机器学习学术速递[8.27]

AI 总结：ExFold是一种无训练的统一专家折叠框架，作为vLLM插件可联合加速MoE的预填充与解码，最高实现1.41倍TTFT和2.45倍TPOT加速，同时保留约99%的原始平均质量。

链接：https://arxiv.org/abs/2608.24938

作者：Juntong Wu, Yifei Liu, Junyi Chen, Siqi Fan, Chaoran Feng, Minghao Li, Liujie Zhang, Weihang Chen, Li Yuan

英文摘要：Mixture-of-Experts (MoE) models scale capacity for strong quality while keeping per-token compute bounded through sparse expert activation. Yet low-latency MoE serving is increasingly challenging, because it spans two inference phases with fundamentally different bottlenecks: prefill is dominated by token-wise expert computation, whereas decode is constrained by memory traffic from the batch-wise activated expert set. However, existing training-free acceleration methods optimize only a single resource proxy, either the experts each token executes or the experts a batch activates, and either discard the excluded experts' contribution or leave it only implicitly approximated. In this paper, we propose ExFold, a unified training-free expert-folding framework for jointly accelerating MoE prefill and decode. ExFold casts both prefill and decode as one budgeted output-approximation problem: execute only a phase-specific constrained expert set while projecting the contribution of budget-excluded experts onto retained experts using calibrated scalar projectors. Motivated by the observation that many expert outputs are directionally aligned but differ in magnitude, ExFold calibrates a pairwise scalar-projector matrix on unlabeled data and uses it at inference time to fold excluded expert contributions into retained experts. Under this view, prefill acceleration becomes token-level Top-K folding, and decode acceleration becomes batch-level expert-pool folding. The two phases differ only in how retained experts are selected, while excluded contributions are recovered by one shared folding mechanism. We implement ExFold as a plug-and-play plugin in vLLM, with a lightweight expert-folding CUDA kernel, delivering up to 1.41x TTFT and 2.45x TPOT speedups while retaining about 99% of the original average quality.

AI 总结：针对Transformer模型部署的高资源消耗问题，提出基于LoRA低秩梯度的REP-LIE剪枝方法，结合稳定性分数迭代剪枝，在LLaMA-7B等模型上实现高效剪枝并保持竞争力性能。

链接：https://arxiv.org/abs/2608.24973

机构：School of Computer Science and Technology, Guangdong University of Technology（广东工业大学计算机科学与技术学院）； College of Information and Artificial Intelligence, Yangzhou University（扬州大学信息与人工智能学院）

作者：Peng Liu, Huibing Zeng, Yiqun Zhang, Yang Yi, Jigang Wu

英文摘要：With the rapid development of large-scale pre-trained language models based on Transformer architectures, their high computational and memory costs have become a major obstacle to deployment, especially in resource-constrained environments. Traditional pruning methods typically depend on full gradient-based importance estimation, and they necessitate prior finetuning of the model to achieve satisfactory performance. This process often results in intolerable resource consumption. This paper proposes REP-LIE, a new approach to enable resource-efficient pruning during the process of finetuning. REP-LIE leverages the gradients of LoRA low-rank matrices to estimate the importance of weights without requiring full gradient computation. To address the inherent randomness in importance estimation, a stability score is introduced, serving as the basis for iterative pruning of unimportant model parameters. The pruned model is further finetuned through lightweight updates, eliminating the need for full-parameter optimization in the process of finetuning. Extensive experiments on both medium-scale encoder models and large-scale generative models (LLaMA-7B and Mistral-7B) demonstrate that REP-LIE still achieves competitive performance compared to existing approaches.

AI 总结：该研究从几何角度分析标准神经网络对动态规划长输入泛化困难的问题，证明动态规划的图、多项式、多面体描述构成同构半环，且长度泛化的决策边界不存在层级决定关系。

链接：https://arxiv.org/abs/2608.25034

机构：Bowdoin College（鲍登学院）； Naval Postgraduate School（海军研究生院）； Aalborg University（奥尔堡大学）

作者：Richard F. M. Lim, Ruriko Yoshida

英文摘要：Standard neural architectures often fail to generalize to longer inputs for dynamic programming (DP) targets. We investigate what makes this hard geometrically. Every finite min-plus DP is a shortest path on a DAG, which is equivalently a tropical polynomial whose extended Newton polyhedron encodes the decision boundary of which path wins. We prove these three descriptions (graph, polynomial, polyhedron) form isomorphic semirings at two levels --- formal polynomials and their computed functions --- connected by operations that characterize all structural redundancies. We then address the length-generalization question geometrically: does the decision boundary at length $T$ decide the boundary at $T+1$? We present two structural negatives. The semiring's two native ways to reduce dimension (setting a variable to each identity) are neither injective nor always closed within the DP. Series and parallel composition fail to construct all DAG topologies from smaller sub-DAGs, and even all terminal-only operations do not capture all DP compositions.

AI 总结：该研究提出VN-SST模型，其前馈模块为低维指令库，在神经解码任务中样本与参数效率优于现有模型，且在语言建模任务中也展现出通用高效性。

链接：https://arxiv.org/abs/2608.25088

机构：BrainCo（脑聚科技）

作者：Morteza Sarafyazd

英文摘要：Cortical computation is strikingly low-dimensional: a handful of latent variables, carried in a neural population's activity, steer the higher-dimensional responses of individual neurons. Our aim is sample efficiency-models that decode well from limited data and at small parameter budgets. In a standard Transformer layer, the feed-forward block applies the same operator to every token. We suggest a von-Neumann inspired hypothesis of efficient computation as an alternative for neural decoding: a controller decodes an instruction and then executes a token-specific operator; the usual realization-a soft mixture of experts-only blends their outputs, not operators. We introduce a von-Neumann State-Space Transformer (VN-SST), a memory-augmented Transformer whose feed-forward block is a low-rank instruction bank: a shared base operator plus a small set of learned low-rank instructions, from which a per-token code synthesizes the weight matrix actually used at that token. The code is read from a low- dimensional projection of a carried state-space memory, so a slow latent trajectory acts as an instruction pointer-mirroring how low-dimensional dynamics may route cortical computation. On three motor-cortex neural-decoding benchmarks, VN-SST is far more data-efficient than a modern Transformer, each jointly predicting spikes and decoding behavior. This model wins by a wide margin on the scarcest benchmark, leads on the other two, and turns longer context into rising rather than falling accuracy. We evaluated that the network compresses a large instruction bank to a few bits per token, so program capacity acts as a control channel, not an accuracy lever. The same model is also more parameter-efficient on two small text benchmarks used for language modeling (LLMs), suggesting a generic mechanism.

AI 总结：本文通过实证研究，明确注意力架构是影响LLM解码能耗随上下文长度缩放的核心因素，发现GQA及带SWA的GQA能效更优，批处理可降低能耗与延迟，为LLM配置提供实用指导。

链接：https://arxiv.org/abs/2608.25096

机构：Algoma University（阿尔戈马大学）； Reutlingen University（罗伊特林根大学）

作者：Molka Chkir, Syed Muhammad Danish, Jos Höll, Arghavan Asad

英文摘要：The growing adoption of large language models (LLMs) has raised increasing concerns about the energy consumption and environmental impact of inference. This paper presents a systematic empirical study of decode-phase energy consumption across representative open-source LLMs employing Multi-Head Attention (MHA), Grouped Query Attention (GQA), and Grouped Query Attention with Sliding Window Attention (SWA) to characterize how attention architecture influences decode-phase energy consumption under varying inference workloads. We evaluate four models across different context lengths, batch sizes, and generation workloads while measuring GPU energy using NVIDIA hardware counters. We examine the effects of context length, attention mechanism, Key-Value (KV) cache growth, and batching on decode-phase energy consumption. Results show that attention mechanism is the primary factor governing how decode energy scales with context length. MHA models exhibit substantially steeper energy growth than GQA models, whereas GQA with SWA maintains nearly constant energy consumption. We further show that model size primarily determines absolute energy consumption, while batching reduces both energy per generated token and request latency by up to 87%. These findings provide practical guidance for selecting energy-efficient LLM architectures and inference configurations.

AI 总结：该研究发现MoE模型对道德内容的编码看似稳健实则脆弱，归因于输出稀释，其稳健性比同等规模密集模型低4.2倍，且该脆弱性为架构性而非学习所得。

链接：https://arxiv.org/abs/2608.25231

机构：Distiller Labs（Distiller实验室）

作者：Orion Reblitz-Richardson

英文摘要： Mixture-of-Experts (MoE) models appear to encode moral content as robustly as dense models, yet prove far more fragile in their encoding. In OLMoE-1B-7B, linear probes recover moral valence from nearly every expert-layer combination, with mean peak-layer accuracy above 90%. But these representations collapse under levels of activation noise that a dense model of matched size easily tolerates, with a 4.2-fold difference in robustness. We trace this to output dilution. Because the MoE block averages across active experts before contributing to the residual stream, the feedforward signal reaching downstream layers is nearly two orders of magnitude smaller than in a dense MLP. Moral information, our interest, survives aggregation intact but at a scale trivially overwhelmed by perturbation. Routing itself remains stable under noise while the vulnerability originates entirely in the diluted aggregate. Checkpoint trajectories confirm this is architectural, not learned. Experts never specialize and accuracy saturates within the first few thousand steps. In sparse architectures, redundant encoding does not imply robust encoding.

AI 总结：本研究以OLMo-2-0425-1B-Instruct为对象，揭示弃权几何与弃权训练的关联，发现多样弃权起始可提升梯度稳定秩，削弱弃权向量消融攻击，为提升AI模型弃权鲁棒性提供新视角。

链接：https://arxiv.org/abs/2608.25390

机构：UC San Diego（加州大学圣迭戈分校）

作者：Andrey Labunets

英文摘要：Refusal training protects AI models from jailbreaks by training models to decline unsafe queries, reducing the risk of misuse. Recent work finds that refusal behavior in aligned language models can be mediated by a single activation direction or a low-dimensional refusal subspace shared across harmful prompts: ablating those directions suppresses refusals while largely preserves other model capabilities. Yet it remains unclear why safety-critical features in a wide range of models emerge and concentrated, low-dimensional structure. In a case study of OLMo-2-0425-1B-Instruct we find that the refusal geometry reflects refusal training: activation updates resulting from refusal-completion first-token losses explain the resulting refusal direction and refusal subspace. We study refusal directions through the training dynamics across refusal datasets and reveal that their brittleness is associated with repetitive refusal starts, which in turn is linked to concentration of gradients and refusal features in a low-dimensional subspace. Across frozen-model analyses and controlled synthetic fine-tuning, we find evidence of a hardening lever: diverse refusal starts can raise stable ranks of gradients and activation changes, making refusals harder to remove with a vector ablation attack.

AI 总结：针对社交媒体用户兴趣漂移问题，提出DUMoE框架，通过时序动态感知骨干与稀疏MoE兴趣适配器实现多模态用户表示学习，在两类预测任务上优于现有最优方法。

链接：https://arxiv.org/abs/2608.25773

机构：Shanghai Innovation Institute（上海创新研究院）； Tongji University（同济大学）

作者：Ziqing Qian, Haohang Chen, Shengqi Dang, Yuhan Xiong, Canyu Shen, Jiaying Lei, Nan Cao

英文摘要：Understanding user preferences from noisy and temporally evolving social media behaviors is fundamentally challenging due to interest drift, where user preferences shift across time and exhibit both multi-scale temporal patterns and diverse co-existing interests. To address this, we propose DUMoE, a unified framework for drift-aware multimodal user representation learning. Our model consists of (i) a temporal dynamics-aware backbone that captures and integrates static profiles, short-term behavioral signals, and long-term dependencies into a coherent representation, and (ii) a sparse mixture-of-experts (MoE) interest adapter that disentangles multiple latent interests via expert specialization and adaptive routing. Each expert models a distinct interest subspace, while a gating network dynamically selects and aggregates a sparse subset of relevant experts for each user. To enable stable and effective optimization, we further introduce a three-stage training strategy that decouples backbone learning, expert specialization, and gating optimization. Extensive experiments on real-world social media datasets show that DUMoE consistently outperforms state-of-the-art methods on both user interest prediction and interaction prediction tasks.

AI 总结：本研究提出Robust CurveMoE混合专家框架，通过模式连通性连接不同范数的专用模型，引入贡献引导的部分更新降低成本，在CIFAR-100等数据集上显著提升了各类准确率。

链接：https://arxiv.org/abs/2608.26043

机构：Illinois Institute of Technology（伊利诺伊理工大学）

作者：Xu Zhang, Ren Wang

英文摘要：Multi-norm adversarial defense aims to protect neural networks against perturbations defined by different norm constraints, but existing methods typically optimize competing robustness objectives within a single parameter configuration, leading to substantial training cost and unfavorable robustness trade-offs. We propose Robust CurveMoE, an efficient mixture-of-experts framework that connects models specialized for different perturbation norms through a low-loss path and exploits the complementary robustness profiles of models along this path. Robust CurveMoE derives clean and norm-specialized experts from robustness-constrained curve locations and selectively expertizes only influential layers, while sharing the remaining parameters across routing paths. To further reduce curve-construction cost, we introduce contribution-guided partial updating, which selects influential curve parameters using initialization-based gradient scores. We also theoretically bound the objective gap between partial and full curve optimization. Experiments on CIFAR-100 and ImageNet-100 with WideResNet and Vision Transformer architectures show that Robust CurveMoE consistently improves clean, norm-specific, and Union accuracy over MSD and ERMC. In particular, it improves Union accuracy by 2.37 and 2.13 percentage points over the strongest baseline on CIFAR-100 and ImageNet-100, respectively. Extensive ablations further validate the effectiveness of partial updating, selective expertization, and robustness-constrained expert selection.

AI 总结：该研究提出智能体自动研究协议，将无线资源管理的机器学习算法设计交由AI编码智能体完成，在小区边缘功率控制任务中实现高性能与低推理成本，还恢复了可证明的最优结构。

链接：https://arxiv.org/abs/2608.26093

机构：Ericsson R&D（爱立信研发部门）； University of Toronto（多伦多大学）

作者：Ahmad Khan, Akram Bin Sediq, Sara Azadegi Naeini, Raviraj S. Adve

英文摘要：Designing machine learning algorithms for wireless resource management is labour-intensive: the architecture, the loss function and the training recipe are all specified by hand. We demonstrate that this design layer can be surrendered to an autonomous agent in its entirety. We adopt the autoresearch protocol, in which an AI coding agent edits a training script, runs a fixed-budget experiment, and retains or discards the change according to a single immutable metric. We grant the agent authority over the architecture family, the input representation, the output parameterization, the loss function and the task-sampling law, and set it a target chosen for its difficulty: sum-least-percentile-rate power control across a multicell network. The formulation targets cell-edge throughput and is non-convex, non-smooth and strongly NP-hard away from its max-min vertex. Safeguards render the results trustworthy: a hash-pinned evaluator, an enforced inference contract and a pre-registered falsifier per experiment. In eighty-one unattended experiments over twenty-six hours, the agent reached $99.5\%$ of a converged minorization-maximization reference in one fixed-cost inference pass, at roughly $600\times$ lower inference cost, closing $94\%$ of the gap from its first working architecture, with one parameter set serving every network size and percentile target. It recovered provable structure rather than tuned constants: the output parameterization it discovered reproduces the exact max-min-optimal allocation at the minimum percentile, for every value of the trained weights.

AI 总结：本研究提出漂移变分自编码器，通过条件后验流匹配统一生成与表示学习，在CrossGeom-4基准上实现了高表示精度与模态一致性，完成多模态概念验证。

链接：https://arxiv.org/abs/2608.25138

机构：The Chinese University of Hong Kong（香港中文大学）

作者：Jiarui Cao

英文摘要：Stochastic masking, cropping, or modality removal makes deterministic reconstruction an incomplete target: one observation can admit many clean completions. This work takes the corresponding posterior $P(X\mid C)$ as the common statistical object for conditional generation and generatively sufficient representation learning. Drift Variation autoencoder trains a masked encoder $Z=E(C)$ and a conditional flow decoder with one clean-prediction Flow Matching loss. The analysis first decomposes the ideal conditional KL into generator approximation and the representation deficiency $I(X;C\mid Z)$. It then derives orthogonal risk decompositions for conditional Flow Matching. For an affine Gaussian path, the clean-prediction representation gap is zero if and only if $P(X\mid Z)=P(X\mid C)$. Thus the encoder-dependent excess clean-prediction risk induced by Flow Matching and the profiled ideal conditional KL have the same posterior-sufficient zero set, without being numerically equal objectives. An exact conditional field with a zero-noise endpoint then generates $P(X\mid Z)$ and hence $P(X\mid C)$ at a joint ideal optimum. The result extends to continuous multimodal product spaces when the complete modality tuple remains the Flow target for every observation mask. On CrossGeom-4, an 18-run controlled benchmark, observable factors have linear-probe $R^2$ of $0.9990$-$0.9992$, shuffling the joint model's encoder condition increases conditional error by $13.5\times$-$15.7\times$, and joint target attention reduces disagreement on an unobserved factor shared by two outputs by $90.1$-$92.8\%$ relative to independent target decoders. Visible modalities are also generated and reconstructed, directly validating the full-tuple objective. Unconditional mode balance remains imperfect, delimiting the empirical claim to a controlled multimodal proof of concept.

AI 总结：针对LLM部署的资源瓶颈，该研究提出FAMPWQ方法，通过费舍尔信息度量层敏感度结合强化学习分配位宽，在7个模型和5个基准上优于7种基线方法，提升了量化性能。

链接：https://arxiv.org/abs/2608.24945

机构：School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）； Hithink Research（海思睿研究中心）； Electronic Engineering, Tsinghua University（清华大学电子工程系）

作者：Gongwei Lee, Ji Liu, Juncheng Jia, Ji Wu

英文摘要：Recent years have witnessed remarkable achievements of Large Language Models (LLMs) in multiple domains, while the excessive resource requirements of LLMs hinder the deployment on resource-constrained devices. Although model quantization stands out as an effective approach, conventional quantization approaches typically incur severe performance degradation due to uniform bit-width or simple heuristic sensitivity evaluation. In this paper, we propose a novel Fisher information-based Adaptive Mixed Precision Weight Quantization approach, i.e., FAMPWQ, which performs layer-adaptive weight quantization for effective LLM inference on commodity GPUs. First, we propose a system model with a novel Fisher information metric to measure the layer-wise sensitivity to quantization. Second, we propose a reinforcement learning-based bit-width allocator in FAMPWQ, which generates an adaptive bit-width allocation strategy based on the Fisher information sensitivity metric. Extensive experiments on 7 models and 5 benchmarks demonstrate that FAMPWQ significantly outperforms 7 baseline approaches in terms of PPL (up to 3.39 smaller), accuracy (up to 6.87% higher), and LLM-as-a-judge comparison (up to 76% win rate).

AI 总结：本研究拆解语言模型的RL后训练算法，探究各因素对其结果的影响，为NLP领域人员提供RL后训练的入门指南。

链接：https://arxiv.org/abs/2608.24949

机构：University of Washington（华盛顿大学）； Allen Institute for AI（艾伦人工智能研究所）

作者：Donovan Clay, Saket Gollapudi, Sankar Harilal, Min Jang, Jacob Morrison, Sewoong Oh, Natasha Jaques

英文摘要：Reinforcement learning (RL) post-training has emerged as a powerful framework for enhancing the capabilities of large language models (LLMs), enabling impressive reasoning, math, and coding capabilities. Yet for many researchers and practitioners, the principles behind classical RL remain a "black box". In this work, we deconstruct the RL post-training algorithm, investigating each step to clarify what is actually happening beneath the surface. By isolating the mechanics of RL with Verifiable Rewards in a controlled and simplified environment, we examine how RL outcomes are shaped by the base model's prior distribution, the granularity of the reward signal, the diversity of the prompt distribution, and model scale. We use the entropy of the policy's output distribution as a lens to compare the distributions learned through pretraining, SFT, and RL post-training, revealing how each stage shapes model certainty. Our investigation sheds light on how these choices interact to affect post-training success. For example, we show that the effect of so-called 'spurious rewards' depends on the prompt distribution used for post-training. We also provide insight into why the success of RL post-training depends on whether the base model already places sufficient probability mass on the desired behavior, linking it to the classical concept of exploration in RL. Ultimately, we provide this primer as a resource to those in the NLP community wishing to incorporate RL as a tool in their toolbox.

AI 总结：针对LLMs生成高风险气象文本时虚构数值的问题，研究提出AFDBench基准，采用GRPO优化7B参数模型，提升其生成专业气象讨论的风格契合度与数据保真度。

链接：https://arxiv.org/abs/2608.24954

机构：Western Kentucky University（西肯塔基大学）； University of Texas at Austin（德克萨斯大学奥斯汀分校）； RediMinds Inc.（睿智公司）

作者：Manmeet Singh, Somnath Luitel, Prabhjot Singh, Manraaj Banga, Naveen Sudharsan, Josh Durkee

英文摘要：Large language models (LLMs) hallucinate numerical values when generating high-stakes meteorological text, posing risks for weather communication. We present AFDBench, an AI meteorologist that generates professional Area Forecast Discussions (AFDs) by reasoning through structured AI weather forecast data from Google's WeatherNext 2. We introduce AFDBench, the first benchmark for evaluating generative meteorological reasoning, comprising 7,732 expert written discussions from 13 National Weather Service (NWS) offices paired with real AI weather forecast inputs, and three complementary metrics: Met-Align (numerical accuracy), Style-Align (professional dialect adherence), and Input-Grounding (fidelity to source weather data). Zero-shot evaluations reveal that open-source LLMs achieve low Style-Align (~0.33) and moderate Input-Grounding (~0.88), failing to write in the professional NWS register or faithfully use their input data. We apply Group Relative Policy Optimization (GRPO) with domain-specific rewards targeting temperature accuracy, synoptic correctness, and format compliance. On 1,033 held-out samples from two unseen NWS offices, GRPO nearly doubles Style-Align from 0.318 to 0.619 and improves Input-Grounding from 0.881 to 0.940, demonstrating that reinforcement learning teaches a 7B-parameter model to write like a professional meteorologist and faithfully interpret AI weather data.

