sample mean estimator used in A/B testing does not induce positive correlation, which is crucial for reducing critical selection errors, namely underestimating the truly superior algorithm and overestimating the truly inferior one. In contrast, offline evaluation methods unintentionally generate this beneficial correlation by relying on shared offline data when estimating and comparing the performance of multiple algorithms. Building on this insight, we propose an estimator that intentionally induces positive correlation to improve algorithm selection in A/B testing. The key idea is to introduce a hypothetical middle algorithm and to estimate the performance difference between algorithms A, M, and B in a stepwise manner using shared data at each step. This approach enables the application of offline evaluation techniques in each step, thereby inducing positive correlation and reducing critical selection errors. Furthermore, we derive the optimal middle algorithm regarding the resulting variance and analyze its advantages over existing methods through bias-variance analysis. Experiments on real-world data demonstrate that our estimator achieves the same selection error rate as existing approaches while using only one half of the A/B testing data.

AI 总结：本研究在统一协议下比较九种轻量级CNN，发现EfficientNet-B0在精度与资源间取得最佳平衡，而新模型仅在特定场景有优势。

链接：https://arxiv.org/abs/2607.01984

作者：Tasnim Shahriar

英文摘要：Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims require controlled evaluation. This study compares nine lightweight CNN model packages across CIFAR-10, CIFAR-100, and Tiny ImageNet under a shared downstream protocol. We report top-1 accuracy, macro F1, top-5 accuracy, parameter count, FP32 storage, GMACs, batch-size-1 latency on an NVIDIA L4 and AMD Ryzen 5 5500U CPU, peak PyTorch CUDA allocated tensor memory, and point estimate Pareto frontiers. EfficientNetV2-S achieves the highest observed top-1 accuracy on CIFAR-10 and CIFAR-100 at 97.57% and 86.98%, while RepViT-M1.0 leads Tiny ImageNet at 79.87%. EfficientNet-B0 remains within 0.22, 0.85, and 1.79 percentage points of the best result on the three datasets while using approximately 79% fewer parameters and 86% fewer GMACs than EfficientNetV2-S. It also appears on every evaluated accuracy and resource Pareto frontier, making it the most consistently competitive intermediate-budget option. MobileNetV3-Small has the lowest GMAC count, is the fastest model under both CPU thread settings, and records higher observed accuracy than MobileNetV4-Conv-S on all three datasets. Under random initialization, it leads MobileNetV4-Conv-S by 2.55, 1.76, and 0.99 points, with paired test-set intervals excluding zero for the fixed trained models. EfficientNet-B0 remains 3.29, 10.10, and 17.54 points below its pretrained counterpart after 100 epochs of scratch training, despite requiring about five times the recorded training time. SqueezeNet1.1 has the fewest parameters and lowest peak CUDA allocation, but substantially weaker accuracy. Latency rankings differ sharply between the L4 and CPU environments, showing that GMACs alone do not predict measured inference performance. Overall, newer designs provide selective rather than universal gains

AI 总结：提出一种基于Haar离散小波和t检验的无监督时间序列异常检测算法，在343个数据集上超越现有无监督和自监督方法。

链接：https://arxiv.org/abs/2607.02046

作者：Emanuele Mele, Massimo Cafaro, Angelo Coluccia, Italo Epicoco

英文摘要：Anomaly detection is a critical and evolving field in Machine Learning, with applications targeting different domains such as cybersecurity, finance, healthcare, manufacturing and IoT (Internet of Things) systems. Traditionally, anomaly detection algorithms have been designed using both supervised and unsupervised learning paradigms. The fundamental challenge in real-world anomaly detection scenarios is related to the inherent class imbalance (anomalies are typically rare) and, for supervised methods, to the scarcity of labelled anomalous data. Indeed, labelling is both expensive and time-consuming. Conversely unsupervised methods do not require labelling, but may suffer from high false positive rates when deployed in safety-critical applications. In this work we introduce a novel unsupervised algorithm for anomaly detection in time series based on the Haar discrete wavelet and a suitably designed $t$-test. We establish the theoretical foundation of the proposed $t$-test and, through extensive experimentation across 343 datasets, demonstrate that our algorithm outperforms state-of-the-art unsupervised and self-supervised benchmarks.

AI 总结：针对空间相关数据中随机划分导致的数据泄露和隐藏分层问题，提出结构感知分层划分（SASP）减少时空泄露并保持类别平衡，以及课程分布鲁棒优化（CDRO）稳定训练，提升泛化与校准可靠性。

链接：https://arxiv.org/abs/2607.02055

作者：Prathamesh Patil, Arpit Jain, Aswanth Krishnan

英文摘要：Performance evaluation in AI systems commonly assumes that random dataset splits produce independent and identically distributed (i.i.d.) subsets. We show that this assumption often breaks down in spatiotemporally correlated domains such as aerial surveillance, precision agriculture, and medical imaging, leading to two systematic failures: data leakage, where correlated samples span training and validation splits and inflate performance estimates, and hidden stratification, where errors on minority subpopulations are obscured by aggregate metrics. To address these issues, we propose a unified evaluation and training framework for spatially correlated data. We introduce Structure-Aware Stratified Partitioning (SASP), which constructs validation splits that reduce spatiotemporal leakage while preserving meaningful class balance, and Curriculum Distributionally Robust Optimization (CDRO), a curriculum-based relaxation of distributionally robust training that stabilizes optimization under these stricter splits. Across multiple benchmarks, this combination yields consistently improved generalization, more reliable confidence calibration, and exposes failure modes that remain hidden under conventional random-split evaluation.

AI 总结： 针对LLM裁判存在噪声和系统性偏差（如偏好冗长或格式好的回答）的问题，提出将裁判过程建模为贝叶斯推断，引入显式的裁判特定偏差协变量，并设计一种Top-k感知的主动获取规则，以在固定比较预算下准确识别Top-k项。

链接：https://arxiv.org/abs/2607.02104

作者：Jian Xu, Delu Zeng, John Paisley, Qibin Zhao

英文摘要：Large language models (LLMs) are increasingly used as cheap, scalable judges that compare candidate outputs pairwise -- to rank responses, select models, or triage papers. Yet LLM judges are both noisy and systematically biased: they favor verbose or well-formatted answers and exhibit position effects, so simply aggregating their votes recovers a ranking of presentation, not of true quality. We study the practical goal of identifying the \topk{} items under a fixed comparison budget, and make two contributions. First, we cast judging as Bayesian inference over latent quality with explicit, judge-specific bias covariates (verbosity, position), regularized by a shrinkage prior so that the data decide which biases a given judge actually exhibits. Second, we introduce a \topk-aware active acquisition rule that chooses the next comparison to maximally reduce uncertainty about \topk{} \emph{membership}, rather than about the full ranking. On a controlled benchmark with known ground-truth quality, judged by sixteen real LLMs spanning open and proprietary families (Llama, Qwen, Phi-4, GPT-4o-mini/5.1/5.5, Gemini, DeepSeek, and Claude Haiku/Sonnet/Opus), naive aggregation plateaus at a wrong \topk{} on biased judges regardless of budget, while our bias-aware model recovers it; \topk-aware acquisition reaches this ceiling with far fewer comparisons than round-robin or a global-uncertainty (D-optimal) rule. Bias is real but heterogeneous and capability-dependent: cheap and mid-tier judges carry a strong verbosity bias that our model corrects (lifting recall from $\sim$$0.5$--$0.6$ to $0.84$--$1.0$), whereas the frontier judges we tested show little bias and already rank accurately, so bias-aware modeling changes little there.

