机器学习学术速递[8.26]

AI 总结：该研究针对MoE应用于卷积网络的结构缺陷，提出MoCE层替代逐点投影，在减少16.7% MAC和延迟的同时，性能匹配或优于基线与现有通道选择方法。

链接：https://arxiv.org/abs/2608.23794

机构：School of Computer Science, Ariel University（阿里尔大学计算机科学学院）

作者：Elian Iluk, Gil Ben-Artzi

英文摘要：Mixture-of-Experts (MoE) scales language models by routing each input through a small set of independently parameterized experts. We show that copying this design into convolutional networks fails for a structural reason: parallel convolutional experts that read the same input channels learn nearly identical filters. We therefore move the expert axis from operator duplication to channel selection. We introduce Mixture of Channel Experts (MoCE), a structured sparse channel-mixing layer, inspired by MoE, that replaces pointwise (1x1) channel-reduction projections. In MoCE, an expert is a single output channel with a learned sparse support of k << C input channels. The selected channels are combined by a softmax whose temperature is predicted per input, so each expert can move between mean-like and max-like aggregation. A residual expert summarizes the unselected channels, and a load-balancing loss keeps channel coverage complete. MoCE replaces a dense projection whose cost is quadratic in C with a mechanism whose relative cost scales as k/C, and the predicted savings hold in measured wall-clock time. Across ResNet backbones on ImageNet-1K and CIFAR-100, transfer learning, EfficientViT, and a strong modern training recipe, MoCE matches or exceeds dense baselines and prior channel-selection methods while reducing MACs by 16.7% and end-to-end latency.

AI 总结：该研究指出现有特征学习理论仅聚焦全局低维预测几何的不足，发现MLPs在聚类数据回归中会产生单义性专用神经元，形成局部低维表示集合，从而获得数据效率优势。

链接：https://arxiv.org/abs/2608.24007

机构：UC San Diego（加州大学圣地亚哥分校）； University of Pennsylvania（宾夕法尼亚大学）； The Wharton School（沃顿商学院）； Halıcıoğlu Data Science Institute（哈利西奥格鲁数据科学学院）

作者：Amirhesam Abedsoltan, Enric Boix-Adsera, Fivos Kalogiannis, Mikhail Belkin

英文摘要：Understanding how neural networks learn and organize features is central to understanding their behavior. Much existing theory of feature learning has focused on the emergence of a global low-dimensional predictive geometry. We show that this picture is incomplete. In regression problems with clustered data, we demonstrate that multilayer perceptrons (MLPs) naturally develop monosemantic specialized neurons: individual neurons become strongly aligned with a specific predictive feature relevant to a particular region of the input space. Rather than learning a single global low-dimensional representation, MLPs learn a collection of local low-dimensional representations that can collectively span a high-dimensional space. This specialization provably gives MLPs a data-efficiency advantage over feature-learning methods based on a global low-dimensional representation.

AI 总结：本研究提出基于电路的框架，结合训练动态数据估值与机制可解释性，引入SAMS方法实现可控数据生成，在多项选择问答任务中提升了下游性能与校准度。

链接：https://arxiv.org/abs/2608.24065

机构：Seoul National University（首尔大学）； Konkuk University（建国大学）

作者：Nakyung Lee, Sangwoo Hong, Jungwoo Lee

英文摘要：While recent advances in data synthesis aim to curate high-quality datasets, most generation pipelines still rely on heuristic prompt-based control. This black-box paradigm provides limited insight into how individual samples interact with a model's underlying learning dynamics. To bridge this gap, we propose a circuit-grounded framework that connects training-dynamics-based data valuation with mechanistic interpretability (MI). Specifically, we conceptualize data quality along three complementary utility axes, learnability, challenge, and alignment. First, we uncover specialized model-internal circuits that causally govern these utility signals. Then, moving beyond heuristic prompting toward mechanistic control, we leverage these circuits as controllable interfaces, actively steering generation to produce utility-targeted data. Building on this capability, we introduce SAMS (Stage-Aware Mechanistic Scheduling), which schedules circuit-steered data according to the model's evolving optimization needs. Experiments on multiple-choice QA tasks demonstrate that our approach yields precisely controlled data with greater diversity than prompt-based baselines, consistently improving downstream performance and calibration. Ultimately, this work establishes a principled white-box paradigm for interpretable data generation, pioneering the use of MI not just as an analytical tool, but as a practical, controllable interface.

AI 总结：本论文探究PDE数值模拟器与神经模拟器的关系，梳理求解器在神经模拟器学习流程中的角色，完成APEBench基准套件等三项贡献，指出二者相似多于差异。

链接：https://arxiv.org/abs/2608.24547

机构：TU Braunschweig（布伦瑞克工业大学）； TU Munich（慕尼黑工业大学）

作者：Felix Koehler

英文摘要：Simulation is central to modern engineering and science, but the cost of numerical solvers for partial differential equations (PDEs) remains a bottleneck whenever fast or many-query evaluations are required. Neural emulators trained on solver-generated data promise significant speedups, yet they are usually framed as opaque alternatives to the very methods that produce their training signal. This thesis argues the two paradigms are more alike than different: neural architectures mirror classical discretizations, their errors are amenable to the same spectral analysis, and insight flows profitably in both directions. We approach the relationship by disentangling the multiple roles a solver plays in the emulator learning pipeline. Mode-wise Fourier analysis then provides a common language in which solver errors, architectural inductive biases, and training objectives can all be read off simultaneously. Taken together, this allows synthesizing three contributions. (1) APEBench, a comprehensive benchmarking suite for autoregressive neural emulators of PDEs that uses fast differentiable pseudo-spectral solvers in JAX. (2) Progressively Refined Differentiable Physics, an investigation of the effect of unconverged solvers on surrogate training. (3) Neural Emulator Superiority, an analysis of the influence of numerical errors and architectural inductive biases.

AI 总结：ChorusTIC是一种无需训练的多变量时间序列分类模型，通过上下文学习结合特定编码与校准方法，在UEA-30和UCR-128数据集上实现了无需目标分类器拟合的优异分类性能。

链接：https://arxiv.org/abs/2608.24033

机构：Guangdong University of Technology（广东工业大学）； Université Paris Cité（巴黎西岱大学）； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）； Shantou University（汕头大学）

作者：Juntao Fang, Shifeng Xie, Ruichu Cai, Shengji Zheng, Zijian Li, Keli Zhang, Lujia Pan, Themis Palpanas, Zhifeng Hao

英文摘要：Time series classification underpins applications in healthcare, sensing, and industrial monitoring. Although time series foundation models support forecasting and transferable representation learning, classification still typically requires fitting a task-specific classifier on each target dataset, while individual channels of multivariate inputs are often encoded independently. We introduce ChorusTIC, a classification-native foundation model for in-context classification across heterogeneous channel configurations without target-task parameter updates. ChorusTIC combines episode-consistent Random Subchannel Slot Concatenation with a shared dual-axis encoder to model temporal and cross-channel interactions and map variable channel configurations into a fixed-width representation independent of the original channel count. It then calibrates feature axes using context-derived distributions and predicts query labels through leakage-protected in-context learning. We pretrain ChorusTIC solely on synthetic labeled episodes comprising context and query sets that share a task background, with classes distinguished by sparse temporal or cross-channel rules. Evaluations on the complete UEA-30 and UCR-128 archives show strong full-context and low-label performance without target-specific classifier fitting.

AI 总结：本文研究了标签稀缺与缺失数据场景下表格SSL预训练的效果，发现其在干净数据集上改进可靠，在高缺失数据集上常失效，且掩码并恢复目标与其他表格SSL基线无显著差异。

链接：https://arxiv.org/abs/2608.24381

机构：Faculty of Mathematics and Computer Science, Kharazmi University（卡拉兹米大学数学与计算机科学学院）

作者：Sahand Mazrouei

英文摘要：Self-supervised learning (SSL) has emerged as a promising approach for tabular data, yet its efficacy under extreme label scarcity and test-time missingness remains under-explored. In this paper, we evaluate a mask-and-recover SSL pretraining objective against training from scratch and classical baselines across 14 diverse classification tasks. First, while SSL outperforms training from scratch on average and remains competitive with state-of-the-art tree ensembles (achieving ~0.8954 AUC vs. Random Forest's 0.9015 at 10% labels), the SSL-vs-scratch gains exhibit high inter-task variance and lack significance (p = 0.626 at both 5% and 10% labels). Second, contrary to the hypothesis that missing-value imputation objectives universally benefit datasets with native missingness, SSL yields the most reliable improvements on clean datasets, while frequently degrading performance on datasets with high inherent missingness. Third, despite this training variance, SSL-pretrained models achieve a higher average AUC than scratch-trained models under both test-time missingness completely at random (MCAR) injection (+0.0245 AUC, positive on 11 of 14 tasks) and structured missingness shifts (MNAR, +0.0418 AUC, positive on 8 of 14 tasks), though neither difference remains statistically significant after Holm-Bonferroni correction for multiple comparisons (adjusted p = 0.118 and p = 0.518, respectively). Fourth, comparing our mask-and-recover objective against three established tabular SSL baselines (VIME, SCARF, SubTab) under an identical encoder architecture, we find no significant difference from any of them (adjusted p = 0.459, p = 1.000, p = 1.000), indicating our findings reflect general properties of tabular SSL rather than idiosyncrasies of one particular pretext task.

AI 总结：本研究提出参数高效自监督适配方法，仅更新9%参数即可适配EEG-FM，在三个临床EEG数据集上较线性探测获最高20倍AUCPR，固定计算预算下仅需20%-50%未标记数据，可降低部署负担。

链接：https://arxiv.org/abs/2608.24727

机构：University of Tübingen（蒂宾根大学）； Hertie Institute for AI in Brain Health (Hertie AI)（赫蒂脑健康人工智能研究所）； University Clinic Tübingen（蒂宾根大学医院）； Hertie Institute for Clinical Brain Research（赫蒂临床脑研究所）

作者：Meghal Dani, Stefanie Liebe

英文摘要：EEG foundation models pretrained via self-supervised learning promise transferable representations, but their generalization remains limited, especially across diverse clinical datasets. Full fine-tuning is impractical for resource-constrained clinical settings due to high computational requirements. In this work, we investigate whether parameter-efficient self-supervised adaptation, updating only 9% of parameters suffices to align representations to target tasks. We evaluate our method on two state-of-the-art models with different pretraining objectives: BIOT (contrastive) and CBraMod (masked reconstruction), and evaluate on three clinical EEG datasets for abnormality detection (TUAB), event classification (TUEV), and seizure detection (CHB-MIT) under both in-distribution and out-of-distribution conditions. SSL adaptation yields consistent gains over linear probing, up to 20x AUCPR. Under a fixed compute budget, peak performance requires only 20--50% of available unlabeled data. Critically, when total window count is fixed, performance remains invariant to patient count, suggesting that performance is dependent on overall temporal window diversity only. Our findings demonstrate that parameter-efficient adaptation enables effective deployment of EEG Foundation models (EEG-FM) with minimal computational overhead and data collection burden. Code available at: this https URL

AI 总结：该研究针对空间解析生物学的组织学-转录组学邻域检索问题，提出BioKERN框架，通过结合转录组相似性与空间邻近性构建生物核实现正则化，在相关数据集上较BLEEP提升了检索性能。

链接：https://arxiv.org/abs/2608.24823

机构：Rice University（莱斯大学）

作者：Seungik Cho, Betul Orcan-Ekmekci

英文摘要：Spatially resolved biology requires representations that preserve biological neighborhood structure rather than only exact cross-modal correspondences. Existing histology--transcriptomics objectives can emphasize instance-level matching even when non-paired spots share molecular or spatial context. We introduce BioKERN, a multimodal spatial representation-learning framework that incorporates biological structure as an explicit, learnable inductive bias. BioKERN constructs a training-time biological kernel by combining transcriptomic similarity and spatial proximity, then uses it to provide graded neighborhood supervision and regularize embedding geometry. Evaluation uses a fixed, model-independent biological neighborhood definition shared by all methods. Across Mouse Brain Visium and Human Liver GSE240429, BioKERN consistently improves biological-neighborhood retrieval over BLEEP in both single- and multi-scale settings. Controlled shared-architecture experiments show that most of the improvement arises from biological-kernel regularization rather than increased model capacity. These results support explicit biological geometry as an interpretable inductive bias for multimodal learning in spatial biology.

AI 总结：本研究针对自动作文评分的固定提示选择策略成本高的问题，提出多臂老虎机驱动的自适应提示选择框架，在保证准确率的同时减少78.4%的LLM调用，生成成本-可靠性学习曲线，为教育技术平台提供平衡成本与有效性的方案。

链接：https://arxiv.org/abs/2608.23814

机构：Carleton University（卡尔顿大学）

作者：Olga Manakina, Igor Bogdanov

英文摘要：Large Language Models (LLMs) demonstrate strong capabilities in automated essay scoring (AES), but contemporary approaches typically employ fixed prompt selection, failing to address operational cost concerns and evolving optimal configurations. We propose a novel cost-aware approach that treats each prompt type as an arm in a multi-armed bandit (MAB) controller, enabling adaptive selection of optimal prompting strategies during inference. Our experiments on IELTS Writing Task 2 essays show that the MAB framework achieves comparable scoring accuracy to exhaustive grid search while reducing LLM calls by 78.4\% to find the best grading approach. We implemented four distinct grading recipes (multi-step vs. single-step assessment, with vs. without calibration examples) and found that the multi-step approach with examples achieves the highest accuracy. By tracking token usage and latency alongside agreement metrics, we produce the first cost-reliability learning curves for essay scoring, providing actionable insights for educational technology platforms that must balance operational costs against assessment validity. This work represents the first application of online control mechanisms to adaptively select prompting strategies in AES, transforming prompt selection from an offline hyperparameter optimization problem into an efficient online learning task.

AI 总结：CoDrift是面向离线强化学习的组合框架，通过组合三类目标场生成策略，在OGBench和D4RL的73个任务中，于离线和离线转在线设置均取得最优平均排名。

链接：https://arxiv.org/abs/2608.23939

机构：Xi’an Jiaotong University（西安交通大学）

作者：Xiewei Ni, Ruofeng Mei, Xiangyu Xu

英文摘要：Offline reinforcement learning is intrinsically multi-objective: a policy must remain compatible with the behavioral support of a fixed dataset while preferentially selecting high-value actions. We recast these objectives in a common form by viewing each as an action-space motion field that specifies how generated actions should move. This perspective enables heterogeneous learning objectives to be combined directly through field composition. Inspired by drifting models, we propose CoDrift, a compositional framework for one-step generative policy learning. CoDrift combines three objective-level fields into a unified policy field. The conditional field preserves state-dependent behavioral structure, while the marginal field pools actions across states to provide a more stable generative signal in the single-positive-sample regime of continuous-control offline RL. The value field moves generated actions toward higher-value regions. The composed field is absorbed into a stochastic generator that produces an action with a single forward pass at deployment. We evaluate CoDrift on 73 tasks from OGBench and D4RL in both offline and offline-to-online settings. CoDrift compares favorably with state-of-the-art methods and achieves the best average rank in both settings.

AI 总结：本研究针对强化学习在线策略评估的高方差问题，提出双循环梯度算法学习鲁棒行为策略，其对转移扰动敏感性更低，可降低真实环境评估成本。

链接：https://arxiv.org/abs/2608.24146

机构：California Institute of Technology（加州理工学院）； Massachusetts Institute of Technology（麻省理工学院）； Purdue University（普渡大学）； University of California, Riverside（加州大学河滨分校）； University of Virginia（弗吉尼亚大学）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

作者：Claire Chen, Shuze Daniel Liu, Licheng Luo, Rohan Chandra, Nan Jiang, Shangtong Zhang

英文摘要：In reinforcement learning policy evaluation, classic on-policy methods often suffer from high variance when estimating policy performance. To mitigate this issue, behavior policy search has been proposed to learn data-collecting policies tailored to reduce online evaluation variance. However, these approaches do not account for uncertainties in the transition functions. In practice, simulator transitions often differ from the real world due to modeling errors or approximation limitations. As a result, behavior policies trained in simulation may still yield high variance when deployed in real environments, leading to costly reliance on real-world evaluation samples. In this work, we propose a double-loop gradient-based algorithm for learning behavior policies that are both efficient and robust to transition uncertainty. Theoretically, we derive novel transition-variance gradient expressions and establish global convergence guarantees for the algorithm. Numerically, we demonstrate that our method is less sensitive to transition perturbations than existing approaches, providing supportive evidence for its practical utility.

AI 总结：针对部分可观测不安分赌机，提出t步前瞻阈值策略，可验证可索引性，其近似惠特尔指数几何收敛，性能优于一步基线且接近最优基准。

链接：https://arxiv.org/abs/2608.24167

作者：Qizhen Jia, Keqin Liu

英文摘要：Whittle index policies offer a scalable method for restless multi-armed bandits, but under partial observability even determining the indifference subsidy at a single belief requires solving an infinite-horizon belief-state problem with no closed-form value function. Liu [10] addresses this difficulty by linearizing the unknown decision boundary, leading to a linear system and a closed-form approximate Whittle index. However, the resulting threshold uses only a one-step active--passive comparison and does not account for longer-horizon continuation values. We extend this framework to a \emph{$t$-step lookahead threshold policy}. For each subsidy $m$, the threshold is defined by the active-minus-passive advantage under $t$-step finite-horizon value iteration. At $t=1$, the threshold is $m$-independent and recovers the linear threshold of Liu [10]; for $t>1$, it becomes subsidy-dependent through the induced first-crossing structure and tracks the exact decision boundary more closely. The proposed algorithm does not require indexability as an input and includes an indexability verification. Under the original Whittle indexability, we prove that the $t$-step approximate Whittle index converges geometrically to the exact Whittle index, \[ |\widehat W_t(\omega)-W(\omega)|=O(\beta^t). \] Numerically, all 2,715 tested three-state instances are verified as indexable according to the proposed criterion. The P95 index error decreases from $2.18\times10^{-2}$ at $t=1$ to $8.93\times10^{-4}$ at $t=8$. In an exact-comparable instance with $\beta=0.9999$, $t=2$ already recovers the exact Whittle-index ordering. Moderate-depth threshold policies also outperform the one-step baseline and remain close to the optimal dynamic-programming benchmark, while runtime grows mildly with $t$.