AI 总结：该研究提出基于贝叶斯流网络（BFNs）的BFN-RL框架，可在单一概率公式内建模离散与连续轨迹空间，经实验验证其能在两类状态空间生成有效轨迹，为离线轨迹规划提供通用生成基础。

链接：https://arxiv.org/abs/2608.25163

机构：Norwegian University of Science and Technology（挪威科技大学）

作者：Ludvig Killingberg, Helge Langseth

英文摘要：Offline reinforcement learning (RL) leverages static datasets to learn decision policies without real-time environment interaction. While recent sequence-modeling approaches rely on continuous diffusion models for trajectory synthesis, applying these methods to discrete planning tasks requires a categorical formulation rather than the standard Gaussian construction. We present BFN-RL, a unified generative modeling framework for offline RL based on Bayesian Flow Networks (BFNs). By iteratively evolving distribution parameters rather than noisy data instances, BFN-RL natively models both discrete and continuous trajectory spaces within a single probabilistic formulation. The categorical planner generates future state sequences, and a learned inverse-dynamics model converts consecutive generated states into actions. Evaluations in discrete planning and continuous control show that BFN-RL can generate effective trajectories across both categorical and continuous state spaces. Our results establish BFNs as a versatile generative foundation for offline trajectory planning across data modalities.

AI 总结：本研究提出基于GRPO的贝叶斯真理血清奖励机制，在无标签情况下微调LLM，有效降低其奉承倾向，提升压力下的回答准确率，效果优于SMART。

链接：https://arxiv.org/abs/2608.25267

机构：Cornell University（康奈尔大学）； Center for Applied Mathematics（应用数学中心）； Department of Electrical and Computer Engineering（电气与计算机工程系）

作者：Serhii Mytsyk, Yiming Zhang, Vikram Krishnamurthy

英文摘要：Large language models (LLMs) frequently exhibit \emph{sycophancy}: they adapt their answers to a user's stated beliefs or preferences instead of reporting what they hold to be true, which lowers factual accuracy and can amplify misinformation. This paper proposes a methodology for mitigating sycophancy that employs the Bayesian Truth Serum (BTS), a peer-prediction mechanism, as the reward in Group Relative Policy Optimization (GRPO) to fine-tune an LLM. BTS pays an answer for being \emph{surprisingly common}, that is, more frequent among respondents than those respondents themselves predicted. We treat a group of responses from a model for one question as those respondents, so the reward is a function of the model's own outputs and fine-tuning needs neither labels nor preference annotations. We prove that in the large-group limit a sycophantic response earns strictly lower expected reward than an honest one. We also prove that if the entire group agrees in advance on a symmetric answering rule, it cannot earn a higher information score than under truthful reporting. On our true/false benchmark the reference model's answer-flip rate under user pressure decreases from 23% to 4%, and its accuracy under that pressure increases from 80% to 93%. Our reward outperforms SMART and is comparable to synthetic-data fine-tuning and to pinpoint tuning, all three of which train on labels. It spends considerably more compute in exchange, which makes it suitable when labeled data is scarce. Peer Truth Serum, which also pays a premium for a rare answer but elicits no prediction report, reproduces the effect. A peer-prediction reward computed inside a single GRPO group therefore reduces sycophancy without labels, and comparing mechanisms suggests that the premium paid for a rarer answer drives the effect.

AI 总结：本研究提出首个结合视觉-语言模型生成偏好与普拉科特-卢斯模型的列表式奖励学习框架，在Meta-World操纵任务中，其表现与基线相当且更灵活，最佳配置达86%平均成功率。

链接：https://arxiv.org/abs/2608.25350

作者：Srivalli Katkuri, Maxwell Kawada, Juan Wachs

英文摘要：Vision-language models (VLMs) have emerged as a powerful source of supervision for reinforcement learning, enabling agents to leverage rich semantic knowledge during training. Inspired by the success of preference-based reward learning (PbRL) in reinforcement learning from human feedback (RLHF), vision-language model generated image-based preferences provide an effective source for learning reward functions. This can be done by visually comparing two outcomes through the Bradley-Terry (BT) model. However, this pairwise formulation utilizes only two observations at a time, despite VLMs being capable of ranking multiple candidates. The Plackett-Luce (PL) formulation can shape a reward model with listwise rankings as opposed to pairwise preferences, allowing for a more suited use of a VLM based ranking. In this work, to our knowledge, we introduce the first framework that combines VLM-generated preferences with the Plackett-Luce model for reward learning. We evaluate our approach on Meta-World manipulation tasks and show that Plackett-Luce (PL) reward models can train robotic policies from VLM-generated rankings as effectively as pairwise Bradley-Terry, $K$-wise Bradley-Terry, and RL-VLM-F baselines. Across all environments, at least one PL ranking size ($K \in \{3,4,5\}$) consistently performs with or outperforms other methods in mean success rate. Unlike pairwise methods, which are restricted to $K=2$, PL supports different ranking sizes and can therefore be adapted to the environment and desired feedback format. Our best PL configuration achieves an 86% mean final success rate and matches the Oracle baseline on Drawer Open. Overall, these results demonstrate that listwise VLM preference supervision is a competitive and flexible approach to reward learning for reinforcement learning.

AI 总结：本文针对电商搜索中长期用户价值建模的粒度对齐问题，提出DCEO框架，通过演员-评论家结构优化相对因果效应，在线A/B测试中GMV较传统方案提升0.36%。

链接：https://arxiv.org/abs/2608.25635

机构：Taobao & Tmall Group of Alibaba（阿里巴巴淘宝天猫集团）

作者：Junzhao Zhang, Tao Zhang, Liren Yu, Feiyi Dong, Zhixuan Zhang, Dan Ou, Haihong Tang

英文摘要：Industrial e-commerce search systems ultimately aim to optimize the user-level long-term objective, such as n-day cumulative purchases or gross merchandise value (GMV) per user. However, such objectives are defined at the user level, whereas search ranking is based on item-level scores within each request. Existing methods typically bridge this granularity gap through manually designed multi-objective fusion, where predictions of multiple item-level objectives, such as clicks, carts, purchases, and transaction value, are combined into a ranking score that serves as a proxy for the ultimate objective. Such hand-crafted fusion schemes rely on a small set of manually tuned weights, limiting fine-grained personalization and leading to suboptimal alignment with the ultimate objective. In this paper, we propose DCEO (Direct Causal Effect Optimization), a data-driven framework for learning item-level proxy scores that are better aligned with the ultimate objective. We first aggregate the item-level proxy scores into a user-level proxy metric and quantify its alignment with the ultimate objective using a relative causal effect. We then develop an actor-critic framework, where the critic estimates the ultimate objective for a given user-level proxy metric, and the actor dynamically generates context-dependent fusion weights over multiple objectives to construct the item-level proxy scores and is trained to directly optimize the relative causal effect. Extensive offline experiments and analyses demonstrate the effectiveness and interpretability of DCEO. In addition, DCEO has been deployed in a large-scale industrial e-commerce search system, outperforming the conventional GMV proxy by 0.36% in GMV in a 41-day online A/B test.

AI 总结：本文提出TailSFT过滤式微调算法，可提升模型后强化学习性能，在OLMo-3 7B上数学与代码评估pass@16最高提17%，后续GRPO的pass@1最高提4%，还引入轻量诊断方法识别适用场景。

链接：https://arxiv.org/abs/2608.25756

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

作者：Sadhika Malladi, Samy Jelassi, Dylan Foster, Jordan T. Ash, Akshay Krishnamurthy

英文摘要：Reinforcement learning post-training drives reasoning and agentic capabilities in modern AI systems, yet a growing body of work shows that it is most effective when used to fine-tune an already capable base model. We question whether existing pipelines yield models that are most suitable for reinforcement learning. Building on prior work highlighting the role of coverage and pass@K as predictors of post-RL performance, we design a simple modification to supervised fine-tuning, TailSFT, which filters out already fit sequences during training, thereby focusing learning on under-modeled regions, or the tail, of the data distribution. We justify and validate the design choices in TailSFT, particularly the specific filtering criteria, through a combination of controlled experiments and theoretical analysis. On OLMo-3 7B, TailSFT often improves pass@16 performance on math and coding evaluations, with gains up to 17% absolute, while incurring minimal computational overhead. These higher-coverage checkpoints consistently translate to up to 4% absolute pass@1 gains in subsequent GRPO runs, demonstrating that TailSFT checkpoints serve as better initializations for RL. We further introduce a lightweight diagnostic for identifying settings where TailSFT is most likely to help. More broadly, our results motivate a principled, stage-aware approach to model development, in which intermediate checkpoints are judged by how effectively they support subsequent training.

AI 总结：针对非独立同分布数据半监督联邦学习的挑战，提出pFedMARL方法，利用多智能体强化学习动态调整聚合策略，提升模型准确率、鲁棒性与公平性，性能优于FedAvg等方法。

链接：https://arxiv.org/abs/2608.25794

机构：Institute of Communication Acoustics, Ruhr-Universität Bochum（鲁尔大学波鸿分校通信声学研究所）

作者：Rene Glitza, Luca Becker, Rainer Martin

英文摘要：Federated Learning (FL) enables distributed training of machine learning models while preserving data privacy. However, FL struggles with heterogeneous, non-IID client data distributions, resulting in sub-optimal and biased global models. In this paper, we propose pFedMARL, a novel approach leveraging Multi-Agent Reinforcement Learning (MARL) with Twin Delayed Deep Deterministic Policy Gradient (TD3) to dynamically adapt aggregation strategies in FL settings. Our method employs a server-side agent adjusting client contributions to optimize global model robustness and client-side agents balancing global and local updates to personalize models effectively without pre-training. We demonstrate superior performance of pFedMARL for training a semi-supervised audio spectrogram transformer, matching or outperforming FedAvg, Ditto, and local training approaches across multiple non-IID scenarios and in the presence of adversarial clients. Our results indicate that pFedMARL actively improves accuracy, robustness, and fairness, making it suitable for real-world deployments.

AI 总结：本综述针对在线策略自蒸馏（OPSD）存在的推理路径崩溃问题，从信号加权、特权信息性质、指导衰减三个杠杆展开分析，以数学推理为范围，提供统一术语并区分已确定与争议内容。

链接：https://arxiv.org/abs/2608.25936

机构：OVHai LLM（OVHai大模型）

作者：Justin Robert, Raheel Qader

英文摘要：On-policy distillation trains a language model on its own generations while a teacher scores them token by token. It combines the dense supervision of imitation learning with the on-policy sampling of reinforcement learning. But it requires a second, larger model to act as teacher. On-Policy Self-Distillation (OPSD) removes that cost. The teacher is the model itself, conditioned on privileged information the student will not have at test time, such as a reference solution, a plan, or environment feedback. The teacher is no stronger than the student, only better informed. Early results were promising, with accuracy comparable to reinforcement learning at a fraction of the generated tokens. But the same asymmetry that produces the signal also biases it. One failure mode now dominates the field: collapse, the progressive narrowing of the set of reasoning paths the model can produce. Collapse is not specific to OPSD, though privileged information aggravates it. This review treats collapse as a symptom governed by three levers: (i) where the signal is applied, that is, how tokens are weighted; (ii) what the teacher is shown, that is, the nature of the privileged information; and (iii) when the signal changes, that is, the teacher's dynamics and the decay of guidance. We restrict our scope to mathematical reasoning, where the method originated and where its failure modes are best documented. We report no new experiments. The contribution is structural: a shared vocabulary for phenomena named differently across papers, and a clear line between what is settled and what is still disputed.

AI 总结：EXAONE Tabular 1.0 是一款紧凑表格基础模型系列，通过重新设计架构实现高效表格上下文学习，在多个公开基准测试中展现出优于同类模型的预测性能与推理效率。

链接：https://arxiv.org/abs/2608.25774

机构：LG AI Research（LG AI研究院）

作者：Moonjung Eo, Min-Kook Suh, Hye-Seung Cho, Jiwon Kim, Seoyoon Kim, Sangjun Nam, Soonyoung Lee

英文摘要： EXAONE Tabular is a compact tabular foundation model family for classification and regression via in-context learning, producing predictions without dataset-specific gradient updates. Pretrained exclusively on a synthetic structural-causal-model (SCM) prior, its central contribution is an architecture-centered redesign of tabular in-context learning. Rather than compressing features into a fixed row embedding before a separate row-level learner, EXAONE Tabular interleaves feature-axis attention within each item with support-conditioned item-axis attention within each feature at every Transformer layer, mediated by item-summary and feature-summary tokens. Across four public benchmarks, EXAONE Tabular combines strong predictive performance with high efficiency. On TabArena, its 20.81M-parameter classification model ranks first overall, surpassing tuned ensembles and 4-hour AutoML pipelines, while regression reaches the performance regime of the 1.64B-parameter TabFM at roughly 1/11 the inference cost. On BCCO and TALENT, EXAONE Tabular ranks second in classification and first in regression. On ScoringBench, it achieves the best mean rank for both point-estimation and predictive-distribution quality, leading the $R^2$, RMSE, and CRPS evaluations. Together, these results establish EXAONE Tabular as a state-of-the-art compact tabular foundation model family, combining strong predictive performance across classification, point regression, and probabilistic regression with an efficient model design.

AI 总结：本研究针对数字移动性结局跨疾病纵向建模的缺口，提出可解释框架DeMMO，其通过自动跨疾病跨结局关系学习机制实现选择性信息共享，在Mobilise-D数据集上优于9种基线，性能显著提升。

链接：https://arxiv.org/abs/2608.25073

机构：School of Computer Science, University of Sheffield（谢菲尔德大学计算机学院）

作者：Menghui Zhou, Zhipeng Yuan, Vitaveska Lanfranchi, Po Yang

英文摘要：Digital mobility outcomes (DMOs) derived from wearable sensors characterise mobility in daily life and offer a promising means of monitoring disease progression. Yet most DMO studies examine one disease at one visit; they do not model how multivariate DMO relationships with multiple clinical outcomes evolve jointly across diseases. Technically, existing temporal multi-task frameworks can model progression within an individual disease, but they do not jointly model multiple prediction outcomes across diseases, particularly when disease cohorts do not share participants. To address these gaps, we propose DeMMO, an interpretable framework for longitudinal, multi-disease, and multi-outcome learning. DeMMO represents each disease-outcome objective by a longitudinal DMO coefficient matrix and combines temporal regularisation with stable and visit-specific feature selection. Its central technical contribution is an automatic cross-disease and cross-outcome relation-learning mechanism that learns signed relations directly from these longitudinal mappings, enabling selective information sharing without paired participants. We evaluate DeMMO on the recently released, large-scale, multicentre Mobilise-D dataset, which provides a new opportunity to study 24 harmonised real-world DMOs over five visits across multiple mobility-limiting conditions. Against nine strong linear, longitudinal, and deep-regression baselines, DeMMO achieves the best overall and outcome-specific prediction performance, with significant improvements over the strongest baselines. Stability selection further identifies reliable longitudinal DMO patterns for subsequent clinical validation and disease monitoring. The implementation code and experimental results are available at this https URL.

AI 总结：该研究提出原生多尺度算子学习的框架核方法，用于多尺度PDE代理建模，其精度优于流行神经算子，可实现后验多尺度分解。

链接：https://arxiv.org/abs/2608.25084

机构：Kahlert School of Computing, University of Utah（犹他大学卡勒特计算机学院）； U.S. Air Force Research Laboratory（美国空军研究实验室）

作者：Branden Frieden, Ryan Whitehead, M. Keith Ballard, Robert M. Kirby, Varun Shankar

英文摘要：We present a natively multiscale operator learning method for the surrogate modeling of (numerical solvers for) multiscale partial differential equations (PDEs). The primary novelty of our method lies in a novel multiscale kernel frame function approximation technique. Leveraging this new kernel frame technique, we cast the operator learning problem as one of learning frame coefficients of output functions as a function of frame coefficients of input functions. The generalization step then automatically allows for a multiscale decomposition of the output functions. Our method is applicable to both tensor-product grids and point clouds. We present interpolation proofs, error estimates, and numerical convergence rates for our frame approximation. We the demonstrate the applicability of our method for the surrogate modeling of inherently multiscale PDEs. The new multiscale frame kernel method is significantly more accurate than popular neural operators on challenging problems from the literature, while simultaneously admitting an a posteriori multiscale decomposition upon generalization.

AI 总结：针对高维黑箱函数优化的查询效率问题，提出GRAPE两阶段框架，经理论与实验验证，在黑箱对抗攻击和大语言模型提示优化任务中表现优于基线方法。

链接：https://arxiv.org/abs/2608.25116

机构：School of Artificial Intelligence（人工智能学院）； The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））

作者：Richard Cornelius Suwandi, Feng Yin

英文摘要： Optimizing expensive, high-dimensional black-box functions remains a central challenge in modern machine learning and scientific discovery. While local Bayesian optimization mitigates the curse of dimensionality, existing techniques often prioritize the probability of descent over the magnitude of progress. This leads to overly conservative steps that yield negligible improvement, wasting queries on directions that are nearly certain to descend but offer little decrease. We introduce Gradient Refinement and Progress-Aware Exploitation (GRAPE), a two-stage framework that first sharpens the local gradient posterior via a closed-form acquisition function, then selects update directions by maximizing the expected decrease conditional on descent. Theoretical analysis proves that this gradient refinement stage monotonically minimizes local uncertainty and that the progress-aware direction converges to true steepest descent as the posterior sharpens. Empirically, GRAPE demonstrates superior query efficiency across high-dimensional tasks: in black-box adversarial attacks, it achieves an average 5.4$\times$ speedup over baselines, and on large language model prompt optimization tasks, it outperforms the second best method by a reduction of 3.8 log-units in the final average regret.

AI 总结：该研究解决了不可知多类直推学习的极小极大速率问题，证明其与不可知多类PAC学习遵循相同的双维法则，给出了最优超额误差的上界及必要条件。

链接：https://arxiv.org/abs/2608.25326

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

作者：Pahan Dewasurendra

英文摘要：In transductive classification, an adversary fixes a labeled population, one label is hidden uniformly, and the learner sees all remaining labels. For binary classes, agnostic transductive and PAC learning have the same minimax rate. Whether this extends to multiclass learning was open, especially for unbounded label spaces where uniform convergence can fail. We resolve the question up to logarithmic factors. For every multiclass class $\mathcal H$ with DS dimension $d_{DS}$ and Natarajan dimension $d_{\mathrm N}$, the optimal agnostic transductive excess error satisfies $\widetilde\Theta\left(\frac{d_{DS}}{n}+\sqrt{\frac{d_{\mathrm N}}{n}}\right).$ The result holds for arbitrary label spaces. The two terms are both necessary. A DS pseudo-cube gives the realizable $d_{DS}/n$ obstruction, while a Natarajan cube with repeated points and fair labels gives the agnostic $\sqrt{d_{\mathrm N}/n}$ obstruction. The upper bound uses a random-reservation principle. The learner deliberately ignores a constant fraction of the visible labels, which makes the true test point uniform in a large unseen block. We combine realizable compression, a label-space reduction, and inside-menu agnostic compression across this finite-population split. A new without-replacement multiplicative-weights lemma preserves the fast $d_{DS}/n$ term. Consequently, agnostic multiclass PAC and transductive learning obey the same two-dimension law up to logarithmic factors.

AI 总结：该研究针对强凸随机优化，提出轨迹自适应停止规则，构建相关置信序列与不等式，将其扩展至小批量SGD，实验显示该规则所需迭代次数远少于确定时间范围。

链接：https://arxiv.org/abs/2608.25551

机构：UC Berkeley（加州大学伯克利分校）； Inria（法国国家信息与自动化研究所）； École Normale Supérieure（巴黎高等师范学院）； PSL Research University（巴黎文理研究大学）； Department of Statistics, UC Berkeley（加州大学伯克利分校统计系）

作者：Liviu Aolaritei, Lucas Lévy, Francis Bach, Michael I. Jordan

英文摘要：Stochastic gradient descent (SGD) is typically analyzed at a deterministic horizon chosen before the algorithm is run, even though practical stopping decisions are made adaptively by inspecting the evolving trajectory. This mismatch creates a fundamental certification problem: fixed-time guarantees do not generally remain valid at data-dependent stopping times, while deterministic horizons derived from worst-case bounds can be highly conservative. We address this problem for strongly convex stochastic optimization by constructing fully observable, trajectory-adaptive upper confidence sequences for the squared distance of the last iterate to the optimizer and the suboptimality of a weighted average. These bounds hold simultaneously over time, attain the optimal $1/t$ decay rate up to iterated-logarithmic factors in the worst case, and adapt to the realized stochastic gradients, allowing SGD to stop as soon as a prescribed accuracy is certified without sacrificing statistical validity. Our approach treats the evolving SGD trajectory as a sequential experiment whose observations provide evidence about the unknown optimization error. To formalize this perspective, we develop new recursive confidence-sequence techniques and a general time-uniform empirical Bernstein inequality for adapted processes with time-varying conditional means and predictable ranges that may grow without bound. We further extend these confidence-sequence constructions to minibatch SGD, with the empirical Bernstein bounds exploiting the realized second-moment structure within each minibatch. Numerical experiments show that the resulting stopping rules can require several orders of magnitude fewer iterations than natural deterministic horizons.