AI 总结：提出HERMES层次化标注基底，通过语义变换和三级残差向量量化实现从粗到细的数据编码，支持多粒度混合策略，在1B参数、25B token预训练中揭示固定粒度无法检测的交互效应，提升16任务宏平均+0.0253。

链接：https://arxiv.org/abs/2607.02266

作者：Ziyun Qiao, Yue Min, Ruining Chen, Yujun Li

英文摘要：Most data-mixing methods assume the corpus has already been partitioned into groups, and the choice of those groups determines what a mixer can express. Existing labels, including provenance, topic or format taxonomies, and flat embedding clusters, commit to one semantic axis at one granularity; changing the resolution rebuilds the labels. We argue the bottleneck is the label system, not the mixer, and provide a hierarchical one. HERMES is a data-derived labeling substrate: a Learned Semantic Transform followed by 3-stage residual vector quantization annotates each document once into a coarse-to-fine code whose prefix length controls granularity up to approximately 130k cells. At coarse granularity HERMES sits at a plateau with KMeans-family methods on standard clustering metrics, so the contribution is the substrate, not the clusterer. On 1B-parameter, 25B-token pre-training, the hierarchy exposes an interaction fixed-granularity pipelines cannot test: at one prefix length, a combined Stage-2 rule contrast, equal-subbucket coverage versus size-proportional within-bucket quality top-30%, lifts a 16-task capability macro-average by +0.0253; at the next finer level, the same rule loses its measurable edge as candidate pools contract approximately 5x. HERMES reframes data mixture design from choosing among fixed label sets to navigating a reusable, data-derived granularity hierarchy.

AI 总结：提出I²RiMA网络，通过频点独立构建协方差矩阵并映射到SPD切空间，结合频率聚类和切片间注意力，实现跨被试脑电压力检测，在三个数据集上达到82.78%平衡精度。

链接：https://arxiv.org/abs/2607.01279

机构：Laboratory of Neural Computing and Intelligent Perception, College of Information Engineering, Capital Normal University（首都师范大学信息工程学院神经计算与智能感知实验室）； Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）； School of Psychology, Capital Normal University（首都师范大学心理学院）

作者：Cheng He, Kunyu Peng, Shangen Han, Jinming Ma, Jinhong Ding, Likun Xia

英文摘要：Cross-subject EEG stress detection remains challenging because discriminative stress-related patterns are both subject-dependent and frequency-specific. Conventional Riemannian methods model spatial covariance mainly in the time domain, overlooking neural oscillations that are critical for high-level cognitive state decoding, while standard temporal tokenization often fragments inter-slice temporal coherence. To address these limitations, we propose \method{}, an Intra-Inter Riemannian Manifold Attention Network for EEG-based stress detection. \method{} constructs spatial covariance matrices independently at each frequency point and maps them to the SPD tangent space, preserving channel-wise geometry together with frequency-specific discriminative cues. It further introduces frequency cluster aggregation to select informative spectral components and reduce redundancy by forming compact, data-driven frequency clusters aligned with EEG rhythms. Finally, an intra-inter slice attention module adaptively integrates local slice-level spectral dynamics and global temporal context across EEG sequences. Experiments on three datasets show that \method{} consistently outperforms five state-of-the-art baselines, achieving up to 82.78\% balanced accuracy while remaining efficient with only 1.60M parameters and 31.95M FLOPs.

AI 总结：提出基于领域知识的图卷积网络，利用PRQST关键点构建双流有向图建模心电周期内和周期间的时空关系，在九分类心电数据集上F1达88.1%，罕见类别F1达76.3%，优于现有模型。

链接：https://arxiv.org/abs/2607.01282

机构：China Mobile Research Institute（中国移动研究院）； China Mobile GBA (Greater Bay Area) Innovation Institute（中国移动大湾区创新研究院）； Beijing Jiaotong University（北京交通大学）； Institute of Microelectronics, Chinese Academy of Sciences（中国科学院微电子研究所）； Purple Mountain Laboratory（紫金山实验室）

作者：Wenting Ma, Zhipeng Zhang, Xiaohang Yuan, Ningwei Xie, Yuxin Xie, Xiaolin Wang, Meng Guo, Xingang Chai, Zhenjie Yao

英文摘要： In light of strides in Arti cial Intelligence (AI) and its wide spread application, challenges persist in the interpretability of AI models, particularly within specialized domains like healthcare, such as electro cardiograph (ECG) recognition. Rather than relying solely on end-to-end convolutional neural networks, this paper introduces a novel approach using a domain knowledge-based graph convolution network for ECG recognition. Key landmarks points of PRQST, vital to ECG interpreta tion, are incorporated as domain knowledge. The double-stream directed graph is employed to model both intra and inter ECG cycles. Speci cally, spatial directed graphs capture the positional relationships among key points, while temporal directed graphs delineate temporal dependencies between adjacent cycles in extended ECG sequences. Experimental re sults on the First Chinese ECG Intelligent Competition dataset, which speci cally classify ECG into nine categories, prove the e cacy of the proposed model. The overall average F1 score is 88.1%, the average F1 score of rare categories is 76.3%, both outperform the state-of-the-art models. The introduction of domain knowledge did enhance the detec tion performance, especially for rare categories.