AI 总结：针对工具集成智能体训练的细粒度信用分配问题，提出CBPO解耦分支采样的预算分配与信用转化，在十个基准上优于现有方法，获两个领域及两种模型规模下最高宏平均准确率。

链接：https://arxiv.org/abs/2608.24300

机构：Alibaba Group（阿里巴巴集团）； Harbin Institute of Technology（哈尔滨工业大学）

作者：Ying Wang, Changlin Qiu, Bang Lin, Linbo Jin, Wen Jiang, Zhe Sun, Jingli Yang

英文摘要：Reinforcement learning with verifiable rewards (RLVR) enables language models to learn multi-turn interaction with external tools, yet its sparse outcome rewards provide no signal for identifying which intermediate decisions are responsible for success. Branch sampling induces local comparisons among alternative continuations, but existing methods tend to conflate two distinct problems: allocating a fixed rollout budget and translating branch outcomes into token-level credit. We introduce Contrastive Branch Policy Optimization (CBPO), which disentangles these two problems and assigns a dedicated mechanism to each. Generation entropy screens candidate branch positions across the entire response, while path-level and node-level decay distribute a fixed budget across trajectories and positions to prevent exploration from collapsing onto a few paths or adjacent tokens. A parent trajectory together with the branches that share an identical token prefix forms an exact-prefix group, and the reward variation within this controlled group defines the Contrastive Branch Value (CBV), an outcome-based estimate of local decision sensitivity that rescales continuation advantages without altering their sign. When multiple nodes are selected along the same trajectory, CBPO partitions it into non-overlapping credit segments, thereby avoiding duplicated gradients on shared tokens. Requiring only outcome rewards and no process-level annotation, CBPO provides a practical solution for fine-grained credit assignment in tool-integrated agent training. Extensive experiments on ten benchmarks, including five for mathematical reasoning and five for knowledge-intensive search, show that CBPO consistently outperforms state-of-the-art policy-optimization and branch-based methods, attaining the highest macro-average accuracy in both domains and across two model scales.

AI 总结：该研究针对大规模并行模拟下离线RL的数据 regime 变化问题，提出具 regime 感知的WarpSAC算法家族，适配不同数据规模场景，在多基准任务及现实部署上较FlashSAC实现显著性能提升。

链接：https://arxiv.org/abs/2608.24479

机构：Tianjin University（天津大学）； Shanxi University（山西大学）； Imperial College London（伦敦帝国学院）

作者：Zihao Wu, Hongyao Tang, Yi Ma, Huizhong Song, Pengyi Li, Yifu Yuan, Fei Ni, Jinyi Liu, Wei Wei, Jianrong Wang, Yan Zheng, Jianye Hao

英文摘要：Massively parallel simulation changes the data regime in which off-policy reinforcement learning (RL) is trained, challenging stabilizers designed for data-limited replay. Through controlled experiments across eight benchmark families, we show that these stabilizers are data-regime-dependent: parameter normalization helps with narrow replay coverage but restricts value fitting when data are abundant, while clipped double-Q can be relaxed in high-throughput manipulation. Age-biased replay weighting improves learning efficiency across regimes, especially with limited network capacity. Based on these findings, we propose WarpSAC, a regime-aware family of off-policy RL algorithms. WarpSAC uses Sample Weight Decay for efficient exploitation and provides two variants: WarpSAC-L (Norm ON, clipped double-Q) for data-limited CPU-scale training, and WarpSAC-A (Norm OFF, single-Q) for data-abundant GPU-parallel training. WarpSAC improves normalized score--step AUC over FlashSAC by 4.5% across nine CPU-scale environments and 23.1% across fourteen GPU-parallel environments. It increases UnitreeG1TransportBox-v1 success rate from 19.8% to 96.4%, improves mean normalized wall-time AUC on MuJoCo Playground by 19.1%, and achieves 36.4% faster sim-to-real deployment on Unitree G1 than FlashSAC. These results show that scalable off-policy RL should adapt its stabilizers to the available data regime.

AI 总结：本研究提出IAPO方法，将轨迹转化为影响依赖图以优化多轮服务智能体的信用分配，在三个服务智能体基准及BFCL-v4多轮任务上，性能优于多轮RL基线。

链接：https://arxiv.org/abs/2608.24588

机构：Fudan University（复旦大学）； WeChat, Tencent Inc.（腾讯公司微信业务）

作者：Bo Ren, Yirong Mao, Yi Yang, Wenhui Que

英文摘要：Large Language Model (LLM) agents increasingly solve long-horizon tasks through multi-turn interactions with users and external tools. In these settings, relevant task information often unfolds over time rather than being fully specified at the initial prompt. Service agents make this challenge especially concrete: users may clarify or revise their goals, while tool responses provide information needed for subsequent decisions. Thus, a final reward alone cannot indicate which actions contributed to resolving the task. Recent methods rely on comparative evidence from other trajectories or resampled continuations, or on separately constructed step-level learning signals, to refine credit. However, a completed rollout already records how information and errors flow between agent actions. We introduce Influence-Aware Policy Optimization (IAPO), which represents each rollout as a typed influence-dependency graph over trainable agent actions, with user and tool observations serving as evidence. IAPO converts support-use and failed-use structure into routing weights that redistribute the same trajectory-level advantage. Experiments with Qwen3-4B and Qwen3-8B demonstrate superior performance over multi-turn reinforcement learning (RL) baselines across three service-agent benchmarks: {\tau^2}-Bench, UserBench, and AgentChangeBench. BFCL-v4 Multi-Turn further shows that these gains do not compromise multi-turn function-calling performance. This work advances the understanding of credit assignment in multi-turn user interactions and provides a principled approach to training service agents from sparse outcome feedback.

AI 总结：该研究针对拟阵约束下的对抗博弈子模极大化问题，提出基于平衡分数交换的多项式时间算法，实现次线性regret，是该方向首个此类算法。

链接：https://arxiv.org/abs/2608.24627

机构：Great Bay University（湾大大学）； Fuzhou University（福州大学）

作者：Zongqi Wan, Zhijie Zhang

英文摘要：We study adversarial bandit maximization of monotone submodular functions under a matroid constraint. For a rank-$k$ matroid on $n$ elements, we give a randomized oracle-polynomial algorithm that makes one feasible value query per round and has expected $(1-1/e)$-regret $\widetilde O(n^{1/3}k^{2/3}T^{2/3})$. This is the first sublinear-regret algorithm for adversarial bandit submodular maximization under general matroid constraints. Technically, we view the problem as learning an exchange policy for the Poisson base walk. This connects the problem to contextual bandits and gives an information-theoretic sublinear-regret guarantee, but directly learning the exponentially many policies requires exponential time and space. We therefore introduce \emph{balanced fractional exchanges}, which compress the policy mixture into a single fractional base while retaining the exchange information needed by the Poisson analysis. This leads to an polynomial time algorithm with the same regret guarantee.

AI 总结：本研究提出OPDVR方法，无缝结合OPD与RLVR且不增加超参数，经六个推理基准实验验证其性能优于标准OPD。

链接：https://arxiv.org/abs/2608.24696

机构：LeapLab, Tsinghua University（清华大学LeapLab）； Beihang University（北京航空航天大学）； SMS, Peking University（北京大学SMS）； NLPLab, Tsinghua University（清华大学NLPLab）

作者：Wenze Lin, Jiale Zhao, Xitai Jiang, Songde Rao, Yining Li, Shenzhi Wang, Bingxiang He, Gao Huang

英文摘要： Reinforcement Learning with Verifiable Rewards (RLVR) and on-policy distillation (OPD) have become two widely adopted paradigms for post-training large language models. However, RLVR suffers from sparse task-level feedback, while OPD provides dense token-level guidance but ignores trajectory correctness, limiting its performance to that of the teacher. Combining them is a promising direction: OPD supplies dense supervisory signals, while RLVR provides task-level correctness. Nevertheless, existing integrations often rely on weighted combination or heuristic switching, introducing extra hyperparameters and trade-offs. We propose On-policy Distillation with Verifiable Reward (OPDVR), a simple yet effective method that seamlessly combines OPD and RLVR without adding any hyperparameters. We first reformulate the implicit reward of sampled-token OPD based on trajectory correctness, then apply a ReLU gating mechanism to ensure that correct trajectories receive non-negative rewards and incorrect ones receive non-positive rewards---thereby aligning the distillation signal with task success while preserving the teacher's distributional guidance. Furthermore, our modification transforms sampled-token OPD into a proper RLVR method, making it readily combinable with any policy gradient algorithm, such as GRPO. Experiments on six reasoning benchmarks show that OPDVR consistently outperforms standard OPD. Our code is available at this https URL.

AI 总结：本文针对离线强化学习中边缘化重要性加权的残留占用平衡违反问题，提出等渗贝尔曼校准方法，可减少此类违反并保证下游策略价值估计等任务的性能。

链接：https://arxiv.org/abs/2608.24858

机构：Stanford University（斯坦福大学）； Netflix（网飞）； Cornell University（康奈尔大学）

作者：Lars van der Laan, Nathan Kallus

英文摘要：Marginalized importance weighting evaluates a target policy by reweighting offline state-action samples with its discounted occupancy ratio, characterized by an adjoint Bellman equation. Existing minimax, primal-dual, and fitted fixed-point estimators can leave residual occupancy-balance violations because of function-class approximation, regularization, or incomplete optimization. These violations are difficult to diagnose and reduce because the objectives generally lack a direct supervised validation loss for hyperparameter tuning, model selection, and early stopping. We introduce isotonic Bellman calibration, a one-dimensional, model-agnostic post-processing method that reduces these violations while preserving the ranking information in any initial occupancy-ratio estimate. The method corrects the estimate's scale and shape by applying fitted occupancy-ratio evaluation (FORE) over a one-dimensional class of nondecreasing transformations. We characterize Bellman calibration as a conditional fixed-point property equivalent to occupancy-balance against every test function of the calibrated ratio. More generally, we derive a calibration-refinement bound showing that any fitted ratio with small calibration error performs nearly as well as the best post-processing based on its fitted values. For isotonic Bellman calibration, we establish finite-sample calibration guarantees and a KL oracle inequality relative to the best monotone transformation of the initial estimate. Consequently, isotonic Bellman calibration achieves small calibration error and KL risk within statistical error of the best monotone correction, with guarantees for downstream target-occupancy functionals, including policy-value estimation.

AI 总结：该研究针对多任务VRP求解器的训练与架构缺陷，提出POLAR算法与PLE编码器，在16个分布内变体上平均差距降21.3%，27个未见变体优于现有方法，提升了跨问题泛化性能。

链接：https://arxiv.org/abs/2608.24859

机构：University of Coimbra（科英布拉大学）

作者：Arthur Corrêa, Paulo Nascimento, Samuel Moniz

英文摘要：Multi-task vehicle routing problem (VRP) solvers seek to handle multiple VRP variants within a single unified model, avoiding the need to train a separate model for every variant. In spite of recent progress, current approaches remain limited on two fronts. On the training side, reinforcement learning suffers from reward-scale disparities and shrinking advantage signals as policies improve, whereas preference optimization stagnates once sampled tours become near-identical and thus fundamentally limited by the quality of the policy's own generated solutions, leaving both paradigms with weak supervision as training progresses. On the architecture side, existing fully shared encoders entangle constraint-dependent representations across heterogeneous variants, which limits generalization. We address these gaps with two model-agnostic contributions. First, we propose Preference Optimization with Locally Augmented Refinement (POLAR), a novel training algorithm that applies a local search refinement pass to the best decoded tour before forming preference pairs, yielding much more informative pairwise margins. Second, a Progressive Layered Extraction (PLE) encoder routes each encoder layer through one shared expert and a set of task-specific experts via a gating mechanism, progressively separating common routing structure from constraint-specific encodings. Through extensive experiments on various VRP variants, we show that POLAR and PLE together elevate the current state-of-the-art among neural multi-task solvers. We reduce the average gap to reference solutions by 21.3% relative to the strongest published baseline on 16 in-distribution variants, and outperform prior neural methods on 27 out of 32 unseen variants. Ablation studies confirm the efficacy of each contribution, showing that both improve cross-problem generalization across multiple backbone model architectures.

AI 总结：本研究评估12个指令微调开放权重LLM作为直接因果边分类器的可靠性，发现其判断过度预测、置信度不可靠，仅跨提示/模型一致性更优，建议将其作为软因果先验来源而非因果结构直接证据。

链接：https://arxiv.org/abs/2608.23660

机构：Texas A&M University-Corpus Christi（德克萨斯农工大学科珀斯克里斯蒂分校）； BITS Pilani Goa（戈亚斯 pilani Bits 大学）； Mississippi State University（密西西比州立大学）； Northern Illinois University（北伊利诺伊大学）； Texas Christian University（得克萨斯基督教大学）

作者：Amit Kumar, Elnur Adl Zarabi, Suranjana Trivedy, Zhiqian Chen, Lei Zhang, Kaiqun Fu, Taoran Ji

英文摘要： Large language models (LLMs) are increasingly used to provide prior causal knowledge for structural causal discovery, yet whether their direct-edge judgments and confidence can be trusted remains unclear. We systematically evaluate 12 instruction-tuned open-weight models across six benchmark causal graphs, five prompting strategies, and four confidence sources: verbalized, logit-based, cross-prompt agreement, and cross-model agreement. Under our language-only pairwise protocol, our evaluation yields three key findings. (i) LLM-based causal judgments are strongly recall-dominant: models predict overly dense graphs with many false-positive edges, while prompting mainly shifts the precision-recall trade-off rather than resolving overprediction. Gains from model scale diminish on the largest graphs and do not eliminate miscalibration. (ii) LLMs often capture causal relatedness without reliably identifying directness or orientation. Relative to published reference graphs, models misclassify 40.0% of indirect and 36.0% of reversed non-edges as direct edges, versus 28.2% of other non-edges. Moreover, 80.8% and 84.6% of these false positives receive verbalized confidence of at least 80%, revealing substantial overconfidence in structurally incorrect predictions. (iii) Conventional confidence estimates are unreliable, whereas agreement offers a more promising signal. Logit-based confidence frequently collapses near 1.0 regardless of correctness, while cross-prompt and cross-model agreement achieve better mean calibration and discrimination, though their advantages are not statistically significant after Holm correction. A benchmark-familiarity audit further identifies potential familiarity in five model-dataset pairs, all involving AsiaM. Overall, our results suggest LLMs are better viewed as sources of externally validated soft causal priors than as direct evidence of causal structure.

AI 总结：该研究提出RGFM框架，利用重整化群的准局域性和尺度分离特性，实现仅用局部计算即可复现长程相关性的可扩展生成建模，在一维分布和FFHQ图像上表现优于传统局部流匹配。

链接：https://arxiv.org/abs/2608.23696

机构：The University of Tokyo（东京大学）； Institute for Physics of Intelligence, The University of Tokyo（东京大学智能物理研究所）

作者：Kanta Masuki, Yuto Ashida

英文摘要：Despite their remarkable success in modeling complex data, generative models face a fundamental tradeoff. Global approaches can capture full structural coherence but suffer from high computational costs, while local models are efficient but often fail to reproduce long-range correlations and global coherence. The renormalization group (RG) bridges this gap by seamlessly connecting spatial structures across different length scales, retaining quasi-local descriptions at each step while preserving long-range correlations. We introduce renormalization group flow matching (RGFM), a generative framework that systematically structures data generation across different spatial scales. By using an exact RG flow as the probability path, RGFM progressively generates data from long- to short-wavelength structures. To reconcile scalability with global structure, we exploit two key properties of the RG: quasi-locality and scale separation. We rigorously show that the RGFM probability flow can be accurately approximated by local velocity fields acting over a spatial range $O(\Lambda^{-1}[\ln L+\ln(1/\varepsilon)])$ for RG wavenumber scale $\Lambda$, linear system size $L$, and prescribed error tolerance $\varepsilon$. This property enables local generative modeling with patches of size $O(\ln L)$ and a computational cost that scales nearly linearly with the system volume. We numerically demonstrate that local RGFM reproduces long-range correlations far beyond its receptive field in representative one-dimensional distributions, while conventional local flow matching exhibits substantial errors at long distances. On FFHQ images, RGFM yields far more coherent and higher-quality samples than local flow matching at 64x64 and 256x256. Our results establish RG-guided probability flows as a promising route toward scalable generative modeling that captures long-range structure using only local computation.