AI 总结：该研究将 Grokking 作为动态探测工具，通过扫描权重衰减脉冲，发现功能选择的 canalization 现象，即剂量有序时间效应在可见泛化前出现，且测试损失障碍收敛时该效应仍持续。

链接：https://arxiv.org/abs/2608.25813

机构：School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）

作者：Yiming Lin

英文摘要：For overparameterized neural networks, many solutions can fit the training data equally well while behaving very differently on unseen samples. Grokking separates training fit from visible generalization, providing a window for studying how this selection develops during training. We sweep short, fixed-duration weight-decay (WD) pulses across this plateau and measure how they shift later generalization time. Across three grokking tasks, these shifts are unordered early in the plateau but later form a stable dose ordering, with stronger WD increases leading to earlier generalization and stronger WD decreases leading to later generalization. This ordering emerges before visible generalization in all three tasks. Meanwhile, test-loss barriers between perturbed and baseline generalization checkpoints collapse toward zero while the ordered timing effects persist. We call this combination of increasingly constrained solution selection and persistent dose-ordered timing sensitivity the canalization of function selection.

AI 总结：本文通过频谱分析揭示Muon优于Adam的机制，提出SAMuon及其简化版SAMuon-lite，在多规模modded-nanogpt模型上，二者均优于AdamW和Muon，且SAMuon可减少13.3%-24.0%训练令牌。

链接：https://arxiv.org/abs/2608.25990

机构：University of Cambridge（剑桥大学）； Tsinghua University（清华大学）

作者：Xiaodong Wu, Wenyi Yu, Chao Zhang, Philip Woodland

英文摘要：Orthogonal optimisers such as Muon can substantially accelerate large language model pretraining relative to Adam, yet the mechanism remains incompletely understood. We investigate this through an out-of-sample spectral probing analysis of Transformer loss landscapes. At checkpoints along real training trajectories, we decompose each momentum buffer into its singular directions and estimate the loss-optimal step size along each direction on held-out data. The resulting spectral profile is anisotropic yet stable across batches and training stages, and consistent across the optimisers and model scales: a volatile head operating at the Edge-of-Stability supports a much smaller step size than the tolerant bulk, which permits substantially larger steps. This profile provides a unified spectral allocation account of why Muon outperforms Adam, which outperforms SGD. It also exposes a limitation of Muon's uniform scaling: it still underutilises the bulk. Guided by this finding, we introduce Spectral-Aware Muon (SAMuon), which holds the head at the Muon scale and amplifies the bulk using a static spectral prior. We provide two variants: the complete SAMuon follows the measured profile using a low-rank randomised SVD and the simplified SAMuon-lite uses a two-level approximation via rank-one power iteration. Neither method adds persistent optimiser state or notable extra FLOPs beyond Muon at scale, and the idealised exact-whitening versions of both retain Muon's asymptotic convergence rate under standard assumptions. Across "modded-nanogpt" models from 124M to 1B parameters, both variants outperform tuned AdamW and Muon (Scion implementation) baselines in all evaluated model-scale and batch-size configurations. SAMuon requires 13.3% to 24.0% fewer training tokens to reach the same validation loss as Muon, while SAMuon-lite retains most of this gain with near-zero wall-clock overhead.

AI 总结：本研究针对单IMU活动识别的部署负担问题，提出动态影响加权（DIW）知识蒸馏方法，利用训练阶段的多IMU信息提升单IMU学生模型性能，在WEAR数据集上取得显著效果。

链接：https://arxiv.org/abs/2608.24904

机构：South China Normal University（华南师范大学）

作者：Bingxuan Xie

英文摘要：Inertial sensors at multiple body locations can improve activity recognition, but requiring every sensor at inference increases the deployment burden. We study whether four synchronized IMUs available during training can improve a student that uses only the right-arm IMU during fitting and inference. A frozen four-IMU teacher provides logit and feature targets. Fixed-weight knowledge distillation applies each target with the same strength to every fitting sample, although the student may not benefit equally from them. We introduce dynamic influence weighting (DIW), which tests a one-step candidate update on separate fold-internal training participants. DIW then assigns separate sample-wise gates to the logit and feature losses. On WEAR, we evaluate 19 labels and 68,298 complete windows from 22 participants using subject-disjoint five-fold cross-validation. Pooled out-of-fold macro-F1 is 0.561820 for Supervised and 0.571623 for Fixed-weight KD. DIW reaches 0.638451, gains of 7.66 and 6.68 percentage points, respectively. It exceeds Supervised for 18 of 19 labels and 21 of 22 held-out participants. All three routes retain the same 80,915-parameter right-arm student at inference. Under this protocol, DIW converts training-only multi-position information into a stronger single-IMU model without changing deployed sensing or the student forward graph.

AI 总结：本研究提出参数0.6B的GreenLeaf Law Embed Tiny法律领域检索嵌入模型，通过两阶段训练等方法，在相关基准取得优异成绩，可部署于资源受限环境。

链接：https://arxiv.org/abs/2608.24936

机构：JudicialMind（司法思维机构）

作者：Surya Saka

英文摘要：We present GreenLeaf Law Embed Tiny, a 0.6B parameter embedding model for legal domain retrieval. GreenLeaf-Tiny achieves 75.11% on the Massive Legal Embedding Benchmark (MLEB) and 64.38% on MTEB(Law, v1),demonstrating competitive performance among models under 1B parameters. Our approach combines a two-stage training pipeline that first distills knowledge from a larger teacher model into a compact student architecture, then applies domain-specific fine-tuning with hard negative mining; a carefully curated dataset of 3.4 million query-passage pairs, including 150,000 human-curated samples across diverse legal jurisdictions; and an efficient inference architecture supporting multiple quantization levels (BF16, INT8, binary) enabling deployment in resource-constrained environments. We provide detailed analysis of our training methodology, architectural choices, and comprehensive evaluation across legal retrieval tasks. Our results demonstrate that domain-specific training with high-quality data can improve performance for specialized domain applications

AI 总结： 该研究针对KV缓存驱逐规则，通过分析168192个注意力行的最优子集情况，提出无需训练的分配器ContourKV，其在配对比较中表现优于多数现有技术，且与最强基线持平。

链接：https://arxiv.org/abs/2608.25230

机构：Stanford University（斯坦福大学）

作者：Jack Shi, Jerry Gu

英文摘要：Every deployed sparse-attention or KV-cache-eviction rule keeps a subset of the keys, discards the rest, and renormalizes the attention weights over the kept set. Enumerating the exact best subset under that constraint on $168{,}192$ attention rows from five models shows that keeping the largest weights is already near-optimal, since the best subset closes only a median $2$ to $5\%$ of the remaining gap to full attention. If selection closes this little, published margins between eviction methods must come from elsewhere, so we measure the bytes each method holds. In the shared evaluation pipeline, the strongest query-agnostic methods hold the full cache because their per-head selections are stored as masks, and only ragged per-head storage frees that memory. Enforcing a nominal budget on one fixed selection costs $14$ to $62$ benchmark points. We trace an $87.6$-point retrieval margin to rankings computed while the question is visible. ContourKV, a training-free allocator built from the dropped-mass statistic, wins $93$ of $160$ paired comparisons against that state of the art and loses $22$ at the byte count of the budget-enforcing baselines, and it ties the strongest of them.

AI 总结：本文提出无需训练的Reflection Steering框架，通过解耦反射与推理的激活实现高效令牌推理，可减少16.9%推理令牌，还引入参数α平衡令牌节省、准确率与生成稳定性。

链接：https://arxiv.org/abs/2608.25542

机构：School of Computing and Data Science, The University of Hong Kong（香港大学计算与数据科学学院）； Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算学院）； School of Data Science, Lingnan University（岭南大学数据科学学院）； Centre for Learning, Teaching and Technology, The Education University of Hong Kong（香港教育大学学习、教学与技术中心）

作者：Jiarui Hu, Zhiyuan Wen, Xiaoyun Liu, Jiaxing Shen, Yu Yang

英文摘要：Large reasoning models often produce reasoning traces with verification, revision, and backtracking. When reflection merely re-checks established results, it wastes reasoning tokens and increases latency. Most existing reflection steering methods add a label-derived mean-difference direction across preset layers, but its entanglement with reasoning and length signals destabilizes the accuracy-efficiency trade-off. In this paper, we propose Reflection Steering, a training-free framework for controlling reflection-associated computation within LLMs by disentangling reflection-related activations from general reasoning. Specifically, we contrast reflective and non-reflective hidden states at each LLM layer, denoise the resulting reflection directions with PCA, and orthogonalize them against general-reasoning directions. To limit downstream amplification from early-layer interventions, we calibrate each layer across multiple intervention strengths on a small set, retain only stable layers, and apply bounded projection removal to their residual-stream activations. We conduct extensive experiments across two public benchmarks and three open-weight LLMs against state-of-the-art activation-steering baselines. Results show that Reflection Steering reduces reasoning tokens by 16.9% on average across six matched settings. Besides, our method further introduces a bounded reflection intervention-strength parameter $\alpha$, enabling deployment-time adjustment to balance token savings, accuracy, and generation stability.

AI 总结：针对大核CNN中逐点卷积占比过高导致边缘部署瓶颈的问题，提出通道组共享低秩近似方法，在保持性能的同时降低存储成本，实现大核CNN的边缘高效部署。

链接：https://arxiv.org/abs/2608.26069

机构：Northwestern Polytechnical University（西北工业大学）； Nanchang University（南昌大学）； China Mobile Chengdu Institute of Research and Development（中国移动成都研究院）； Hong Kong University of Science and Technology（香港科技大学）； Institute of AI for Industries, Chinese Academy of Sciences（中国科学院人工智能产业研究院）； University of Electronic Science and Technology of China（电子科技大学）

作者：Hao Luo, Yiting Yang, Wenyi Zhao, Man Jiang, Zhijun Lin, Ghulam Mohiuddin, Ting Jiang, Kunming Luo, Zihao Zhang, Qingsen Yan, Guoqing Wang, Wei Dong, Peng Wang

英文摘要：Large-kernel Convolutional Neural Networks (CNNs) deliver remarkable performance in vision tasks by significantly expanding receptive fields, yet their quadratic parameter growth critically impedes storage-efficient edge deployment. While existing efficient architectures adopt parameter-efficient depthwise separable convolution backbones that leverage techniques like low-rank approximation and weight sharing to compress depthwise convolutions, we identify a critical oversight: pointwise convolutions dominate parameter volume (>87% in models like RepLKNet-31B) and constitute the primary deployment bottleneck on resource-constrained edge devices. This results in prohibitive storage costs and severe memory-loading constraints on resource-limited devices (e.g., smartphones with 4-12 GB Random Access Memory (RAM)). To overcome this, we propose Channel Group-Shared (CGS) low-rank approximation, a novel Singular Value Decomposition (SVD)-based parameter-sharing strategy. CGS constructs a structured low-rank paradigm isomorphic to SVD decomposition, comprising shared (high-parameter-cost) down/up-projection matrices across channel groups within a layer and channel-group-specific (low-parameter-cost) scalable diagonal matrices. This group-sharing design achieves significant parameter reduction. Extensive experiments demonstrate that large-kernel CNNs (RepLKNet, ConvNeXt, SLaK) enhanced with CGS strike an empirically favorable balance between competitive performance and substantially reduced storage costs. Crucially, by alleviating storage constraints, reducing memory bandwidth pressure during loading, and minimizing model loading latency, CGS enables the feasible deployment of pre-trained large-kernel CNN models on edge devices, thereby bridging the gap between high-performance vision models and practical edge deployment.

AI 总结：Flower Hub是一款联邦学习基准测试平台，可将基准打包为可执行应用，支持跨仿真与部署运行，涵盖多领域任务，推动联邦学习基准测试向可复用方向发展。

链接：https://arxiv.org/abs/2608.25114

机构：Flower Labs； University of Cambridge（剑桥大学）； University of Auckland（奥克兰大学）； University of Melbourne（墨尔本大学）； Vector Institute； Fraunhofer IMS（弗劳恩霍夫应用固体物理与材料力学研究所）； NetCompany； Gachon University（嘉泉大学）； Owkin； Sony AI（索尼人工智能）

作者：Yan Gao, Mohammad Naseri, Javier Fernandez-Marques, Dimitris Stripelis, Lorenzo Sani, Davide Eynard, Fan Zhang, Hong Jia, Ting Dang, D. B. Emerson, Fatemeh Tavakoli, Ole Werger, Lars Wulfert, Petros Demetrakopoulos, Sofia Tsekeridou, InSeo Song, KangYoon Lee, Honghao Li, Lingjuan Lyu, John P Dickerson, Daniel Janes Beutel, Nicholas D. Lane

英文摘要：Federated learning (FL) has emerged as a key approach for training models across decentralized data, yet benchmarking in FL remains difficult to reproduce, compare, and extend. Existing evaluations are often tied to custom infrastructure, released as incomplete research code, and conducted primarily in simulation, which limits portability and practical relevance. We present Flower Hub, a platform for publishing, discovering, and executing decentralized and federated applications. We show how it enables reproducible benchmarking by packaging benchmarks as executable, versioned applications with standardized metadata, pinned dependencies, and explicit evaluation workflows. We instantiate this approach with a multi-domain benchmark suite spanning cross-silo and cross-device settings, and including tasks in medical imaging, financial tabular learning, legal instruction tuning, phishing URL detection, and audio tagging. We further demonstrate that the same benchmarking application can run across both simulation and deployment runtimes without changing the application code, enabling unified evaluation across varying learning environments. Beyond model quality, our benchmark design supports system-aware reporting, including runtime and communication metrics. This work advances benchmarking in FL settings from ad hoc code artifacts towards portable, executable, and reusable benchmark applications.

AI 总结：本文针对联邦学习场景，分析对抗样本的可迁移性，设计基于对抗训练的防御机制，经真实数据集验证其性能优于现有最先进方法。

链接：https://arxiv.org/abs/2608.25133

机构：University of Nevada Las Vegas（内华达大学拉斯维加斯分校）； Cyber Security Research Center at KAIST（韩国科学技术院网络安全研究中心）； Georgia State University（佐治亚州立大学）

作者：Zuobin Xiong, Deval Mukherjee, Homook Cho, Wei Li

英文摘要：The development of federated learning (FL) techniques has helped improve the privacy preservation of users' data and extended the applications of machine learning models. However, the involvement of a large number of users in FL also creates open opportunities for different adversaries, such as poisoning attacks, Byzantine attacks, and adversarial example attacks. Yet, recent research has disclosed that existing poisoning attacks and Byzantine attacks can not achieve satisfactory penetration in realistic FL scenarios caused by strong assumptions, \textit{e.g.,} client selection rate, and the ratio of malicious attackers. In this paper, the transferability of adversarial examples among different client models is analyzed to understand the relation between adversarial examples and clients' data distribution. Moreover, to mitigate the attacks of transferable adversarial examples, we design a defense mechanism stemming from the transferability of model robustness by adversarial training. As a result, through theoretical analysis of transferability, we gain insights into adversarial examples and the vulnerability of federated learning systems. Our proposed adversarial attack and defense methods are evaluated via real-life datasets in various settings to show their performance over the existing state-of-the-art methods.

AI 总结：本文提出QEF-GT-AdamW算法，结合梯度跟踪、AdamW优化与带误差反馈的双流偏置量化，解决无线分布式学习的通信开销与不可靠传输问题，在异构数据集上实现更优性能。

链接：https://arxiv.org/abs/2608.25535

机构：University of Luxembourg（卢森堡大学）； Interdisciplinary Centre for Security, Reliability and Trust (SnT)（安全、可靠性与跨学科信任中心（SnT））

作者：Nguyen Van Thieu, Ti Ti Nguyen, Ons Aouedi, Vu Nguyen Ha, Symeon Chatzinotas

英文摘要：Wireless Internet-of-Things (IoT) edge networks require decentralized learning (DecL) methods that can operate reliably under both heterogeneous local data and communication-constrained wireless links. However, existing decentralized optimization schemes often incur substantial communication overhead and degraded performance when transmissions are constrained by strict airtime budgets, fading channels, and packet losses. This paper proposes QEF-GT-AdamW, a communication-efficient and outage-resilient algorithm for DecL over wireless communication (WCom) networks. The proposed method combines gradient tracking to mitigate the effect of non-IID data, AdamW-based adaptive optimization to improve training stability, and dual-stream biased quantization with error feedback to reduce communication payloads for both model and tracking exchanges. To address unreliable broadcast communication, the proposed framework further employs a local fallback strategy when scheduled packets are not successfully received. We explicitly model the effect of bandwidth, transmit power, airtime constraints, and fading channels on DecL performance, and establish convergence guarantees for the proposed algorithm under compressed and unreliable wireless communication. Experimental results on heterogeneous MNIST and CIFAR-10 settings show that QEF-GT-AdamW consistently improves robustness and convergence performance over representative DecL baselines while achieving favorable accuracy-communication trade-offs under limited wireless resources.

AI 总结：本研究指出联邦优化中的稳定性边缘（EoS）和渐进锐化是SCAFFOLD性能弱于FedAvg的原因，发现EoS会导致SCAFFOLD估计全局梯度的能力严重下降。

链接：https://arxiv.org/abs/2608.25873

机构：Georgia Institute of Technology（佐治亚理工学院）； George Mason University（乔治梅森大学）； Flatiron Institute（弗拉蒂伦研究所）

作者：Anant Khandelwal, Michael Crawshaw, Mingrui Liu

英文摘要：In federated learning, it is well known that heterogeneous data can (in theory) slow down optimization, and much effort has been directed at designing optimization algorithms that are unaffected by data heterogeneity, such as the SCAFFOLD algorithm. Yet, despite strong theoretical guarantees, SCAFFOLD does not usually outperform the much simpler FedAvg in practice. In this work, we propose that this gap is due to the presence of Edge of Stability (EoS) and progressive sharpening in federated optimization, supported by extensive empirical probing. First, we find that EoS-like dynamics occur with both FedAvg and SCAFFOLD under a variety of architectures and hyperparameters. We observe that the equilibrium value of the sharpness is inversely proportional to the learning rate (as in GD), and interestingly, the degree of data heterogeneity (but not the number of local steps) also affects the equilibrium value. Most importantly, we observe that SCAFFOLD's ability to estimate the gradient of the global objective is severely degraded at the EoS, as measured by the correlation between sharpness and SCAFFOLD's error in estimating the global gradient along the optimization trajectory. This suggests a mechanism for SCAFFOLD's lackluster performance in deep learning: with high sharpness at the EoS, SCAFFOLD cannot reliably estimate the global gradient.

AI 总结：InsightSR是嵌入PySR遗传编程引擎的框架，通过LLM的语义与结构引导优化符号回归搜索空间，在多个基准测试中性能优于现有方法且泛化能力强。

链接：https://arxiv.org/abs/2608.25291

作者：Yating Ling, Wenjing Cun, Zhitang Chen

英文摘要：Symbolic regression (SR) seeks to discover parsimonious mathematical laws from observational data, yet conventional approaches often struggle with the vast combinatorial search space of physically meaningful expressions. We present InsightSR, a framework that embeds Large Language Models (LLMs) as a guiding layer around the PySR genetic programming engine. Rather than relying on LLMs to generate expressions directly, InsightSR uses LLMs to progressively transform the search space itself through two complementary pathways: a Semantic Seed Pathway that proposes dimensionally consistent functional skeletons, and a Structural Feature Pathway that recommends nonlinear feature transformations. These transformations accumulate over iterations, broadening the input space and shifting the symbolic search from constructing deep expression trees over raw variables to assembling shallow trees over a rich, semantically informed feature set. A post-generation feedback loop evaluates candidates, categorizes features by their empirical utility, and refines the guidance for the next iteration, transforming the discovery process from open-ended generation into iterative, self-correcting refinement. Across three benchmarks, InsightSR achieves a 95% exact recovery rate on the Feynman benchmark and 80.18% accuracy on the LLM-SRBench LSR-Transform task, substantially outperforming state-of-the-art genetic programming and neural-symbolic methods while maintaining strong out-of-distribution generalization on real-world datasets.

AI 总结：针对线性模型易受隐蔽攻击的问题，提出基于检测器的切换模型，推导对抗风险凸公式，经数值模拟验证其在部分受攻击数据上性能更优。

链接：https://arxiv.org/abs/2608.25681

机构：Uppsala University（乌普萨拉大学）

作者：Lovisa Eriksson, Dave Zachariah, André M. H. Teixeira

英文摘要：Predictive models are widely used in many fields, but are vulnerable to false data injection attacks. To address this, detection schemes and adversarial training have been proposed, but such approaches lack guarantees against stealthy attacks. We therefore propose a detector-based switched model, in which optimal attack strategies are stealthy. For linear prediction models, we derive a convex formulation of the resulting adversarial risk. The model incorporates protected features and introduces a hyperparameter modelling attack probability, enabling an explicit performance trade-off between clean and attacked data regimes. Numerical simulations on real and synthetic data show improved performance on partially attacked data, even for misspecified attack probabilities.

