机器学习学术速递[8.28]

AI 总结：本文提出无需训练的ClusterAttention，通过适配键查询几何的快速递归聚类实现双向注意力加速，在表格数据上提速2-6倍、精度保留≥99%，在视频生成上比SVOO加速效果更好。

链接：https://arxiv.org/abs/2608.26965

作者：Kasper Nordenram, Amelie Dittmann

英文摘要：This paper introduces ClusterAttention, a general training-free speedup of bidirectional attention layers. Existing sparse attention methods either rely on structure in the input, such as order in language or spatial proximity in images, or use slow clustering processes amortized over several forward passes. ClusterAttention instead uses a fast recursive clustering method that adapts to the geometry of the keys and queries in each attention head to produce useful clusters. This method allows setting the size of the clusters arbitrarily. We utilize this by setting all clusters to be a fixed size that is a power of two, allowing the block-sparse attention to run at the same latency per query-key interaction as dense attention on GPUs. We also derive an expression for the output error in sparse attention, that explains the counterintuitive experimental finding that tight clusters can lead to larger errors than random clusters. We then derive the error when excluded clusters are compensated through their centroids, and show that this error shrinks with tighter clusters. We integrate this compensation into the method. On large-scale tabular data ClusterAttention speeds up TabPFN-3 arXiv:2605.13986 by two to six times, while retaining at least 99% of the dense accuracy. To our knowledge, it is the first training-free method that can be successfully applied in the setting of unstructured input and a single forward pass. For video generation with Wan 2.1-14B T2V arXiv:2503.20314, ClusterAttention achieves output closer to dense attention and a larger speedup (1.8x versus 1.4x) compared to SVOO arXiv:2603.18636, a leading method developed specifically for this domain, both run without offline calibration.

AI 总结：本研究针对表格数据学习，提出注意力头重要性评分方法，经40个数据集实验验证，可优化Transformer架构效率，相关代码已公开。

链接：https://arxiv.org/abs/2608.27241

机构：Tennessee State University（田纳西州立大学）； Enosis Solutions（伊诺西斯解决方案公司）； North Carolina Agricultural and Technical University（北卡罗来纳农工大学）

作者：Ahmad Jad Allah, Kazi F. Akhter, Md. Kamrozzaman Bhuiyan, Manar D. Samad

英文摘要：Computationally demanding and opaque deep learning models can be better understood and optimized by analyzing how they transform data. While deep transformers have been widely studied in computer vision and natural language processing, their application in tabular data remains relatively underexplored. This paper presents one of the first applications of an importance-scoring metric to interpret multi-head transformer models in learning from tabular data. Experiments conducted on 40 diverse tabular datasets demonstrate robustness to head drops based on the proposed head importance score. In 72.5\% of experimental examples, the model remains most resilient to performance drops when heads with the lowest importance scores are gradually removed. In contrast, removing the most important attention head first results in the greatest reduction in classification performance. A closer look at individual head importance scores across six attention layers reveals that important heads are scattered across layers, with no consistent layer-specific trends. In contrast to the image and language domains, the importance of individual attention heads varies considerably across tabular datasets with different schemas and feature spaces. The proposed importance score can improve efficiency and redundancy within transformer architectures. We make the source code for measuring the importance of individual attention heads publicly available.

AI 总结：针对多光谱序列直接连接的性能下降问题，提出MM-Spectrum稳定MoE框架，引入模态感知路由与异质专家，在分子结构解析的多模态设置下取得显著改进。

链接：https://arxiv.org/abs/2608.27286

机构：The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； Southeast University（东南大学）； Fudan University（复旦大学）

作者：Hai-tao Yu, Nan Min, Zheng Fang, Hongyu Zhan, Yusen Tan, Yuhan Wang, Jun Xia

英文摘要： Inferring molecular structures from multimodal spectroscopic measurements requires integrating complementary yet highly heterogeneous signals. However, the common paradigm of directly concatenating multispectral sequences can exhibit anomalous performance degradation, primarily due to pronounced heterogeneity and the resulting multimodal imbalance across modalities. As a remedy, we propose MM-Spectrum, a sparse Mixture-of-Experts framework tailored for multimodal multispectral spectra-to-structure elucidation. To better match the information characteristics under multispectral imbalance, MM-Spectrum introduces an explicit modality-aware routing mechanism that exposes spectral identity to the router in addition to token content representations. Moreover, it incorporates shared and interaction experts, together with heterogeneous expert capacities, to extract multispectral modality-unique and cross-modal synergistic information while suppressing noise-induced interference. Across full-modality, bimodal, and missing-modality settings on molecular structural elucidation, MM-Spectrum achieves consistent and substantial improvements, supported by ablation studies and interpretability analyses.