AI 总结：本研究建立紧致黎曼流形上生成式扩散模型的物种形成内蕴理论，刻画其分岔机制，推导相关估计与稳定性结论，经球面实验及神经网络学习方案验证。

链接：https://arxiv.org/abs/2608.23798

机构：University of Milan（米兰大学）

作者：Alessio Marta, Paola Causin

英文摘要：Speciation in generative diffusion models denotes the emergence of distinct stable branches during denoising, through which initially undifferentiated trajectories progressively commit to different data classes. In this work we develop an intrinsic theory of speciation for diffusion models supported on compact Riemannian manifolds: the aim is to go beyond existing theoretical descriptions, which usually identify speciation with a symmetric pitchfork bifurcation and assume to work in a large-dimensional space. We characterize speciation by bifurcations of the critical points of the evolving probability density. A spectral heat-kernel representation makes explicit the role of the manifold geometry, while Poincaré-Hopf and Morse theory impose global constraints on the number and type of score equilibria and reveal topologically-imposed geometrical modes. For mixtures of heat kernels, we prove that generic speciation events have a one-dimensional critical kernel and admit an A2 fold normal form; pitchforks and simultaneous multidirectional transitions arise from nongeneric symmetric configurations. We derive geometry-dependent estimates of speciation times for bimodal mixtures and Riemannian regular simplices. We further establish structural stability of nondegenerate folds under score perturbations and show that the first-order time shift is determined solely by the component of the score error along the critical direction. The theory is illustrated on the sphere using mixtures of von Mises-Fisher distributions, where pitchfork and saddle-node bifurcations, topological modes, and hierarchical multiple speciations are observed. Finally, a chart-based intrinsic score-learning scheme based on neural networks contrasts the theoretically predicted transitions on prototypal and more complex datasets.

AI 总结：该研究推导出去噪分数匹配的损失下限的精确表达式，关联薛定谔桥与费希尔几何，揭示扩散模型训练损失的固有信息几何成分，指出不同噪声设置下原始损失无法一致排序的原因。

链接：https://arxiv.org/abs/2608.23916

机构：Great Wall Motors Co. Ltd.（长城汽车股份有限公司）； China Patent Information Center（中国专利信息中心）

作者：Avinash Raju, Kai Zhang

英文摘要：Denoising score matching trains diffusion models by regressing onto a conditional score, although generation ultimately requires the marginal score. The two objectives share the same population minimizer, but the conditional target remains random at fixed noisy state and introduces an irreducible excess in the training loss. We isolate this excess and show that, for a general corruption kernel under mild regularity assumptions, it is exactly the trace of the Fisher--Rao metric of the conditional endpoint family, integrated along the diffusion trajectory. This gives an exact conditional-variance decomposition of the denoising objective and identifies the information geometry observed in diffusion latent spaces as an intrinsic component of the training loss. We derive the result from a Schr"odinger bridge variational principle, in which the ideal objective arises as excess path-space relative entropy. For corruption diffusions, the Fisher term is proportional to the rate at which the noisy state loses mutual information about the clean data, separating the loss floor into an information flow determined by the data and a weight determined by the corruption schedule and objective. In the Gaussian case, this yields a closed form for the floor, recovers reparametrization invariance of the continuous-time objective, and relates its high-SNR divergence to the information dimension of the data. Finally, we show that raw losses obtained with different noise ranges or weightings need not rank models consistently because they contain different additive floors, and contrast the second-order geometry seen by training with the third-order conditional statistics entering numerical sampling error.

AI 总结：本文针对GraphGANFed无法按用户定义指标生成分子的问题，提出cGraphGANFed模型，引入评判网络整合评估结果优化生成器，经实验证实其在多指标优化、QED提升及抗非IID数据干扰上表现更优。

链接：https://arxiv.org/abs/2608.24610

作者：Daniel Manu, Abee Alazzwi

英文摘要：Generative adversarial networks (GANs) have garnered considerable attention in molecular discovery for their ability to generate novel and high-quality molecules. To efficiently train a GAN model while preserving data privacy, GraphGANFed has been proposed to incorporate federated learning and graph convolutional networks into GAN. Yet, GraphGANFed cannot produce synthetic molecules that only optimize a user-defined metric(s) to facilitate the new drug discovery process. To address this issue, we introduce a novel extension to GraphGANFed, namely conditional GraphGANFed (cGraphGANFed), by incorporating the critic network to assess generated molecules using user-defined metric(s). The evaluation results from both the critic network and discriminator are integrated into the loss function of the generator, guiding it to generate novel molecules that maintain similar chemical properties to real ones while optimizing user-defined metrics. Extensive simulations are conducted in two scenarios. First, cGraphGANFed endeavors to optimize all seven commonly used metrics, and the results show that cGraphGANFed significantly outperforms GraphGANFed in Validity and LogP, with a slight advantage in QED, across different settings. Second, cGraphGANFed focuses solely on optimizing QED, and the results show that the synthetic molecules produced by cGraphGANFed can achieve more than 10% improvement in QED than GraphGANFed. Also, the results demonstrate cGraphGANFed has enhanced resilience against mode collapses and performance reduction caused by non-IID data.

AI 总结：本文针对低秩恢复的约束核范数最小化问题，通过新的上界分析证明调和均值权重算子的最优性，给出IRLS算法的收敛速率，并经数值实验验证其优于单侧重加权方案。

链接：https://arxiv.org/abs/2608.23765

机构：University of Central Florida（中佛罗里达大学）； Wirtschaftsuniversität Wien（维也纳经济大学）； KU Eichstätt-Ingolstadt（艾希施泰特-英戈尔施塔特大学）

作者：Christian Kümmerle, Tomas Masak, Dominik Stöger

英文摘要：Iteratively reweighted least squares (IRLS) methods constitute a natural approach to nuclear norm minimization, but their convergence rates and the role of the weight operator have remained poorly understood. This paper establishes sharp convergence rates for IRLS methods for constrained nuclear norm minimization in low-rank recovery. A central ingredient is a new majorization analysis for the smoothed nuclear norm: we prove that the harmonic-mean weight operator defines a valid global quadratic majorizer. Furthermore, we show that this weight operator is optimal within the family of power-mean weights, clarifying why it improves over classical one-sided reweighting schemes that use only row- or column-space information. Under a Schatten-1 null space property, we prove global linear convergence of IRLS algorithms using a variety of weight operators, including the harmonic-mean weights. For IRLS with harmonic-mean weights, we prove a dimension-independent, locally linear convergence rate. We provide a counterexample showing that this dimension-independent local rate cannot in general be obtained for IRLS algorithms using one-sided weight operators, which predominate in the literature. Numerical experiments corroborate the theoretical results and illustrate the practical advantage of harmonic-mean reweighting across square, rectangular, and adversarially initialized recovery problems.

AI 总结：该研究针对圆上的部分最优传输问题，提出时间复杂度为O(N log N)的PAWC算法，可高效返回所有传输基数的最优成本，在实验中展现出比现有方法更优的鲁棒性与计算效率。

链接：https://arxiv.org/abs/2608.23910

机构：College of Connected Computing（互联计算学院）； Vanderbilt University（范德堡大学）

作者：Soheil Kolouri

英文摘要：Partial optimal transport compares two measures while leaving part of the mass unmatched, which is what makes it robust to outliers, occlusion, and clutter. The quantity of interest is usually the whole profile - the optimal cost at every transported cardinality - because the right amount to transport is rarely known in advance, and on the real line the PAWL algorithm returns that profile in $O(N\log N)$. Much data is periodic rather than linear: angles, phases, orientations, time of day, hue, and every direction obtained by projecting onto a great circle. On the circle the same problem acquires a global circulation, or equivalently an optimized cut, which the naive exact method handles by running the line algorithm once per support gap, at $O(N^{2}\log N)$. We show that this factor $N$ is unnecessary. The line structure survives in cut-free form, and a free-gap invariant supplies, at every step, a cut at which all previous local updates remain valid line updates. This yields PAWC: an exact $O(N\log N)$ time, $O(N)$ memory algorithm returning all $K+1$ costs, nested active sets and plans in one run, together with a single gap that is simultaneously optimal for every cardinality. Slicing over great circles extends it to $\mathbb{S}^{d-1}$. Empirically the whole profile costs $0.56$ms at $N=4096$ against $1.5$s for a single transported fraction from a general solver; on occluded, cluttered mpeg-7 shapes, holding the descriptor fixed and varying only the cost, it retains $66\%$ of the clean-data retrieval score against $16\%$ for balanced circular OT, and on $\mathbb{S}^{2}$ it halves the fitting error of spherical sliced Wasserstein against contaminated targets, synthetic and real. Code is available at this https URL.

AI 总结：该研究针对LLM智能体提出贝叶斯自我升级策略，将生成中委派建模为贝叶斯最优停止问题，经模拟和真实代码级联验证，其升级机制在同等成本下优于事后路由，能力信念区分度随生成提升。

链接：https://arxiv.org/abs/2608.24087

作者：Nadeem Shaikh

英文摘要：Current LLM agent systems decide delegation before reasoning begins (a router picks a model) or after a response is complete (a verifier scores it and may retry). We study a third regime: an agent that recognises, during its own reasoning, that it is unlikely to succeed and transfers control to a stronger model. We formulate intra-generation delegation as a Bayesian optimal-stopping problem over a learned competence posterior -- an online estimate of the agent's eventual task success whose sufficient statistics are learned from labelled trajectories, not read off raw entropy. We derive the myopic escalation threshold in closed form, characterise the optimal policy via dynamic programming, and prove that the optimal policy is a time-varying threshold with no shape assumption on the raw signal. We further prove exponential separation of the oracle belief at the Chernoff-information rate of the signal, a regret bound governed by the calibration of the posterior, and a finite-sample guarantee: with n labelled calibration trajectories the deployed plug-in policy's regret decays as 1/sqrt(n). A controlled simulation study confirms each prediction of the theory, including the predicted 1/sqrt(n) rate. We additionally report a real-model validation on a Qwen2.5-Coder 1.5B->7B code cascade (MBPP, 257 tasks), confirming two of three pre-registered predictions: the escalation frontier dominates post-hoc routing at equal cost, and the cumulative competence belief's discrimination rises over generation.

AI 总结：本研究提出一种基于L1范数Rademacher复杂度的分析框架，无需训练即可估计早停最优时间，可应用于线性模型及经线性探测方法适配的非线性神经网络。

链接：https://arxiv.org/abs/2608.24210

机构：Université Paris-Saclay（巴黎-萨克雷大学）； CNRS（法国国家科学研究中心）； ENS Paris-Saclay（巴黎-萨克雷高等师范学校）； Inria（法国国家信息与自动化研究所）； CIAMS（运动与健康科学研究所）； LURPA（巴黎-萨克雷大学自动控制与生产实验室）； LMF（力学与流体实验室）

作者：Duy Hoang, Bastien Berret, Olivier Bruneau, Laurent Fribourg

英文摘要：Training neural networks requires balancing the trade-off between fitting the training data and achieving robust performance on unseen inputs. This ability, commonly referred to as generalizability, is determined by the gap between the empirical risk on the training set (``empirical loss'') and the expected risk over the data distribution (``generalization error''). Existing approaches typically estimate the generalization error numerically, requiring gradient descent training and an ``early stopping'' strategy. In this work, we introduce an analytic framework that estimates the optimal time of early stopping without the need for training. Several works in the literature also give such analytical estimations, but they are generally based on random matrix theory and often make assumptions on the distribution of the data or the eigenvalue distribution of the covariance matrix. In contrast, our work is based on Rademacher complexity (RC) without needing such probabilistic assumptions. For both theoretical and numerical reasons, it is more relevant to express RC with the L1- norm rather than with the L2-norm. We focus on the case of linear models and the problem of linear regression. Thanks to the ``linear probing'' method, our results can, however, be successfully applied to nonlinear neural networks, as illustrated in the classification MNIST example.

AI 总结：本文提出KENDO框架，将集成高斯过程与分歧感知获取策略结合，实例化KENDO-BO和KENDO-AL，在单/多目标优化及主动学习任务上，兼具更优性能与更高计算效率。

链接：https://arxiv.org/abs/2608.24721

机构：University of Georgia（佐治亚大学）； University of California San Diego（加利福尼亚大学圣迭戈分校）

作者：Heng Zhang, Haotian Xiang, Qin Lu, Konstantinos D. Polyzos, Tara Javidi

英文摘要：Hyperparameter selection remains a key challenge in Bayesian optimization (BO) and Bayesian active learning (AL), as model misspecification can lead to suboptimal performance, while more accurate fully Bayesian treatments typically rely on computationally expensive MCMC sampling. This paper proposes a unified framework, KENDO (Kernel ENsemble Disagreement-aware Operator), that integrates Ensemble Gaussian Processes (EGP) with disagreement-aware acquisition strategies. The central idea is to replace hyperparameter sampling with a kernel ensemble and adaptive Bayesian weighting, combined with disagreement-aware acquisition strategies. Within this unified framework, we instantiate KENDO-BO for BO and KENDO-AL for Bayesian AL, demonstrating that both arise from a common self-correcting mechanism with task-specific acquisition objectives. We further extend the approach to multi-objective optimization via random scalarization that preserves the single-optimizer conditioning structure. Thorough numerical tests on synthetic and real-world benchmarks across single-objective optimization, multi-objective optimization, and active learning demonstrate that (i) KENDO-BO achieves competitive or superior optimization performance compared to state-of-the-art methods while reducing computational overhead by up to $5\times$ and (ii) KENDO-AL achieves superior predictive calibration over MCMC-based active learning baselines with up to $27\times$ speedup.

AI 总结：该研究解决在线线性与凸优化的交替遗憾问题，提出OLO和OCO的最优算法，改进了此前的遗憾界，获得更快的博弈均衡收敛速度，还证明了对应的下界。

链接：https://arxiv.org/abs/2608.24731

机构：Shanghai University of Finance and Economics（上海财经大学）； Yale University（耶鲁大学）

作者：Yixin Tao, Weiqiang Zheng

英文摘要：We settle the minimax-optimal alternating regret, a regret notion motivated by alternating learning dynamics in games, for both online linear optimization (OLO) and online convex optimization (OCO). For OLO over the probability simplex $\Delta_d$, we give an algorithm with $O(\log d)$ alternating regret that remains a constant for any time horizon $T$, and a matching lower bound. Our constant regret bound significantly improves previous results with $O(\log ^{2/3}d \cdot T^{1/3})$ regret [Cevher, Cutkosky, Kavis, Piliouras, Skoulakis, Viano, NeurIPS 2023, Hait, Li, Luo, Zhang, COLT 2025]. As a result, we obtain alternating learning dynamics with $O(\log d /T)$ convergence to Nash equilibria in two-player zero-sum games and $O(\log d /T)$ convergence to coarse correlated equilibria in two-player general-sum games. This is the first uncoupled learning dynamics with $O(1/T)$ convergence to CCE in two-player general-sum games, while all prior works suffer additional $\log T$ factors. For general OCO over a $d$-dimensional compact convex set, we give an algorithm with $O(d\log (1+T/d))$ alternating regret, improving the previous best of $\widetilde{O}(d^{2/3}T^{1/3})$. We also prove a matching lower bound of $\Omega(d\log (1+T/d))$, showing that the $\Omega(\log T)$ factor is unavoidable.

AI 总结：PuzzleKV将KV缓存划分为固定长度逻辑页，以页为独立压缩单元，在匹配存储预算下实现高压缩率与近似完整KV的性能，在RULER、LongBench等基准上表现优于Global SVD。

链接：https://arxiv.org/abs/2608.23843

作者：Zizhong Wang, Jieying Wang, Zhao Zhang, Jiajia Li

英文摘要：Long-context inference in large language models (LLMs) is increasingly limited by the memory required for the key-value (KV) cache. KV cache compression addresses this problem by reducing the storage cost of previous tokens. Among existing approaches, low-rank compression is particularly attractive because it represents every token in reduced dimensions. Previous low-rank methods typically derive fixed projection spaces from model weights, construct fixed spaces from calibration activations, or construct a shared basis over a broad cache region. Such representations may not capture detailed but important information. We partition each per-head KV cache into fixed-length logical pages and observe substantial low-rank structure within individual pages. Based on this observation, we propose PuzzleKV, a training- and calibration-free method that treats each completed page as an independent compression unit. PuzzleKV decomposes pages within each layer and KV head, computes attention directly over dense and factorized pages, and incrementally compresses newly eligible pages during autoregressive decoding. Experiments across models, context lengths, and benchmarks demonstrate the effectiveness of PuzzleKV under matched storage budgets. At approximately 60% of the original KV cache storage, PuzzleKV achieves more than 96% of Full KV performance across both evaluated models and all benchmark settings, with substantial gains over Global SVD on RULER and competitive performance on LongBench. To achieve a more aggressive compression ratio, PuzzleKV can be further combined with quantization while retaining more than 93% of Full KV performance using only 18.7% of the original storage.

AI 总结：该研究针对持久图的事件空间差异问题，定义诱导概率以扩展交叉熵为持久交叉熵（PCE），证明其性质与稳定性，经数值研究验证PCE可区分特定图、分离因果方向及用作知识蒸馏的定向拓扑损失。

链接：https://arxiv.org/abs/2608.24549

机构：Artificial Intelligence Graduate School, Pohang University of Science and Technology（浦项科技大学人工智能研究生院）； Department of Mathematics, Pohang University of Science and Technology（浦项科技大学数学系）

作者：Sijin Yeom, Jae-Hun Jung

英文摘要：Persistent entropy is the Shannon entropy of a persistence-based probability measure defined on a persistence diagram. However, its cross-entropy version is not naturally defined because two persistence diagrams generally have different event spaces. To bridge these event spaces, we combine a similarity function with persistence weighting to define an induced probability. The induced probability reflects information from one diagram on the event space of the other diagram and assigns unexplained probability mass to the unexplained event. Using the induced probability, we extend cross entropy to persistence diagrams, called persistent cross entropy (PCE). We establish the main properties of both the induced probability and PCE and prove stability theorems for both. Through three numerical studies, we show that PCE distinguishes diagrams with the same persistent entropy, separates causal directions in dynamical systems without constructing a joint persistent diagram, and can be used as a directional topology loss for knowledge distillation.