AI 总结：本研究针对时间序列解释的现有方法存在的局限，提出统一信息瓶颈框架，引入ModelName，在合成与真实基准上均优于现有方法，可生成忠实归因与稳定反事实解释。

链接：https://arxiv.org/abs/2608.25897

机构：Florida International University（佛罗里达国际大学）； Carnegie Mellon University（卡内基梅隆大学）； University of Houston（休斯顿大学）； NEC Labs America（美国 NEC 实验室）； Singapore Management University（新加坡管理大学）

作者： Xu Zheng, Zichuan Liu, Zhuomin Chen, Mayur Akewar, Janki Bhimani, Jason Liu, Mo Sha, Jingchao Ni, Wei Cheng, Dongsheng Luo

英文摘要：Explaining deep learning models operating on time series data is crucial in various applications that require transparent and interpretable insights into model behavior. {Existing explanation methods generally fall into two categories: attribution-based explanations, which identify the temporal regions most responsible for a prediction, and counterfactual explanations, which reveal how an input should be modified to alter the model's decision.} {Despite valuable insights, these two fields are largely studied independently. This disconnect leaves attribution methods lacking causal validation, while counterfactual methods suffer from severe instability, producing adversarial-like noise instead of meaningful explanations.} In this work, we revisit time-series explainability from an information-theoretic perspective and show that existing explainers are vulnerable to trivial solutions and distributional shifts. To address these limitations, we propose a unified objective function for explainable time series learning that bridges attribution and counterfactual reasoning within a single framework. Building upon the Information Bottleneck principle, our formulation explicitly prevents trivial explanations and out-of-distribution counterfactuals. {Based on this objective function, we introduce {\modelname}, a novel explanation framework that learns a parametric transformation network to construct explanation-embedded instances, where preserved information yields attribution explanations and controlled information removal produces stable counterfactual explanations.} We evaluate {\modelname} on synthetic and real-world benchmarks against state-of-the-art baselines. Extensive quantitative and qualitative results show that {\modelname} consistently outperforms competing methods, yielding faithful attributions and stable counterfactual explanations.

AI 总结：该研究针对深度神经网络的捷径学习问题，提出ICON分解方法，通过量化概念在考虑其他概念及结果后的方差解释度，在合成数据及皮肤病变、脑成像模型上实现更准确的概念级解释，可用于模型审计。

链接：https://arxiv.org/abs/2608.26083

机构：Hertie Institute for AI in Brain Health, University of Tübingen（蒂宾根大学赫蒂脑健康人工智能研究所）； Charité - Universitätsmedizin Berlin（柏林夏里特医学院）； Humboldt-Universität zu Berlin（柏林洪堡大学）； Tübingen AI Center, University of Tübingen（蒂宾根大学蒂宾根人工智能中心）； German Center for Mental Health (DZPG)（德国心理健康中心）； Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希赫兹研究所）； Technische Universität Berlin（柏林工业大学）

作者：Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer, Marc-Andre Schulz, Nys Tjade Siegel, Maximilian Dreyer, Frederik Pahde, Wojciech Samek, Sonja Greven, Kerstin Ritter

英文摘要：Deep neural networks often exploit spurious associations in their training data, a failure known as shortcut learning. Concept-based explainability methods screen for shortcuts by testing whether concepts such as a patient's sex or scanner settings can be decoded from a network layer. Because each concept is evaluated in isolation, these methods can mistake correlations between concepts as evidence that the model uses them. We introduce ICON decomposition, which instead quantifies how much of a layer's variance each concept explains after accounting for all other concepts and the outcome. On synthetic data with known ground truth, ICON recovers concept importance more accurately than seven alternative baseline methods. On skin-lesion and brain-imaging models, it isolates the concepts on which a model genuinely relies, quantifies the representation unexplained by any of the supplied concepts, and yields sparse explanations that we validate by retraining and out-of-distribution testing.

AI 总结：该研究针对混合整数线性规划（MILP）解预测的一次性范式缺陷，提出SHSP框架，采用分层条件解码与置信度掩码修复机制，在四个基准上使解间隙平均降低54%，性能优于现有方法。

链接：https://arxiv.org/abs/2608.25282

机构：State Key Laboratory of Novel Software Technology, Nanjing University（南京大学 现代软件工程国家重点实验室）； School of Artificial Intelligence, Nanjing University（南京大学 人工智能学院）； State Key Laboratory of Technology and Equipment for Defense Against Power System Operational Risks, Nari Technology Co., Ltd.（南瑞科技股份有限公司 电力系统运行风险防御技术与装备国家重点实验室）

作者：Zherong Zhang, Guanlin Li, Chengrui Gao, Haopu Shang, Ke Xue, Jixiang Lu, Weiyong Yang, Chao Qian

英文摘要：Mixed-Integer Linear Programming (MILP) is a fundamental optimization paradigm in combinatorial optimization and has been widely applied across real-world domains. Due to its NP-hard nature, obtaining optimal solutions for large-scale or highly constrained MILP instances remains computationally prohibitive. Learning-based solution prediction has therefore emerged as a promising approach to provide high-quality variable assignment for solver acceleration. However, existing methods typically adopt a one-shot prediction paradigm that predicts the marginal probabilities of all variables simultaneously. As a result, the conditional dependencies among variables are only implicitly captured through message passing, with the burden of modeling the combinatorial structure falling entirely on the representational capacity of graph neural networks. To address this limitation, we propose the Structure-Aware Hierarchical Solution Prediction (SHSP) framework that replaces the parallel marginal decoding of one-shot methods with a novel hierarchical conditional decoding mechanism. Specifically, SHSP constructs a variable coupling graph from the constraint structure, decodes variables sequentially along a hierarchy of increasing coupling strength, and conditions each hierarchy on previously predicted assignments. To mitigate error accumulation during the decoding process, SHSP further incorporates a confidence-aware mask-and-repair mechanism to identify and correct unreliable intermediate predictions. We integrate SHSP with multiple learning-guided search methods, and evaluate it on four standard MILP benchmarks. Experimental results demonstrate that SHSP significantly outperforms existing one-shot prediction baselines, achieving a 54% average reduction in solution gap.

AI 总结：本文通过5阶段统一框架评估LLM增强型GNNs的隐私风险，发现其隐私脆弱性高于浅层文本基线，差分隐私可部分缓解风险但会导致效用下降，凸显了该领域的隐私-效用权衡。

链接：https://arxiv.org/abs/2608.25727

机构：Beijing University of Posts and Telecommunications（北京邮电大学）

作者：Longzhu He, Zelang Wen, Chaozhuo Li, Sen Su

英文摘要：Large language models (LLMs) have recently advanced graph neural networks (GNNs) by enriching node representations with semantic information, giving rise to LLM-enhanced GNNs that achieve substantial performance gains. However, their vulnerability to privacy attacks, in which adversaries infer sensitive information from model outputs, remains largely underexplored. To bridge this gap, we present a systematic evaluation of privacy risks in LLM-enhanced GNNs through a unified framework consisting of five stages: (1) dataset preparation, (2) victim model training, (3) privacy attack, (4) risk assessment, and (5) defense analysis. Specifically, we conduct experiments on six real-world text-attributed graph datasets covering diverse domains. We consider six representative privacy attack methods targeting three fundamental threats, namely link, label, and membership inference, and construct 42 victim model configurations by combining multiple LLM-based feature enhancers with representative GNN backbones. Extensive experiments show that, despite their utility improvements, LLM-enhanced GNNs consistently exhibit increased vulnerability to privacy attacks compared to shallow text representation baselines. Further analysis reveals that semantic enrichment amplifies link-, label-, and membership-related signals in the embedding space, making them more exploitable by inference attacks. Finally, we evaluate differential privacy as a defense strategy and show that, while it can partially mitigate privacy risks, it introduces significant utility degradation, highlighting a fundamental privacy-utility trade-off in LLM-enhanced graph learning. Overall, this work provides a comprehensive understanding of privacy risks in LLM-enhanced GNNs and offers practical insights for developing more secure and trustworthy graph learning systems.

AI 总结：该研究针对结合自监督GNN与交替优化语言模型的多模态图学习模型未充分提升性能的问题，分析了六个关键影响因素并通过分阶段实验验证。

链接：https://arxiv.org/abs/2608.25741

机构：SOKENDAI（总研究大学院大学）； National Institute of Informatics（情报学研究所）

作者：Fumiaki Kimino (1), Ryoma Sato (1 and 2) ((1) SOKENDAI, (2) National Institute of Informatics)

英文摘要：Graph neural networks (GNNs) are widely used to represent complex interactions and relationships among entities. We investigate a multimodal model that combines two complementary ideas: a self-supervised method that enables a GNN encoder pretrained on one dataset to operate directly on another dataset with a different node-feature dimensionality, without rebuilding the model or realigning the data; and an alternating optimization method that updates a language-model module in an E-step and a GNN module in an M-step, rather than jointly training a large language model and a GNN end to end on a large graph. Despite expectations, the combined model did not sufficiently improve predictive performance. We identify six factors: (1) an external anchor in the E-step has a strength-safety trade-off: a weak anchor has little effect, whereas an overly strong anchor can damage the graph representation; (2) the knowledge of the E-step teacher is not injected directly into the GCN embedding Z; (3) the representation space constructed in the M-step is not optimized for the same objective as the E-step teacher space, resulting in a compromise representation for target classification; (4) GCN propagation averages a node's own textual information with information from its neighbors; (5) cosine alignment does not guarantee axes that are discriminative for classification, so stronger geometric alignment with the E-step text anchor need not sufficiently improve the target decision boundary or classification performance; and (6) the force that preserves the source-side self-supervised geometry in the M-step conflicts with the force that moves the representation toward the E-step teacher. We support these observations through a staged set of experiments that varies the influence of the E-step.

AI 总结：该研究提出将知识图谱编译为 LoRA 适配器库的参数化知识存储方案，发现其存在存储的知识无法通过语义相似性检索的差距，为参数化知识图谱记忆的应用提供了思路并指出核心开放问题。

链接：https://arxiv.org/abs/2608.25489

机构：Bosch Center for Artificial Intelligence（博世人工智能中心）； LMU Munich（慕尼黑大学）； University of Oslo（奥斯陆大学）； Munich Center for Machine Learning（慕尼黑机器学习中心）

作者：Martino M. L. Pulici, Cuong Xuan Chu, Evgeny Kharlamov, Volker Tresp

英文摘要：Graph retrieval-augmented generation places retrieved subgraphs into the model's context window at query time, paying a recurring token cost and exposing source data on every call. We study an alternative: compiling a knowledge graph offline into a bank of LoRA adapters, one per entity, that serve as a parametric knowledge layer queried by injecting weights rather than text, at zero query-time context cost. On the MetaQA dataset, we find that subgraph-trained adapters encode context-free factual knowledge that generalizes to unseen questions: on single-valued relations the adapter gains $+0.243$ exact-match score over a base model that is nearly blind closed-book ($0.007$), and only the correct adapter recovers this knowledge (an oracle gap of $+0.283$ over the base model). However, the stored knowledge is not recoverable by similarity: given a query with no subgraph, embedding-based and weight-space geometry retrieval both perform at chance, because a semantically neighbouring entity's adapter does not contain the answer - knowledge is stored locally and does not transfer. Weight geometry correlates with subgraph semantics ($\rho = +0.329$) but not with functional retrievability. We quantify the byte and context-token costs against graph retrieval-augmented generation and discuss deployment implications. Our results establish that parametric knowledge graph memory is feasible for storing knowledge, and identify selecting and composing the right adapters by a mechanism other than semantic similarity as the central open problem - motivating a learned, query-conditioned composition mechanism.

AI 总结：本文针对分布偏移下视觉-语言模型的公平性问题，提出了感知公平性的情节式测试时自适应方法FairTPT，通过软提示调优联合优化熵，实现公平性提升并优于现有方法。

链接：https://arxiv.org/abs/2608.25707

机构：University of Cambridge（剑桥大学）； Visa Inc.（维萨公司）； University of Manchester（曼彻斯特大学）

作者：Yoann Launay, Parameswaran Kamalaruban, Tom Kempton, Stuart Burrell, David Sutton

英文摘要：Vision-language models have displayed remarkable capabilities in multi-modal understanding and are increasingly used in critical applications where economic and practical deployment constraints prohibit re-training or fine-tuning. However, these models can also exhibit systematic biases that disproportionately affect protected demographic groups and existing approaches to addressing these biases require extensive model retraining and access to demographic attributes. There is a clear need to develop test-time adaptation (TTA) approaches that improve the fairness characteristics of pretrained models under distributional shift. In this paper, we evaluate how episodic TTA affects fairness in CLIP classification under subpopulation shifts and develop FairTPT, a novel fairness-aware episodic TTA method that jointly minimizes target marginal entropy while maximizing spurious marginal entropy through soft-prompt tuning. We find that standard episodic TTA generally exacerbates disparities between majority and minority groups, that blinding a model to spurious attributes without degrading target performance is inherently challenging, and that excessive blinding can lead to catastrophic forgetting. This model collapse can be prevented by monitoring test-time changes in target loss within the linear regime, while still achieving fairness improvements on reactive data and preserving overall performance. FairTPT outperforms all state-of-the-art episodic test-time debiasing methods and establishes a foundation for robust TTA, which is essential for achieving fairness in practice.

AI 总结：本文针对Transformer注意力，建立了LoRA秩与近似误差的理论边界，分析了秩的选择规律，扩展了相关分析至融合多头LoRA及联合查询/键更新的场景。

链接：https://arxiv.org/abs/2608.26052

机构：Aily Labs

作者：Gerard Conangla Planes

英文摘要：Choosing the rank of a low-rank adaptation (LoRA) update is usually an empirical task. In this paper, we provide a task-dependent theory of the approximation error achievable at each LoRA rank for Transformer attention. We fix a pretrained attention head, a target attention function, and a distribution over inputs from the downstream task, and bound the smallest expected Kullback--Leibler (KL) error achievable by a rank-$r$ query LoRA update. When target attention probabilities are bounded away from zero, we prove a lower bound of the error proportional to $\psi(\|d\|_2)$, where $d$ is the difference between candidate and target attention scores and $\psi(t)=\min\{t^2,t\}$. We also prove an unconditional upper bound $\min\{\|d\|_2^2/4,\sqrt2\|d\|_2\}$. Under explicit realizability, geometry, and moment conditions, we then bound the best rank-$r$ error between an explicit multiple of $\psi(\sqrt{T_r})$ and $\min\{T_r/4,\sqrt{2T_r}\}$, where $T_r$ is the downstream-weighted tail energy of the target update. We also provide target-Fisher bounds when candidate scores remain within a fixed range of the target scores, and an unrestricted lower bound when a subset of tokens carries most of the probability mass. These spectral bounds describe finite-score approximation. We then construct explicit families in which softmax saturation makes the rank required to match the attention function strictly smaller than the rank required to match the finite logits. Finally, we extend the analysis to fused multi-head LoRA and joint query/key updates, exposing the effects of rank sharing and query/key factorization constraints.

AI 总结：本文明确了影响神经替代模型在无导数优化中作用的三个关键因素，通过117个基准实例等实验验证了各因素对求解性能的影响，化解了该领域的应用矛盾。

链接：https://arxiv.org/abs/2608.24963

机构：University of California, Berkeley（加州大学伯克利分校）； Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）

作者：Chengkuo Bian, Pengcheng Xie

英文摘要：Published experience with neural surrogates in derivative-free optimisation is contradictory: the same family of models that cuts the evaluation count of one solver leaves another unchanged, or makes it worse. We show that the contradiction dissolves once three factors are stated, and that these, rather than the fit accuracy a training curve reports, are what delimit when a learned local model pays. Role: a surrogate that proposes candidates the true objective must still approve helps, while one that replaces a gradient the solver depends on hurts. Radius: a model fitted to an optimisation path is reliable only inside a bounded neighbourhood, and its error neither vanishes as that neighbourhood shrinks nor survives its growth. Room: a surrogate can only accelerate progress the base method is still able to make. We formalise radius-aware local generalisation, relate it to the classical fully linear condition, and test each factor with the surrogate class, training pipeline and base method held fixed. Over 117 benchmark instances safeguarded assistance raises the instances solved to high accuracy from 67 to 84 while gradient replacement lowers them to 65; removing the gradient term from the training loss cuts surrogate acceptance from 0.703 to 0.148; and 1000 paired comparisons over ten noise levels show no noise threshold, only a base method that stops early. The same factors bound the gain: a model-based trust-region solver, which leaves little room, drops from 88 to 86 when the identical surrogate is attached, and released interpolation software stays ahead at 103, and on a Monte-Carlo inventory model repairing the acceptance interface is worth 10.40 cost units against 0.00 for the surrogate.

AI 总结：本文提出将数据解释作为大型语言模型处理时空场的阶段，以物理不变量为数据表示，在PDE发现基准中使方程恢复准确率近三倍提升，为自动化场理论构建提供实用途径。

链接：https://arxiv.org/abs/2608.25189

机构：California Institute of Technology（加州理工学院）

作者：Fan Yang, Matt Thomson

英文摘要：Understanding how molecular interactions govern macroscopic behaviour is a central challenge in molecular sciences. However, conventional theory building cannot keep pace with the vast datasets modern experimentation routinely produces. Large language models offer a promising route to automating theory construction, but a spatiotemporal field cannot be directly placed in a prompt. Existing models generally learn about the data only through a score measuring how well each proposal fits it. Here we introduce data interpretation, a stage that measures the field into the quantities a theorist would consult and supplies them to the model as a direct input. On a benchmark of simulated fields, interpretation nearly triples the accuracy of recovered equations relative to showing the raw data, at negligible computational cost and without any training. By allowing a language model to read field data as a theorist does, data interpretation offers a practical route to automated field theory construction that can coevolve with experimentation.

AI 总结：本研究推出含100小时脑磁图数据的LibriBrain100数据集，通过深度受试者内数据与多受试者数据结合，验证其可提升单词分类解码性能，助力无创脑机接口发展。

链接：https://arxiv.org/abs/2608.25204

机构：University of Oxford（牛津大学）； FMRIB； OHBA

作者：Francesco Mantegna, Dulhan Jayalath, Gereon Elvers, Tasha Kim, Benjamin Ballyk, Alex Fung, SungJun Cho, Teyun Kwon, Luisa Kurth, Miran Özdogan, Gilad Landau, Pratik Somaiya, Natalie Voets, Mark Woolrich, Oiwi Parker Jones

英文摘要：We introduce LibriBrain100, a large-scale MEG dataset for speech decoding designed from the ground up for reproducible, standardised evaluation. LibriBrain100 more than doubles the size of the original LibriBrain release, resulting in over 100 hours of high-quality MEG acquired while subjects listened to naturalistic continuous speech. With $\sim$80 hours from a single subject, LibriBrain100 sets a new record for deep, within-subject neural data (8$\times$ more than the next comparable dataset and roughly 80$\times$ more than other datasets). To demonstrate the payoff of this depth-first design, we evaluate on a word-classification benchmark---an increasingly well-established stepping stone towards the open challenge of noninvasive brain-to-text decoding. Using an existing decoding model, we achieve state-of-the-art performance---validating both the quality of the recordings and the value of within-subject data at scale. Because collecting 80 hours of data per user is impractical for real-world applications, we also collected $\sim$40 minutes of additional data from each of 32 subjects. Using the same word-classification benchmark, we demonstrate the value of broad multi-subject data: supervised finetuning of a pre-trained model can substantially compensate for limited per-subject data. We provide standard train, validation, and test splits, all reproducible through an open-sourced Python library that supports easy downloading, optional preprocessing, and data loading for common deep learning frameworks. In addition, the dataset and evaluation infrastructure are being released alongside an open machine-learning competition with a public leaderboard for standardised benchmarking. Ultimately, our hope is that LibriBrain100 will accelerate progress towards practical non-invasive brain-computer interfaces, capable of restoring communication to people living with severe paralysis.

AI 总结：FedQoS是一种联邦QoS风险学习框架，通过各接入节点本地学习并联邦聚合训练全局预测器，在无需集中用户数据的情况下，降低动态异构室内外环境的QoS故障率，实现可靠接入选择。

链接：https://arxiv.org/abs/2608.25496

机构：Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg（卢森堡大学跨学科安全、可靠性与信任中心（SnT））

作者：Nguyen Van Thieu, Ti Ti Nguyen, Ons Aouedi, Zerihun Huruy, Vu Nguyen Ha, Symeon Chatzinotas

英文摘要：Reliable access selection in dynamic and heterogeneous indoor-outdoor environments is challenging because instantaneous radio measurements alone cannot capture future QoS degradation caused by mobility, blockage, traffic load, and resource competition. This paper proposes FedQoS, a federated QoS-risk learning framework for predicting the future reliability of candidate access links and supporting access-node selection without centralizing user-level network data. In FedQoS, each access node locally learns from its observed network logs, including radio, traffic, load, and service-context features, while a global QoS-risk predictor is trained through federated aggregation. The learned model estimates the probability of QoS failure for each candidate link, and the controller uses these risk scores to select reliable access nodes under dynamic network conditions. To evaluate the framework, we construct physics-based synthetic indoor-outdoor wireless datasets using the Sionna framework, covering normal traffic, mobility, event-driven congestion, and non-IID client observations. Simulation results show that learning-based access selection substantially reduces the QoS-failure rate compared with signal-based and historical-QoS heuristic methods. FedQoS achieves near-centralized predictive performance and provides clear reliability gains under mild non-IID data while remaining competitive under the more challenging severe non-IID condition. These results demonstrate the potential of federated QoS-risk learning for reliable, data-local access selection in dynamic wireless environments.