AI 总结：提出结合稀疏随机投影降维与多项逻辑回归的机器学习方法，在参考队列上达到96%交叉验证准确率，独立队列上91类准确率86%，优于现有方法。

链接：https://arxiv.org/abs/2607.01307

机构：Universidade Federal de Pelotas（佩洛塔斯联邦大学）； Hospital de Clínicas de Porto Alegre（阿雷格里港临床医院）

作者：Paulo R. Ferreira Jr., Lucas Coutinho Freitas, Laís dos Santos Gonçalves, William Borges Domingues, Lucas Petitemberte de Souza, Mariana B. Michalowski, Vinicius F. Campos

英文摘要：NA methylation profiling has become a powerful approach for central nervous system (CNS) tumor classification, yet important challenges remain regarding cross-cohort transferability, methodological correctness, and robust multiclass evaluation. In this work, we propose a novel and methodologically rigorous machine-learning approach for methylation-based CNS tumor classification that combines Sparse Random Projection for dimensionality reduction with multinomial logistic regression for classification. We evaluate the proposed approach in the same general experimental setting established by a widely used reference classifier. On the 2,801-sample reference cohort, our method achieves a mean accuracy of 96\% under stratified 3-fold cross-validation. On the independent 1,104-sample clinical evaluation cohort, it reaches 86\% accuracy at the 91-class level and 93\% when predictions are evaluated at the methylation class family level. These results improve upon the corresponding state-of-the-art reference figures of 82\% class-level concordance and 88\% family-level concordance, yielding absolute gains of approximately 4 and 5 percentage points, respectively. This improvement is clinically relevant: in a diagnostic setting, a 5-point increase in correct tumor classification can directly affect cancer subtype assignment and, in turn, influence treatment selection and downstream clinical decision-making. Our results show that the proposed model, grounded in stronger methodological practice in machine learning, consistently outperforms the previous state of the art across evaluation settings and can materially improve the reliability of CNS tumor classification.

AI 总结：提出多模态管道，利用视觉线索和事故报告评估铁路道口安全，基于FRA评分实现高风险/低风险分类（F1=0.757）和分数估计（RMSE=0.078）。

链接：https://arxiv.org/abs/2607.01365

机构：University of California, Riverside（加州大学河滨分校）； Riverside County Transportation Commission（河滨县交通委员会）

作者：Paimon Goulart, Chansong Lim, Nícolas Roque dos Santos, Yue Dong, Sheldon Peterson, Jia Chen, Evangelos E. Papalexakis

英文摘要：Given one or more images of a railway crossing, can we leverage visual cues that allow us to robustly estimate how safe it is? Can we improve our ability to do so by introducing structured data (such as official accident reports) about the accident history of that crossing into our models? In this work, we explore how to best answer those questions towards building an AI system that can ingest multi-modal data for railway crossings and provide safety assessment and scores that align with expert opinion and with safety scoring used by the Federal Railroad Administration (FRA). To that end, we propose a proof-of-concept pipeline that delivers on that goal, while at the same time exploring and tackling a number of critical research challenges that pertain to different parts of the pipeline, from data preparation to different learning paradigms that can allow us to realize such a system. Indicatively, our proposed system identifies HIGH-RISK and LOW-RISK crossings with a macro F1 score of 0.757 and estimates FRA-based safety scores with an RMSE of 0.078 and correlation of 0.492 using a routed fine-tuned compact VLM pipeline, while producing qualitative results that align with domain-expert assessment.

AI 总结：提出NeuroBridge框架，通过大规模自监督MRI预训练与多任务学习（海马分割、萎缩分类、重建）及门控融合微调，在AD和MCI诊断中达到88.17%准确率，优于单任务方法。

链接：https://arxiv.org/abs/2607.01401

作者：Mengyu Li, Guoyao Shen, Chad W. Farris, Xin Zhang

英文摘要：INTRODUCTION: Accurate MRI-based identification of Alzheimer's disease (AD), mild cognitive impairment (MCI), and related dementias remains challenging because disease-related structural changes are often subtle and heterogeneous. We developed NeuroBridge, a clinically guided multi-task MRI framework for neurodegenerative disease diagnosis. METHODS: NeuroBridge integrates large-scale self-supervised MRI pretraining with hippocampal segmentation, hippocampal atrophy classification, and reconstruction objectives, followed by gated fusion fine-tuning. Performance was evaluated across ADNI and OASIS cohorts, including cross-cohort transfer, probability-based analysis, and opportunistic screening. RESULTS: NeuroBridge achieved the highest performance across evaluated classification tasks, reaching 88.17% accuracy for AD versus cognitively normal controls in ADNI and 82.78% in OASIS. The largest gains occurred in MCI-related and mixed-diagnosis settings. The framework demonstrated strong cross-cohort generalization, systematic associations between predicted-class probability and accuracy, and the feasibility of probability-based opportunistic screening. DISCUSSION: Clinically guided multi-task representation learning improves neurodegenerative MRI diagnosis beyond conventional single-task approaches. NeuroBridge provides a robust and scalable framework for dementia assessment and MRI-based opportunistic screening.

AI 总结：提出两阶段学习框架：先通过注意力增强门控循环网络从机载运动学与动力学估计局部风，再在强化学习控制器中利用该估计，使轨迹跟踪误差降低48%，并在强风中保持稳定。

链接：https://arxiv.org/abs/2607.01528

机构：School of Aerospace and Mechanical Engineering（航空航天与机械工程学院）

作者：Abdullah Al Tasim, Wei Sun

英文摘要：Small multirotor aircraft are increasingly tasked with operations in the atmospheric boundary layer, where turbulent winds comparable to the vehicle's airspeed degrade trajectory tracking and can defeat conventional feedback control. This work illustrates a two-stage learning pipeline that first estimates the local wind from onboard kinematics and dynamics and then exploits that estimate inside a reinforcement learning (RL) flight controller. The wind estimator, an attention-augmented gated recurrent network trained on thousands of simulated flights through von Karman turbulence with power-law shear and veer, recovers the horizontal wind vector with a per-flight root-mean-square error of 0.40 m/s and a direction error of 3.2 degrees on unseen wind regimes, an accuracy near the floor imposed by unresolved turbulence, and generalizes to vertical ascent profiles with a skill score of 0.861 over a constant-wind reference. A proximal policy optimization controller receiving the frozen estimator's output reduces horizontal trajectory tracking error by 48% relative to a wind-blind proportional-derivative baseline across mean winds of 4 m/s to 12 m/s, winning on 100% of evaluation episodes. A three-way ablation decomposes this improvement into a kinematic component, available without wind information, and a wind-perception component; the perception share rises with wind speed, from small in light winds toward roughly half the total benefit in strong winds, consistent with the quadratic scaling of aerodynamic drag. The controller degrades gracefully on out-of-distribution winds of 13 m/s to 15 m/s, where the baseline fails catastrophically.