AI 总结：针对几何深度学习中张量值预测的不确定性量化难题，提出E(3)等变UQ框架，通过分解协方差与矩阵指数法保证正定性，构建LE-ESO损失，在两类数据集上验证了方法的竞争力与不确定性估计的有效性。

链接：https://arxiv.org/abs/2608.24386

机构：College of Intelligent Robotics and Advanced Manufacturing, Fudan University（复旦大学智能机器人与先进制造学院）； School of Microelectronics, Fudan University（复旦大学微电子学院）； ByteDance（字节跳动）； School of Information Science and Engineering, East China University of Science and Technology（华东理工大学信息科学与工程学院）

作者：Ruihan Liu, Yu Ji, Jianbo Yu, Shifu Yan, Qingchao Jiang

英文摘要：Tensor-valued prediction is fundamental to geometric deep learning, yet uncertainty quantification (UQ) for such outputs remains an open challenge. While E(3)-equivariant neural networks excel at point estimates, they lack rigorous confidence measures. We focus on symmetric rank-2 tensor prediction, where the target has six Kelvin--Mandel coordinates and full uncertainty is represented by a $6\times6$ covariance matrix. We introduce a framework for E(3)-equivariant UQ, modeling the full predictive distribution where both mean and covariance preserve rotational symmetry. Our approach decomposes the covariance into irreducible representations $\mathrm{Sym}^2(\rho_c) \cong 2\times(l=0) \oplus 2\times(l=2) \oplus 1\times(l=4)$. By mapping from the flat Lie algebra $\mathfrak{sym}(6)$ to the curved SPD manifold via matrix exponentiation, we strictly ensure positive-definite covariances while maintaining exact equivariance. Furthermore, we formulate a Log-Euclidean Equivariant Scoring Objective (LE-ESO)---a robust surrogate loss based on the Multivariate Laplace distribution---providing robustness to heavy-tailed errors and stable optimization. Validation on ModelNet40 inertia tensors and Materials Project dielectric tensors demonstrates that our method achieves competitive performance and provides physically consistent, symmetry-preserving uncertainty estimates with useful risk and OOD sensitivity.

AI 总结：本文研究监督式UQ集成对LLM幻觉检测的鲁棒性，在多模型、多数据集、多生成范式下分析其性能，发现其多数场景优于单个评分器，采样黑盒集成效果接近全集成。

链接：https://arxiv.org/abs/2608.24492

机构：CVS Health（CVS健康公司）

作者：Mohit Singh Chauhan, Vipin Gyanchandani, Dylan Bouchard

英文摘要：Uncertainty quantification (UQ) methods are widely used for hallucination detection in large language models (LLMs) in closed-book settings where ground-truth evidence is unavailable at inference time. Prior work has proposed combining UQ signals via learned ensembles, but empirical investigations into the robustness of these ensembles are limited. We study a supervised ensembling framework that trains a classifier over heterogeneous UQ-based scorer outputs on a small, domain-specific dataset of labeled LLM responses, then applies it to out-of-sample hallucination classification without retrieval, tools, or reference documents. Across four LLMs, nine datasets, and three generation regimes (short-form QA, long-form generation, and code generation), we provide a systematic robustness analysis along three axes: sample efficiency, in-domain dataset transfer, and generation regime dependence. We find that supervised ensembles outperform the best individual scorer in 30 of 32 settings, with gains realized from as few as 100 labeled instances. Ensembles retain most of their advantage in cases of in-domain transfer under distribution shift, outperforming the best non-ensemble scorer in 23 of 28 transfer settings. Sampling-based black-box ensembles are nearly as effective as full ensembles, while single-generation white-box ensembles offer limited benefit.

AI 总结：该研究针对高维输出空间的深度学习，提出低秩加对角协方差结构的联合不确定性建模方法，实现偶然与认知不确定性的统一，在多项视觉任务中提升了不确定性量化效果。

链接：https://arxiv.org/abs/2608.24518

作者：Leonhard F. Feiner, Manuel Nickel, Martin Menten, Laurin Lux, Rickmer Braren, Daniel Rueckert, Georgios Kaissis, Raphael Rehms, Johannes Paetzold

英文摘要：Uncertainty Quantification (UQ) plays a vital role in enhancing the reliability of deep learning model predictions, especially in scenarios with high-dimensional output spaces. This paper addresses the dual nature of uncertainty -- aleatoric and epistemic -- focusing on their joint integration in high-dimensional regression tasks. For example, in applications like medical image segmentation or restoration, aleatoric uncertainty captures inherent data noise, while epistemic uncertainty quantifies the model's confidence in unfamiliar conditions. Modeling both jointly enables more reliable predictions by reflecting both unavoidable variability and knowledge gaps, whereas modeling only one limits transparency and robustness. We propose a novel approach that approximates the resulting joint uncertainty using a low-rank plus diagonal covariance structure, capturing essential output correlations while avoiding the computational burdens of full covariance matrices. Unlike prior work, our method explicitly combines aleatoric and epistemic uncertainties into a unified second-order distribution that supports robust downstream analyses like sampling and log-likelihood evaluation. We further introduce stabilization strategies for efficient training and inference, achieving superior UQ in the tasks of image inpainting, colorization, optical flow, and depth estimation.

AI 总结：FraudBench是面向金融风险评估的协议敏感型对抗鲁棒性基准，通过三种匹配协议评估不同模型，发现鲁棒性结论具协议敏感性，提出应将领域约束纳入攻击生成。

链接：https://arxiv.org/abs/2608.24551

作者：Xitong Zeng, Zhaoge Bi, Yitian Yang, Huaming Chen, Quan Z. Sheng

英文摘要：Machine learning models are widely used in financial fraud and credit-risk detection, yet their adversarial robustness remains difficult to evaluate because financial tabular data involve domain-specific constraints, severe class imbalance, and asymmetric attacker capability. We argue that, in this setting, robustness is not only an attribute of the model, but also an attribute of the evaluation protocol. Different ways of enforcing constraints and capability can lead to substantially different robustness conclusions. This paper presents FraudBench, a protocol-sensitive benchmark for adversarial robustness evaluation in financial fraud and credit-risk detection. Rather than treating domain constraints as post-hoc validity checks, FraudBench evaluates the same dataset--model--attack--defence setting under three matched protocols: unconstrained attacks, post-hoc feasibility filtering, and deployment-aware constraint-integrated attacks. FraudBench covers four public financial datasets, and evaluates neural, tree-based, and ensemble models using three attack settings. Our results show that robustness conclusions are highly protocol-sensitive. On Lending Club Loan Data under the white-box setting, post-hoc filtering leaves only 3.7 feasible-flipped examples on average, whereas in-attack projection with attacker mutability masking produces 2,832.3 feasible-flipped examples under the same perturbation budget. The results on IEEE-CIS further show that feasibility and attacker capability are separate axes, while black-box evaluation shows that protocol choice can alter model-family rankings. These findings suggest that fraud robustness evaluation should report predictive degradation and attack feasibility jointly, and should incorporate domain constraints into attack generation rather than treating them as post-processing checks.

AI 总结：本文提出轻量级架构SeisMamba，结合分层卷积编码等技术实现低延迟单台站地震震级估计，在STEAD基准及跨区域实验中均表现优异，为分布式低成本地震预警提供新方案。

链接：https://arxiv.org/abs/2608.24561

机构：The University of Sydney（悉尼大学）； Accenture（埃森哲）； The University of New South Wales（新南威尔士大学）

作者：Quenton Yeo, Zhaoge Bi, Linghan Huang, Luke Stephen Higgins, Flora Salim, Huaming Chen

英文摘要： Rapid earthquake magnitude estimation is central to earthquake early warning, yet many operational systems depend on dense regional seismic networks and region-specific calibration. This creates a spatial coverage barrier for high-risk areas with sparse sensing infrastructure. Single-station learning offers a lower-cost alternative, but existing models often face an accuracy--latency trade-off and may degrade under regional distribution shift. We present SeisMamba, a lightweight Mamba-based architecture for low-latency magnitude estimation from minimally processed three-component seismic waveforms recorded at a single station. SeisMamba combines hierarchical convolutional encoding, sparse selective state-space modelling, multi-scale feature fusion, and an auxiliary temporal prediction head to support efficient long-sequence waveform analysis. On the STEAD benchmark, SeisMamba achieves the best MSE, RMSE, and $R^2$ among tested baselines while requiring only 0.55 ms for a batch of 32 waveforms on an NVIDIA T4 GPU, making it about three times faster than transformer-based baselines. We further conduct a Chile--Taiwan regional hold-out experiment as a diagnostic test of cross-region deployment, where SeisMamba retains useful performance on geographically unseen seismic regions. These results suggest that selective state-space waveform modelling provides a promising accuracy--latency backbone for spatially distributed, low-cost earthquake early warning.

AI 总结：该研究提出两阶段贪心框架G2I，将反事实解释转化为干预设计问题，在节点层面生成可操作反事实、网络层面解决预算约束下的DNF覆盖问题，实验显示其干预策略效率优于掩码方法。

链接：https://arxiv.org/abs/2608.23835

机构：University of Southern California（南加州大学）； Northeastern University（东北大学）

作者：Mulin Tian, Ajitesh Srivastava

英文摘要：Real-world decision-making in public health and social science can greatly benefit from predictive models, yet translating predictions into effective interventions requires explaining the model behavior. While Graph Neural Networks (GNNs) are well-suited for modeling relational data, existing explanation methods largely operate at the node level and fall short of supporting actionable, network-level intervention design. Existing counterfactual GNN explainers, such as CF-GNNExplainer and CF$^2$, rely on continuous mask optimization over features and edges, which implicitly assume feasible edge manipulation, may allocate effort to immutable or non-actionable attributes, and incur substantial computational overhead. Further, the method of arriving at the explanation itself is difficult to explain to a domain specialist who is not an AI expert. Can simple methods generate good explanations? To explore this, we reframe counterfactual explanation as an intervention design problem. At the local level, we generate counterfactuals via a greedy search that directly identifies minimal, actionable changes to node features and neighbor-level conditions. We derive conditions under which the greedy search provides guarantees, and empirically show that these conditions are approximately met. These counterfactuals are converted into interpretable rules suitable for real-world intervention. At the network level, we formulate intervention selection as a Disjunctive Normal Form (DNF) coverage problem under a budget constraint, which is nondecreasing and approximately submodular, enabling a greedy algorithm with theoretical guarantees. Experiments on synthetic graphs and real-world suicide risk networks demonstrate that our approach produces scalable, cost-effective intervention strategies with significantly improved efficiency over mask-based counterfactual methods.

AI 总结：FlowNeg是一种GFlowNet引导的知识图谱嵌入难负采样方法，在多个基准实验中，其MRR显著优于EMU和IF-NS，具有高梯度信息性与低冲突的优势。

链接：https://arxiv.org/abs/2608.23849

机构：Iowa State University（爱荷华州立大学）； BRAC University（BRAC大学）； University of Delaware（特拉华大学）

作者：Ibne Farabi Shihab, Naoshin Anzum Hridi, Joyanta Jyoti Mondal

英文摘要：Negative sampling determines whether a knowledge graph embedding (KGE) model learns from informative counterexamples or wastes updates on implausible corruptions. Uniform negatives are diverse but easy, whereas hard-negative miners concentrate on few entities and collide more with held-out positives. We introduce FlowNeg, a context-conditioned hierarchical generative flow network that amortizes reward-proportional sampling without normalizing a composite reward over the entity set: given a positive triple and corruption side, it selects a type, then an entity. Its terminal reward combines bounded model-based hardness with a training-only structural score for held-out-positive collision, over a relation-specific type-compatible support. We derive the reward, specialize standard trajectory balance, and bound multiplicatively how residual imbalance perturbs terminal and mode probability. Across a descriptive five-seed grid of five architectures and five benchmarks, FlowNeg has higher mean MRR than EMU and than IF-NS in 24 of 25 cells ($+0.0172$ and $+0.0160$ on average). A separate 15-seed FB15k-237/RotatE control fixing negative count, diagnostic budget, and compute gives FlowNeg $0.359\pm0.001$ MRR against $0.346\pm0.002$ for EMU, with near-uniform fixed-partition diversity, high gradient informativeness, and low collision. The evidence supports mode-covering negative generation without treating structural similarity as an open-world truth oracle.

AI 总结：该研究提出GATNextHop模型，探究GAT能否近似最短路径并跨拓扑泛化，通过合成图训练、真实ISP网络评估，对比Dijkstra算法分析二者权衡以评估模型性能。

链接：https://arxiv.org/abs/2608.23917

机构：San José State University（圣何塞州立大学）

作者：Chia-Hong Chou, Katerina Potika

英文摘要：Common shortest-path algorithms, such as Dijkstra's (SPF), that OSPF uses, provide exact routing solutions but must be recomputed for each network topology, limiting scalability in dynamic or large-scale networks. This paper proposes the GATNextHop model to determine whether a Graph Neural Network, namely the Graph Attention Network, can approximate shortest paths and generalize across topologies. By training on synthetic graphs and evaluating on real-world Internet Service Provider networks from the Internet Topology Zoo, we aim to benchmark our model's ability to learn routing heuristics that transfer across network structures. Performance will be evaluated in terms of accuracy, inference speed, and generalization, comparing the GNN against Dijkstra's algorithm to quantify trade-offs between learned and classical routing approaches.

AI 总结：针对持续学习的灾难性遗忘问题，提出引入实例级适应性的GAP-Prompt方法，含三个协同模块，在多基准测试中性能最优，CUB-200数据集准确率达87.29%，接近联合训练上限。

链接：https://arxiv.org/abs/2608.23782

机构：Université d’Orléans（奥尔良大学）； INSA CVL（中央卢瓦尔河谷国立应用科学学院）； CY Cergy Paris University（塞尔吉-蓬图瓦兹大学）； ENSEA（法国高等电子与数字学院）； CNRS（法国国家科学研究中心）； Université de Technologie de Troyes（特鲁瓦技术大学）

作者：Trung-Anh Dang, Duy-Cuong Bui, Ngoc-Son Vu, Christel Vrain, Vincent Nguyen

英文摘要：Continual learning faces the persistent challenge of catastrophic forgetting, where sequential task updates degrade previously acquired knowledge. While prompt-based methods integrated with pre-trained models offer a compelling solution by freezing the backbone, they often rely on static, task-level prompting strategies that overlook fine-grained intra-task diversity. In this paper, we propose Gated Adaptive Prompting (GAP-Prompt), a novel method that introduces instance-level adaptability to the prompting process. GAP-Prompt consists of three synergistic modules: (1) instance-conditioned gating, which dynamically determines optimal prompt injection layers for each individual image; (2) dynamic knowledge fusion, which performs instance-aware aggregation of current and historical prompts, enabling knowledge integration across tasks; and (3) shared prompt distillation, which anchors foundational knowledge in early shared layers to mitigate forgetting. Extensive evaluations on CIFAR-100, ImageNet-R, and CUB-200 benchmarks demonstrate that GAP-Prompt consistently achieves state-of-the-art performance. Notably, on the fine-grained CUB-200 dataset, GAP-Prompt reaches 87.29% accuracy, approaching the joint training upper bound (88.00%) and outperforming existing methods by a significant margin.

AI 总结：AQLoRA是无需搜索、无需校准的快速量化LoRA微调方案，通过保留部分层为fp16跳过反量化提升速度，在多模型数据集上验证了其速度与准确率表现，还总结了共享硬件的计时规则。

链接：https://arxiv.org/abs/2608.23816

机构：Kennesaw State University（肯尼索州立大学）

作者：Md Romyull Islam

英文摘要：Quantized fine-tuning (QLoRA) saves memory but not time. It dequantizes every 4-bit weight on the fly, so it trains more slowly than fp16 LoRA. We present AQLoRA (Adaptive-Quantization LoRA), a recipe that buys part of that time back. One CPU pass over the weights sets everything, with no search and no calibration data. The pass ranks layers by NF4 reconstruction error and keeps the top-K in fp16 under a memory budget. Those layers skip dequantization, which is where the speed comes from. A quality setting adapts every layer. A speed setting adapts only the top blocks, so the backward pass stops early. The rule reproduces Unsloth's hand-curated dynamic-4bit selection exactly, in seconds, where search-based allocation needs repeated calibration passes. We evaluate on Commonsense-170K across six models and four architecture families, from 1.4B to 14B. The speed setting trains 11.1 +/- 2.7% faster than well-tuned QLoRA and gives up about one accuracy point. It was faster in all nine independent timing sessions, at worst by 7%. The quality setting trains 4.8 +/- 2.4% faster. Its accuracy is level with QLoRA on every model and within a point of fp16 LoRA, for 0.2 GiB more memory. These error bars are measured between independent sessions, not within one. Earning them taught us three rules for timing on shared hardware. Fix the measurement duration, not the step count. Measure the noise floor from a duplicated arm, not a nearly identical method. Repeat whole sessions: a floor computed inside one sweep understates the real uncertainty several times over, and the random seed controls almost none of it. We validate the recipe with controls and report the two that failed. Choosing adapter layers by weight density is no better than random. Choosing protected layers by quantization error is not either. The count of protected layers, not their identity, carries the speed effect.