AI 总结：该研究提出量子启发式驾驶行为表示，在I-24 MOTION数据集无监督训练后恢复出三种可解释驾驶模式，可支持跟驰模型与自动驾驶车辆的实际应用，且开源了相关工具包。

链接：https://arxiv.org/abs/2608.25907

机构：University of Nebraska–Lincoln（内布拉斯加大学林肯分校）

作者：Mohammad Elayan, Omid Armantalab, Wissam Kontar

英文摘要：Driver behavior is heterogeneous, context-dependent, and changes over time, and these properties shape the traffic phenomena we observe. Most models, however, fix in advance which behavioral variables interact and how. Behavior outside that form is absorbed as noise, while models flexible enough to capture it tend to lose interpretability. We introduce a quantum-inspired representation of driver behavior that combines properties usually treated separately or in part: it is continuous, probabilistic, context-dependent, history-dependent, and represents interactions among behavioral variables as learned from data. Each driver is encoded as an evolving density matrix, providing a unified representation of behavioral uncertainty, temporal evolution, and context-dependent behavioral variation. Trained without supervision on the I-24 MOTION dataset, the framework recovers three interpretable driving profiles representing three regimes: free flow, transition, and congestion. The profiles capture the behavioral range of the data and the smooth transitions drivers make between regimes as conditions change. The same representation also reproduces known macroscopic phenomena, aligning with the fundamental diagram and reproducing hysteresis loops. We also show how the representation supports practical use: it supplies context-dependent parameters to classical car-following models, and gives an autonomous vehicle a live behavioral read of the surrounding drivers with a short-horizon forecast of their motion. The framework points toward models of traffic that are interpretable and trustworthy by construction. We release an open-source toolkit on GitHub ( this https URL ) spanning data processing, training, inference, and analysis.

AI 总结：TraceML通过构建人类与智能体在Kaggle竞赛中的配对轨迹数据集，实证分析了人类与智能体在机器学习开发规划上的差异，发现智能体存在行为循环问题，提炼的人类规划提示可缩小部分差距。

链接：https://arxiv.org/abs/2608.26086

机构：Carnegie Mellon University（卡内基梅隆大学）

作者：Jiarui Yan, Weiwei Sun, Sijie Li, Wenhan Li, Yiming Yang

英文摘要：Large language models write correct code for isolated problems but remain far weaker at autonomous machine-learning development, where an agent must revise data pipelines, models, and validation over hours of feedback, and on most competitions still finishes below strong human competitors. Outcome-based benchmarks record this gap but not its cause, because they grade the final submission and discard the development process behind it. We introduce TraceML, which pairs human and agent work on the same competitions under one version-level schema: 4,465 human Kaggle trajectories across 134 competitions, seven of which are also worked by two agent scaffolds, giving 430 paired human and 207 agent trajectories. Every code version carries its score, its timestamp, and labels for the action taken, its intent, the edit size, and the score effect. Read this way, the gap becomes concrete. Experts alternate data work, validation, model changes, and ensembling, and return to approaches they had set aside. Each agent scaffold instead collapses into a narrow loop: Codex spends its steps re-weighting ensembles and tuning submissions, MLEvolve mutates its model in place, and neither pivots at the human rate nor reopens abandoned work. A short planning prompt distilled from human practice moves the behaviors it names toward the human profile and lifts scores, but the effort profile stays agent-shaped: instruction closes only the part of the gap that reduces to instructions. We release the corpus, the schema, the labelers, and the extraction pipeline at this https URL.

AI 总结：该综述从假设驱动视角梳理多模态异常检测（MMAD），划分两种互补方法范式，探讨基础模型对MMAD的重塑，汇总基准与评估协议并指出未来方向。

链接：https://arxiv.org/abs/2608.24937

机构：School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）； School of Software, Beihang University（北京航空航天大学软件学院）； Shandong Inspur Intelligent Production Technology Co., Ltd（山东浪潮智能生产技术有限公司）

作者：Xudong Mou, Zexin Wu, Chuan Luo, Shiru Chen, Xudong Liu, Chunming Hu, Renyu Yang

英文摘要：Multi-Modal Anomaly Detection (MMAD) detects rare abnormal events from heterogeneous data sources and is increasingly used in safety- and reliability-critical applications such as industrial inspection and cybersecurity. Yet the literature is fragmented across domains and modality combinations, and existing surveys usually group methods by architecture rather than by how abnormality is defined and separated in multi-modal settings. We survey MMAD from an assumption-driven perspective. We formalize the problem, identify five intrinsic characteristics underlying its core challenges, and organize prior work into two complementary paradigms. The first, normality-assumption methods, models regularity via representation learning, cross-modal alignment, and knowledge enhancement. The second, anomaly-assumption methods, sharpens decision boundaries through coarse-grained, structural, and semantic anomaly injection. We also investigate how foundation models are reshaping MMAD through scalable pretraining, flexible cross-modal transfer, and emerging reasoning capabilities. Finally, we compile representative benchmarks and evaluation protocols across domains and highlight open problems and future directions for robust, adaptive, and interpretable MMAD systems.

AI 总结：本研究提出双分支频谱门控架构DBSG-PINN，通过消融实验发现频率分解仅在频谱复杂的物理信息神经网络基准问题上可显著降低误差，在平滑问题上益处有限。

链接：https://arxiv.org/abs/2608.24940

作者：Shubham Rai

英文摘要：Partial differential equations (PDEs) often have high-frequency and multi-scale features that neural networks struggle to approximate. Physics-Informed Neural Networks (PINNs) build the governing equations directly into training, but suffer from spectral bias: they learn low-frequency components faster than high-frequency ones. Techniques such as Fourier feature embeddings and sinusoidal activations address this, but most studies assume they help across the board without checking which spectral regimes actually benefit. We introduce a dual-branch, spectrally-gated architecture (DBSG-PINN) that splits low- and high-frequency components into separate subnetworks joined by an adaptive gate, and use it to run a partially controlled ablation of frequency decomposition and spectral routing. We test this on five one-dimensional benchmark PDEs, ranging from smooth, single-scale problems to oscillatory, multi-scale ones. Frequency decomposition helps most on the spectrally complex benchmarks, cutting relative $L_2$ error by up to $59.2\%$ on a multimodal wave problem, but gives little benefit on smoother PDEs. On one benchmark (1D Wave), it performs substantially worse than a simpler fixed-combination variant. The gate's benefit scales with how spectrally rich the target solution is: the full model's advantage over the ablations is largest on multi-scale benchmarks and smallest (or negative) on single-scale ones, consistent with the gate exploiting frequency structure rather than acting as noise,though we do not directly visualize or quantify its spatial activations in this study. All results come from a single training seed across five 1D benchmarks, so we present this as an exploratory study meant to raise questions rather than answer them, and outline the additional seeds and benchmarks needed to test whether the pattern holds.

AI 总结：本文提出PIEFL框架作为PINNs的训练后优化策略，通过引入辅助误差网络修正预测误差，在相同计算预算下提升了PINNs的解精度。

链接：https://arxiv.org/abs/2608.24970

机构：College of Mathematics and Systems Science, Shandong University of Science and Technology（山东科技大学数学与系统科学学院）

作者：Jiuyun Sun, Yong Zhang

英文摘要：Physics-Informed Neural Networks (PINNs) have emerged as an important class of numerical methods for solving partial differential equations (PDEs). However, during the late-stage optimization process, further parameter updates often yield diminishing accuracy improvements while increasing computational costs. To address this issue, this paper proposes a Physics-Informed Error Field Learning (PIEFL) framework for PINNs. Unlike conventional approaches that continuously approximate the solution field using a single network, PIEFL introduces an auxiliary error network after the primary network achieves satisfactory accuracy and shifts the learning objective from the solution field to the error field. By deriving error control equations under physical constraints, the error network learns the discrepancy between the current approximation and the exact solution, and the learned error correction is combined with the primary prediction to improve solution accuracy. The proposed framework avoids continuous optimization of the entire solution space and focuses computational resources on correcting existing prediction errors. Moreover, PIEFL requires no modification to the primary network architecture, making it compatible with existing PINN models and applicable as a general post-training optimization strategy. Numerical experiments on representative PDEs demonstrate that PIEFL achieves higher solution accuracy under the same computational budget, validating its effectiveness in improving the performance of PINNs.

AI 总结：该研究提出模型无关的NVExplain框架，通过潜在轨迹分析与结构保持替代模型，提升时间序列预测解释的忠实性与效率，解释具鲁棒性。

链接：https://arxiv.org/abs/2608.25080

机构：NVIDIA（英伟达）

作者：Muyan Anna Li, Manikandan Ravikiran, Aditi Gautam

英文摘要：Time series forecasting models are widely used in high-stakes settings, yet their predictions remain difficult to interpret because existing post-hoc methods often ignore temporal dependence and fail to provide horizon-specific explanations. We propose a model-agnostic explainability framework that explains forecasting predictions by attributing each forecast horizon to temporally relevant historical lags. The framework models forecasting as a latent trajectory and introduces semantic flow to quantify how information evolves across time in the model's internal representations. By aggregating semantic flow, it constructs a lag-horizon attribution matrix that captures horizon-resolved temporal influence. To improve explainability, we further generate structure-preserving perturbations and fit sparse local surrogate models, producing human-readable and temporally coherent explanations. We evaluate the method using faithfulness and stability diagnostics across multiple benchmark datasets. Results show that the semantic-flow variant achieves competitive or superior faithfulness compared to standard post-hoc baselines, while being substantially more computationally efficient. Stability analysis further demonstrates that the explanations are robust and identifies regimes where interpretation should be applied with caution.

AI 总结：该研究明确了多模态时间序列预测中辅助上下文有效的两个数据集条件，通过实验证实仅当两条件满足时，文本条件专家调制可显著降低均方误差，且确立了因果关系。

链接：https://arxiv.org/abs/2608.25128

机构：University of Tennessee, Knoxville（田纳西大学诺克斯维尔分校）； WorkMagic； University of Texas at Austin（德克萨斯大学奥斯汀分校）

作者：Ruizhe Zhou, Gaoyuan Du, Xiaoyang Liu, Haoqi Yao, Deepayan Chakrabarti, Jiating Lin, Yixuan Shen

英文摘要：Multi-modal time series forecasting methods integrate auxiliary context into temporal predictions through increasingly sophisticated fusion mechanisms. A growing body of work reports substantial gains, yet it is often unclear whether they reflect genuine use of the context or incidental architectural effects. We ask a narrower, checkable question: when can auxiliary context help a forecaster at all? We identify two dataset-level conditions that must both hold: (1) the target is not dominated by a last-value shortcut (low autocorrelation rho_h), and (2) the context carries information about the target beyond history (non-zero conditional mutual information delta; when delta=0 no predictor can benefit---a distribution-free result). Through controlled experiments on MoME (a 14.3B-parameter mixture-of-experts model, 6 datasets, 10 seeds) and four additional fusion mechanisms implemented within a single-backbone testbed (5 datasets), we find that when both conditions hold, text-conditioned expert modulation contributes a sizeable MSE reduction; when either fails, the contribution collapses to the capacity floor of the modulation pathway and carries no context-attributable signal. We establish causality through two interventions: adding a shortcut to MoME suppresses routing contribution by 77-93% across 3 datasets; progressively corrupting context quality drives the context-specific benefit from +44% to negative. We validate the autocorrelation component of our diagnostic on 27 Monash Archive datasets. We provide a calibrated pre-training diagnostic that, on the datasets we test, yields no false positives in well-powered settings. We are explicit about the asymmetry of our evidence: the negative arm is broadly reliable, while the large positive magnitudes come from a single model family (MoME) and are corroborated only in direction by the testbed.

AI 总结：该研究对照测试了PINNs的两种故障修复方案，发现二者作用场景互不重叠，需联合评估精度、架构等因素并按种子报告结果。

链接：https://arxiv.org/abs/2608.25327

机构：Hubei University（湖北大学）

作者：Jinyuan Zhang, Peng He, He Hu, Yin Yuan, ShengShuo Jiao

英文摘要：Physics-Informed Neural Networks (PINNs) frequently fail on stiff or advection-dominated PDEs, and two recent accounts offer competing remedies: switching from FP32 to FP64 to repair an L-BFGS stopping artifact, or replacing the MLP with a state-space-model (SSM) backbone plus sub-sequence alignment to counter architectural simplicity bias. We test both under matched, seed-paired controls in a pre-registered 144-run study spanning convection, reaction, and wave, plus an independent 85-run convection/wave study; success is relative $\ell_2$ error below $0.05$. The two remedies act on disjoint regime-and-seed slices: neither substitutes for the other. On hard convection ($\beta{=}50$), alignment recovers 2/5 seeds in FP32 and 3/5 in FP64, where the unaligned SSM succeeds on 0/5 seeds at either precision and the vanilla MLP moves only from 0/5 to 1/5 across the precision switch---the recoveries trace to the alignment objective, not the backbone. On reaction the backbone alone already succeeds on 3/5--4/5 seeds, so each remedy covers a regime the other does not. Responses are also seed-specific: the same precision switch flips individual seeds in opposite directions and, on wave, lowers median error with no statistically significant success gain. Tightening the inner L-BFGS tolerance in an independent repeated-step runner likewise lowers median error at a large runtime cost, with success counts unchanged. Precision, stopping, backbone, and alignment must therefore be evaluated jointly and reported per seed.

AI 总结：针对PINNs求解中子扩散K本征值问题效率不足的问题，提出JI-PINN方法，通过联合初始化通量网络参数与keff，在多测试案例上实现计算时间显著减少且精度相当。

链接：https://arxiv.org/abs/2608.25443

机构：School of Computer Science and Technology, Chongqing University of Posts and Telecommunications（重庆邮电大学计算机科学与技术学院）； Center for Scientific Intelligence Innovation, University of Science and Technology of China（中国科学技术大学科学智能创新中心）； Institute of Advanced Technology, University of Science and Technology of China（中国科学技术大学先进技术研究院）

作者：Qin Hang, Yangdi Yi, Jiayi Li, Xu Wang, Heng Zhang

英文摘要：Efficient determination of the effective multiplication factor (keff) is an important computational task in reactor core neutronics analysis. Physics-informed neural networks (PINNs) incorporate neutron diffusion equations and boundary conditions into network training to efficiently determine the neutron flux distribution and keff. To further improve the efficiency of keff calculations using PINNs, a Joint Initialization Physics-Informed Neural Network (JI-PINN) is proposed in this work. In this method, a low-resolution approximate solution to the K-eigenvalue problem is used to construct a joint initial state for the flux network parameters and keff, and both are then jointly optimized under physical constraints. The proposed method was validated on a two-dimensional two-group two-material case, the IAEA 2D benchmark, a two-dimensional two-group four-material case, and a three-dimensional single-group case. For these test cases, the total computational time was reduced by 25.4%, 38.2%, 49.4%, and 28.9%, respectively, while comparable solution accuracy was maintained. The occurrence of anomalous results associated with marked deviations of keff from the reference value was also reduced. The proposed method provides a more efficient and robust initialization strategy for solving neutron diffusion K-eigenvalue problem with PINNs.

AI 总结：针对非线性PDE稀疏PINN求解器，提出PI-SAP剪枝方法，其利用PDE残差灵敏度分配显著性，在高稀疏度下保留Gray-Scott残差保真度，平衡解侧与残差侧训练动态。

链接：https://arxiv.org/abs/2608.25564

作者：Ahmad Ishaque Karimi, Uvini Balasuriya Mudiyanselage, Kookjin Lee

英文摘要：Physics-informed neural networks (PINNs) often rely on over-parameterized models to optimize coupled solution and differential-residual objectives, leaving unclear how much capacity is necessary and what pruning should preserve. We study foresight pruning at initialization for sparse PirateNet PDE solvers. Standard neural tangent kernel spectrum-aware pruning (NTK-SAP) aims to preserve output-side training dynamics but may overlook parameters whose main influence arises through derivatives in the governing equations. We introduce physics-informed spectrum-aware pruning (PI-SAP), which assigns saliency using sensitivity of the PDE residual. Experiments on the Gray-Scott equations, complex Ginzburg-Landau equation, Burgers' equation, and linear convection equation show that PI-SAP more consistently preserves Gray-Scott residual fidelity and is competitive under aggressive sparsity. However, no criterion is uniformly optimal across equations or sparsity levels. Small-batch PINN-NTK diagnostics further show that residual fidelity, solution accuracy, and kernel conditioning are distinct objectives, motivating pruning methods that explicitly balance solution-side and residual-side training dynamics during optimization.

AI 总结：针对台风阵风短期预测难题，提出整合平稳小波分解等模块的WDANet框架，以西太平洋近海区域为对象验证，其在24小时预测时域的短提前期预测中精度优于ECMWF-HRES，可应用于海上风电等场景。

链接：https://arxiv.org/abs/2608.25604

机构：School of Artificial Intelligence, Hubei University（湖北大学人工智能学院）； School of Economics and Management, Wuhan University（武汉大学经济与管理学院）； School of Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电气工程学院）

作者：Xuefei Wang, Tingyi Liu, Heng Zhang, Shengjun Zhang

英文摘要：Accurate gust forecasting under typhoon conditions remains challenging due to the highly non-stationary and multi-scale characteristics of extreme wind fluctuations. Existing deep learning models often struggle to simultaneously capture long-term trends and rapid local variations, resulting in degraded performance during extreme events. We propose WDANet, a frequency-aware forecasting framework that integrates stationary wavelet decomposition, a Feature-wise Linear Modulation (FiLM) strategy, and a dual-branch encoder-decoder architecture, enabling separate modeling of trend and fluctuation components. Taking the offshore regions of the Western Pacific in China as an example, we conduct fine-grid wind gust prediction research. The results demonstrate that WDANet shows advantages for short lead times under the experimental setting across a 24-h forecasting horizon and achieves higher prediction accuracy than ECMWF-HRES within the first 6 h. During extreme wind events, WDANet more accurately captures gust peaks and attains the best RMSE and MAE performance. These results highlight its potential for offshore wind power operation, disaster warning, and risk mitigation.

AI 总结：本文提出名为SPALT的方法，通过线性模型树与结合时空局部性的剪枝策略，建模地理参照时间序列的时空局部性，在3个真实数据集的多步能源产量预测中，性能优于树模型和融合时空的最先进神经网络。

链接：https://arxiv.org/abs/2608.25698

作者：Annunziata D'Aversa, Gianvito Pio, Michelangelo Ceci

英文摘要：Forecasting future measurements from geographically distributed sensors is essential across many domains. However, the spatial distribution of these sensors raises multiple challenges, primarily due to spatial autocorrelation phenomena, that introduce inter-dependencies among nearby locations, that cannot therefore be treated independently. While some existing approaches can capture such phenomena, they generally model the spatial dimension globally across all locations. On the other hand, the method we propose in this paper, called SPALT, focuses on capturing spatial relationships among time series with similar trends, even if they occur at different times, thus modeling the spatio-temporal locality. SPALT leverages linear model trees, which allow us to consider the spatial autocorrelation locally: during the tree-building process, the adopted heuristics group time series exhibiting similar trends into the same node, on which additional features considering the spatial dimension are selectively injected. Additionally, we propose a new pruning strategy, based on Reduced Error Pruning, that also considers the spatio-temporal locality during the tree simplification. Designed for a multi-step setting, SPALT provides forecasts for multiple future time steps across multiple sensors simultaneously. The characteristics exhibited by SPALT can provide significant benefits in different domains, where measurements come from distributed sensors. In this paper, we focus on data produced by sensors located in multiple renewable power plants measuring their energy production at regular, short intervals. Experiments on 3 real-world datasets demonstrate the effectiveness of SPALT in forecasting the production of energy at different time horizons, and its superior performance in comparison with tree-based models and state-of-the-art neural networks that incorporate both temporal and spatial dimensions.

AI 总结：针对瞬态动力学神经算子的自回归不稳定性问题，提出构造性稳定的MPNO，在三类PDE测试中表现优异，参数量少且推理速度远超LS-DYNA。

链接：https://arxiv.org/abs/2608.25744

机构：School of Environment and Safety Engineering, North University of China（中北大学环境与安全工程学院）

作者：Wenpu Du, Peng Zhou, Yunlong Xia, Sinuo Xin, Congcong Zhang, Boyang Zhang, Yi Zhang, Wenzheng Xu

英文摘要： Neural operators applied to transient-dynamics PDEs with strong discontinuities exhibit autoregressive instability: in concrete-penetration stress-field prediction, the wavelet neural operator (WNO) diverges in autoregressive rollout, while MeshGraphNets collapse to zero predictions. WNO's instability stems from the lack of a structural constraint on the spectral radius of its propagation operator; the Fourier neural operator (FNO) is stable in these measurements but only emergently, not by construction. We propose a constitutive Markov physics-informed neural operator (MPNO) modeling one-step evolution as a Markov (row-stochastic) propagation operator. Physics-coupled edge weights (acoustic-impedance harmonic mean, contact area, and traction amplitude) encode material-interface constitutive information into a nonnegative symmetric adjacency matrix W; after normalizing the graph Laplacian L = D - W by lambda_max, the propagator P = I - alpha*L~ is constructively constrained to spectral radius rho(P) <= 1, suppressing exponential amplification of autoregressive errors. Stability is thus a designable architectural property, not an optimized loss objective. On three PDEs (Burgers and two-dimensional transverse-section concrete penetration), MPNO rolls out stably with bounded error on all test seeds at 100/135/165 m/s; the single-step relative L2 error is 0.7304 +/- 0.0008, better than WNO and comparable to FNO at about one quarter of FNO's parameters. The edge-weight formula transfers across scenarios by replacing material-property variables. With about 20K parameters, MPNO delivers roughly 10^5x inference speedup over LS-DYNA.