AI 总结：该研究提出OpEmbed框架，利用生产支持案例元数据学习LLM云服务的操作指纹，在Google Cloud的大规模生产案例评估中表现优异，可用于模型上线、支持评估等场景。

链接：https://arxiv.org/abs/2608.26332

机构：Google Cloud Platform, Google LLC（谷歌云平台，谷歌有限责任公司）

作者：Meiwei Zhang, Eduardo Miranda, Bruce Baynes, Suvigya Jain, Wanlong Chen, Tao He, Sergey Borodavkin

英文摘要：Managed LLM services are now part of real production systems, but model selection and service planning still rely heavily on capability benchmarks that reveal little about operational behavior after deployment. We present Operational Embedding (OpEmbed), a framework for learning compact operational fingerprints of LLM cloud services from structured, privacy-preserving support-case metadata, without using case text. OpEmbed aggregates model--time windows into an eight-channel operational signature and learns a low-dimensional representation via temporal contrastive learning, cross-view reconstruction, and generational-ordinality regularization. Evaluated on more than 33,000 production support cases spanning seven LLM families over 26 months at Google Cloud, OpEmbed recovers interpretable family- and version-level structure, improves leave-one-model-out operational forecasting over non-learned baselines, remains useful under limited early-window data, and supports cross-model fault-type transfer. We report the practical lessons learned from building and evaluating this tool for model onboarding, support readiness assessment, and operational monitoring.

AI 总结：提出Diff Mining框架，通过对比微调模型与基础模型的对数来识别微调目标，在微调领域检测、偏见识别等任务上优于现有方法，可用于开发微调审计工具。

链接：https://arxiv.org/abs/2608.26462

机构：EPFL（洛桑联邦理工学院）； ENS Paris-Saclay（巴黎萨克雷高等师范学校）； Université Paris-Saclay（巴黎萨克雷大学）； MATS

作者：Greg Kocher, Robert West, Clément Dumas, Julian Minder

英文摘要：Finetuning has become the gold standard for refining existing behaviors and inducing new ones in language models, yet it often remains unclear exactly which behaviors emerge during this process. As models grow ever more capable, understanding finetuning better becomes increasingly important, particularly since unwanted behaviors may arise during finetuning. In this paper, we introduce Diff Mining, a simple yet effective framework for identifying what a finetuned model has learned by comparing its logits to those of its base model. Diff Mining effectively surfaces salient tokens that are amplified in the finetuned model, serving as a fingerprint of its training -- even on text unrelated to the finetuning domain. Unlike many existing model diffing methods which require model internals, Diff Mining only needs access to output logits and scales to large models. The framework consists of two modular stages: (i) extracting per-context logit differences between the finetuned and base models on a reference corpus, and (ii) aggregating the resulting signals to construct an interpretable token set representing the finetune. For aggregation, we explore both a simple Top-K frequency method and a Non-negative Matrix Factorization (NMF)-based approach for disentangling multiple finetuning objectives into distinct token clusters. Empirically, Diff Mining succeeds across diverse settings: on finetune domain detection, it significantly outperforms state-of-the-art model diffing methods both in identifying relevant tokens and in downstream performance when an interpretability agent is given access to the extracted token set; on models with injected biases, it identifies more than one third of the biases without targeted probing. Overall, our framework shows promise in developing auditing tools to detect finetuning objectives.