AI 总结：提出SINA，一种全自动开源流水线，集成深度学习、连通分量标记、OCR和视觉语言模型，实现从电路原理图图像到网表的转换，在IC和PCB级别均达到96.67%的生成准确率。

链接：https://arxiv.org/abs/2607.01609

机构：The Department of Electrical and Computer Engineering, University of Utah（犹他大学电气与计算机工程系）； The Department of Electrical, Computer & Energy Engineering, University of Colorado Boulder（科罗拉多大学博尔德分校电气、计算机与能源工程系）

作者：Saoud Aldowaish, Yashwanth Karumanchi, Kai-Chen Chiang, Mohammed Ayman Habib, Finn Murphy, Rishen Cao, Morteza Fayazi

英文摘要：Recent advances in Artificial Intelligence (AI) have revolutionized Electronic Design Automation (EDA), particularly through Large Language Models (LLMs) for circuit design tasks. However, their application to analog and mixed-signal domains remains limited by the lack of machine-readable representations of existing circuit design knowledge. Circuit schematic images found in research manuscripts, textbooks, and websites constitute a vast repository of validated designs; however, these visual representations cannot be directly processed by EDA tools. Converting them into machine-readable netlists is essential for enabling simulation, verification, and building comprehensive databases for AI-based models. Current conversion methods lack generalization across both Integrated Circuit (IC) and Printed Circuit Board (PCB) level schematics. Moreover, they struggle with component recognition and connectivity inference, and fail to distinguish between connected junctions and crossing wires. In this paper, we propose SINA, an open-source circuit schematic image-to-netlist generator. SINA is a fully automated pipeline that integrates deep learning for robust component detection, connected-component labeling for accurate connectivity inference, Optical Character Recognition (OCR) for component reference designator extraction, and a Vision-Language Model (VLM) for reliable reference designator assignment. SINA handles both IC- and PCB-level schematics and incorporates dedicated crossing-wires detection to differentiate wire intersections from connections. We validate the correctness of the generated netlists using graph isomorphism techniques. Our experiments demonstrate an overall netlist generation accuracy of 96.67%, which is 2.72x higher compared to state-of-the-art approaches.

AI 总结：提出CALM框架，通过线性投影对齐脑区和遗传通路的潜在分布，从完全不相交的人群中学习可解释的跨模态关联，在自闭症谱系障碍数据上优于现有方法。

链接：https://arxiv.org/abs/2607.01656

机构：Department of Electrical and Computer Engineering, Boston University（波士顿大学电气与计算机工程系）； School of Data Science, University of Virginia（弗吉尼亚大学数据科学学院）； Department of Psychology, University of Virginia（弗吉尼亚大学心理学系）； Department of Neurology, University of Virginia（弗吉尼亚大学神经病学系）； Departments of Computer Science and Biology, Johns Hopkins University（约翰霍普金斯大学计算机科学与生物学系）

作者：Jueqi Wang, Zachary Jacokes, John Darrell Van Horn, Kevin A. Pelphrey, Michael C. Schatz, Archana Venkataraman

英文摘要：The interaction between brain structure and genetic influences is key to understanding neuropsychiatric disorders. However, most large-scale datasets are unimodal, providing either neuroimaging or genetics data. We propose CALM, a framework that learns interpretable associations between brain ROIs and genetic pathways from completely disjoint populations. CALM aligns the two modalities in a shared latent space via linear projections that simultaneously match the class-conditional latent distributions and ensure group separability. These projections provide interpretable pathway--ROI associations. When trained on unimodal imaging and genetics datasets, CALM generalizes to an unseen paired dataset, outperforming several state-of-the-art methods and ablation baselines. We also demonstrate stability of the learned associations against a paired baseline. Our experiments on autism spectrum disorder reveal immune and metabolic pathways linked to specific cortical regions and are consistent with established literature. Thus, CALM opens the door to leveraging large unimodal repositories for studying cross-modal interactions in brain disorders across disparate datasets.

AI 总结：提出消息传递双时间尺度贝叶斯深度学习框架，利用残差循环门控单元建模硬件损伤记忆，通过快速时变马尔可夫先验和慢变高斯马尔可夫先验分别处理信道与损伤参数，结合Turbo-OAMP和DAMP实现联合跟踪。

链接：https://arxiv.org/abs/2607.01660

机构：Zhejiang University（浙江大学）； National Key Laboratory of Millimeter-Wave and Terahertz Remote Sensing（毫米波与太赫兹遥感全国重点实验室）； Zhejiang Provincial Key Laboratory of Information Processing, Communication and Networking (IPCAN)（浙江省信息处理、通信与网络重点实验室）； Zhejiang Provincial Key Laboratory of Multi-Modal Communication Networks and Intelligent Information Processing（浙江省多模态通信网络与智能信息处理重点实验室）

作者：Wei Xu, An Liu

英文摘要：Hardware impairments in massive multiple-input multiple-output (MIMO) receivers introduce inter-symbol memory and inter-element coupling, severely degrading channel estimation. This paper employs a residual recurrent gated unit (RGRU) to model the intra-slot memory of the hardware impairments and proposes a message-passing-based two-timescale Bayesian deep learning (MP-TTBDL) framework for joint channel and impairment tracking. Owing to small-scale fading, the wireless channel varies rapidly across slots, whereas hardware impairments drift slowly due to hardware aging and environmental variations. To capture these distinct physical timescales, a fastvarying Markov prior and a slow-varying Gaussian Markov prior are assigned to the sparse channel and the network parameters, respectively. Based on a multi-slot factor graph formulation, a message-passing algorithm is developed. Specifically, the inter-slot messages admit closed-form updates, while the intra-slot factor graph, due to its complex recurrent structure, is partitioned into a channel tracking module and an impairments calibration module. The channel tracking module performs sparse channel estimation via turbo orthogonal approximate message passing (Turbo-OAMP), and the impairments calibration module updates the impairment parameters via a specially designed deep approximate message passing (DAMP) procedure, with the two modules iteratively exchanging extrinsic information through expectation propagation (EP) until convergence. Simulation results show that the proposed framework robustly achieves lower channel estimation error than conventional compensators followed by channel estimation across different online impairment scenarios and signal-to-noise ratio (SNR) conditions.

AI 总结：提出UniWind模型，通过物理先验估计器和潜在状态编码器，结合状态路由与专家校正，实现准确鲁棒的日前风电功率预测，在20多个真实数据集上验证了效果。

链接：https://arxiv.org/abs/2607.01670

机构：East China Normal University（华东师范大学）； Southern University of Science and Technology（南方科技大学）； Tsinghua University（清华大学）

作者：Ronghui Xu, Tongxin Wu, Guozhen Zhang, Yihan Li, Chenjuan Guo, Bin Yang, Yong Li

英文摘要：Day-ahead wind power forecasting is essential for cost-effective power-system operation. It is primarily driven by future meteorological conditions while retaining temporal dependencies in power generation. In practice, observed wind-farm power often entangles physically available power with local environmental effects and latent operational states, such as shutdowns and curtailment. Existing physical models provide useful constraints but adapt poorly across wind farms, whereas data-driven models can capture rich correlations but often conflate meteorological effects with state-induced deviations. In this study, we propose UniWind, a wind power forecasting model based on physics-informed state routing. UniWind first employs a Physical Prior Estimator to construct a site-calibrated physical prior by combining site-conditioned monotonic warping with a shared physical power curve. It further applies a physical upper-bound constraint to shape this prior as a soft envelope of available wind power generation. UniWind then proposes a Latent State Encoder to model operating-state embeddings and transforms the physical prior into final power forecasts through a State-aware Power Corrector, which uses knowledge-guided supervised state routing and bounded, state-specific expert correction. Full-shot and cross-farm zero-shot experiments on more than 20 real-world datasets demonstrate the accuracy and robustness of UniWind.