AI 总结：该研究针对现有时间序列预测方法对策略不敏感、反事实分析不可靠的问题，提出基于残差分解的两阶段框架CEDAR，在阿里1688数据集上验证其可提升模拟精度并助力预算规划。

链接：https://arxiv.org/abs/2608.25871

机构：School of Artificial Intelligence and Data Science, University of Science and Technology of China（中国科学技术大学人工智能与数据科学学院）； Alibaba Group（阿里巴巴集团）； Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）人工智能学域）

作者：Junjie Meng, Ranxu Zhang, Zi-an Zhang, Shujun Liu, Xiaoning Qi, Xiaozhou Xu, Yanyong Zhang, Hui Xiong, Chao Wang

英文摘要：Forecasting in large-scale e-commerce marketplaces is increasingly required to support planning: merchants need to evaluate sales outcomes under future action sequences such as budget schedules, rather than passively predicting what happens next. However, most existing time series forecasting (TSF) approaches remain inherently passive. Even when incorporating operational decisions as auxiliary covariates, they typically optimize for correlation-based extrapolation under historical policies. This design suffers from autoregressive inertia and conflates endogenous market evolution with decision-induced transitions, leading to policy-insensitive rollouts and unreliable counterfactual analysis. To bridge this gap, we propose CEDAR (Controlled and Event-Driven Demand forecasting via Action-aware Residual decomposition), a two-stage framework for robust decision-conditioned simulation. In Stage I, an Action-Interleaved Transformer learns controllable action-conditioned state transitions for rollout under planned interventions. In Stage II, a Residual Correction Module leverages external event signals and LLM-assisted text representations to align noisy event descriptions with product context and correct event-driven deviations. Our study is enabled by a large-scale real-world dataset from Alibaba 1688, comprising approximately 32 million product trajectories with paired state-action sequences and aligned event signals. Extensive offline experiments and online controlled experiments in production demonstrate that CEDAR consistently improves simulation accuracy over strong TSF baselines and delivers practical gains for real-world budget planning.

AI 总结：该研究提出SCROLL方法，通过共享主干的自由路由最后一层信念组合多可观测量似然，在随机动力学基准及真实空气质量数据上实现了更优的预测性能与校准。

链接：https://arxiv.org/abs/2608.25898

作者：Pavel Prochazka

英文摘要：Forecasting a stochastic dynamical system rarely means a single number: one wants several observables---future state, threshold event, regime label---each with its own likelihood. Standard multi-task recipes balance per-task losses, tuned or learned. We instead compose the observables' likelihoods in per-task free-routed last-layer beliefs on a shared backbone; this absorbs unit-dependent loss scaling into likelihood parameters learned in the same gradient pass. Stochastic dynamics supply what static benchmarks cannot: computable ground truth for the predictive variance. Results land where theory puts them: on the well-specified, homoscedastic Ornstein--Uhlenbeck process the learned predictive law recovers the analytic kernel and correctly specified baselines tie. On heteroscedastic systems (stochastic Lorenz-63, real air-quality data) the belief's input-dependent variance separates: best single-run NLL on the state and regime tasks, calibration matched only by arms whose NLL it beats, at a fraction of the tuned grids' cost. On the real series the state margin holds across five rolling origins.

AI 总结：MacroAgent是结合LLM智能体设计轮廓算法的四阶段宏合法化框架，在TILOS、Chipyard等基准及Cadence Innovus工具上，实现布局规则性、布线长度等指标的显著提升与更好鲁棒性。

链接：https://arxiv.org/abs/2608.24946

机构：The Chinese University of Hong Kong（香港中文大学）； Peking University（北京大学）

作者：Jiaxi Jiang, Xufeng Yao, Yuxuan Zhao, Yuntao Lu, Peiyu Liao, Zuodong Zhang, Yibo Lin, Bei Yu

英文摘要： Macros constitute a large part of the core area in modern very large-scale integration (VLSI) designs. Moreover, macro positions have a significant impact on the final quality of result (QoR), and macro legalization is typically the final step in determining the macro positions. However, existing approaches related to macro legalization either lack robustness or incur substantial computational costs or neglect the regularity between macros. To address these limitations, we introduce MacroAgent. The novel framework is a four-stage approach: clustering, contour generation, template matching, and inter-cluster refinement. We propose leveraging Large Language Models (LLMs) to discover multiple, effective heuristic regularity-aware contour algorithms. This framework successfully generates robust and effective algorithmic solutions for macro legalization. Compared with state-of-the-art macro legalization works, experimental results on TILOS and Chipyard benchmarks demonstrate a 2 to 8 fold improvement in layout regularity, a 3% to 5% reduction in routed wirelength with comparable congestion after global routing, and significantly better robustness with an acceptable runtime. Furthermore, end-to-end evaluation through Cadence Innovus place-and-route confirms that the regularity improvements translate into tangible PPA gains, including 2.9% lower routed wirelength and 68.3% TNS improvement over the DREAMPlace macro legalization baseline; it also achieves 1.8% lower routed wirelength when integrated into the Innovus macro placement flow.

AI 总结：CAT-GS是一种无需修改模型的优化控制器，通过校准门控与融合操作解决多模态学习的三种失效模式，在多类基准上提升或匹配多模态准确率，且门控更平稳、融合冲突更少。

链接：https://arxiv.org/abs/2608.24947

机构：North South University（北南大学）

作者：Mahir Shahriar Tamim, Sharjil Khan, Md. Samiul Alim, Tanvir Ahmed Khan, Shafin Rahman, Nabeel Mohammed

英文摘要：End-to-end training of multimodal neural networks often exhibits unstable neural dynamics characterized by three coupled failure modes that degrade learning: (i) modality imbalance, where one branch dominates gradient-based optimization; (ii) unstable gating, where noisy confidence cues induce erratic modality selection; and (iii) fusion interference, where modality-specific gradients conflict at the shared fusion layer. We propose CAT-GS (Calibrated, Adaptive, Thresholded Gating with Fusion Surgery), a neural dynamics-based optimization controller for intelligent computing applications. CAT-GS operates during backpropagation without modifying model architectures, fusion modules, or task losses. Through calibration of teacher-derived reliability via temperature scaling and EMA smoothing, CAT-GS stabilizes neural dynamics using a margin-thresholded policy to switch between warm-up dropout, weak-modality prioritization, and weak-biased blending, stabilizes gradient magnitudes under aggressive gating via capped gradient-budget renormalization, and applies fusion-only PCGrad to reduce destructive cross-modal interference at the primary shared bottleneck. We evaluate CAT-GS on audio--visual multimodal pattern recognition benchmarks (CREMA-D, AV-MNIST, and VGGSound), a tri-modal setting (UR-FUNNY), controlled synthetic data (CG-MNIST), and additional cross-domain benchmarks (AVE and CMU-MOSI). CAT-GS improves or matches fused multimodal accuracy against strong imbalance-aware baselines (including OGM-GE, G$^2$D, and UMT) across settings, and yields smoother gating behavior with fewer conflicting fusion gradients.

AI 总结：该研究在自回归Transformer模型基础上添加FSQ分词器层，结合推理优化技术，在低延迟下提升了对OFDM数字电视干扰的抑制性能，通过PESQ指标验证优势并探索了相关应用场景。

链接：https://arxiv.org/abs/2608.24974

机构：MIT Lincoln Laboratory（麻省理工学院林肯实验室）

作者：Rahul Jain, Pierre Trepagnier, Rick Gentile, Joey Botero, Alexia Schulz

英文摘要：AI-based structured interference rejection has grown more popular because deep learning approaches can outperform traditional methods by jointly considering the signal of interest (SOI) and the signal mixture (SOI plus interference). This work builds on a previous AI-enabled approach utilizing autoregressive transformer-based models by adding a Finite Scalar Quantization (FSQ) tokenizer layer which aims to improve the interference rejection performance while keeping overall latency to a minimum. Additionally, we experiment with other inference optimization techniques with the goal of speeding up inference without much accuracy loss. We explore this space with an experiment where the SOI is a digitally modulated radio frequency (RF) signal and the structured interference is a digital television signal, an extremely common type of Orthogonal Frequency-Division Multiplexing (OFDM) transmission. Our results achieve low latency and increased interference rejection over traditional techniques and prior work with other AI-enabled methods. We demonstrate the benefits of the AI-enabled approaches via audio metrics such as Perceptual Evaluation of Speech Quality (PESQ). Additionally, we explore a variety of applications and detail how our interference rejection algorithm may be used in operationally-relevant scenarios.

AI 总结：该研究针对sMRI与dFNC融合时IVA方法的缺陷，提出MSR-IVA框架，在ADNI队列实验中提升匹配源耦合、降低非匹配依赖，实现受控结构共享以适配状态差异。

链接：https://arxiv.org/abs/2608.24978

机构：Georgia State University（佐治亚州立大学）； Georgia Institute of Technology（佐治亚理工学院）； Emory University（埃默里大学）

作者：Victor Solomon, Zening Fu, Rafal Angryk, Vince D. Calhoun, Jingyu Liu

英文摘要： Multimodal fusion of structural MRI (sMRI) and dynamic functional network connectivity (dFNC) can reveal how brain structure relates to changing functional states. When the same structural latent representation is coupled with multiple states, applying independent vector analysis (IVA) separately to each state can produce unrelated structural decompositions, while forcing identical decompositions may suppress state-specific relationships. In addition, not every subject expresses every dynamic state. We propose masked structural residual IVA (MSR-IVA), a state-aware framework that combines a shared structural representation with state-specific residual adaptations and masks for incomplete state expression. On an Alzheimer's Disease Neuroimaging Initiative cohort, MSR-IVA improved matched source coupling by 6.5% and reduced unmatched dependence by 15.7% relative to the independent pairwise IVA baseline. Among subjects expressing both states, mean absolute cross-state structural source correlation was 0.9177 for MSR-IVA versus 0.2978 for no sharing, demonstrating controlled structural sharing that preserves source correspondence while allowing state-specific adaptation.

AI 总结：该研究针对多教师在线蒸馏中固定域混合比例的缺陷，提出零开销调度器 D³-MOPD，通过跟踪 KL 轨迹自适应调整域采样比例，在 Qwen3.6-35B-A3B 模型上显著提升蒸馏效率与性能。

链接：https://arxiv.org/abs/2608.24987

作者：Zechen Sun, Zhiwei Zhang, Fei Zhao, Juntao Li, Mu Chuan, Huayu Deng, Guojian Zhan, Wenliang Chen, Yao Hu, Min Zhang

英文摘要：Multi-teacher on-policy distillation (MOPD) distills several domain-expert teachers into a single student by minimizing per-domain reverse-KL divergence on the student's own rollouts. Existing approaches typically fix the per-domain data mixture before training, overlooking the fact that different domains converge at substantially different rates: some plateau early while others continue to improve throughout the training budget. A fixed mixture therefore wastes compute on fast-converging domains and undertrains slower-converging ones. To address this, we propose D$^3$-MOPD (Dynamic Domain ScheDuling for MOPD), a zero-overhead scheduler that repurposes the per-domain reverse-KL signal already produced during training to adapt the domain mixture online. Running asynchronously outside the training process, an off-process watcher periodically tracks each domain's KL trajectory, estimates remaining headroom and current improvement rate, and accordingly adjusts the domain sampling ratios without altering the core training loop. Our D$^3$-MOPD scales naturally to arbitrary numbers of domains, and the expected benefit grows as more domains introduce more diverse convergence patterns for the scheduler to exploit. On a Qwen3.6-35B-A3B student distilled from four domain-expert teachers, D$^3$-MOPD closes 97% of the average student-to-teacher performance gap, compared with 63% for vanilla MOPD, reaches the same peak performance with an approximately 3$\times$ reduction in rollout steps, and surpasses the specialist teachers on three of seven benchmarks.

AI 总结：本文提出回推解码重构（RDR）损失项，提升了潜在世界模型在混沌Kuramoto-Sivashinsky方程上的长时序预测性能，参数规模不变且仅增加训练开销。

链接：https://arxiv.org/abs/2608.25017

机构：E3A Healthcare（E3A医疗保健公司）

作者：Rishi Shah, Rishav Shrestha

英文摘要：A latent world model trains its decoder on latents anchored to observations, then deploys it on the model's own free-running rollout, hundreds of steps past the last observation. Rollout-Decoded Reconstruction (RDR) closes this gap with a single loss term that free-runs the model during training exactly as evaluation will, decodes every rollout latent, and penalizes reconstruction error against ground truth. The term adds no parameters, costs training-time compute only, and reduces to the standard objective at weight zero, so every comparison in this paper is a one-flag A/B. On the chaotic Kuramoto-Sivashinsky equation, RDR raises valid prediction time (the time to first crossing of normalized error 0.5) from $3.87 \pm 0.23$ to $6.97 \pm 0.42$ time units at an identical 193,568 parameters, a $1.80\times$ improvement confirmed on seeds never used in selection and holding in 10 of 10 preregistered configurations at ratios of 1.71-2.50$\times$. The results come from a single system; a sweep in which the advantage grows with latent width is descriptive, and control experiments on two classic tasks are preliminary.

AI 总结：该研究提出以单元为机器学习的显式语义基元，定义单元关联事件的学习框架，给出监督学习特例的形式化结果，区分单元敏感与不敏感学习，解决单元身份未明确时的学习问题。

链接：https://arxiv.org/abs/2608.25118

作者：Heyang Gong

英文摘要：Machine learning is usually formalized through samples, while the persistent individual to which multiple observed or possible events refer often remains implicit. We propose the \emph{unit} as an explicit primitive at the level of task semantics. A learning task first declares a population of persistent referents and a sameness criterion; the realized value $u$ denotes the selected referent. Supervised learning is the main formal specialization. Its semantic object is a family of unit-conditioned response laws. Homogeneity is the special case in which those laws coincide; a sample-only conditional is silent as to whether the world is homogeneous or the observed law is only the marginal of a heterogeneous family. What is learned from data is a pair $(T_\phi,R_\theta)$: a tokenizer that produces a contextual unit token and one shared response-law form that reads it. The structured class takes that form to be a simple relation in the token; a linear predictor is the running instance. The token is the learner-side representation through which the task-side unit affects prediction, while a learner specification that omits unit information is unit-insensitive; homogeneity remains a property of the world-side response family. When identity is unresolved, the world-side law mixes unit-conditioned targets, while the learner composes its shared form with a token. A trusted resolver may fix the unit and supply a lookup token; otherwise \emph{unit abduction} forms a token of the same type from factual evidence. Unlinked single-row observations can fail to distinguish a heterogeneous unit world from a homogeneous pooled world; trusted same-unit pairs separate a restricted witness. The formal results concern this supervised specialization.

AI 总结： 本文提出多模态网球运动员准备度预测框架PART，整合多源数据，可评估网球运动员健康、损伤风险等，在大学生网球运动员数据上表现良好，也适用于业余选手。

链接：https://arxiv.org/abs/2608.25126

机构：Monmouth University（蒙茅斯大学）

作者：Francisco Erramuspe Alvarez, Shobharani Polasa, Weihao Qu, Jay Wang, Ling Zheng

英文摘要：Machine learning has had a significant positive impact on the prediction of athlete performance and injury risk. Most works in this field rely on subjective observations and expert assessments, which restrict their effectiveness. In sports like soccer, basketball, and wrestling, some studies attempt to address this challenge by integrating data from alternative sources, such as readings from wearable devices, alongside traditional subjective observations and expert assessments to enhance accuracy. However, similar research in tennis remains largely unexplored. In this paper, we propose a multimodal Predictive Athlete Readiness framework for Tennis (PART) to assess both performance and injury risk in tennis players. By leveraging machine learning and deep learning techniques, PART processes multiple sources of data collected from nine collegiate tennis players, including physiological metrics, training and match data, sleep data from wearable devices, self-reported information via daily questionnaires, jump assessments, and motion analysis from match play videos. PART captures four characteristics of tennis players: overall wellness, injury risk, physical capability, and playing style. By integrating these four characteristics by supervised learning, it is capable of providing a holistic assessment of the tennis athlete's condition, along with advanced forecasts of specific body areas at risk such as the upper body (e.g., elbows) or lower body (e.g., knees). Our evaluation, conducted with data from nine collegiate tennis players, shows that PART achieves strong performance in predicting both overall wellness and injury risk. Additionally, our framework also shows promise for recreational tennis players, who often suffer from injuries due to incorrect playing techniques.

AI 总结：该研究提出SNAP-KG框架，通过训练投影器实现流式知识图谱实体的快速分配，在多个基准数据集和生产级KG上实现推理速度大幅提升与候选搜索范围显著缩小。

链接：https://arxiv.org/abs/2608.25149

机构：Rensselaer Polytechnic Institute（伦斯勒理工学院）

作者：Jui-Chien Lin, Mohammad Mohammadi Amiri, Oshani Seneviratne

英文摘要：Knowledge graph (KG) construction pipelines must continuously integrate newly arriving entities into a growing graph. Unlike inserting triples between existing nodes, a newly arriving entity has no graph connectivity: it emerges from the acquisition phase as a raw feature vector and must be assigned to a semantic community before entity resolution and link prediction can operate over a tractable candidate set. Existing multi-view graph clustering methods exploit multiple relation types as structural views, but are transductive: they assume a fixed graph and cannot assign unseen entities without retraining. We propose SNAP-KG (Streaming Node Assignment via Projection for Knowledge Graph Entity Integration), a framework supporting graph-structural multi-view relational clustering and inductive inference for streaming entities. SNAP-KG trains a projector to map a new entity directly to the learned embedding space using only raw features, enabling immediate cluster assignment without graph access or model retraining. Experiments on five benchmark multi-view graph datasets and a production-scale KG of 2.4 million nodes demonstrate multiple orders-of-magnitude inference speedups over retraining-based approaches and competitive clustering quality. As a candidate scoping mechanism for downstream tasks, SNAP-KG achieves 62-75% candidate search reduction on the five benchmark datasets and 97% on OGB-WikiKG2 for entity resolution and link prediction.

AI 总结：本研究提出一种框架，可同时非参数推断群体动力学的相互作用核并学习环境力，通过引入的模型选择程序能从轨迹数据区分群体动力学框架并恢复相互作用机制。

链接：https://arxiv.org/abs/2608.25181

机构：Clarkson University（克拉克森大学）； University of Houston（休斯顿大学）

作者：Nipuni de Silva, Ming Zhong, James M. Greene

英文摘要：Collective dynamics arise in a wide range of physical, biological, and engineering applications. Examples include cell migration, swarm robotics, social dynamics, and animal behavior. A defining characteristic of these systems is the emergence of large-scale coordination from local interactions among agents; a fundamental question is thus to understand the local interactions that give rise to the observed emergent dynamics. We are interested in methods for learning interactions generally, which can describe a wide class of physical systems exhibiting collective dynamics defined by an interaction kernel, without a priori assumptions on the analytical form of this kernel (i.e. it is nonparametric). The advantage of this kernel-based approach is that it incorporates the underlying physics of the model (i.e. collective dynamics), which more general equation-learning approaches may ignore, potentially limiting their effectiveness for model accuracy and predictions. In this work, we extend existing variational learning approaches to collective systems with both interaction kernels and environmental/intra-agent forces. The proposed framework simultaneously infers the interaction kernel non-parametrically while learning the environmental force using either semi-parametric or fully nonparametric representations. The methodology is validated on several benchmark models exhibiting synchronization, alignment, attraction-repulsion, and external environmental forces. We also introduce a model-selection procedure based on our nonparametric learning framework to identify models that optimally explain a given set of trajectory observations. By exploiting the feature-identification capability of the learned models, the proposed procedure can distinguish among different collective dynamics frameworks and recover mechanistic interaction mechanisms directly from trajectory data.

AI 总结：本研究针对LLM量化的变换阶段，提出大逆变换原则，分析变换与数字格式的协同设计，综述200项研究分类43种变换方法，提炼部署指南并指出开放问题。

链接：https://arxiv.org/abs/2608.25188

作者：Ehsan Jokar

英文摘要：Most competitive 4-bit LLM research pipelines now open the same way: apply a linear, function-preserving transform (rotation, scaling, permutation, non-orthogonal affine) so the outlier mass sits more favorably against the group scales, and only then round. Yet we are aware of no survey dedicated to this transform stage, and its literature is quietly re-deriving an older theory. We identify and formalize the principle that organizes it, the Great Inversion: allocation-flexible coding rewards energy concentration, whereas the grouped shared-scale quantization a deployed matrix instruction performs rewards within-group flattening. Classical transform coding (1963: decorrelate, allocate bits, quantize) spends different bits per coordinate at a fixed total rate; for a Gaussian source at high rate the Karhunen-Loeve transform's concentration minimizes distortion. A deployed operand tile instead carries one absolute-maximum scale per group and equal bits everywhere, with no allocation; on a uniform grid that objective rewards flattening, approached by Hadamard incoherence. We prove that opposition under within-group majorization: the prescriptions point in opposite directions, each backed by a proof against its own objective, and for a generic spectrum no optimality guarantee transfers. A second axis is the number format: the non-uniform FP4 grid makes flattening buy less, MXFP4's power-of-two block scale still rewards a rotation confined to that block, and NVFP4's mantissa-carrying scale largely removes that pull, so the target pole depends jointly on allocation regime and format. We survey 200 works to a June 2026 cutoff; classify 43 transform methods by structure, data-awareness, searched-versus-constructed, and runtime cost; record, where reported, how they compose with GPTQ rounding; distill a first-choice guide by deployment regime; and close with the open problems it exposes.