AI 总结：针对现有12导联ECG分析方法难以捕捉导联间依赖与全局模式的问题，提出Graph-CMMC框架，通过将ECG波形转换为GADF图像构建伪多模态表征，结合图关系模块建模导联间依赖，在冠状动脉闭塞分类任务上取得了有竞争力的性能。

链接：https://arxiv.org/abs/2608.26964

机构：Yokohama National University（横滨国立大学）； Yokohama City University Medical Center（横滨市立大学医学中心）； Fukuda Denshi Co.,Ltd（福田电子株式会社）

作者：Mengyu Wang, Kozo Okada, Takafumi Goto, Natsuko Jinba, Hiroki Yamaya, Kiyoshi Hibi, Tomoki Hamagami

英文摘要：12-lead electrocardiogram (ECG) is a standard, non-invasive examination widely used for diagnosing coronary artery disease, where clinical interpretation relies on comparing waveform patterns across multiple leads. However, most existing ECG analysis methods focus on single-lead signals or treat each lead independently, and typically process ECG signals as one-dimensional time-series data using CNNs or RNNs. While effective in modeling local waveform changes, such approaches have difficulty capturing inter-lead dependency and global waveform patterns essential for clinical diagnosis. To address this limitation, we propose a graph-based pseudo-multimodal contrastive learning framework called Graph-CMMC. ECG waveforms are transformed into Gramian Angular Difference Field (GADF) images to construct complementary representations of the same cardiac activity, enabling a pseudo-multimodal learning setting. Using all 12 leads, Graph-CMMC aligns waveform and GADF representations in a self-supervised manner, while a graph-based relational module is employed to model inter-lead dependency and enforce structural consistency across leads during contrastive learning. Experimental results on a multi-label coronary artery occlusion classification task demonstrate that the proposed framework achieves competitive performance compared to supervised learning methods. These results further suggest the effectiveness of using GADF as a complementary representation and incorporating explicit graph-based modeling of inter-lead dependency for learning robust 12-lead ECG representations.

AI 总结：提出HALO异构性感知语言对齐IMU基础模型，通过两阶段训练解决HAR的异构性与泛化问题，在多数据集上优于基线，零样本准确率提升13.7个百分点。

链接：https://arxiv.org/abs/2608.27233

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

作者：Zihan Ding, Liyu Zhang, Xiaomin Ouyang

英文摘要：Human Activity Recognition (HAR) using inertial measurement units (IMUs) enables a wide range of applications, yet the field still lacks a unified model that can generalize across diverse subjects, devices, and activities. Training such a model is difficult due to two key challenges: sensing heterogeneity -- differences in sampling rates, channel configurations, and sensor placements -- and poor generalization to unseen activities and label vocabularies. We introduce HALO (Heterogeneity-Aware Language-aligned Open-set model), a domain-specific IMU foundation model that addresses both challenges through a two-stage training framework. Stage 1 pretrains the IMU encoder with heterogeneity-aware self-supervised learning, including adaptive-pooling tokenization, channel-independent feature extraction, and contextualized sensor conditioning that injects natural-language sensor descriptions into each channel embedding. Stage 2 aligns this IMU encoder with text embeddings via synonym-aware soft contrastive learning, enabling open-set recognition via cosine-similarity retrieval without per-dataset classifiers. Trained on 10 public HAR datasets and evaluated on 7 held-out datasets, HALO outperforms five state-of-the-art baselines on all 8 aggregate metrics, and still leads on 3 of 4 settings under baseline-matched inputs. Despite using only ~35M trainable parameters -- 10x fewer than the latest foundation model MOMENT (341.2M) -- HALO improves zero-shot open-set accuracy, measured over all 87 training labels, by 13.7 percentage points. On two further datasets with severe distribution shift, every model including HALO collapses zero-shot. A video demonstration of HALO's performance in real world is available at this https URL

AI 总结：该研究针对强化学习中环境的有向无环课程图结构，提出主动课程学习框架PATH，通过采样多样化课程路径并重新分配训练资源，提升了模型的鲁棒性与泛化能力。

链接：https://arxiv.org/abs/2608.26469

机构：The University of Chicago（芝加哥大学）

作者：Zhenya Liu, Yuxin Chen

英文摘要：In many reinforcement learning (RL) domains, environments are connected by prerequisite relations, such as difficulty-increasing edits or parameter increments, which induce a directed acyclic curriculum graph (DAG). Although this structure is often exploited only implicitly, explicitly modeling it can improve training. We introduce PATH, a curriculum-learning framework that performs active learning over the curriculum graph. PATH first expands coverage by sampling diverse curriculum paths and then reallocates training toward regions that remain unmastered. Experiments across diverse environments show that PATH explicitly leverages the graph structure to achieve strong robustness and generalization.