AI 总结：提出EHHN，一种事件驱动异质超图网络，通过超边绑定多对象事件并融合微观状态演化与宏观时间动态，实现对象中心的下一个活动预测，在多个基准上取得最优性能。

链接：https://arxiv.org/abs/2607.01785

机构：College of Computer Science and Technology, Zhejiang University of Technology（浙江工业大学计算机科学与技术学院）； University of Southern Queensland（南昆士兰大学）

作者：Jiaxing Wang, Kaitao Chen, Zhubin Han, Chenyu Hou, Bin Cao, Jing Fan, Ji Zhang

英文摘要：Next activity prediction helps service-oriented processes anticipate upcoming steps before delays, exceptions, or service-level risks occur. Most existing methods assume classical single-case event logs, whereas real service processes often involve events shared by multiple typed business objects. Object-centric event logs (OCELs) capture such interactions, but current predictors remain limited. Flattening-based approaches lose cross-object context, and native OCEL graph-based approaches encode multi-object events through pairwise relations. Existing models also do not jointly capture event-driven object state changes, inter-event timing, and global execution patterns. We propose EHHN, an Event-driven Heterogeneous Hypergraph Network for object-centric next activity prediction. EHHN represents each prediction prefix as a heterogeneous hypergraph, where event--object hyperedges bind retained co-participating objects and a lifecycle hyperedge groups the primary object's observed lifecycle events. Based on this representation, EHHN uses a dual-stream architecture in which a micro-spatial stream models event-driven object-state evolution and a macro-evolution stream captures temporal dynamics using retrieved global prototypes. The two streams are fused to predict the next activity. Experiments on four public OCEL benchmarks against nine baselines show that EHHN achieves the best accuracy and macro F1-score on all datasets, with improvements of up to 8.1 and 12.4 percentage points over the strongest baselines. Compared with the strongest OCEL-native graph baseline, EHHN also reduces peak GPU memory by up to 24 times. Code is available at this https URL.

AI 总结：本研究使用单通道消费级EEG设备，通过混合CNN+LSTM+Attention模型区分在线教育视频内容的难易程度，在受试者内设置下达到78.5%准确率，并强调受试者独立评估应成为标准。

链接：https://arxiv.org/abs/2607.01795

机构：University of Ottawa（渥太华大学）； Queen’s University（女王大学）

作者：Rowan Hussein, Mohamed Ouf

英文摘要：Monitoring cognitive load during online learning could help instructors identify content that learners find difficult, but remote settings remove the visual cues that support this judgement in a classroom. We study whether a single-channel, consumer-grade EEG device (the NeuroSky MindWave Mobile 2) can distinguish easy from difficult educational-video content, using the publicly available dataset of Wang et al. [24] (ten learners, one excluded for excessive noise, leaving nine). We implement a hybrid CNN+LSTM+Attention model that combines the raw waveform with band-power features. In a within-subject setting, the model reaches up to 78.5% accuracy, compared with 55% for conventional feature-based classifiers; regularization (dropout and L2) closes the large gap between training and validation accuracy that we observe without it, keeping validation accuracy stable at roughly 68-73%. We are deliberately cautious about these numbers: with only nine subjects, within-subject evaluation is optimistic, and we argue that subject-independent evaluation -- in which no learner appears in both training and test data -- should be the standard for this task. To that end we release a reproducible evaluation pipeline. We frame the work as a feasibility study rather than a deployable system, and pair it with an open, notebook-based tool that records EEG, runs inference, and visualizes estimated cognitive load as a heatmap over the video timeline to help educators locate potentially challenging segments.

AI 总结：针对多变量时间序列分类器在康复数据分析中难以解释的问题，提出两阶段框架，通过可学习门控机制生成基于语义特征组的反事实解释，在保持有效性的同时提升组级稀疏性和临床可解释性。

链接：https://arxiv.org/abs/2607.01838

作者：Emmanuel C. Chukwu, Rianne M. Schouten, Monique Tabak, Mykola Pechenizkiy

英文摘要：Counterfactual explanations (CEs) for multivariate time-series classifiers are often difficult to interpret in domains where experts reason in terms of semantic feature groups rather than individual channels. In rehabilitation movement analysis with multi-sensor inertial measurement units (IMUs), clinicians interpret motion through muscle-group and joint-segment abstractions; yet, most existing counterfactual methods operate at the channel level, producing scattered and biomechanically incoherent explanations. We propose a two-stage framework for group-based counterfactual generation in high-dimensional IMU data. We first show that Shapley-Adaptive (SA) group ranking preserves counterfactual validity but fails to enforce group-level sparsity, motivating the need for explicit group selection. We then introduce Learnable Gate (LG) methods, which incorporate trainable per-group relevance gates jointly optimized with perturbation masks. Experiments on the KneE-PAD rehabilitation dataset demonstrate that LG substantially improves modality-group sparsity compared to the channel-level M-CELS baseline while maintaining or improving validity, temporal smoothness, and generation efficiency. Exercise-specific analyses further show that group-structured counterfactuals yield concise, muscle-level corrective guidance aligned with clinical reasoning. Overall, the proposed framework enhances interpretability without sacrificing counterfactual quality, enabling more actionable explanations for rehabilitation movement analysis.

AI 总结：提出SABER框架，通过多尺度超图建模功能子网络与高阶依赖，并引入决策级语义对齐机制，将大语言模型语义直接融入预测，在ABIDE和ADHD-200数据集上取得最优性能，尤其在小样本场景下。

链接：https://arxiv.org/abs/2607.01901

作者：Yidan Xu, Xiangmin Han, Rundong Xue, Huihui Ye

英文摘要：Effective brain disease diagnosis requires the synergy of brain connectivity patterns and high-level semantic knowledge. Existing methods, however, largely treat semantics from large language models (LLMs) as auxiliary features or supervision, limiting their direct role in decision-making and constraining classification stability and robustness. To overcome this, we propose a semantic-aligned brain network framework that actively integrates LLM-derived semantics into the prediction process. Specifically, ROI-level semantics are first incorporated via global self-attention to enrich node representations and provide whole-brain context. Multi-scale hypergraphs are then constructed to explicitly model functional subnetworks and multi-ROI interactions, addressing the locality limitations of traditional GNNs and capturing high-order dependencies. Finally, a decision-level semantic alignment mechanism selectively injects patient-specific textual embeddings into graph representations, enabling semantics to directly guide predictions without perturbing the underlying network structure. Experiments on public brain network datasets ABIDE and ADHD-200 demonstrate state-of-the-art performance, enhanced stability, and improved interpretability, particularly in small-sample settings.