AI 总结：该研究在分层分类模型中，对比庞加莱球与欧氏空间作为树结构原型网络的潜在流形，发现双曲流形能更好保留近邻图拓扑，在局部检索任务上优于欧氏流形，为两类潜在几何提供经验区分。

链接：https://arxiv.org/abs/2608.25199

机构：Harvard University（哈佛大学）

作者：Peter Flo, Luca Grossmann

英文摘要：We study a tree-structured regularizer over class-prototype layouts in a hierarchical-classification model and ask whether the choice of latent manifold for the prototypes (Euclidean R^d vs. the Poincare ball B^d_c) affects how well that regularizer can be satisfied without distorting the data likelihood. The two manifolds differ only in their volume growth: hyperbolic space grows exponentially with radius and embeds trees with provably lower distortion than R^d of matched dimension, so the structured regularizer should be cheaper to satisfy on B^d_c. Across 150 seed-replicated regularized maximum-likelihood fits spanning embedding dimension, curvature, and regularizer strength on WikiArt (27 styles, 81,446 paintings, frozen CLIP ViT-B/16 features), we find a single robust effect: Poincare prototypes preserve the topology of the nearest-neighbor graph in latent space substantially better than matched Euclidean prototypes (sibling recall@5 +8.7 pp, cousin recall +15.2 pp; paired-t p < 10^-4, sign agreement 0.94), and the gap holds across three reference-tree definitions (hand-built lineage, CLIP-derived, and DINOv2-derived). On classification, Euclidean prototypes are tied with logistic regression on raw encoder features, indicating no detectable contribution from the latent geometry; only the hyperbolic fit improves on a k-NN encoder baseline for local retrieval. Global tree-fidelity comparisons are unstable across reference trees and we do not claim a winner. The results give an empirical separation, on a real hierarchical-classification problem, between two natural latent geometries for a class-structured regularizer.

AI 总结：该研究针对异质偏好下多向排序的模型混合问题，提出MoPLEx算法，通过扩充排序并结合梯度估计与期望最大化，在偏好优化任务上显著优于基线方法。

链接：https://arxiv.org/abs/2608.25200

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

作者：Dongyue Li, Ziniu Zhang, Lu Wang, Hongyang R. Zhang

英文摘要：We consider the problem of learning a mixture of $k$ Plackett-Luce models given multi-way ranking responses from annotators that may represent heterogeneous underlying preferences. This problem has many applications in AI alignment and preference optimization. Prior work has studied mixtures of Bradley-Terry models from pairwise comparisons. However, uncovering mixture models is theoretically unidentifiable when $k$ exceeds $m/2$, where $m$ is the length of a ranking. We propose an efficient implementation to address this limitation, which involves first augmenting the rankings to a larger size by generating new responses from a base language model, followed by a gradient-based estimation to reduce inference cost in the input embedding space. Based on this procedure, we then design an expectation-maximization algorithm with these two steps to fit a mixture of Plackett-Luce models, called MoPLEx. Extensive experiments are conducted to verify this approach. First, we show that the gradient-based approximation estimates true probabilities with less than 5% error on models with up to 34 billion parameters. Second, we show that MoPLEx improves clustering and ranking accuracy by an average of 43.7% and 15.2% over baselines using single ranking and mixtures of Bradley-Terry models, on preference optimization datasets. These results demonstrate the effectiveness of MoPLEx for tackling multi-way rankings from heterogeneous preferences through measuring alignment between gradients.

AI 总结：该研究针对MAX_N函数的双隐藏层ReLU网络表示问题，通过计算机辅助搜索独立得到MAX₅至MAX₈的表示，与近期Ruess等人的成果存在细微差异，为相关研究提供了新进展。

链接：https://arxiv.org/abs/2608.25221

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

作者：Zhimao Wang, Amitabh Basu

英文摘要：We study exact representations of $\mathrm{MAX}_N(x)=\max{x_1,\ldots,x_N}$ using two-hidden-layer ReLU neural networks. This problem has been studied in recent years in an attempt to characterize the exact number of hidden layers required to represent continuous piecewise linear functions. The best lower bound is 2, while the current upper bound is logarithmic in $N$. It remains completely open if the right answer is a constant number of hidden layers (possibly even 2!) or not. In fact, a recent breakthrough was the representation of $\mathrm{MAX}_5$ as a two-hidden-layer ReLU function obtained in [Bakaev et al., 2026], and the case of $\mathrm{MAX}_N$ was stated as open for $N\geq 6$ in that paper. Using a careful computer assisted search, we obtain two-hidden-layer ReLU representations of $\mathrm{MAX}_5, \mathrm{MAX}_6, \mathrm{MAX}_7$, and $\mathrm{MAX}_8$. We obtain these by considering rational linear combinations of terms of the form $\max\{\sum_{r=1}^{s}\max(x_{a_r},x_{b_r}),\sum_{r=1}^{s}\max(x_{c_r},x_{d_r})\}$, where $a_r,b_r,c_r,d_r\in\{1,\ldots,N\}$. Each inner maximum of two coordinates can be computed in a first hidden layer, and the outer maximum of the two side-sums can be computed in a second hidden layer. Consequently, every finite linear combination of these terms has a two-hidden-layer ReLU realization. An identity for $\mathrm{MAX}_N$ in this form therefore gives an exact two-hidden-layer ReLU representation of $\mathrm{MAX}_N$. Very recently, two-hidden-layer representations of $\mathrm{MAX}_N$ of the above form were obtained for all $N\leq 10$ in [Ruess et al., 2026]. Our representations are different and were developed independently. While our techniques share most of the high-level ideas presented in [Ruess et al., 2026], there are also some minor differences which may be of interest for future research on this problem.

AI 总结：本研究针对可信合作者选择的长期行为评估挑战，提出双向Mamba模型BM，通过构建图聚合特征并整合时间依赖，提升评估准确率以选出高价值合作者。

链接：https://arxiv.org/abs/2608.25232

机构：Western University（西安大略大学）

作者：Botao Zhu, Xianbin Wang

英文摘要：Effective selection of trustworthy collaborators is crucial to ensuring the successful completion of collaborative tasks, which requires accurate assessments of both long-term device behavior and short-term collaborative dynamics. Consistent device behavior patterns, which are learned from historical collaborations, can be used to predict their reliability in future collaborations. However, accurately assessing device behavior based on historical collaborations remains challenging. First, behavior assessment from limited historical collaborations captures only instantaneous past behavior, failing to represent the devices' true behavior. Second, due to the temporal dependencies of device behavior, a unidirectional evaluation that relies only on earlier collaborations loses the opportunity to learn from subsequent collaborations. Addressing these challenges requires evaluating device behavior based on long-term collaborations while considering both forward and backward temporal dependencies. To this end, this work proposes a bidirectional Mamba-enabled model (BM) for long-term behavioral evaluation. For each short time slot, a graph is constructed among devices based on historical collaborations, and device behavioral features within the slot are then aggregated accordingly. Subsequently, a bidirectional Mamba model integrates these short-term representations across all time intervals, producing a stable and reliable long-term behavior evaluation for each device. Experimental results demonstrate that BM achieves higher evaluation accuracy than baseline methods, thereby enabling the selection of collaborators that maximize the value of task completion.

AI 总结：本文提出ShuttleArena羽毛球自博弈环境，采用PPO训练策略，实现了可解释的战术探测与竞争力提升，为交互式数字娱乐AI提供了有用测试平台。

链接：https://arxiv.org/abs/2608.25246

机构：Columbia University（哥伦比亚大学）

作者：Peize Ding

英文摘要：Badminton is a compact but challenging domain for game AI: a player must choose a physically feasible shuttle trajectory, anticipate the opponent's interception, and recover to a court position whose value depends on the opponent's next response. The central challenge is that shot selection and recovery are not separable: the best recovery depends on the shot-induced opponent response, while the value of the shot depends on whether the hitter can cover the reply. This paper presents ShuttleArena, a physics-based singles badminton self-play environment that couples continuous shuttle flight, player interception, structured shot generation, and post-shot recovery. The policy uses role-conditioned outputs: a masked interception choice on receiver turns and a factorized hitter action over shot azimuth, shot elevation, shot speed, and recovery target, enabling interpretable tactical probes. Episodes are single rallies rather than full scored games, and training uses Proximal Policy Optimization (PPO) self-play against a staged checkpoint opponent pool with sparse terminal rally-outcome rewards and a factor-specific recovery update. Evaluation with frozen checkpoint play, controlled tactical probes, recovery ablations, qualitative rollouts, and a human-data sanity check shows competitive improvement together with interpretable opponent-conditioned changes in shot geometry and recovery behavior. The learned policies produce recognizable badminton-like structure while also reflecting the abstractions of the simulator, and the recovery intervention shows that learned recovery behavior is competitively important. These results suggest that physics-based racket sports are a useful testbed for interactive digital entertainment AI because they require agents to coordinate execution, positioning, and opponent-relative tactical value.

AI 总结：本文提出Neural-BSL框架，耦合可微结构学习与离散选择估计，经首尔、伦敦数据评估，其预测性能与传统基准相当，可恢复行为一致的依赖结构，能有效分析干预措施的下游影响。

链接：https://arxiv.org/abs/2608.25258

作者： Hyunsoo Yun, Eun Hak Lee, Jiaru Zhang, Ziran Wang, Eui-Jin Kim

英文摘要：Conventional discrete choice and machine learning models are estimated primarily from observational data and typically treat explanatory covariates as parallel inputs, providing no internal mechanism for determining how related attributes should adjust when one is deliberately changed. This paper proposes Neural-Bayesian Structure Learning (Neural-BSL), a framework coupling differentiable structure learning with random-utility-based discrete choice estimation in a single differentiable procedure. To prevent mutually exclusive choice outcome from distorting the recovered attribute structure, the observed choice is maintained outside the graph as an alternative-specific utility comparison, while the attribute structure and random-utility parameters are learned jointly. The learned structure enters the choice model through structure-weighted attribute interactions and provides the structural basis for propagating interventions through downstream attributes. An intervention is evaluated by updating the intervened attribute, propagating its model-implied downstream changes in topological order, and then recomputing utilities and choice probabilities. This yields both predicted mode-share responses and the associated changes in downstream traveler or trip attributes. We evaluate Neural-BSL using stated-preference data from Seoul and the revealed-preference data from London. Neural-BSL achieves predictive performance comparable to conventional benchmarks while recovering behaviorally coherent dependency structures. Across policy scenarios, propagating interventions through the learned structure changes the predicted redistribution across modes while exposing the downstream traveler and trip adjustments underlying those responses.

AI 总结：该研究针对扩散语言模型提出测试时自验证方法PDC，通过前缀条件再生的轨迹稳定性差异修正初始生成样本，在两类推理基准中提升性能且具鲁棒性。

链接：https://arxiv.org/abs/2608.25311

机构：MBZUAI（穆罕默德·本·扎耶德人工智能大学）； Nagoya University（名古屋大学）； RIKEN AIP（理化学研究所人工智能项目）

作者：Yuki Ichihara, Naoto Iwase, Mohammad Atif Quamar, Junpei Komiyama

英文摘要：Diffusion Language Models (DLMs) have recently become increasingly competitive with autoregressive (AR) models, and even outperform them on certain tasks. Unlike AR models, DLMs produce output through iterative denoising without a left-to-right order. To further improve the performance of DLMs, we introduce PDC (\emph{Prefix-Denoising Consistency}), a test-time self-verification method for DLMs. PDC exploits a distinctive test-time signal in DLMs under prefix conditioned regeneration, correct trajectories are more stable and reproducible than incorrect ones. Concretely, given an initially generated sample, PDC splits the sentence at an intermediate position and regenerates the remaining tokens conditioned on the fixed prefix. Across mathematical reasoning and commonsense reasoning benchmarks, PDC consistently improves upon the initial sample, outperforms independent generations under a computational constrained comparison, and is robust to different unmasking strategies and parameter settings. These results highlight prefix-conditioned regeneration as an effective DLM-specific primitive for test-time verification.

AI 总结：本文针对激活空间序交换几何提出位点非对称性检验，通过分解响应、在多类语言模型及非语言模型上开展实验，提出解读序交换向量的测量准则。

链接：https://arxiv.org/abs/2608.25315

机构：Substrate Labs

作者：Anqi Peter Li

英文摘要：Order-dependent activation statistics are often interpreted as evidence of interaction, but that interpretation can be confounded by where interventions enter the network. We introduce a no-fit site-asymmetry audit. For a twice-differentiable readout, the open-path order-swap decomposes into a canonical additive response measured by single interventions and an antisymmetrized second difference free of first-order and pure self-curvature terms to second order. Across six open-weight language-model families, the single-intervention baseline explains 84.3-97.7 percent of the bracket norm (mean 93.7 percent), while the no-interaction self-curvature term is 1.8-5.2 times larger than the corrected residual in the two families with the plus/minus injection split. The corrected residual clears a generic-interaction null in three of six families under a confound-free prompt split and two of six after configuration robustness. A known-positive surrogate recovers planted mixed interaction, while a matched site-separation test changes the baseline share and a random architecture reproduces the first-order regime. The same estimator transfers to released non-language references: trained residual fractions fall below a fixed Gaussian-direction null in 11/12 contrasts (5/6 ViT-B/16, 6/6 ResNet-50), a portability check rather than pooled evidence. The contribution is a reusable measurement criterion: run the single-intervention baseline before reading an order-swap vector as interaction or geometric structure; if it explains the vector, form the second difference instead. All claims are scoped to activation-space interventions at distinct sites; we do not claim that representation geometry is globally Abelian.

AI 总结：针对多任务模型合并的任务干扰问题，本文提出基于SAEs的高维稀疏解缠合并框架，结合GR-ZOO实现选择性合并，在Qwen2.5系列模型的多任务上优于现有基线。

链接：https://arxiv.org/abs/2608.25354

机构：Central South University（中南大学）； Nanjing University of Science and Technology（南京理工大学）； Hefei University of Technology（合肥工业大学）

作者：Yihang Zhang, Shengke Sun, Junjie Wen, Feng Zeng

英文摘要： Model merging provides an efficient way to construct multi-task generalist models without additional training, but its performance often degrades under severe task interference. Task interference in model merging primarily stems from \textit{superposition}, where task-specific features become entangled within the parameter space. This entanglement renders conventional decomposition methods insufficient for effectively isolating useful task directions from interfering components. In this paper, we propose a sparse-representation-based merging framework that uses Sparse Autoencoders (SAEs) to project task vectors into a high-dimensional sparse feature space, enabling feature-level disentanglement before fusion. To reduce computational overhead, we further introduce a lightweight Group-Ranked Zeroth-Order Optimizer (GR-ZOO) to identify task-critical layers for selective merging. Experiments on both Qwen2.5-1.5B and Qwen2.5-7B demonstrate that our method consistently outperforms representative baselines, including Task Arithmetic, TIES-Merge, DARE, Fisher-Merge,and several recent training-free merging methods, across mathematical reasoning, code generation, instruction following, and general knowledge tasks. In a highly conflicting four-task setting on Qwen2.5-1.5B, our method further achieves a 2.78\% improvement over the strongest baseline.

AI 总结：针对噪声节点分类任务，提出基于部分标签学习的自训练框架PaSta，通过多标注器聚合构建部分标签并结合双损失函数，经闭环迭代优化，在五个数据集上较SOTA方法平均提升1.1%性能。

链接：https://arxiv.org/abs/2608.25365

机构：School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院）

作者：Yujing Liu, Yixin Liu, Yu Zheng, Yue Tan, Alan Wee-Chung Liew, Shirui Pan

英文摘要：Noisy node classification problem is a fundamental yet challenging task for real-world graph-related web services, where node labels are often corrupted or unreliable due to weak supervision or automatic annotation. However, existing methods typically train models based on one-hot labels, which not only makes models susceptible to overfitting on noisy labels, but also leads to error accumulation after pseudo-label-guided enhancement. In this paper, we propose a novel Partial label-based Self-training framework (PaSta for short) that leverages partial label learning technique to overcome the limitations of existing methods. Specifically, PaSta first trains multiple annotators to comprehensively capture the class distribution of nodes and aggregates their predictions to construct high-quality partial labels. Subsequently, we design a partial label-based classification model with two well-crafted loss functions to guide the model learning at both label and representation spaces. To further enhance the robustness against noisy labels, we introduce a self-training strategy where the labels refined by partial label learning are then used to further optimize the annotators in a closed-loop iterative manner. Extensive experiments on five datasets demonstrate that, compared with existing state-of-the-art methods, PaSta achieves an average improvement of 1.1% in classification performance under various noise settings.

AI 总结：针对多模态回归的均值崩溃问题，提出差商聚类（DQC）方法，通过最小化簇内差异分配标签，在合成基准上取得优于随机标签和均值崩溃的最小平方误差，为后续生成优化减轻负担。

链接：https://arxiv.org/abs/2608.25467

机构：Guangdong Polytechnic Normal University（广东技术师范大学）

作者：Huang Weiquan

英文摘要：Multimodal regression suffers from the mean-collapse pathology: under squared loss, an unconstrained regressor converges to the conditional mean, which for K > 1 lies away from all modes. We attribute this failure to pairwise contradictions--samples with nearly identical inputs but distant outputs--and propose Difference-Quotient Clustering (DQC), which partitions data to minimize intra-cluster output-vs-input discrepancy. Each sample is assigned to the cluster that minimizes its maximum contradiction ratio; a logits generator and a conditional network are then trained on the resulting labels. Since the generating modality is unknown at test time, we evaluate via minimum squared error (minMSE) against all K true outputs. On synthetic benchmarks (K=5, 10), DQC achieves test minMSE 0.19 (K=5, nx=500), versus 0.09 for an oracle, 1.08 for random labels, and 1.33 for mean collapse. We observe two empirical regularities: larger intra-cluster contradictions require deeper networks, and oracle labels generalize from fewer samples than cluster-derived equivalents. The clustering is a hard, parallelizable O(n^2/2) front-end for coarse conditional assignment, reducing the burden of downstream generative refinement. A second-stage re-clustering on residual errors is outlined as future work.

AI 总结：本研究提出通过正交投影技术去除蛋白质语言模型嵌入中的可解释生化特征效应，证明其编码与生化特性相关的模式并量化其对蛋白质适应性预测的贡献，该方法可迁移至其他问题场景。

链接：https://arxiv.org/abs/2608.25548

机构：Hasso Plattner Institute, University of Potsdam（波茨坦大学哈索·普拉特纳研究所）； Broad Institute of MIT and Harvard（麻省理工学院及哈佛大学布罗德研究所）； Humboldt University of Berlin（柏林洪堡大学）； Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）

作者：Paulo Yanez Sarmiento, Pia Francesca Rissom, Manuel Pfeuffer, Marco Simnacher, Jordan F. Safer, Sumaiya Iqbal, Henrike O. Heyne, Nadja Klein, Bernhard Y. Renard

英文摘要： Recently, there has been a growing adoption of protein language models (PLMs) in biomedical science. Their embeddings provide a rich numerical representation of protein sequences which achieve state-of-the-art performance on several downstream tasks including protein fitness prediction. However, PLM embeddings are not directly interpretable and, thereby, it remains unclear what features they encode. To gain insight into which biochemical properties of the protein are driving the prediction, we leverage an orthogonal projection technique that removes linear effects of known tabular features from embeddings and extend it to high-order and interaction effects. In this way, we remove the effects of interpretable biochemical features from PLM embeddings. In an ablation study, we show that this leads to a decrease in performance for a downstream classifier trained only on the embeddings to predict protein fitness. In an additional evaluation, we find that these biochemical features explain a substantial part of the variance in the predictions of this classifier. Hence, we can show that PLM embeddings encode patterns correlated with biochemical properties and quantify their contribution to predicting protein fitness. This computationally efficient approach is not limited to the features or embeddings considered here and is readily transferable to problem settings beyond protein fitness prediction.

AI 总结：本文提出KOPE框架，通过经验图记忆与主动上下文管理实现硬件内核优化自演进LLM智能体，在相同模型设置下其加速比、通过率等关键指标显著优于现有基线方法。

链接：https://arxiv.org/abs/2608.25570

机构：City University of Hong Kong（香港城市大学）； Huawei Technologies Ltd.（华为技术有限公司）

作者：Siyuan Chen, Runlin Hou, Shenxiu Wu, Yansong Sun, Junming Cao, Yiyu Zhang, Shudi Shao, Junhao Qiu, Zhichao Lu, Qingfu Zhang

英文摘要：Hardware kernel optimization requires repeated compilation, correctness testing, profiling, and revision. LLM agents can automate parts of this process, and stronger foundation models, longer context windows, and longer execution horizons have improved optimization within individual tasks. These advances alone do not enable an agent to learn from completed optimization runs. Existing kernel-optimization agents seldom preserve a decision, its observed execution feedback, and the later decisions that use that evidence. Retaining every prior trajectory is also impractical because an expanding history competes with the current task for context. We present KOPE, an experience-driven framework for hardware kernel optimization. KOPE records optimization trajectories with correctness and performance feedback in Experience Graph Memory, then uses Active Context Management and Injection to retrieve relevant experience under a fixed token budget. The graph retains decision order, observed outcomes, and alternative branches, allowing evidence collected on the target hardware to inform later optimization steps and tasks. Under the same GLM-5.2 setting, the geometric mean of KOPE's per-operator speedups is $1.54\times$ that of CANNBot, the strongest competing baseline. In a complete 53-operator ablation, Active Context Management and Injection raises pass rate from 60.0\% to 84.6\%, increases the evaluator-reported positive-field geometric mean from 0.0382 to 0.0661, and reduces optimization token consumption from 15.9B to 1.113B tokens relative to passive agent-led context construction. Enabling Experience Graph Memory raises full-suite pass rate from 55.2\% to 84.6\% and yields a $1.43\times$ geometric-mean speedup on valid timing comparisons. These results support continual optimization through external experience while the foundation model remains fixed.