AI 总结：该研究针对并行强化学习中评论家共享导致的价值不匹配问题，提出仅给评论家环境索引的干预方法，在多类任务中提升了学习稳定性与回报，Procgen 游戏中聚合归一化回报提升 40.8%。

链接：https://arxiv.org/abs/2608.26481

机构：University of Chicago（芝加哥大学）； University of Florida（佛罗里达大学）

作者：Zhenya Liu, Yang Meng, Zhuokai Zhao, Xuefeng Liu, Yuxin Chen

英文摘要：When a single policy is trained in parallel across multiple environments of the same task, such as procedurally generated levels, randomized dynamics, or curricula, implementations commonly use one critic across all sampled environments. Yet different environments can assign different expected returns to the same input visible to the critic. A critic without environment information must then reconcile distinct value targets, systematically shifting the sampled advantages within individual environments. Using illustrative bandit models with multiple environments and a common optimal arm, we characterize how this value mismatch redistributes sampled policy updates, reinforcing unhelpful actions while attenuating or even reversing useful ones. The oracle processes using no baseline, the shared value, or the value specific to the sampled environment have the same mean logit update at a fixed policy and converge to the same optimal policy, yet their realized learning paths can differ sharply. The analysis motivates a minimal intervention: give only a logged environment index to the critic so that it can separate the value targets. Controlled CartPole and MuJoCo experiments expose the predicted shifted values, advantages, and performance gaps. In the more complex BipedalWalker and Procgen settings, the same intervention yields more stable learning and higher returns. Across all $16$ Procgen games, the multihead conditional critic improves aggregate normalized return on $600$ unseen levels per game by $40.8\%$. In conclusion, the theory identifies value mismatch as a direct mechanism through which critic sharing can degrade stochastic learning dynamics, not captured by scalar estimator variance alone, and the experiments show that conditioning on an index is broadly effective in parallel reinforcement learning.

AI 总结：本文针对失败终止CRL的系统性偏差，提出Safe-CRL方法，仅用失败的一位信号，在12个机器人任务中提升了存活率与目标到达性能，完善了失败终止下的CRL理论。

链接：https://arxiv.org/abs/2608.26571

机构：Southeast University（东南大学）； Yinwang Intel. Tech. Co. Ltd.（银网智能科技有限公司）； Lab（2030实验室）

作者：Guopeng Li, Yiyang Duan, Yiru Jiao, Chengcheng Xu

英文摘要： Contrastive reinforcement learning (CRL) scales effectively in goal-conditioned tasks by casting policy learning into a self-supervised contrastive objective. However, in a failure-terminated Markov decision process, established CRL considers pre-failure future goals only when constructing positive samples, without accounting for the probability mass removed by failure termination. Our theoretical analysis shows that this omission induces a systematic overestimation bias in goal-reaching values. Consequently, near-failure trajectories provide disproportionately strong supervision of success despite retaining little future occupancy. Unsafe actions can thereby be reinforced through catastrophic failure bootstrapping, leading to failed policy learning and unsustainable goal-reaching behaviours. To address this problem, we introduce two minimal yet strong corrections: mass-weighted InfoNCE corrects the overweighting of short surviving futures in critic learning, and a log-survival-mass score restores the missing survival mass in policy optimization. The resulting method, Safe Contrastive Reinforcement Learning (Safe-CRL), requires only the one-bit signal provided by failure termination to scale safe goal-conditioned policy learning. Across twelve failure-prone robot navigation and locomotion tasks, Safe-CRL consistently improves survival and substantially outperforms the Scaling-CRL baseline in goal-reaching performance. Additionally, deep Safe-CRL policies exhibit complex failure-avoidance behaviours. This study completes the CRL theory under failure termination and provides a scalable safe RL framework. The code is available via this https URL.

AI 总结：本文提出LAC算法，将容量分配给深度评论家而非简单演员，解决离线RL中加深评论家的三种失效模式，在OGBench上实现与强基线相当性能且推理延迟最高降4倍。