AI 总结：本文针对通用域适应（UniDA）场景，推导其泛化误差上界，提出JAUA算法并结合渐进式伪标签方法，在6个公开图像数据集上验证了该算法的优越性。

链接：https://arxiv.org/abs/2608.24429

机构：School of Software Engineering, South China University of Technology（华南理工大学软件工程学院）； School of Future Technology, South China University of Technology（华南理工大学未来技术学院）； College of Computer Science, Chongqing University（重庆大学计算机学院）

作者：Shizhe Li, Hongshan Pu, Mengying Xie, Yi Xiang, Xiaowei Yang

英文摘要：Unsupervised domain adaptation (UDA) has been widely concerned in the fields of machine learning, pattern recognition, and computer vision. Traditional UDA learning usually assumes that the label spaces of the source and target domains are exactly the same and only needs to solve the problem of sample distribution drift existing between two domains. However, in real world applications, the label spaces between two domains may be different. In this case, there are both sample distribution drift and class spatial difference between domains, namely Universal Domain Adaptation (UniDA) learning scenario. At present, existing works rarely offer theoretical analysis for universal domain adaptation. In this paper, we provide an upper bound of the generalization error for universal domain adaptation. According to the proposed generalization error bound, we propose a novel UniDA algorithm called Joint Distribution Alignment for Universal Domain Adaptation (JAUA), which aligns the joint distributions by minimizing the distribution discrepancy calculated by Chi-Square divergence. Furthermore, we propose a progressive pseudo-labeling method to assign the pseudo labels to unlabeled target samples. The experiment results on six public image datasets demonstrate the superiority of JAUA in handling the UniDA problem.

AI 总结：本研究推出首个双源城市热岛建模基准UHI-Bench，评估多模型在多城市多气候区的表现，为城市热建模提供指导并支持气候研究发展。

链接：https://arxiv.org/abs/2608.23857

机构： Technical University of Munich（慕尼黑工业大学）； Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院）； RWTH Aachen University（亚琛工业大学）； Hainan Bielefeld University of Applied Sciences（海南比勒费尔德应用科学大学）； Heilbronn Data Science Center（海尔布隆数据科学中心）； Munich Data Science Institute（慕尼黑数据科学研究所）

作者：Wanyun Ling, Chenxi Liu, Yi Xie, Aopu Xu, Zhuoqi Zeng, Ziyue Li

英文摘要：Urban heat islands (UHIs) are intensifying under climate change, exacerbating thermal exposure risks. Their two primary observations, land surface temperature UHI (LST-UHI) and near-surface air temperature UHI (AirT-UHI), capture physically distinct aspects of urban heat. However, most studies rely on a single source, and substituting one for the other can substantially bias the magnitude and spatial variability of human heat exposure. Accurate UHI modeling also requires dynamic meteorological drivers and static urban morphology features, but spatiotemporal incompatibilities hinder their alignment. Cloud gaps in LST observations and sparse AirT station networks further limit dual-source UHI modeling, motivating cross-city transfer across diverse climates. To bridge these gaps, we introduce UHI-Bench, the first UHI benchmark for dual-source UHI modeling that integrates dynamic and static environmental context. Following a unified signal, mechanism, and transfer framework, it evaluates over 20 baselines from four model families on five tasks across 20 cities and nine Köppen climate classes. Results show that no model is uniformly best, although foundation models remain consistently competitive and stable. Environmental covariates generally improve performance, but their utility varies across sources and tasks. Cross-city transferability is better explained by overlap in UHI regimes than by climate-zone similarity. With the dataset and standardized pipeline, our work provides practical guidance for urban heat modeling, promotes climate data equity, and supports future advances in climate research.

AI 总结：PhysicsBench是面向工程设计与仿真的统一基准排行榜，涵盖多维度任务与数据集，采用标准化流程评估66个模型，可实现模型去偏排名，助力模型选择。

链接：https://arxiv.org/abs/2608.24056

作者：Sang Won Lee, Hyogu Jeong, Namwoo Kang

英文摘要：Generative and predictive artificial intelligence models are increasingly used to generate geometry and to predict physical fields and scalar quantities in engineering design and simulation. Yet these models are typically evaluated in isolation, on academic datasets at unconstrained scales, with inconsistent metrics and procedures. We present PhysicsBench, a unified benchmark and leaderboard that evaluates generative and predictive models under one standardized procedure. PhysicsBench spans seven generation and prediction tasks across 1D, 2D, and 3D domains and ranks 66 models on nine datasets, comprising industrial-scale CAD/CFD/FEA simulations and public references, expanded into 28 configurations. One procedure and ranking apply to both families, each ranked within its own tasks. Evaluation spans realistic, limited data scales from S to XL rather than the unlimited training sets common in academic benchmarks. A common metric suite captures geometric fidelity with distributional distances, physical-field and scalar accuracy, and engineering-specific field- and shape-validity. BenchRank debiases correlated metrics and ranks by PageRank over a head-to-head dominance graph, so every reported quality metric is also ranked, with computational cost in a separate efficiency view. Across tasks, an architecture's large-scale academic standing weakly predicts its small-data ranking. The top model changes with data scale in six of the seven tasks, and no model leads more than one task. PhysicsBench turns "state-of-the-art" from a self-reported claim into an openly published foundation for model selection.

AI 总结：本研究针对可穿戴设备数据的结构化缺失问题，开发了保留共缺失结构的评估与训练协议，评估BRITS、SAITS等模型性能，发现模型排名依赖评估设计，为改进多传感器可穿戴数据插补策略提供了关键基础。

链接：https://arxiv.org/abs/2608.24436

机构：University of Bristol（布里斯托大学）； University of Manchester（曼彻斯特大学）； University of Birmingham（伯明翰大学）

作者：Skye Goodman, Roussel Desmond Nzoyem, Leandro Junges, Peter Kissack, Yasser Qureshi, Amberly Brigden, Jeff Clark, Nawid Keshtmand

英文摘要：Wearable device data enables continuous health monitoring, but suffers from structured missingness: features sharing a physical sensor drop out together. Deep imputation methods such as BRITS and SAITS have seen limited evaluation on multimodal physiological data under realistic missingness, and existing benchmarks use random-point holdout protocols that incorrectly assume missingness is independent across features and time. Using data from a person with epilepsy recorded on a Garmin smartwatch, we develop an evaluation protocol that mines contiguous missing-run templates from training data, stratifies them by per-feature gap-length quantiles, and injects them as block masks with preserved co-missingness structure. A matched training protocol exposing models to the same missingness distribution reduces BRITS's severe-gap MAE by 43%, demonstrating the potential benefit of the proposed evaluation and training protocol within this single-participant dataset. We further extend BRITS with time-of-day encoding and a circadian harmonic channel. No single model dominates: linear interpolation is optimal for slow-moving features over short gaps; extended BRITS achieves lower MAE on dynamic cardiac features in moderate and severe gaps; and SAITS better preserves the ground-truth distribution by Jensen-Shannon distance despite higher MAE. Ultimately, model rankings strongly depend on evaluation designs. By exposing how traditional evaluation methods obscure true model capabilities, our transferable protocol establishes critical steps towards developing better imputation strategies for future multi-sensor wearable datasets.

AI 总结：针对流数据超参数优化需处理边界约束的问题，提出四种在线优化算法的边界约束策略，经实证验证其性能优于现有“边界”策略。

链接：https://arxiv.org/abs/2608.24712

机构：University of Porto（波尔图大学）； INESC TEC

作者：Bruno Veloso, João Gama

英文摘要： Optimization of hyperparameters is a critical factor to obtain optimal model performance. While existing research has predominantly concentrated on batch-learning scenarios, addressing the complexities inherent in data streams presents a challenge. The deployment of sophisticated methodologies to manage data streams becomes highly important. Consequently, the capacity for self-adjusting hyperparameters during on-line learning phases emerges as a goal. Many hyperparameters exhibit constraints and are confined within bounded search spaces, rendering specific solutions unacceptable upon applying optimization operators. To solve this issue, employing boundary constraint- handling techniques becomes imperative to rectify invalid solutions. This paper presents strategies for effectively managing boundary constraints within constrained numerical optimization problems. Recent methodologies, including heuristic and evolutionary-based optimization, employ a "boundary" strategy, wherein values that surpass boundary thresholds for a given hyperparameter are realigned to the respective limits. Our study introduces four strategies to navigate boundary constraints in online optimization algorithms. Through empirical investigations conducted on established datasets, we demonstrate that adopting boundary strategies outperforms the "boundary" strategy.

AI 总结：针对基于邻域的公平性审计的鲁棒性问题，提出几何框架分析其在有界扰动下的鲁棒性，引入审计波动性指标，实验验证框架可解释该类审计的观测稳定性。

链接：https://arxiv.org/abs/2608.24818

机构：Indian Institute of Technology, Gandhinagar（印度理工学院甘地纳格尔分校）

作者：Binita Maity

英文摘要：Neighborhood-based fairness audits evaluate individual fairness by comparing predictions among similar individuals in feature space. Despite their widespread use, little is known about the robustness of the auditing procedure itself. Because these audits rely on nearest neighbor relationships, small perturbations in feature space can alter local neighborhoods and produce different fairness assessments even when model predictions remain unchanged. We develop a geometric framework for analyzing the robustness of neighborhood-based fairness audits under bounded perturbations. Our analysis establishes sufficient conditions for neighborhood invariance, quantifies how neighborhood replacement propagates to audit instability, and introduces audit volatility, a measure of the expected sensitivity of fairness audits under repeated perturbations. Experiments on benchmark datasets support the theoretical analysis and show that the proposed framework explains the observed stability of neighborhood-based fairness audits.

AI 总结：本文提出SAR层、合成知识蒸馏等方法，改进NOMAD架构与VSN，在换热器数据集上大幅降低LEE指标与L2误差，为边缘部署的能效虚拟感知提供了新框架。

链接：https://arxiv.org/abs/2608.23987

机构：National Center for Supercomputing Applications（国家超级计算应用中心）

作者：William Howes, Farid Ahmed, Syed Bahauddin Alam

英文摘要：Virtual sensing enables digital twins and safety-critical systems to reconstruct and forecast spatial-temporal physics in real time. However, conventional computational and data-driven methods often face challenges in generalization, latency, and energy efficiency for edge deployment. Neural operators offer a promising alternative but remain reliant on power-intensive hardware. Spiking neurons and neuromorphic computing can improve efficiency, yet surrogate-gradient training and multi-step spiking introduce convergence and latency challenges. We propose the Sparse-Activation-ReLU (SAR) layer, a single-step alternative that promotes activation sparsity without surrogate-gradient training while remaining compatible with event-based computing. Within a trunk-based NOMAD architecture, SAR achieves over a fivefold improvement in the combined Latency-Error-Energy (LEE) metric compared with Variable Spiking Neuron (VSN) and Leaky Integrate-and-Fire (LIF) implementations. We further analyze spiking entropy and feature usage and introduce synthetic knowledge distillation, reducing the LEE score by more than twofold. Finally, we improve VSN through a ReLU-based spiking loss and graph-neighbor thresholding. On the Heat Exchanger dataset, these approaches reduce L2 error by more than twofold and nearly sevenfold, respectively, while reducing spiking and spatial aggregation. Overall, the work presented is a step towards energy-efficient virtual sensing by providing an alternative framework that can be positioned towards neuromorphic or other edge device integration that can be a gold standard to compare latency, energy, and error performance for future efficient designs that are sparsity or brain-inspired spiking based.

AI 总结：本研究提出基于前馈高斯溅射（FFGS）表示的物理集成算子学习框架，在多类PDE系统长时序预测中降低相对ℓ₂误差1.5-2.2倍，提升光谱保真度，对部分已知控制方程具鲁棒性。

链接：https://arxiv.org/abs/2608.24049

机构：Cornell University（康奈尔大学）

作者：Jihao Zhang, Junyi Guo, Jian-Xun Wang

英文摘要：Neural operators provide efficient surrogates for spatiotemporal PDE systems, but purely data-driven formulations often accumulate substantial errors during long-horizon autoregressive prediction and may fail to exploit available governing-equation structure. Existing approaches incorporate physics primarily through residual-based training objectives or PDE-specific architectural constraints, which can introduce optimization difficulties or limit architectural generality. In this work, we introduce a representation-level approach to physics integration in which a feed-forward Gaussian splatting (FFGS) representation serves as a continuous interface between discretized solution fields and governing operators. The FFGS representation reconstructs the state as a continuous Gaussian field with closed-form spatial derivatives, allowing available physical PDE operators to be integrated directly within the learned evolution map without introducing a physics-residual loss. We evaluate the framework across two- and three-dimensional PDE systems, including advection, diffusion, nonlinear self-advection, and reaction dynamics. Over long-horizon autoregressive rollouts, the proposed framework reduces relative $\ell_2$ error by $1.5\times$--$2.2\times$ compared with the strongest purely data-driven baseline across the benchmark suite, while consistently improving spectral fidelity. The framework also remains effective when the governing equations are partially known, demonstrating robustness to incomplete physics. These results demonstrate that continuous field representations can provide a practical interface for incorporating known physical structure into generic neural-operator surrogates.

AI 总结： 该研究针对现有基于LLM的时间序列异常检测方法缺乏显式频域证据的问题，提出证据增强的零样本TSAD框架，经多模型实验验证频域证据可提升检测性能。

链接：https://arxiv.org/abs/2608.24113

机构：Hanyang University（汉阳大学）

作者：Jungwook Seo, Sangwon Son, Minjeong Kim, Seungmin Han, Seojin Yoo, Sungyong Baik

英文摘要：Time-series anomalies can appear not only as pointwise deviations but also as changes in recurring temporal structure, such as shifted periodicity or localized oscillatory fluctuations. However, existing LLM-based time-series anomaly detection methods mainly expose time-domain evidence through indexed values, plots, or de-seasonalized representations, leaving spectral structure implicit. We propose an evidence-augmented zero-shot TSAD framework that preserves indexed de-seasonalized observations while adding compact frequency-domain evidence computed with the Fast Fourier Transform (FFT). The evidence is constructed at two resolutions: global frequency-domain evidence summarizes sequence-level periodic context, while local frequency-domain evidence captures time-localized spectral departures. Experiments on AnomLLM with InternVL2-LLaMA3-76B, Qwen2.5-VL-72B-Instruct, Gemini-2.5-Flash, and GPT-4o, together with evaluation on the TSB-AD-U subset, show that explicit frequency-domain evidence improves LLM-based TSAD baselines. These results suggest that frequency-domain evidence can complement indexed and de-seasonalized time-domain inputs for zero-shot LLM-based TSAD.

AI 总结：本文介绍了将生产环境客户支持推荐系统从梯度提升树迁移到成对二元深度推荐器的实践，通过多种技术优化后，该方法在对话后期的推荐性能优于CatBoost基线。

链接：https://arxiv.org/abs/2608.24132

机构：Intuit（英图易公司）

作者：Sonia Sharma, Jeyendran Balakrishnan, Shreya Rajpal, Swapnil Parekh, Nagaraj Janardhana, Andrew Mattarella-Micke

英文摘要：Product catalogs in fast-moving service businesses are shifting from static, independently priced SKUs toward dynamically bundled, discount-coupled offerings--a shift that strains the tree-based classifiers traditionally preferred for sparse and highly imbalanced data. These classifiers assume a fixed, slowly changing label space and struggle to incorporate multimodal signals such as tabular data and transcripts. We present the migration of a live, production conversational recommendation system from a gradient-boosted multiclass model to a pairwise-binary deep recommender. Because this system is critical to ecosystem growth initiatives and downstream features like dynamic pitching--surfacing the most relevant pitch text to a support agent in real time during a live customer conversation--maintaining live recommendation quality was a non-negotiable constraint. We detail the techniques that made this migration successful--reformulating recommendation as pairwise binary prediction to learn jointly from user and item features, and enhancing learned representations via negative sampling and noise injection. To efficiently incorporate long, live conversation context, we apply attention pooling over transcript chunks and benchmark it against TF-IDF and sentence-embedding baselines. Finally, we explore multiple architectures (including two-tower models, DeepFM, and their variants) and loss functions such as contrastive loss. Evaluating against a CatBoost baseline across all conversational stages, we demonstrate that our approach achieves parity at conversation beginning and outperforms at later conversational stages.

AI 总结：该研究针对预测编码网络的顺序反向误差传播瓶颈，提出并行训练生成式与编码式两类PCN的单状态更新训练技术，将其应用于时间序列异常检测，实现了更稳定连续的在线学习。

链接：https://arxiv.org/abs/2608.24697

机构：Ghent University（根特大学）； imec

作者：Matteo Cardoni, Sam Leroux

英文摘要：Predictive Coding (PC) is a neural learning paradigm that enables parallelizable neural network layer updates. However, the main bottleneck of PC Networks (PCN) is the sequential backwards error propagation. To tackle this, we introduce a training technique that pairs a Generative PCN with a support Encoding PCN. The two PCNs are trained in parallel to match their neural activations, without sequential propagation. We apply this to time series anomaly detection and show that our approach results in more stable, continuous, online learning.