AI 总结：针对层次聚类扭曲局部相似性影响单个数据点的问题，将个体公平性要求限制在k近邻范围，刻画可行性所需松弛量并通过实验验证相关理论结果。

链接：https://arxiv.org/abs/2608.25586

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

作者：Binita Maity, Shrutimoy Das

英文摘要：Hierarchical clustering produces ultrametric representations that impose strong global geometric constraints and may distort local similarities in ways that disproportionately affect individual data points. We study hierarchical clustering under an individual fairness requirement that bounds relative distortion within local $k$-nearest neighborhoods. We formulate this requirement as a feasibility problem over dominated ultrametrics and characterize the minimal multiplicative slack required for feasibility. We identify a sharp local threshold, prove stability under bounded perturbations, establish monotonicity in $k$, and show an intrinsic $\Theta(\log n)$ separation between local and global realizability. Experiments on synthetic and real world datasets support our theoretical results.

AI 总结：本文提出M-纤维化理论框架，将图纤维化理论扩展至交换幺半群带标签图等场景，并将其应用于任意神经网络压缩，为相关几何深度学习成果提供理论支撑。

链接：https://arxiv.org/abs/2608.25598

机构：Università degli Studi di Milano（米兰大学）

作者：Paolo Boldi

英文摘要：The purpose of this paper is to provide a general, comprehensive, theoretical framework that allows one to deal with fibrations on graphs labelled on a commutative monoid. This is a genuine extension of the theory of graph fibrations (as introduced in "Fibrations of Graphs" [Discrete Math., vol. 243, pp. 21-66, 2002]), that makes it possible to deal with weighted graphs, and also graphs labelled with other algebraic structures. The derived theory also lends itself naturally to consider approximate fibrations. As an example, we show how this framework can be applied to the compression of arbitrary neural networks (including CNNs), providing a strong theoretical underpinning to the recent results in "The role of fibration symmetries in geometric deep learning" [Proc. Natl. Acad. Sci. USA, vol. 123, no. 4, p. e2416552123, 2026]

AI 总结：本研究分析反向KL策略上蒸馏的梯度特性，提出Surprise-aware Reweighting（SuRe）加权规则，在Qwen3学生模型上提升了数学指标且域外基准无明显下降。

链接：https://arxiv.org/abs/2608.25643

机构： College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院）

作者：Bing Shao, Jiazheng Zhang, Long Ma, Yujiong Shen, Senjie Jin, Xin Guo, Yuming Yang, Mingxu Chai, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang

英文摘要：On-policy distillation (OPD) supervises a student on its own trajectories with token-level signals from a frozen teacher, yet how a sampled loss allocates updates across tokens remains poorly understood. We analyze the gradient of the per-token K2 estimator of reverse KL with respect to the student logits. The $\ell_1$ norm of this gradient factorizes into the absolute teacher--student log-probability gap and a student-side softmax factor that grows as the sampled token becomes less likely under the student. In our math-distillation runs, these per-token norms are highly non-uniform: low-student-probability tokens account for a disproportionate share of their sum and are also enriched in large teacher--student gaps. As a lightweight intervention suggested by this analysis, we study Surprise-aware Reweighting (SuRe), a detached, bounded weighting rule that further amplifies this existing allocation. Across two Qwen3 student scales, SuRe improves several math metrics over vanilla OPD and shows no clear degradation on the selected out-of-domain benchmarks. Our primary contribution is therefore a gradient-level characterization of reverse-KL OPD trained with the K2 estimator, with SuRe as one empirical instantiation.

AI 总结：该研究针对低成本MOX气体传感器信号漂移等问题，提出LDAC-Net网络，在SmellNet等数据集上的识别准确率优于现有方法，证明可学习预处理比固定差分更有效。

链接：https://arxiv.org/abs/2608.25646

机构：Manchester Metropolitan University（曼彻斯特城市大学）

作者：Xin Zhang, Liangxiu Han, Yue Shi, Tam Sobeih

英文摘要：Portable electronic-nose systems based on low-cost metal-oxide (MOX) gas sensors offer a practical solution for gas and odour recognition, but their signals are affected by slow chemical transients, drifting sensor offsets, scale variation, and cross-channel correlations. Existing pipelines commonly use fixed first-order temporal differencing (FOTD), which requires a manually selected lag and may discard useful response information. We propose LDAC-Net, an end-to-end learnable multi-lag differencing attention-convolution network that operates directly on multi-channel MOX signals. Its learnable differential feature enhancement front-end combines window-conditioned statistical affine normalisation, which compensates for window-specific offset and scale variation, with learnable multi-lag differencing, which weights and combines temporal differences across multiple lags. A compact attention-convolution backbone subsequently models local transients and longer-range temporal dependencies. On the 50-class SmellNet-Base task, LDAC-Net achieves 68.2% top-1 accuracy, exceeding the best FOTD-preprocessed comparison model by approximately 14 percentage points and the raw-input Transformer by more than 30 points. Ablation studies confirm the contributions of both proposed components. The representation also transfers to SmellNet-Mixtures, improving accuracy from 45.4% to 50.5%, and generalises to the 62-channel eNose-Drift benchmark under strong long-term drift, achieving 70.6% top-1 accuracy and 69.6% macro-F1. These results outperform the best comparison model with dataset-retuned FOTD preprocessing by 8.0 and 3.0 points, respectively, demonstrating that learnable, sensor-aware preprocessing is more effective than fixed handcrafted differencing for low-cost MOX gas-sensor recognition.

AI 总结：本研究提出一种空间感知深度学习框架，利用Meteosat灵活组合成像仪数据反演对流层温湿廓线，无需数值天气预报预报场，经探空数据验证性能良好，可支持快速大气自主监测。

链接：https://arxiv.org/abs/2608.25700

机构：Delft University of Technology（代尔夫特理工大学）； Bern University of Applied Sciences（伯尔尼应用科学大学）； Meteomatics AG（美迪奥马蒂克斯公司）

作者：Alejandro Salgueiro, Johannes Rausch, Julie Thérèse Villinger, Angela Meyer

英文摘要：The Meteosat Third Generation (MTG) Flexible Combined Imager (FCI) offers new opportunities for tropospheric temperature and humidity profiling, at higher spatio-temporal resolutions and expanded spectral coverage relative to its predecessor. Vertically resolved retrievals from broadband imagers are inherently challenging, and operational retrieval algorithms typically rely on numerical weather prediction (NWP) background fields to compensate for limited infrared spectral resolution, reducing the retrievals' independence. We develop a spatially aware deep learning framework to retrieve all-sky tropospheric temperature and humidity profiles from FCI, without forecast profiles as input. A Residual U-Net that exploits spatial context across all 16 FCI channels was trained on 14 months of collocated FCI observations and CERRA reanalysis targets over Europe. Validated against independent radiosondes, retrieved temperatures show biases below 0.4 K and standard deviations of 1.5-1.9 K. Retrieved relative humidity standard deviations range from 12-20 %, compared to 9-19 % for CERRA. Performance degrades modestly under clouds, with standard deviation increases below 0.4 K and 3 % RH beneath cloud tops despite limited direct radiative information. Ablation experiments show that spatial context improves retrievals, with the largest gains below cloud tops. Feature sensitivity analysis indicates broad consistency with FCI bands' established radiative transfer characteristics. Visible and near-infrared channels contribute despite not being commonly used in physics-based profile inversions. These results demonstrate that spatially aware deep learning models can extract statistically reliable tropospheric profiles from geostationary imager observations, independent of NWP forecast fields, enabling more rapid autonomous monitoring of the atmosphere.

AI 总结：本文针对多目标强化学习及后继特征方法未考虑同一决策问题中不同时间尺度非线性效用效应的不足，通过示例论证后提出新视角，指出相关研究存在显著空白。

链接：https://arxiv.org/abs/2608.25723

机构：AI Lab, Vrije Universiteit Brussel（布鲁塞尔自由大学AI实验室）； Institute of Informatics - Federal University of Rio Grande do Sul（南大河州联邦大学信息学研究所）； Federation University Australia（澳大利亚联邦大学）

作者：Liam P.H. Mertens, Lucas N. Alegre, Florent Delgrange, Diederik M. Roijers, Ann Nowé, Peter Vamplew

英文摘要：Time is of the essence when dealing with multiple reward signals and non-linear utility. In this paper we argue that the current main approaches in multi-objectiveRL (SER and ESR), and successor features, are insufficient. While each approach deals with non-linear effects on user utility on different timescales, none of them take into account that different effects happening on different timescales can happen within the same decision problem. We motivate that this can indeed be the case by an example, both intuitively and numerically, leading to a new perspective, and a significant and non-trivial gap in the literature.

AI 总结：本文针对约束学习场景，通过反例证明经典数据处理不等式不成立，提出广义数据处理不等式并推导其成立的充分条件。

链接：https://arxiv.org/abs/2608.25745

作者：Laura Iacovissi, Rabanus Derr, Robert C. Williamson

英文摘要：A key result in statistics is the data processing inequality, originally proved by Blackwell (1951) and later refined by DeGroot (1962) in terms of statistical uncertainty. It states that the Bayes risk of a statistical experiment obtained by stochastically modifying another experiment cannot be lower than the Bayes risk of the original experiment, regardless of the loss function or prior chosen. In machine learning, this result underlies applications such as the information bottleneck principle and some feature learning techniques. However, machine learning problems are constrained learning problems: the model class used does not include all measurable functions. We present a simple counterexample showing that the classical data processing inequality fails to hold in such a setting. Hence, we formulate a generalized data processing inequality, requiring the constrained Bayes risk of a joint distribution (with respect to a loss function and a constrained hypothesis class) to lower bound the constrained Bayes risk on the stochastically modified distribution, regardless of the choice of distribution. We show this inequality to be equivalent to a set containment condition on a specific function set induced by the loss and model class, called the superprediction set. Finally, we derive sufficient conditions for this containment.

AI 总结：本研究针对加纳废物处置与疾病的关联问题，用随机森林模型预测疾病类别、MobileNetV2模型实现废物自动分类，为该关联提供定量证据，同时强调制度支持对公共卫生改善的必要性。

链接：https://arxiv.org/abs/2608.25759

机构：Kwame Nkrumah University of Science and Technology（夸梅·恩克鲁玛科技大学）； University of Nottingham（诺丁汉大学）

作者：Hilda Adwubi Osei, Catherine Tenewaa Osei, Desdemona Yaa Asobayire

英文摘要：The inappropriate disposal of solid waste remains a significant public health and environmental concern worldwide, including in Ghana. Poor sanitation and improper waste management practices contribute to substantial economic costs and avoidable deaths annually. In 2022, a field study in Atonsu, Kumasi, Ghana, reported a community-perceived relationship between household waste disposal and illness patterns, but only through descriptive analysis without quantitative validation. This study extends that investigation using two data-driven approaches. First, a Random Forest classifier was developed to predict illness categories using waste disposal practices and demographic survey data. On a held-out group of respondents who reported illness (N=69), the model obtained a macro F1 score of 0.63, with disposal method emerging as the most important substantive predictor of illness type. Second, a MobileNetV2 image classification model enabled automated waste sorting via visual recognition, achieving 88.2% accuracy and a macro F1 score of 0.87 on the test set (N=415). The vision-based approach offers an affordable, camera-driven alternative to complex multi-sensor systems, making it highly suitable for resource-constrained settings. Taken together, the findings provide quantitative evidence for a community health relationship previously documented only qualitatively. They demonstrate the potential for automated waste-sorting in low-resource environments. Importantly, the results illustrate that technological performance alone does not guarantee public health improvements; effective institutional support and implementation are equally necessary.

AI 总结：该研究提出几何约束KANs，通过每条边的标量指数p学习边几何，在50个符号回归任务中，其在噪声下稳定性优于多数固定基模型，小样本表现更优，可学习指数具可解释性。

链接：https://arxiv.org/abs/2608.25807

机构：Brevan Howard Centre for Financial Analysis（布赖恩·霍华德金融分析中心）； Imperial Business School（帝国理工商学院）

作者：K S Sesh Kumar

英文摘要： Kolmogorov-Arnold Networks (KANs) replace fixed activations in deep architectures with learnable univariate edge functions, making the choice of edge parametrisation central. Existing variants rely on fixed bases such as splines, polynomials, or Fourier features, which impose a function-space geometry before data are observed. We introduce geometry-constrained KANs, a family of edge activations derived from Banach duality maps in which the geometry itself is learned through a scalar exponent $p > 1$ per edge. This exponent controls the qualitative response: sub-Euclidean values produce sharp, threshold-like behaviour reminiscent of the $\ell_1$ (LASSO) geometry, $p = 2$ recovers the linear regime, and larger values produce flatter responses near the origin. Across 50 symbolic-regression targets ($40$ from the AI Feynman benchmark plus $10$ synthetic stress tests), geometry-constrained KANs match or beat every fixed-basis baseline on median NRMSE (Banach-KAN $0.030$, tying Chebyshev and improving on splines); on average rank Banach-KAN is best on the $18$-equation core ($2.00$) and statistically tied with the strongest spline on the full benchmark ($2.32$ vs. $2.34$). The clearest gains appear under measurement noise: as $\sigma$ grows from $0$ to $1$, $\ell^p$-KAN degrades only $3.7\times$ -- below even a cross-validated spline ($\approx 11\times$) -- while an unregularised spline degrades $21.6\times$; Banach-KAN degrades $8.8\times$, comparable to a tuned spline but far more stable than the unregularised one. Banach-KAN also takes the most per-equation wins in the small-sample regime, with fixed-basis models catching up only as the training set grows. Learned exponents provide an interpretable, relative signal: at a fixed initialisation they reveal a consistent, target-dependent geometric ordering across equation families and input dimensions.

AI 总结：该研究针对现有区域温度预报器输出固定的问题，提出CSTF模型，通过引入提前期、分辨率等查询实现灵活的温度预报，在基准测试中降低了17.0%的偏差，表现出更优性能。

链接：https://arxiv.org/abs/2608.25823

机构：Southeast University（东南大学）； Fudan University（复旦大学）； Sun Yat-sen University（中山大学）； Tsinghua University（清华大学）

作者：Chunlei Shi, Jiong Wang, Yi-Lin Wei, Junming Hou, Jinjin Liu, Yecheng Zhang, Dan Niu

英文摘要：Accurate regional near-surface temperature forecasting is fundamental to short-range weather services and downstream risk assessment. Existing deep learning-based regional forecasters commonly produce a fixed set of future frames on a prescribed grid, limiting their use when forecast products must be evaluated at query-dependent lead times or display resolutions. To overcome these fixed-output constraints, we formulate regional T2M forecasting as query-conditioned continuous spatiotemporal temperature field evaluation and propose the Continuous Spatiotemporal Temperature Forecaster (CSTF), a neural field that turns forecast lead time and output resolution into explicit queries when evaluating 2-m temperature (T2M). Specifically, CSTF first encodes multivariable ERA5 histories into latent meteorological states and then decodes T2M as a coordinate-based field. Accordingly, spatial location, forecast lead time, and output resolution are introduced as queries, enabling standard hourly forecasts, intermediate lead-time diagnostics, and resolution-controllable outputs within a unified field-evaluation framework. Furthermore, to maintain coherence across flexible field queries, we design spatial-gradient, temporal-difference, and scale-consistency objectives that regularize regional thermal structures, lead-wise evolution, and cross-resolution agreement. Experiments on the Southeast China 0-6 h ERA5-Land benchmark demonstrate that CSTF achieves the best aggregate deterministic skill, including a 17.0 percent reduction in Bias, with global-scope diagnostics further illustrating flexible lead-time and resolution-controllable inference.

AI 总结：本研究提出后训练框架VINCENT，通过闭环扰动验证生成满足化学连贯等标准的跨药物基序对协同作用解释，其基序召回率和真阳性/真阴性分离性能优于基线模型。

链接：https://arxiv.org/abs/2608.25841

机构：North Carolina State University（北卡罗来纳州立大学）

作者：Fan-Sheng Chuang, Xuchen Li, Yujing Bian, Kaixiong Zhou

英文摘要：Drug synergy prediction estimates whether two drugs produce a stronger joint effect than expected from their individual activities. For drug combination discovery, a single synergy score is often not enough: researchers also need to know which molecular regions jointly drive the prediction. We study motif-pair synergy explanation, which identifies pairs of chemically coherent regions, one from each drug, that jointly contribute to predicted synergy. Existing interpretable synergy models expose atom- or substructure-level signals, but their explanations are built into the predictor architecture, and none validates cross-drug region scores under repeated perturbations or feeds that evidence back to refine the explanation. A reliable motif-pair explanation should instead be chemically coherent, perturbation-stable, and aligned with predictor behavior. We introduce VINCENT (Validated Interaction Network for Cross-drug Explanation of Therapeutics), a post-training framework for a fixed interaction-aware synergy predictor. VINCENT extracts atom-pair evidence from attention and gradient signals, groups atoms into chemically coherent motifs, and validates candidate motif pairs through repeated local perturbations. The validated evidence is fed back to refine motif assignments, yielding explanations that satisfy these three criteria. On a 25-pair literature-annotated subset, VINCENT achieves a mean motif recall of 0.826 (95% CI: 0.78-0.87), compared with 0.49-0.66 for baselines. Across all 71 test pairs, its validated interaction scores yield a TP/TN separation of 3.36. These results show that closed-loop perturbation validation recovers literature-supported molecular regions more accurately than existing alternatives while producing cross-drug interaction scores that better reflect predictor behavior.

AI 总结：本文研究在单一嗅觉任务上微调的Uni-Mol2能否跨多种机器嗅觉任务迁移，发现其性能与专用基线相当且可稳定迁移，三维表征能区分镜像分子，支持机器嗅觉的跨任务迁移范式。

链接：https://arxiv.org/abs/2608.25893

机构：University of Michigan（密歇根大学）

作者：Yikun Han, Yi Wang, Neil Mankodi, Stephen Yang, Ambuj Tewari

英文摘要： Foundation models have transformed molecular property prediction, yet it remains unclear whether a molecular foundation model, fine-tuned on a single canonical olfactory prediction task, can learn representations that transfer across diverse machine olfaction problems. We investigate this question by fine-tuning Uni-Mol2 on the GS-LF benchmark for multi-label odor descriptor prediction and evaluating the resulting model, without additional deep-learning training, on four complementary downstream settings: cross-dataset odor descriptor prediction, odorous-versus-odorless classification, enantiomer evaluation, and odor mixture discriminability. The fine-tuned model matches or exceeds the performance of the state-of-the-art olfaction-specific baseline on the primary GS-LF benchmark and consistently transfers across these downstream evaluations. The enantiomer analysis further shows that three-dimensional molecular representations distinguish mirror-image molecules in a way that two-dimensional graph models fundamentally cannot, although accurately predicting the perceptual consequences of stereochemistry remains an open challenge. Together, these results support a train-once, transfer-across-tasks paradigm for machine olfaction and suggest that chemically pretrained molecular representations provide a strong foundation for transferable olfactory prediction.

AI 总结：本研究探讨剪枝对大语言模型稀疏自编码器的影响，提出扰动能量理论，指出激活感知剪枝方法更鲁棒，发现中间层更敏感，提出分层稀疏策略并经多模型实验验证。

链接：https://arxiv.org/abs/2608.25941

机构：The Ohio State University（俄亥俄州立大学）

作者：Suchit Gupte, Xueru Zhang, Mohammad Mahdi Khalili

英文摘要：Sparse autoencoders (SAEs) are widely used to interpret the internal representations of large language models (LLMs), yet their reliability under post-hoc model compression remains poorly understood. We present a systematic study of how pruning affects SAE behavior and theoretically show that, for a fixed SAE, its impact is governed by perturbation energy, a covariance-weighted norm. This perspective exposes a key limitation of magnitude pruning: by ignoring activation geometry, it distorts the learned representation space and degrades SAE functionality. Activation-aware methods such as Wanda and SparseGPT, in contrast, implicitly control perturbation energy and are therefore substantially more robust at preserving SAE behavior. We further reveal a consistent structural vulnerability across all pruning methods: middle layers are significantly more sensitive to pruning than early or late layers. Guided by this insight, we propose a layer-wise sparsity allocation strategy, achieving lower perplexity under the same average pruning sparsity. Experiments across four model architectures validate our theoretical findings. Code is publicly available at this https URL.

AI 总结：本研究提出非对称交替框架DualOPSD，让在线自蒸馏的特权教师与学生策略自适应，在Qwen3-8B等模型上提升了数学推理指标并减少截断。

链接：https://arxiv.org/abs/2608.26019

机构：Clemson University（克莱姆森大学）； University of Utah（犹他大学）

作者：Yutong Chen, Guangfu Guo, Zhichao Xu, Kunpeng Liu

英文摘要：On-policy self-distillation (OPSD) uses a privileged copy of the student model to provide dense supervision without an external teacher. OPSD keeps this privileged teacher fixed, even though the student distribution and output style change during training. We propose DualOPSD, an asymmetric alternating framework that adapts both policies. The student first learns from the privileged teacher. The teacher then moves toward the updated student distribution on the same student trajectory. This update makes later supervision responsive to the learner and does not require another rollout. On Qwen3-8B in non-thinking mode, DualOPSD improves avg@12 over OPSD by 23.61, 13.89, and 10.00 points on AIME 2024, AIME 2025, and HMMT 2025. Results at 1.7B and 4B show that the accuracy gain depends on model scale. Across all three scales, DualOPSD reduces truncation. The 4B diagnostic also shows lower KL in both directions between the teacher and student.