AI 总结：提出混合量子-经典神经网络用于情感分析，在COVID-19推文数据集上达到与经典模型相当的准确率，并在迁移学习中比经典模型提升15个百分点（从66%到81%），展示了更强的泛化能力。

链接：https://arxiv.org/abs/2607.01943

机构：Dept. of Physics and Astronomy, Florence Univ.（佛罗伦萨大学物理与天文学系）； School of Computer Science and Mathematics, Kingston University London（伦敦金斯顿大学计算机科学与数学学院）

作者：Giacomo Cappiello, Filippo Caruso, Xing Liang, Dimitrios Makris

英文摘要：Quantum machine learning has recently emerged as a promising paradigm that leverages the expressive power of quantum circuits to address complex learning tasks. In this work, we investigate the applicability of hybrid quantum-classical neural networks to sentiment analysis, a central problem in natural language processing. We focus on a dataset of tweets related to COVID-19, where the textual content is vectorized using TF-IDF and fed into both classical feedforward networks and hybrid architectures incorporating parameterized quantum circuits. Our results show that hybrid models can achieve accuracy comparable to the classical baseline, while exhibiting distinct learning dynamics, especially in terms of validation loss and accuracy, that suggest a richer representational capacity. Moreover, when applying transfer learning to an SMS spam classification task, the hybrid models consistently outperform the classical counterpart, achieving an accuracy increase of 15 percentage points (from 66% to 81%) on the spam class, demonstrating enhanced generalization. These findings highlight the feasibility of employing QML for natural language processing and point toward the potential advantages of hybrid models as quantum hardware continues to advance.

AI 总结：本研究评估时间序列基础模型在200个实际低压馈线短期净负荷预测中的性能，提出面向应用的指标连接峰值预测与电网资产规划中的成本-风险权衡。

链接：https://arxiv.org/abs/2607.01966

机构：Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）； Netze BW GmbH（Netze BW有限公司）

作者：Benedikt Kaas, Manuel Treutlein, Hannes Benedikt Gerber, Oliver Neumann, Cheewan Phatthanakhuha, Oliver Resch, Ralf Mikut, Veit Hagenmeyer

英文摘要：Low-voltage load forecasting is an important component in current and future energy systems with a high degree of electrification and decentralized generation. However, current forecasting methods require significant manual effort, often lack uncertainty estimation and proper peak prediction, and they are often not adequately evaluated in terms of grid requirements. In the present study, we provide an extensive evaluation of short-term net load forecasts of 200 real-world low-voltage feeders with a focus on the rapidly evolving time series foundation models. Our study compares Chronos-Bolt, Chronos-2 and TabPFN-TS to six baseline models and demonstrates superior performance, in particular for Chronos-2. An ablation study, in which weather covariates are omitted, shows that time series foundation models adapt to increased uncertainty, despite the importance of weather information. A novel application-oriented metric links the model's forecasting capabilities in peak prediction to the trade-off in grid asset planning and operation between cost reduction and minimizing the risk of failure.

AI 总结：提出液态神经网络作为潜在动力学模型，通过分解潜在状态为退化与工况分量，在C-MAPSS上实现可解释的退化建模，传感器预测RMSE从0.2438降至0.2266。

链接：https://arxiv.org/abs/2607.01986

机构：Tianjin University（天津大学）

作者：Weizhi Nie, Weijie Wang, Yuting Su

英文摘要：Multivariate time-series models for prognostics are often evaluated by point prediction accuracy, yet their internal states rarely expose a coherent degradation process. We study liquid neural networks as latent dynamics models for aircraft engine health monitoring on the C-MAPSS benchmark. The proposed model encodes a history window into a latent state, evolves that state with a liquid transition model, and decodes future sensor observations. To separate health evolution from operating-condition variation, the latent state is factorized into degradation and condition components. Remaining useful life, monotonic risk, and latent-consistency losses supervise the degradation component, while condition prediction and decorrelation losses discourage operating-condition leakage. Across FD001--FD004, the full disentangled model improves overall sensor forecasting RMSE from 0.2438 for a GRU baseline to 0.2266, with the largest gains on the multi-condition subsets FD002 and FD004. The learned degradation state also forms a clearer temporal degradation axis, reaching an average state-speed Spearman correlation of 0.5960. Direct remaining-useful-life regression remains stronger for the GRU baseline, indicating that the proposed representation is currently more effective as an interpretable world model for degradation dynamics than as a calibrated lifetime regressor. These results suggest that liquid latent dynamics can bridge predictive maintenance forecasting and inspectable health-state modeling.

AI 总结：提出SA-HGNN模型，通过样本自适应图构建、双曲图卷积和注意力池化模块，准确提取抑郁症脑网络的层次结构，在EEG数据集上优于现有方法。

链接：https://arxiv.org/abs/2607.02063

作者：Yang Li, Pan Hu, Yan Zhang, Wenfan Yang, Tao Wu, Lianbo Guo

英文摘要：Graph Neural Networks (GNNs) have been widely used to capture spatial functional connectivity patterns to improve electroencephalography (EEG)-based depression recognition performance. However, the functional connectivity of brain networks in patients with depression exhibits an inherent hierarchical structure, making it difficult to capture accurate connection patterns. To address these issues, this paper proposes a novel model named Sample-Adaptive Hyperbolic Graph Neural Network (SA-HGNN), which aims to accurately extract the authentic hierarchical structure of depression-affected brain networks. Specifically, the proposed model comprises three core modules. First, a Sample-Adaptive Graph Construction module dynamically constructs personalized brain network topologies to capture more complex spatial relationships within the brain network. Second, hyperbolic graph convolution is employed to overcome the representation bottlenecks of Euclidean space, leveraging hyperbolic geometry to precisely capture latent hierarchical relationships within the brain network. Finally, an Attention Pooling module adaptively filters out highly redundant noise channels in EEG signals, effectively mitigating the interference of inherent noise on the authentic hierarchical topology. Extensive experiments on public EEG datasets demonstrate the superior performance of our method across resting-state and task-related paradigms, validating its robustness to noise and efficacy in capturing abnormal functional connectivity patterns in brain networks of patients with depression.