AI 总结：本文提出等变胞层网络，将分子哈密顿量建模为胞层拉普拉斯算子，兼具拓扑性质与E(3)等变性，在共轭分子非键轨道预测等任务上性能更优。

链接：https://arxiv.org/abs/2608.23571

机构：Elkins High School（埃尔金斯高中）

作者：Krishna Harish

英文摘要： Equivariant message-passing networks are the standard model for molecular property and interatomic-potential prediction, and recent work predicts the electronic Hamiltonian itself in an E(3)-equivariant way. Separately, topological deep learning has extended graph networks to cellular sheaves. Our central observation is structural: in a localized atomic-orbital basis, the molecular single-particle Hamiltonian, after a constant shift that makes it positive semidefinite, is the Laplacian of a cellular sheaf on a regular cell complex built from the molecule. Making the restriction maps O(3)-steerable two-center kernels from bond geometry recovers the Slater-Koster form as a special case and yields an E(3)- and permutation-equivariant operator. Three consequences follow. First, the zeroth sheaf cohomology H^0 = ker L is a topological invariant equal to the non-bonding (zero-mode) orbitals, recovering the classical alternant non-bonding-orbital count as a lower bound. Second, the Hodge 1-Laplacian lets higher cells (rings) carry cycle and delocalization information through H^1. Third, the model strictly generalizes E(3)-equivariant message-passing networks and CW networks, and inherits the anti-oversmoothing of non-trivial sheaf diffusion. We prove equivariance, expressivity, and cohomological-correspondence results for the Equivariant Cellular Sheaf Networks, and validate them numerically: the Hamiltonian-to-sheaf embedding is exact to machine precision, the cohomology dimension reproduces non-bonding-orbital counts across eleven conjugated molecules, the sheaf Laplacian is O(3)-equivariant to machine precision, and the equivariant model attains lower error and rotation generalization on a directional electronic target. Our contribution is this sheaf-theoretic formalization and its invariants, not equivariant Hamiltonian prediction itself.

AI 总结：该研究发现训练前计算的二元条件熵可预测Transformer训练中Weibull权重尺度的增长规律，构建了学习率相关的量化关系，在两种架构上验证了规律的普适性。

链接：https://arxiv.org/abs/2608.23573

作者：Tiexin Ding

英文摘要：A trained transformer's weight magnitudes can be summarized by a two-parameter Weibull distribution whose shape $k \approx 1.2$ is stable across layers and models, so the scale $\lambda$ carries most training-induced movement. What corpus property sets how much $\lambda$ grows? Using the bigram conditional entropy $D = H(\text{next} \mid \text{prev})$, a training-free statistic computed before training, we find across controlled corruption families a learning-rate-conditioned law, $\lambda^2 - \lambda_0^2 = C_0(\eta) + C_1(\eta)(H_r - D)^{0.59}$, where $H_r$ is a matched-budget shuffle baseline. The convex exponent is inherited from an independently measured data-side saturation relation rather than fitted directly to the growth curve. After removing the two per-$\eta$ coefficients, 23 runs spanning an order of magnitude in learning rate collapse onto $(H_r - D)^{0.59}$ with unit slope ($R^2 = 0.941$; direct per-$\eta$ fits are weaker, $R^2 \approx 0.82$). Because $D$ is computed before training, the law is a forward predictor: an end-to-end self-validation recovers held-out within-family weight growth with 5.7% relative error. The readout holds at model and per-layer resolutions and across two tested architectures, with the functional form preserved and only the coefficients changing. It also marks its boundary: cross-corpus prediction over-predicts code, implicating redundancy as a second axis of a broader $\Phi(D,R,A,H)$ data-to-weight framework.

AI 总结：本研究针对深度均衡模型训练中伴随系统因雅可比近奇异导致梯度放大的问题，提出响应重归一化框架，通过CMR等方法控制近临界伴随放大，提升参数更新可靠性且保留有效梯度信息。

链接：https://arxiv.org/abs/2608.23725

机构：Federal University of Bahia（巴伊亚联邦大学）； Grupo de Estudos e Aplicação de Inteligência Artificial em Geofísica (GAIA)（地球物理学人工智能研究与应用组（GAIA））

作者：Jose Luis Lima de Jesus Silva

英文摘要：Deep Equilibrium Models (DEQs) compute predictions from a hidden representation unchanged by the model update. Training through this equilibrium uses implicit differentiation and requires solving an adjoint system built from the residual Jacobian. If this Jacobian is nearly singular along loss-sensitive directions, small perturbations can be strongly amplified in the adjoint response, producing large, highly sensitive gradients that can make optimization unreliable. We introduce Response Renormalization, a backward-pass framework that lifts selected near-pole denominators while leaving unlifted response channels unchanged. Collective Mode Response Renormalization (CMR) applies this correction in a low-dimensional critical subspace, while Phi-adaptive CMR computes a bounded response mass from a positive susceptibility rule. We derive dense and matrix-free collective formulations, distinguish exact gradients of a modified frozen-anchor residual from backward-response surrogates, and extend the construction to Structured Implicit Layers and Vector Attractors (SILVA). Across 23 multiphysics families spanning partial differential equations, three-dimensional fields, operator maps, complex geometries, and particle systems, CMR and Phi-CMR yield test errors no more than five percent higher than those from models trained with exact implicit differentiation in more than 98% of static and 95% of transient family-seed comparisons. Solver-index experiments show convergence toward the static adjoint, while physical-time rollouts retain predictive fidelity under the evaluated conditions. These results demonstrate that selective response renormalization can control near-critical adjoint amplification without globally damping well-conditioned sensitivity. Therefore, the method can make parameter updates more reliable while preserving the useful gradient information needed for learning.

AI 总结：本文提出保留校准的剪枝（CPP）方法，通过拆分共形预测保证剪枝后模型的覆盖率，在DBpedia-14等数据集上实现更小预测集尺寸，提升多数任务的预测效率。

链接：https://arxiv.org/abs/2608.23744

机构：Iowa State University（爱荷华州立大学）； Independent University of Bangladesh（孟加拉独立大学）

作者：Ibne Farabi Shihab, Adria Binte Habib, Anuj Sharma

英文摘要：Split conformal prediction, not the pruning rule, supplies finite-sample marginal coverage once a pruned model is fixed independently of the conformal calibration split. We study the separate efficiency problem: can pruning preserve score geometry well enough to obtain smaller valid prediction sets? Calibration-Preserving Pruning (CPP) augments a base pruning score with nonconformity-gradient saliency and uses disjoint pruning, validation-selection, conformal-calibration, and test splits. Bounded score perturbations imply bounded conformal-quantile shifts and controlled set inflation, but do not make the generic coverage theorem CPP-specific. Final five-seed Qwen2.5-1.5B results at 50\% sparsity show the largest gains on large-label tasks. On DBpedia-14, CPP-SparseGPT reduces mean set size from \(10.1\) to \(8.6\) while changing accuracy from \(0.347\) to \(0.366\); CPP-Wanda reduces \(11.2\) to \(9.0\) with an accuracy trade-off from \(0.310\) to \(0.295\). Across 15 dataset--sparsity cells, CPP-SparseGPT produces smaller sets in 13 and higher accuracy in 11. Matched controls show that generic supervised gradients explain much of the gain: true-label CPP is not statistically resolved from matched Wanda+SNIP, whereas threshold-aware candidate-label CPP reaches \(7.8\) mean set size at explicit accuracy and offline-compute costs. RoBERTa-base and Llama-3-8B diagnostics support transfer, but our claims remain limited to reliability-sensitive classification.

AI 总结：本研究提出SAIL方法，将人类技能建模为可解释多维构造，通过反事实子技能交换解耦，在赛车、棒球任务中预测性能优异，解耦效果优于基线且提升AI指导性能。

链接：https://arxiv.org/abs/2608.23776

机构：Toyota Research Institute（丰田研究所）

作者：Mariah Schrum, Deepak Gopinath, Srijan Srivatsa, Guy Rosman, Tiffany Chen

英文摘要：Understanding human skill is important for AI systems that collaborate with, coach, or assist people. Unlike typical latent variable estimation problems which rely on single observations, skill is a persistent, compositional, and behaviorally grounded construct that must be inferred from patterns over time. We introduce Skill Abstraction with Interpretable Latents (SAIL), a method for modeling human skill as an interpretable, multi-dimensional construct inferred from naturalistic behavior. Our approach produces a skill embedding that is robust to transient performance fluctuations and learns a transferable representation of human subskills. Furthermore, SAIL supports skill-informed behavior prediction that generalizes across a variety of in-domain contexts. We represent each individual with a persistent skill embedding that controls a blend between expert and novice bases and is trained using counterfactual subskill swaps for disentanglement. This design encourages representations that are both robust to performance variation and structured for interpretability. We demonstrate across racing and baseball that SAIL achieves strong predictive performance and consistently improves behaviorally grounded disentanglement over the evaluated baselines, while also improving downstream AI coaching performance.

AI 总结：本研究以MGSM数据集探究多语言LLM跨语言推理的特征机制，提出GI-SAE方法，发现跨语言特征共享依赖模型架构，GI-SAE主要放大现有跨语言结构且模型特异性明显。

链接：https://arxiv.org/abs/2608.23809

机构：Carleton University（卡尔顿大学）

作者：Igor Bogdanov, Changcheng Huang

英文摘要：Multilingual language models can solve the same mathematical problem in different languages, but it remains unclear whether they rely on shared features or on language-specific computations that only produce similar outputs. We study this question in five models from four families using the Multilingual Grade School Math (MGSM) dataset, with problems solved in English, German, French, Spanish, Russian, and Chinese, retaining problems with valid reasoning traces in all six languages and replaying those traces through the model to record representations at multiple layers. For each model, we first use Centered Kernel Alignment (CKA) to identify layers with cross-language alignment. At each selected layer, we train two sparse autoencoders (SAE): a baseline reconstruction-only model and a contrastive variant introduced in this work, the Geometry-Invariant SAE (GI-SAE). GI-SAE supplements the reconstruction loss with an Information Noise-Contrastive Estimation (InfoNCE) loss that trains the encoder to produce similar activations for traces of the same problem, regardless of language or token position. We then test whether the resulting shared features are functionally interchangeable by swapping their values between languages during the model's forward pass and measuring the resulting change in output, quantified by Kullback-Leibler (KL) divergence per feature. Although GI-SAE yields higher CKA and Jaccard similarity at nearly every layer, higher geometric similarity does not consistently imply greater functional interchangeability. We find that cross-language feature sharing is model- and architecture-dependent in this sample and appears at different depths in different models. GI-SAE primarily amplifies cross-language structure already present: the pattern is model-specific, with strengthening in Qwen, no functional benefit in Gemma, and mixed layer-dependent effects in Llama and Phi.

AI 总结：该研究针对学习系统提出揭示控制理论，定义决策充分揭示等概念，给出代价调整分解准则，通过Qwen2.5-7B和Mistral-7B-v0.3实验验证相关结论，支持结构迁移而非数值迁移。

链接：https://arxiv.org/abs/2608.23860

作者：Qinyou Wang

英文摘要：Revelation Control is the problem of choosing priced interventions that reveal hidden state only insofar as the revealed distinctions can change a consequential decision, while accounting separately for any useful progress created by the intervention itself. We develop this theory for learning systems, where states equivalent under declared current information can respond differently to future training and favor different actions. The framework defines decision-sufficient revelation and revelation depth, separates pure information value from productive reuse, embeds static Bayes refinement into state-dependent continuation value, and gives an exact cost-adjusted factorization criterion: an additional shallow coordinate is decision-nonredundant only when states sharing a scalar summary lie on opposite sides of the priced Stop/Continue boundary. We also give a target-independent protocol for model-specific instantiation and prove that bounded stop-flip risk alone cannot certify positive expected utility under unrestricted severity. Across Qwen2.5-7B and Mistral-7B-v0.3, deeper future-learning probes have positive decision value and productive reuse yields strict equal-compute utility advantages. Qwen additionally provides evidence for a decision-nonredundant shallow revealability regime; in Mistral, a scalar continuation architecture fit only on an independent development panel retains positive familywise-adjusted lower bounds on a disjoint target panel, consistent with scalar decision sufficiency within the tested architecture family and resolution. The evidence supports structural rather than numerical transfer: the decision theory, cost accounting, continuation logic, and evaluation protocol transport, while empirical proxies, coefficients, thresholds, and even the required shallow state dimension may be system-specific.

AI 总结：

链接：https://arxiv.org/abs/2608.23877

作者：Itay Safran

英文摘要： We prove a depth hierarchy for ReLU neural networks in which every additional ReLU layer can save exponentially many neurons. For every $\ell\geq 3$, a globally $[0,1]$-valued, $1$-Lipschitz function is realized by a depth-$\ell$ network of width $\mathcal{O}(d^4)$, whereas every depth-$(\ell-1)$ network with unrestricted weights and width at most $2^d/[2d(\ell-2)]$ has squared $L_2$ error at least $1/24$ under an absolutely continuous distribution. To the best of our knowledge, this is the first exponential separation for ReLU networks between two fixed depths whose shallower depth is at least $3$, and the first exponential hierarchy across all adjacent fixed depths. The lower bound also immediately yields the corresponding hierarchy for exact computation. Moreover, the case $\ell=3$ gives a compactly supported depth-$3$-versus-depth-$2$ separation with unrestricted shallow-network weights, answering a question raised by Safran, Eldan, and Shamir (2019, Sec. 2.3). The corresponding distribution nevertheless has all its mass at exponential radius, so the construction falls outside the regularity regime in which such a separation would imply major threshold-circuit lower bounds. We also prove an exact separation for a more benign function. It is computed by a polynomial-width depth-$4$ network, whereas every depth-$3$ network agreeing with it on the unit hypercube requires exponentially many neurons in its first hidden layer, again without any restriction on the weights. The function is globally $[0,1]$-valued and $\mathcal{O}(\sqrt d)$-Lipschitz, and maps the unit hypercube onto $[0,1]$.

AI 总结：本研究提出基于动力学系统的MnemoDyn模型，通过4万条rs-fMRI序列训练，采用分块脑区多分辨率时间建模，计算高效且泛化性强，在重建质量上优于Transformer方法，适用于神经影像学下游任务及小样本研究。

链接：https://arxiv.org/abs/2608.23936

机构：University of Wisconsin–Madison（威斯康星大学麦迪逊分校）； Pohang University of Science and Technology (POSTECH)（浦项科技大学）； University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）

作者：Sourav Pal, Viet Luong, Hoseok Lee, Tingting Dan, Guorong Wu, Richard Davidson, Won Hwa Kim, Vikas Singh

英文摘要：We present a dynamical-systems based model for resting-state functional magnetic resonance imaging (rs-fMRI), trained on a dataset of roughly 40K rs-fMRI sequences covering a wide variety of public and available-by-permission datasets. While most existing proposals use transformer backbones, we utilize multi-resolution temporal modeling of the dynamics across parcellated brain regions. We show that MnemoDyn is compute efficient and generalizes very well across diverse populations and scanning protocols. When benchmarked against current state-of-the-art transformer-based approaches, MnemoDyn consistently delivers superior reconstruction quality. Overall, we find that with such large-scale pre-training on (non-proprietary) rs-fMRI datasets, we get a highly performant model for various downstream tasks. Our results also provide evidence of the efficacy of the model on small sample size studies which has implications for neuroimaging studies at large where resting state fMRI is a commonly acquired imaging modality.

AI 总结：本文提出PinSieve，即面向企业内容质量分类的选择性VLM服务智能体，结合受控内存飞轮维护机制，提升审核效率、降低成本并改善信号交付，具有任务可迁移性。

链接：https://arxiv.org/abs/2608.24040

作者：Chuqing Gao, Yuanfang Song, Jonathan Zhang, Yifan Wu, Vishwakarma Singh, Qinglong Zeng, Andrey Gusev

英文摘要：Enterprise AI agents in production often need to be bounded, stateful, observable, and governable rather than fully autonomous. We present PinSieve, a production case study in a large-scale content-quality pipeline. Its deployed component is a selective vision-language-model (VLM) Serving Agent that operates only on the grey-zone slice left unresolved by lightweight upstream models, exposes a scalar routing score online, and preserves controlled human escalation. On this slice, the deployed system filters 2.05x more non-actionable items than the previous production module while slightly reducing estimated miss rate; after promotion, it improves review productivity by 25.7%, reduces normalized operating cost by 16.2%, and moves signal delivery from next-day to same-day. We then study maintenance through a governed memory flywheel under selective feedback, where escalated items are reviewed by default and auto-passed items are labeled mainly through audit sampling. Feedback Memory records routing traces, observation paths, audit propensities, and replay metadata for evaluation and debugging. The Data Curation Agent uses a bounded proposal-verifier loop over representative, uncertainty, recency, and fresh-review replay, with positive-rate and score-bin guardrails before batch acceptance. In chained monthly refresh over six months of production data, this design reduces average FNR@50% from 17.73% under representative random replay to 13.29%. A Reasoning Review Agent audits teacher-generated rationales and supports keep/repair/drop decisions. Production claims are attributed only to the deployed Serving Agent; replay and rationale-review results are offline or sampled-governance evidence. The same serving-agent recipe has been adopted to several additional internal signals, suggesting transferability beyond one task.

AI 总结：XP-JEPA通过将视觉与物理表征交叉预测，提升了潜在动力学的可预测性，在多任务套件上降低了展开漂移并提高了控制成功率，无需特权输入即可实现更优的基于展开的控制性能。

链接：https://arxiv.org/abs/2608.24044

作者：Kehan Wen, Ziming Li, Siyuan Luo, Fan Shi

英文摘要：Latent world models plan by predicting how candidate actions transform learned representations. In self-predictive models, however, the encoder and predictor are optimized jointly and can co-adapt to latent transitions that are easy to predict but only weakly constrained by the physical evolution of the scene. We introduce the cross-predictive JEPA (XP-JEPA), which grounds visual latent dynamics in privileged physical trajectories. XP-JEPA separately encodes visual observations and physical states, advances both through a shared action-conditioned predictor, and matches each prediction to both future representations. This objective encourages unified latent dynamics across the two modalities, grounded in the underlying physical transitions. The physical branch is discarded after training, leaving a visual-only model at deployment. On a multi-task suite spanning six evaluation subfamilies, XP-JEPA reduces rollout drift of a newly fitted predictor from $0.361$ to $0.104$ and increases mean control success from $53.6\%$ to $78.2\%$. Direct physical-state regression raises position decodability but leaves forecastability and control near the visual-only baseline. Cross-predictive physical grounding can therefore produce more forecastable latent dynamics for rollout-based control without privileged inputs at test time.

AI 总结：ALPHABET是一种紧凑线性时间模型，可将时间历史压缩为复极点模态，在82任务基准中平均排名3.97，6437个参数的推理与训练速度远超9个基准。

链接：https://arxiv.org/abs/2608.24051

机构：Korea Aerospace University（韩国航空大学）

作者：Daehwa Ko, JaeHyeon Kim, Oh Seong Kwon, Jay Hoon Jung

英文摘要：Can a sequence model remain competitive with only a few thousand parameters and an explicitly auditable prediction interface? We introduce ALPHABET, a compact linear-time model that compresses temporal history into stable complex pole modes: a direct bank synthesizes its modal states back into the feature trajectory, an independent cascaded bank analyzes the transformed trajectory without resynthesis, and an affine head reads only modal energies and lag moments from both banks. We characterize the temporal information this descriptor retains: for a stationary, fully observed feature process, each mode energy is a frequency-localized measurement of the second-order spectrum, the continuum of such measurements identifies the spectrum, and almost every mode separates any fixed finite set of spectrally distinct classes. On a Gaussian control with matched low-lag statistics, the learned descriptor approaches the Bayes oracle where raw autocovariances remain at chance. Across the fixed 82-task registry, ALPHABET attains mean rank 3.97 in the complete ten-family comparison. At the common-width D=64 runtime anchor, its 6,437 parameters deliver 5.02 times faster inference and 3.93 times faster complete training steps than the nine baselines on average.

AI 总结：本文提出特征主导码本的稀疏-二元自组织映射，通过优化码本布局将BMU搜索加速4.5-8.5倍，在单24 GB GPU上训练MEDLINE图谱达105万神经元，是目前最大的自组织映射，性能远超现有方法。

链接：https://arxiv.org/abs/2608.24067

机构：College of Medicine and Dentistry, James Cook University（詹姆斯库克大学医学与牙科学院）

作者：Andrew James Amos

英文摘要：A self-organising map turns a large corpus into a browsable two-dimensional atlas, but building one at MEDLINE scale has been impractical: the best-matching-unit (BMU) search that dominates training is bound by the bandwidth needed to read the codebook every epoch. I show that this bottleneck is largely an artefact of codebook layout. Storing it feature-major with each feature's weights contiguous, W[v.M+i], recasts the search as a tiled sparse-dense product in which every loaded weight column is reused across a tile of samples. Varying only the layout, with implementation, precision and update rule held fixed, accelerates the BMU search by 4.5-8.5x. Because an exact-argmin BMU is invariant to how the codebook is stored, this gain costs nothing: held-out quantisation error agrees with a cuSPARSE baseline to within 0.5% at every map size. Against that baseline the advantage is a crossover rather than a constant: this http URL is faster at small maps, this http URL is 1.5x faster at 128x128 and 2.6x at 256x256, and at 512x512 it is the only one that runs at all on 24 GB. Paired with a radius-independent box-blur update and a convergence-based stopping rule, it trains a converged map over 29.9 million MEDLINE articles in about 72 s at 64x64 on one 24 GB GPU, and accommodates 262,144 neurons (512x512 edges) where every alternative algorithm I tested exceeds memory constraints. On a 141 GB H200 it reaches 1,048,576 neurons (1024x1024 edges) - to my knowledge the largest self-organising map yet reported. Held-out error follows a smooth power law with no elbow across three decades of map size, so the limit on resolution is compute rather than any breakpoint in the data. At matched work the design is ~82x faster than MedSOM, the CUDA implementation behind our earlier MEDLINE atlases and, at 128x128, 621x faster than the best available multicore-CPU library.

AI 总结：本文针对一致稳定性的泛化差距尾部分布问题，构造确定性γ-一致稳定学习问题填补了无对数上界与现有下界间的空白，确定了一致稳定性的最优高概率依赖关系。

链接：https://arxiv.org/abs/2608.24098

机构：Johns Hopkins University（约翰斯·霍普金斯大学）

作者：Pahan Dewasurendra

英文摘要：Uniform stability controls how much one training example can change the loss at any test point. A new logarithmic-free upper bound shows that a $\gamma$-uniformly stable algorithm with loss in $[0,L]$ has generalization gap at most $O \left(\gamma\log(1/\delta) +L\sqrt{\frac{\log(1/\delta)}{n}}\right)$ with probability $1-\delta$. Whether an actual bounded-loss learning algorithm can realize the linear dependence on $\log(1/\delta)$ has remained open. The known construction realizes it only for auxiliary weakly dependent random variables whose pointwise range grows with $n$. The known learning lower bound holds only at constant probability. We close this gap. For every $n$, stability level $\gamma$, and loss bound $L$, we construct one deterministic $\gamma$-uniformly stable learning problem whose tail satisfies, simultaneously for $1\le p\le c n$, $\mathbb P \left( R(A_S)-R_S(A_S) \ge c'\min \left\{L,\gamma p+L\sqrt{p/n}\right\} \right)\ge e^{-p}.$ The construction is ordinary bounded absolute-loss regression with constant labels. Its key is a multiscale collection of rare Rademacher features. A coordinatewise ramp is stable in sup norm, while an odd symmetrized maximum converts a unique extreme feature into a gap of order $\gamma p$ without violating the loss bound. Geometrically spaced ramps put all confidence levels into the same problem. Together with the logarithmic-free upper bound, this determines the optimal high-probability and moment dependence of uniform stability up to universal constants.

AI 总结：本文提出一种结合多分辨率特征编码与分层蒙特卡洛积分的无网格多分辨率深度能量方法，用于脆性断裂相场建模，在多个测试问题上的结果优于基准方法，零样本分类随机多裂纹状态的准确率达90%。

链接：https://arxiv.org/abs/2608.24126

机构：University of New South Wales（新南威尔士大学）； Central Queensland University（中央昆士兰大学）； Bauhaus-Universität Weimar（魏玛包豪斯大学）

作者：Han Zhang, Mehrisadat Makki Alamdari, Babak Shahbodagh, Mohammad Vahab, Cosmin Anitescu, Timon Rabczuk, Elena Atroshchenko

英文摘要： Phase-field modeling of brittle fracture removes the need to track cracks explicitly by recasting their evolution as the minimization of an energy functional. In return it requires a discretization dense enough to resolve a localization band whose width is set by a regularization length and whose path is not known in advance. We propose a mesh-free discretization in which a single neural network represents the displacement and phase fields and is trained by minimizing the incremental energy directly. The coordinates enter the network through a multiresolution feature encoding built from $C^1$ quadratic B-spline grids, so the finest scale the representation can express is set by choice rather than reached through slow training, and the energy is estimated by stratified Monte Carlo integration on points redrawn at every optimizer iteration. This pairing proves critical, since the crack fails to advance both when the integration points are held fixed and when the encoding is too coarse to represent the band, while each ingredient tolerates a wide range of settings once the other is in place. Because the representation is globally $C^1$, the second- and the fourth-order fracture energy densities run on the identical discretization. Across six problems, from single-edge-notched tension and shear to a thick-walled ring on a single spline patch, the computed load-displacement curves follow staggered finite element references at matched regularization length, with peak loads within about 1% on the single-edge-notched tests and within 8% where the crack pattern changes topology. On a public benchmark dataset of random multi-crack configurations the method classifies the active or dormant state of 90% of the seeded cracks in twenty zero-shot runs, where the deep Ritz baseline of the dataset authors fails.

AI 总结：该研究提出测试时干预方法RoFB，将中间预测转为耦合力注入循环模型隐动态，在数独、迷宫任务的三类循环模型上提升性能，且计算成本相当或更低。

链接：https://arxiv.org/abs/2608.24136

机构：Graduate School of Engineering, The University of Tokyo（东京大学大学院工学系研究科）

作者：Shunsuke Kamiya, Masanori Koyama, Seongcheol Jeong, Fumiya Uchiyama, Kenji Kubo, Kohei Hayashi, Masahiro Suzuki, Yutaka Matsuo

英文摘要：Recurrent models, which repeatedly update latent states with shared computation blocks, have emerged as powerful architectures for solving complex reasoning tasks. Existing inference-time methods scale computation by running more steps or sampling more trajectories, but ignore information revealed within each trajectory. Here we show that recurrent models can be improved at inference time by using their own readout probabilities to steer latent dynamics without retraining. We introduce Readout Feedback (RoFB), a test-time intervention that converts intermediate predictions into token-wise pairwise coupling forces injected into the latent dynamics. Across three recurrent models (AKOrN, ItrSA++, TRM) on Sudoku and Maze, RoFB yields clear gains in four of six model-task pairs, achieving performance unattainable by merely running more steps or selecting from multiple trajectories, at comparable or lower computational cost. These results suggest that closed-loop steering of latent dynamics can serve as a complementary inference-time control mechanism for recurrent reasoning models.

AI 总结：针对语义ID分词的残差量化局限，提出PRQ-KMeans方法，在工业搜索及推荐基准上实现分词器最优性能，获命中率、平均倒数排名的显著提升。

链接：https://arxiv.org/abs/2608.24207

机构：Kuaishou Technology（快手科技）

作者：Yunxiao Luo, Siyuan Wang, Ben Chen, Chenyi Lei

英文摘要：Semantic identifiers (SIDs) represent entities as hierarchical token sequences for generative retrieval and recommendation. Residual-quantization tokenizers construct these sequences by selecting a codeword at each level and passing a residual to the next. We view this process as progressive commonality removal: each token captures a component shared within its group, while later tokens should model the remaining differences. This view reveals three limitations: a corpus-wide shared component can consume first-level capacity, hard assignment ignores graded similarities to nearby codewords, and full-codeword subtraction can leave variation along the selected-codeword direction in the next residual. We therefore develop our solution in the post-hoc setting, where residual construction is not constrained by input reconstruction. Specifically, we propose PRQ-KMeans, which removes the global-mean component, refines centroids with Top-k similarity-weighted updates, and replaces full-codeword subtraction with a projection residual that removes each representation's selected-centroid component. Experiments on a large-scale industrial search dataset and four public recommendation benchmarks show that PRQ-KMeans achieves the strongest overall performance among the evaluated tokenizers, including gains of up to 7.4% in HitRate and 11.8% in MRR on the industrial dataset.

AI 总结：本研究提出因果分析框架，应用于Chronos-2和TimesFM-2.5，识别时间序列基础模型部署前的偏差与故障模式，为模型开发和应用选择提供建议。

链接：https://arxiv.org/abs/2608.24303

机构：Faculty of Behavioral, Management and Social Sciences, University of Twente（特温特大学行为、管理与社会科学学院）； European Central Bank（欧洲中央银行）

作者：Mathis Jander, Wouter van Heeswijk, Martijn Mes

英文摘要：Transitioning from bespoke time series models towards time series foundation models changes the relationship of model and application from one-to-one to one-to-many. This shift introduces concentration risk as many, potentially high-risk, forecasting applications are exposed to the same biases and failure modes of a single time series foundation model. At the same time, this centralization allows for economies of scale in model development and validation. In this study we investigate how biases and failure modes of time series foundation models can be identified before deployment. We propose a causal analysis framework to investigate the ability of a time series foundation model to preserve time series patterns. To achieve this, we intervene on parameterized synthetic time series generators and measure the corresponding change in model output under ceteris paribus conditions. We apply our causal analysis framework to Chronos-2 and TimesFM-2.5 and test them across six distinct time series patterns. We find safe configurations for trend and harmonic oscillation patterns. The results also indicate a bias in both models towards overestimating persistence, sudden failures for both models against the regime switch pattern and failure for TimesFM-2.5 against the energy-release pattern. Our review of the original works for both models indicates that the findings might be explained by the data used for pretraining. We conclude our study with suggestions for further model development, recommendations for application-specific model selection, and a discussion of limitations and further research directions.

AI 总结： 本研究提出结构化FHMM模型，用于分析T2DM患者疾病轨迹，通过IQVIA EHR数据验证，可识别临床相关潜在组件及异质性进展通路，为T2DM演变提供可解释见解。

链接：https://arxiv.org/abs/2608.24328

机构：Swiss Data Science Center (SDSC)（瑞士数据科学中心（SDSC））； Ecole Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）； ETH Zürich（苏黎世联邦理工学院）； Institute of Pharmaceutical Sciences（药学院）

作者：Alessandro Mari, Ekaterina Krymova, Guillaume Obozinski, Maria Luisa Marques de Sa Faquetti, Adrian Martinez de la Torre, Andrea Burden

英文摘要：In this work, we propose a structural variant of the Factorial Hidden Markov Model (FHMM) for the analysis of disease trajectories in patients with Type 2 diabetes mellitus (T2DM). The model represents a patient's latent health state as a combination of multiple independent, simultaneously evolving components, associated with comorbidities and lab results. This structured latent representation facilitates the identification of clinically meaningful patient states and clustering of common disease trajectories. We evaluate the proposed approach using The IQVIA Medical Research Data incorporating data from THIN, a Cegedim database of anonymized electronic health records (EHR), identifying patients with a first-ever prescription for a non-insulin antidiabetic drug (NIAD) between January 2006 and December 2019. The model identifies multiple clinically coherent latent components corresponding to known patterns of diabetes-related complications and reveals heterogeneous progression pathways, including distinct microvascular-dominant and multi-organ trajectories associated with elevated comorbidity burden and mortality. These results demonstrate that the proposed framework captures meaningful longitudinal structure in EHR data and provides interpretable insights into the evolution of T2DM and its comorbidities.

AI 总结：本研究针对传统机制可解释性无法在训练前识别任务关键机制的局限，提出前瞻性定位框架，结合双粒度定位流程，实现了更优的SFT指导与稳健的可扩展性能。

链接：https://arxiv.org/abs/2608.24482

机构：College of Computing and Data Science（计算与数据科学学院）； Nanyang Technological University（南洋理工大学）； School of Computer Science and Engineering（计算机科学与工程学院）； The Chinese University of Hong Kong（香港中文大学）

作者：Hang Chen, Jiaying Zhu, Wenya Wang

英文摘要：Mechanistic Localization bridges mechanistic interpretability and post-training optimization by isolating critical parameters via interpretative approaches and then guiding parameter-efficient Supervised Fine-Tuning (SFT) in a ``locating-then-tuning'' paradigm. However, due to the retrospective nature of mechanistic interpretability, directly interpreting pre-SFT models introduces misleading conclusions. Specifically for novel tasks, initially identified neurons differ drastically from those governing the final model, introducing biases that actively disrupt SFT. To address this, we propose a forward-looking localization framework that accurately estimates the post-SFT interpretability state using only pre-SFT parameters and the target dataset. Theoretically, we model SFT as a continuous parameter evolution, leveraging Taylor expansion to rigorously bridge the post-tuning mechanistic objective with the pre-SFT model's dynamic gradients. Practically, we design dual-granularity (neuron- and component-level) localization pipelines. Extensive experiments demonstrate that our approach not only provides superior SFT guidance but also exhibits robust performance and temporal scalability across increasing model sizes. This work transcends the fundamental limitation of traditional interpretability-its inability to identify task-critical mechanisms before they are trained-pioneering a predictive frontier that unites mechanistic interpretability with targeted optimization.

AI 总结：该研究发现熵的测量位置会影响PPO学习的有界连续控制策略几何，通过MyoLeg、Dog-Stand任务实验，表明熵测量空间是均值-方差耦合的设计选择，仅任务回报无法表征有界策略几何。

链接：https://arxiv.org/abs/2608.24488

机构：Lancaster University（兰卡斯特大学）； Beihang University（北京航空航天大学）； Tsinghua University（清华大学）

作者：Yiyang He, Zhichun Zhou, Ziwei Wang, Tao Xue, Haolin Fei

英文摘要：Many continuous-control policies are optimized as unbounded Gaussians and then mapped into bounded actions. We show that where entropy is measured changes the policy geometry learned by proximal policy optimization (PPO). In an 80-muscle MyoLeg task, a clipped Gaussian executes 89.07% of actions within 5% of a bound. A same-state decomposition shows that this is not due to variance alone: setting variance to zero still leaves 83.83% of actions near a bound, while 82.12% of state-conditioned means lie outside the executable interval. Replacing clipping with a tanh map does not remove the high-variance regime. For latent Gaussian entropy H(u), the entropy loss has zero gradient with respect to the mean and a constant variance-increasing gradient. For executed-action entropy H(a), the transform Jacobian adds an inward gradient on the mean. Across three matched MyoLeg seeds, near-boundary occupancy is 71.42%, 29.76%, and 18.83% under latent entropy, no entropy, and executed-action entropy. A 38-dimensional Dog-Stand replication with an independent CleanRL-based PPO implementation reproduces the ordering in mean geometry, which also survives shared-state evaluation and boundary margins from 1% to 10%. Direct mean penalties can match or exceed the centering produced by H(a), showing that interior means are not unique to executed entropy. However, matched mean geometry can coexist with substantially different variance and return. Entropy measurement space is therefore a coupled mean-variance design choice, and task return alone does not characterize bounded-policy geometry.