AI 总结：提出改进的傅里叶神经算子，通过预测时间增量而非完整解来模拟二维瑞利-贝纳德对流，在保持紧凑和快速的同时实现更高精度。

链接：https://arxiv.org/abs/2607.02088

机构：Jülich Supercomputing Centre（于利希超级计算中心）； Hamburg University of Technology（汉堡工业大学）

作者：Chelsea Maria John, Thibaut Lunet, Sebastian Götschel, Andreas Herten, Stefan Kesselheim, Daniel Ruprecht

英文摘要：We propose an improved Fourier Neural Operator (FNO) for modeling two-dimensional Rayleigh-Bénard convection by predicting time increments instead of full solutions, achieving higher accuracy than a standard FNO baseline. The resulting model is compact (314k parameters, 1.26 MB) and fast (7 ms inference), while maintaining similar accuracy as demonstrated in previous benchmarks. We show that although FNOs generalize to finer meshes, accuracy remains limited by the resolution of the training data.

AI 总结：本文实证评估滚动分割符合预测在赛车牵引力损失前发出预警的有效性，发现该方法在19名车手和55,563个样本中精确率和召回率均为0，误报率高，结论为阴性。

链接：https://arxiv.org/abs/2607.02124

作者：Varshith Roy Kotla

英文摘要：Conventional traction control architectures intervene only after the adhesion limit of a tire has already been breached. This paper investigates whether Rolling Split Conformal Prediction, monitoring the volatility of non-conformity residuals from a per-driver Random Forest model of expected slip behavior, can serve as a statistically grounded pre-incident warning signal, ahead of gross traction loss. Unlike an earlier internal draft of this work, the evaluation reported here corrects a confound in the slip proxy (vehicle speed is included as an explicit model feature, not left implicit in the target's denominator), uses every racing lap for each driver rather than only the fastest lap, and is scored against real, timestamped incident labels extracted from FIA Race Control Messages and track-limits lap deletions rather than narrated post-hoc. The result is negative: across 19 drivers and 55,563 test-phase telemetry samples, the rolling-volatility detector achieves a mean precision of essentially 0.0 and mean recall of 0.0 against 14 ground-truth incidents, while flagging on average 15.3% of all samples as anomalous, too high a false-alarm rate for any early-warning use. A static 95th-percentile threshold baseline performs no better in any way that would justify the added complexity of the conformal-volatility formulation. Residual autocorrelation diagnostics show the split-conformal exchangeability assumption is violated for every driver (Ljung-Box p < 0.001, n = 19/19), which is one plausible driver of the high false-alarm rate. We report this as a methodologically rigorous negative finding, diagnose its likely causes, and outline what a genuinely predictive version of this approach would require.

AI 总结：提出结合深度神经网络与集成机器学习模型，利用临床、神经心理测试和神经影像数据，通过处理缺失值、类别不平衡和特征选择，实现阿尔茨海默病早期检测并识别关键生物标志物。

链接：https://arxiv.org/abs/2607.02142

作者：Debopriya Ghosh

英文摘要：Alzheimers disease (AD) is a brain disorder that develops slowly and mainly affects memory, thinking, language, and daily activities. It is one of the most common causes of dementia and creates many difficulties for patients as well as their families. In the early stage, the symptoms are often mild and may look like normal ageing. For this reason, many people are diagnosed late, when the disease has already progressed. At present, there is no complete cure for AD. Still, early detection can help doctors manage the condition better and take suitable steps at the right time. In this study, a machine learning model is proposed to detect the early stages of Alzheimers disease using clinical details, neuropsychological test scores, and neuroimaging-related measures. The data used in this work is collected from the Alzheimers Disease Neuroimaging Initiative (ADNI). As the dataset has missing values, iterative imputation is applied to fill them. The dataset also has class imbalance, which is handled using Borderline SVM-SMOTE. After that, feature selection is carried out using wrapper-based and embedded methods so that only important features are used for training. The selected features are divided into training and testing sets, and feature scaling is applied. A stacking ensemble model is developed using Logistic Regression, Extra Trees, Bagging KNN, and LightGBM as base classifiers. Along with this, an artificial neural network is also trained on the same dataset. The performance of these models is compared using precision, recall, F1-score, and AUC-ROC. This study aims to find the best classifier and also identify important biomarkers that may help in the early diagnosis of Alzheimers disease.

AI 总结：提出自解释算子学习框架，通过将算子学习重构为积分方程线性组合，实现输入子域对预测贡献的局部化解释，在血流和非定常气动问题中验证了其物理可解释性。

链接：https://arxiv.org/abs/2607.02203

机构：Scientific Computing and Imaging Institute, University of Utah（犹他大学科学计算与成像研究所）； Mechanical Engineering Department, University of Utah（犹他大学机械工程系）

作者：Mojgan Alishiri, Amirhossein Arzani

英文摘要：Operator learning has emerged as a powerful tool for modeling complex physical systems in functional spaces. However, their neural network-based architectures make them opaque models, obscuring the reasoning behind their predictions. In this work, we introduce a self-explainable operator learning framework that overcomes this challenge by reformulating operator learning as a linear combination of generalized functional linear models expressed through integral equations. Exploiting the additive decomposability of these integral equations, we divide the input domain into subdomains and compute localized integrals to evaluate the contribution of each region to the final prediction. This decomposition enables direct interpretability where the model explains both inputs and outputs by linking specific input regions to corresponding output patterns, thereby revealing which spatial features drive predictions. We demonstrate the framework on function-to-scalar and function-to-function mappings in fluid flow problems involving blood flow and unsteady aerodynamics. The results show that the operator most often prioritizes regions with strong feature gradients, providing physically meaningful insight into the model's decision-making process. Comparisons with established post-hoc explainability methods demonstrate qualitative agreement while highlighting the key advantage of the proposed approach: explainability is embedded directly within the operator structure itself and does not require an external tool. Therefore, our framework provides a mathematically transparent and physically interpretable approach to uncover relationships within data, fostering trust in machine learning for scientific applications by enabling more informed data-driven analysis of physical systems.

AI 总结：针对当前商业LLM API仅返回单logit且禁止logit偏置的限制，提出NightVision方法，通过新型公共集提示技术和首令牌时间测量，估计隐藏维度、深度和参数数量，在32个开源模型上验证了可行性。

链接：https://arxiv.org/abs/2607.01313

机构：Carnegie Mellon University（卡内基梅隆大学）； Pittsburgh Supercomputing Center（匹兹堡超级计算中心）

作者：Christopher Ellis, Shreyas Chaudhari, Mei-Yu Wang, Leighton Barnes, Giulia Fanti, José M. F. Moura

英文摘要：In practice, most commercial LLM providers do not publicly release details of underlying LLM architectures. However, prior work has shown that given limited API access to an LLM (namely, top-$k$ logits and/or a logit bias function), one can recover certain architectural details of an LLM, such as the hidden dimension of the feed-forward network. Perhaps in response to these results, most commercial LLM providers have restricted their APIs to expose only the single logit for each decoded token, and they no longer give users the ability to bias logits. We show that even under current restrictive APIs, several architectural parameters are still recoverable. We present NightVision, an attack that uses restrictive black-box API access to estimate the hidden dimension, depth, and parameter count of an LLM. Algorithmically, NightVision relies on a novel common set prompting technique in which multiple prompts expose log probabilities for the same set of output tokens; a spectral analysis of these results is used to infer hidden dimension. NightVision additionally uses end-to-end time to first token (TTFT) measurements and the estimated hidden dimension to estimate depth and parameter count. We empirically evaluate NightVision on 32 open-source LLMs, recovering hidden dimension to within 23% average relative error across all models (9% on MoE models), and depth and parameter count to within 53% for models exceeding three billion parameters. We run extensive ablations to demonstrate how these accuracies scale with token budget and model properties. Overall, our results suggest that current LLM APIs are not sufficiently restricted to fully obfuscate the architectural details of their underlying models.

AI 总结：通过分析Transformer隐藏状态空间中思维链轨迹的谱、位置和运动学几何特征，提出有效维度d_ρ衡量轨迹复杂度，发现平坦特征谱对应更难任务，并利用运动学特征在生成早期预测答案正确性。

链接：https://arxiv.org/abs/2607.01571

机构：Northeastern University（东北大学）； University of Southern California（南加州大学）； Google Research（谷歌研究院）

作者：Aria Masoomi, Mahsa Bazzaz, Adel Javanmard, Vahab Mirrokni

英文摘要：Chain-of-thought (CoT) reasoning enables large language models (LLMs) to solve complex problems by generating intermediate reasoning steps. While much attention has been paid to the length and content of these reasoning chains, far less is known about their internal geometry. We study the \emph{geometry} of CoT trajectories in the hidden state space of transformer models, formalizing each reasoning chain as a discrete curve in $\mathbb{R}^d$ and characterizing it through spectral, positional, and kinematic geometric functionals. We introduce the effective dimension $d_\rho$ as a measure of trajectory complexity and show theoretically that trajectories with flatter eigenvalue spectra correspond to harder tasks, as they explore more of the hidden dimensions. Lastly, we explore how kinematic features of the trajectory, mean position, positional dispersion, initial and current hidden states, mean velocity, mean speed, and speed dispersion, can be used to predict solution correctness before generation is complete, and may inform future early-stopping strategies. Experimentally, on mathematical reasoning problems from the MATH500 dataset, $d_\rho$ achieves $0.93$ AUC in distinguishing easy from hard problems, while kinematic features potentially can predict correctness from only the first $20\%$ of generated tokens. These correctness signatures transfer across questions of varying difficulty, establishing that the shape of a model's internal reasoning trajectory is a principled window into both task hardness and solution quality.

AI 总结：提出BOUNDARY_SYNC协议，通过耦合放大因子(CAF)测量多智能体LLM系统中通信导致的表征耦合，发现文本通信导致显著同质化，图像通信也有类似效应，且组大小调节耦合方向。

链接：https://arxiv.org/abs/2607.01600

机构：Qilu Institute of Technology（齐鲁理工学院）

作者：Zewen Liu

英文摘要：As large language models (LLMs) are deployed as communicating agents, does inter-agent communication cause outputs to converge? We introduce BOUNDARY_SYNC, a protocol measuring representational coupling via the Coupling Amplification Factor (CAF = JSD_cond / JSD_baseline), where CAF < 1 indicates homogenization and CAF > 1 indicates diversification. In controlled GPT-4o experiments (N=30, ~9,900 API calls), we measure coupling in text and image communication. Key findings: (1) text communication causes significant homogenization (CAF=0.803 [0.740, 0.873], d=1.30, p<0.001), confirmed by no-communication ablation and prompt-perturbation controls; (2) image communication also homogenizes under within-modality baselines (CAF=0.834 [0.811, 0.858]), with comparable proportional effect; (3) group size moderates coupling direction -- K=5 produces homogenization while K=3 yields CAF > 1.0 (point estimates 1.14 and 1.06, CI pending), suggesting a directional shift toward diversification; (4) cross-model replication shows extreme variation (CAF 0.034-0.803), with DeepSeek dominated by format artifacts; (5) coupling is stateless -- driven by prompt context rather than cumulative updating, with continuous consensus producing monotonic convergence. These results establish LLM agent coupling as real, measurable, and controllable at the prompt level, with direct implications for multi-agent system design.

AI 总结：提出条件共消融（CoAx）方法，通过测量在移除主要组件后剩余单元消融效应的增长，来发现变压器电路中因自修复而隐藏的备份组件，在GPT-2-small IOI电路上将备份头恢复的ROC-AUC从0.33提升至0.91。

链接：https://arxiv.org/abs/2607.01940

机构：College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学计算机与数据科学学院）； Interdisciplinary Graduate Programme, Nanyang Technological University, Singapore（南洋理工大学跨学科研究生项目）； School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore（南洋理工大学电气与电子工程学院）

作者：Zhiren Gong, Zihao Zeng, Chau Yuen, Wei Yang Bryan Lim

英文摘要： Mechanistic interpretability often relies on component-level interventions to discover how a model produces a behavior. This guides attribution, capability knockout, and model pruning downstream to operate by scoring each unit by the effect of ablation in isolation. Such first-order scoring is natural when component importance is additive, but becomes misleading when a transformer self-repairs: after a primary component is removed, a dormant backup can take over, muting the primary's measured effect while the backup itself appears irrelevant on the intact model. We recast this failure as a recovery task, conditional circuit completion, and introduce Conditional Co-Ablation (CoAx), a label-free, output-grounded score that asks how much each remaining unit's ablation effect grows once a primary set has been removed. This conditional growth exposes the second-order interaction that single-unit scores discard. On the GPT-2-small IOI circuit, CoAx raises backup-head recovery from 0.33 to 0.91 ROC-AUC, outperforming all baselines, including self-repair-aware gradient scores (best 0.82); counterfactual patching verifies that the recovered heads causally carry the repair. The same label-free procedure transfers to induction across eight models. Beyond discovery, the recovered backups correct self-repair-masked attribution, identify the components required for capability knockout, and yield repair-aware structured pruning scaling from 124M to 7B. Component importance is therefore not merely an isolated-unit property: in robust circuits, the components that matter can become visible only under the interventions that make them necessary.