AI 总结：该研究将增长视为渐进式约束放松，提出迭代扩展可训练参数的策略，证明其可使训练偏向平坦区域，虽能生成平坦解但曲率降低未必提升测试性能，揭示平坦性与泛化关联的微妙性。

链接：https://arxiv.org/abs/2608.24568

机构：Université Paris Dauphine-PSL（巴黎多芬大学-PSL大学）； LORIA CNRS（法国国家科学研究中心LORIA实验室）； ESPCI-PSL（巴黎市政工程工业物理和化学高等学校-PSL大学）

作者：Paul Caillon, Christophe Cerisara, Alexandre Allauzen

英文摘要： Deep neural networks generalize well despite their highly nonconvex, overparameterized loss landscapes, a phenomenon often associated with the geometry of the minima found by stochastic optimization. We study how incremental grow-and-optimize strategies bias training toward flatter regions by viewing growth as progressive constraint relaxation. Starting from a low-dimensional submodel, we iteratively expand the trainable parameters by unlocking nested random subspaces while freezing the orthogonal complement at the network initialization, re-optimizing after each expansion until the full architecture is reached. Under standard local regularity conditions around non-degenerate minima, we prove that local sublevel sets are well approximated by ellipsoids and that basin accessibility under frozen constraints can be characterized by an explicit effective curvature in the frozen directions. This leads to an explanation of the bias: progressive growth increases the relative weight of wide basins and suppresses sharp ones through a volume effect induced by the frozen constraints. We empirically validate these predictions in controlled toy landscapes and in a realistic ResNet/CIFAR-100 setting and confirm that although progressive subspace growth reliably produces flatter solutions, curvature reductions do not universally translate into improved test performance, highlighting subtleties in the flatness-generalization connection. The code is available at this https URL.

AI 总结：该研究发现优化器状态与未来数据的延迟传输可改变Transformer短程训练决策，在Math--Code数据集上提升损失，为有限视野训练干预提供了机制依据。

链接：https://arxiv.org/abs/2608.24593

机构：School of Physics, Beihang University（北京航空航天大学物理学院）

作者：Jinhui Guo

英文摘要：Adaptive optimizers retain gradient history in moment variables, allowing a local change in loss weighting to alter later updates. We examine whether this delayed transport is large enough to change prospective short-horizon decisions. On committed future-minibatch sequences, we differentiate eight-step AdamW trajectories through the complete model--optimizer state and select exposure-matched Math--Code loss schedules before independent evaluation. Across 12 unused 0.3M Transformer histories, full transport lowers token-disjoint loss relative to an optimizer-aware immediate derivative in 10/12 histories (mean benefit $4.71\times10^{-4}$; exact one-sided sign test, $p=0.0193$). The two controllers act equally often but select different schedules in 60/96 windows. Crossed checkpoint--future-path tests attribute this reordering to the interaction between optimizer state and near-future data, while an independent Ising--CNN experiment shows that deleting moment-state transport destroys accurate response prediction. Full-transport scores also concentrate exact-rollout winners in larger candidate libraries, focusing finite-amplitude evaluation on a shortlist. On these committed short paths, optimizer memory and near-future data order are therefore actionable components of the training state, providing a mechanism-based criterion for when finite-horizon rather than one-step intervention is required.

AI 总结：研究针对EEG模型的局限性，提出以不变性为导向的EEG基础模型INCEPT，经超11000小时临床EEG训练，在广谱EEG任务基准中多数指标领先，验证了不变性学习构建可复用EEG基础模型的潜力。

链接：https://arxiv.org/abs/2608.24597

机构：ShanghaiTech University（上海科技大学）； Shanghai United Imaging Intelligence Co., Ltd.（上海联影智能医疗科技有限公司）； Shanghai Clinical Research and Trial Center（上海临床研究与试验中心）

作者：Yulong Dou, Han Wu, Guo Chen, Fangmao Ju, Zhiming Cui, Dinggang Shen

英文摘要：Electroencephalography (EEG) is a widely used window into human brain function, but most EEG models remain tied to a one-dataset-one-model supervised paradigm. Recent EEG foundation models offer a route toward reusable representations, but most remain reconstruction-centered, assuming that EEG content predictable from local context is necessarily transferable neural information. Here we present INCEPT, an invariance-oriented EEG foundation model trained on over 11,000 hours of unlabelled clinical EEG. Rather than prioritizing signal recovery alone, INCEPT learns representation-level stability across correlated EEG observations, separating stable neural structure and essential subject-sensitive information from the nuisance variability that dominates scalp recordings while preserving subject-, state- and condition-discriminative information. We evaluate INCEPT on a broad-spectrum benchmark of ten datasets spanning three levels of post-acquisition EEG analysis: signal-level assessment, brain-state decoding, and brain-health evaluation. INCEPT ranks first among recent EEG foundation models on 26 of 30 linear-probing metrics and 24 of 30 fine-tuning metrics, and also surpasses strong task-specific specialist encoders across diverse downstream settings. Objective ablations and representation analyses further show that invariance-oriented pre-training improves transfer and organizes subject-sensitive neural representations beyond reconstruction alone. These results establish invariance learning as a promising principle for building reusable EEG foundation models.

AI 总结：该研究指出停电预测模型因数据泄露夸大了可推广性，评估时采用更贴近现实的空间/时间/事件拆分后性能大幅下降，GeoAI嵌入仅小幅改善空间泛化，需改进数据与评估方式。

链接：https://arxiv.org/abs/2608.24665

机构：University of Toronto（多伦多大学）； North Carolina State University（北卡罗来纳州立大学）

作者：Yamil Essus, Ranga Raju Vatsavai, Benjamin Rachunok

英文摘要： Power outage prediction models are increasingly used in assessments of climate-driven infrastructure risk, yet current evaluation practices obscure whether these models generalize to the novel conditions such applications require. We identify three common methodological choices in power outage prediction models that influence their ability to generalize across spatial, temporal, and event-based settings. We compare the predictive performance impacts of different methodological decisions using publicly available data for the U.S. East Coast from 2018 to 2023 and feature sets derived from weather reanalysis and land-cover data, and embeddings from a GeoAI foundation model (Prithvi WxC). Specifically, we assess model performance under multiple test selection strategies, including unfiltered random splits, leave-one-state-out, and leave-one-event-out designs, which increasingly approximate real-world deployment conditions. While random train-test splits yield strong performance, we show that these results are inflated by spatial and temporal autocorrelation. Under spatial and temporal holdout experiments, predictive accuracy degrades substantially, with models often failing to outperform a simple null baseline. Incorporating GeoAI foundation model embeddings yields limited and inconsistent improvements, primarily for spatial generalization, and does not resolve poor event-level transferability. These findings suggest that, given current data availability and evaluation practices, publicly trained outage prediction models offer limited and uncertain operational value. Progress will likely require improved data coverage, more realistic evaluation protocols, and a shift in focus from marginal modeling advances toward addressing structural data constraints.

AI 总结：本研究推出多模态基础模型oFM，基于167万肿瘤患者数据整合多模态信息，在预后基准及治疗队列中表现优于基线特征，还开发了机制发现框架以解释模型，助力肿瘤学临床与药物开发应用。

链接：https://arxiv.org/abs/2608.24688

机构：Tempus AI, Inc.（Tempus AI公司）

作者：Eugene Vorontsov, Yi Kan Wang, Alican Bozkurt, Adam Casson, Ludmila Tydlitatova, Michal Zelechowski, Ezra E. W. Cohen, Jyoti D. Patel, Max Banaszak, Caitlin McWilliams, Shane Colley, Kate Sasser, Ryan Fukushima, Eric Lefkofsky, Razik Yousfi, Siqi Liu

英文摘要：Precision oncology necessitates a longitudinal model of patient state that captures cancer evolution and treatment over time, integrating multimodal observations. We introduce the oFM, a foundation model developed on a real-world oncology cohort of 1.67 million cancer patients that integrates clinical trajectories with DNA, RNA, and H&E pathology. Patient-level partitions were reserved for training, validation, and testing, with over one million patients used for training. The oFM encodes daily clinical and molecular episodes and, along with pathology images, integrates them over time to produce a patient state embedding. We evaluate frozen oFM embeddings against expert-curated clinical and molecular baseline features. In prognostic benchmarks, the oFM improved AUC for treatment response, progression-free survival, and overall survival (0.774 vs. 0.563 for overall survival). Across 11 comparative-treatment cohorts, the oFM embeddings achieved a three-fold higher pooled and scale-normalized treatment-benefit AUTOC than baseline features with improved benefit ranking in 9 of 11 cohorts, and provided stronger prognostic discrimination within both treatment arms. We also evaluated a mechanism discovery framework that interprets downstream models built on oFM embeddings by linking their predicted outcomes to clinically and biologically grounded mechanisms through an evidence-grounded temporal graph, enabling evaluation in clinical and drug-development applications.

AI 总结：该研究针对训练网络的对称性参数归因问题，通过逐参数功能敏感性分析，揭示了参数空间中实现函数空间对称性群作用的条件，并在旋转不变分类器与哈密顿神经网络上验证了相关结论。

链接：https://arxiv.org/abs/2608.24700

机构：Mathematical Institute, University of Oxford（牛津大学数学研究所）； Heidelberg Institute for Theoretical Studies（海德堡理论研究所）

作者：Alan Muriithi, Vedanta Thapar, Torben Berndt

英文摘要：When a network has learned a function with a known symmetry, can that symmetry be moved through the parametrisation---is there a motion in parameter space realising the group action in function space? We formulate this as a lifting problem for the realisation map $\Phi:\theta\mapsto f_\theta$, and show that a smooth parameter-space action exists only if the tangent space to the function's symmetry orbit lies within the image of $\mathrm d\Phi_\theta$, whose columns are the \emph{functional sensitivities} of individual parameters. This condition is also sufficient for pointwise first-order lifting. Relaxing it in least squares yields two local parameter directions: one following the symmetry orbit, one descending towards the equivariant subspace, with residuals measuring what the parametrisation cannot reach. On a rotationally invariant classifier we find these directions induce their predicted function-space motion, but only locally: recomputed directions track the orbit and reduce the equivariance defect, while directions held fixed depart from both after training. The same holds for Hamiltonian neural networks trained on a rotationally symmetric potential, even though the architecture does not explicitly enforce the symmetry.

AI 总结：该研究针对DNN验证的松弛间隙问题，提出特征值最大化程序，使(DNN)²方法的验证边界比标准SDP更紧且可认证，为安全关键自主系统部署神经网络模块提供支撑。

链接：https://arxiv.org/abs/2608.24743

机构：Northeastern University（东北大学）； University of Michigan（密歇根大学）

作者：Hanna Jiamei Zhang, Alan Papalia, Michael Everett, David M. Rosen

英文摘要：Existing linear program (LP) and semidefinite program (SDP) relaxations for rectified linear unit (ReLU) neural network (NN) verification yield overly-conservative safety guarantees due to significant relaxation gaps. While the completely positive program (CPP) formulation closes this gap, it is NP-hard to solve. Its cheapest tractable relaxation, the doubly non-negative program (DNN), retains critical constraints as an SDP, but one whose size exceeds the reach of interior-point methods at practical scale. While Burer-Monteiro (BM) factorization has been applied to make SDP-based verification scalable, no such result exists for the strictly tighter DNN formulation. A key obstacle is that additional non-negativity constraints in the DNN cause dual multipliers for optimality certification to be non-unique, making standard certification methods inapplicable. We propose a novel eigenvalue maximization procedure that searches the non-unique multiplier space for a valid certificate, i.e. a global optimality guarantee. Experiments demonstrate that our approach $(\text{DNN})^2$ produces bounds consistently tighter than the standard SDP method, often matching the exact solution, and that our certification procedure confirms global optimality when a valid certificate exists. These results are a key step toward providing tight, certifiable, and computationally scalable verification guarantees needed to deploy neural network controllers and perception modules in safety-critical autonomous systems.

AI 总结：该研究针对现有解耦表示方法未考虑因子空间非均匀几何的问题，提出FactoMap方法，通过引入因子空间结构学习可解释原型，实验证明其能保持因子连续性并实现因子解耦。

链接：https://arxiv.org/abs/2608.24762

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

作者：Sohini Gupta, Bahareh Tolooshams

英文摘要：Many disentanglement methods represent generative factors using Euclidean product coordinates, although the underlying factor spaces may wrap, collapse, or have position-dependent geometry. We introduce factor-space structure, combining factor domains, generator-induced identifications, and position-dependent scales to distinguish topologically equivalent spaces with different factor geometries. We show that statistically independent factors need not be geometrically separable: hue and scale produce effects that grow at different rates, yielding anisotropy that no fixed rescaling removes. We propose the Factor-Space Topographic Map (FactoMap), which learns interpretable prototypes indexed by a factor-space lattice. Topographic learning transfers the lattice's periodicity, collapses, and non-uniform extent to the representation. Experiments show that matching this structure preserves factor continuity and enables disentanglement of the underlying factors.

AI 总结：针对多模态属性图学习中模态对齐忽略上下文、模态融合缺乏适应性的问题，提出基于克利福德代数和解耦图神经范式的LION方法，在9个文本-图像多模态属性图数据集上的多类下游任务中显著优于现有最优基线。

链接：https://arxiv.org/abs/2608.24795

机构：Beijing Institute of Technology（北京理工大学）； Ant Group（蚂蚁集团）

作者：Xunkai Li, Zekai Chen, Zhengyu Wu, Henan Sun, Daohan Su, Guang Zeng, Hongchao Qin, Rong-Hua Li, Guoren Wang

英文摘要：Recently, the rapid advancement of multimodal domains has driven a data-centric paradigm shift in graph ML, transitioning from text-attributed to multimodal-attributed graphs. This advancement significantly enhances data representation and expands the scope of graph downstream tasks, such as modality-oriented tasks, thereby improving the practical utility of graph ML. Despite its promise, limitations exist in the current neural paradigms:(1) Neglect Context in Modality Alignment: Most existing methods adopt topology-constrained or modality-specific operators as this http URL aligners inevitably neglect graph context and inhibit modality interaction, resulting in suboptimal alignment.(2) Lack of Adaptation in Modality Fusion: Most existing methods are simple adaptations for 2-modality graphs and fail to adequately exploit aligned tokens equipped with topology priors during fusion, leading to poor generalizability and performance this http URL address the above issues, we propose LION (c\underline{LI}ff\underline{O}rd \underline{N}eural paradigm) based on the Clifford algebra and decoupled graph neural paradigm (i.e., propagation-then-aggregation) to implement alignment-then-fusion in multimodal-attributed graphs. Specifically, we first construct a modality-aware geometric manifold grounded in Clifford this http URL geometric-induced high-order graph propagation efficiently achieves modality interaction, facilitating modality this http URL, based on the topology-aware Clifford components of aligned tokens, we propose adaptive holographic aggregation. This module integrates component-wise energy and propagation-scale information with learnable parameters to improve modality fusion. Extensive experiments on 9 text-image MAG datasets demonstrate that LION significantly outperforms SOTA baselines across 3 graph and 3 modality downstream tasks.

AI 总结：针对时序图不平衡节点分类中少数类表示被同化、判别证据不足的问题，提出MDTE框架，通过分布感知选择性传播与多视图判别融合，在五个真实数据集上显著提升少数类相关指标。

链接：https://arxiv.org/abs/2608.24812

机构：Zhejiang University of Technology（浙江工业大学）； The University of Sydney（悉尼大学）； Vecton AI

作者：Zhou Zelong, Zhang Tianming, Yang Zhengyi, Tang Yifu, Hou Chenyu, Cao Bin, Fan Jing

英文摘要：Class-imbalanced node classification on temporal graphs is challenging because majority-dominated temporal propagation progressively assimilates minority representations, while conventional node and neighborhood information provides insufficient discriminative evidence for minority classes. To address these issues, we propose MDTE, a minority-aware diffusion framework that reconstructs stable and discriminative temporal edge-event representations through conditional diffusion denoising. Specifically, MDTE introduces Distribution-Aware Selective Propagation, which combines Local Outlier Factor (LOF)-based propagation filtering with cluster-aware low-frequency propagation. The module preserves informative neighborhood dependencies while mitigating harmful propagation and majority-class information assimilation. It further develops Multi-View Discriminative Fusion, which exploits feature reconstruction and topology prediction to characterize class-wise differences in distribution learning and extracts complementary discriminability signals to guide denoising. Experiments on five real-world datasets demonstrate that MDTE consistently achieves the best performance on minority-class-oriented metrics, improving minority-class recall by up to 23.53 percentage points, minority-class F1 by 8.68 percentage points, and AUPRC by 2.67 percentage points over the strongest baselines.

AI 总结：该研究发现语言模型预训练中存在ELR崩溃现象，确定ELR是连接LR调度、范数控制与损失动态的共同坐标，提出的基于ELR的FSL可实现跨范数控制方法的迁移并解释延迟加速效应。

链接：https://arxiv.org/abs/2608.24814

机构：Peking University（北京大学）； Ant Group（蚂蚁集团）

作者：Zihan Liu, Ruiheng Zheng, Shaobo Zhang, Changxin Tian, Kunlong Chen, Zhiqiang Zhang, Lei Wu

英文摘要：We uncover ELR collapse in language model pretraining: learning rate (LR) and parameter norm govern loss dynamics primarily through their ratio, the effective learning rate (ELR). When ELR is matched across runs, their loss trajectories collapse throughout training despite substantially different LRs and parameter norms. Across optimizers, architectures, datasets, and model scales, mean collapse errors are typically a few x 10^-3, below the seed-to-seed variation measured in a representative configuration. Systematic ablations identify normalization design and the timescale of LR-norm variation as key determinants of collapse precision. Controlled interventions further show that weight decay and Hyperball shape loss dynamics primarily through the ELR schedules they induce. Replacing LR with ELR enables a fitted functional scaling law (FSL) to transfer across norm-control methods. The resulting ELR-based FSL also explains delayed acceleration, a recurring effect of norm control. Together, these results establish ELR as a common coordinate linking LR scheduling, norm control, and loss dynamics.