链接：https://arxiv.org/abs/2608.26659

机构：Sungkyunkwan University（成均馆大学）； Soongsil University（崇实大学）

作者：Guhyeon Kang, Jaehwi Lee, Minhae Kwon

英文摘要：Recent progress in offline reinforcement learning (RL) has been driven by expressive generative actors such as diffusion and flow-matching policies, which capture multimodal behavior in offline datasets. However, these actors require multiple denoising or integration steps per action and thus incur substantial overhead at every decision in deployment. In this work, we revisit where capacity should be invested in an offline actor--critic method. Since the critic is used only during training and is discarded at deployment while the actor runs at every decision step, allocating capacity to the critic rather than the actor is more favorable for inference-time efficiency. However, scaling MLP critics in offline RL is known to introduce several distinct instabilities that have, in practice, kept critics shallow. We identify three distinct failure modes that arise when critics are deepened in offline RL---optimization, bootstrap-noise amplification, and value-range drift---and address each with a corresponding ingredient: a residual MLP backbone, n-step bootstrap targets, and a categorical cross-entropy loss. Combining these ingredients with a lightweight deterministic actor, we propose LAC (Light Actor, deep Critic). On OGBench, LAC matches the strongest diffusion- and flow-matching baselines while achieving up to 4x lower inference latency, comparable to one-step distilled policies without distillation. Its critic recipe also transfers across actor parametrizations.

AI 总结：针对带连续动作的上下文博弈机，提出高概率约束UCB算法，通过保守估计安全动作集保障实现代价安全，实验显示其能显著减少安全违规。

链接：https://arxiv.org/abs/2608.26755

机构：Boston University（波士顿大学）； Broad Institute of MIT and Harvard（麻省理工学院与哈佛大学博德研究所）

作者：Spyros Dragazis, Aldo Pacchiano

英文摘要：Contextual bandits are a standard framework for sequential decision-making under uncertainty, with applications in clinical trials, dosage selection, recommendation systems, and autonomous systems. Safety is central in many of these applications, since a single unsafe decision in settings such as dosage selection or autonomous driving can have catastrophic consequences. A common way to model safety in bandit problems is to associate each action with both a reward signal and a cost signal, and to optimize reward subject to constraints on cost. Most existing safety-constrained bandit models enforce safety by requiring the expected cost of each action to remain below a prescribed threshold. However, this may be insufficient in heteroscedastic settings, where the chosen action affects not only the expected reward and cost, but also the variability of the observed outcomes. We study contextual bandits with one-dimensional continuous actions and stage-wise high-probability constraints on the realized cost. We propose High-Probability Constrained UCB, an optimistic-pessimistic algorithm that explores for reward while conservatively estimating the safe action set. For linear reward and cost models, we prove a tight $\tilde{\mathcal{O}}(d\sqrt{T})$ regret bound, and we extend the analysis to general function classes using the eluder dimension. Experiments show that enforcing realized-cost safety substantially reduces violations compared with expected-cost constrained baselines.

AI 总结：该研究针对混合交通环境下CAV队列汇入的安全高效控制问题，提出结合SUMO的建模框架，评估PPO等DRL算法，发现PPO在平衡安全与效率上表现更优。

链接：https://arxiv.org/abs/2608.26860

机构：Université Gustave Eiffel（古斯塔夫·埃菲尔大学）； Université Paris Dauphine-PSL（巴黎多芬大学-PSL）； Cosys-Grettia, Univ Gustave Eiffel（古斯塔夫·埃菲尔大学Cosys-Grettia机构）

作者：Biao Yin, Abderrahmane Kasmi, Nadir Farhi

英文摘要： Connected and automated vehicle (CAV) platooning offers a promising approach to improving road safety and traffic capacity. However, platoon control in real-world traffic is challenging due to uncertainty and heterogeneous driving behaviors. Reinforcement learning (RL) has strong potential for addressing such control problems, but its practical deployment raises challenges related to safety and learning efficiency. This paper proposes a generic modeling and simulation framework for investigating CAV platoon joining maneuvers and comparing deep reinforcement learning (DRL)-based control algorithms. The problem is particularly challenging in mixed-traffic environments, where CAVs coexist with human-driven vehicles exhibiting heterogeneous longitudinal and lateral behaviors. The objective is to achieve safe and efficient joining maneuvers by either incorporating penalties for risky behaviors into the learning process or using an external safety controller to constrain the learned policy. An agent-based modeling framework coupled with the Simulation of Urban MObility (SUMO) simulator is used to evaluate Deep Q-Network (DQN), Double Deep Q-Network (DDQN), and Proximal Policy Optimization (PPO). Results show that PPO outperforms DQN and DDQN, achieving a joining success rate of approximately 98 % and a collision rate below 1 %, largely due to risk-related penalties incorporated into the reward function. However, this improved performance requires more decision steps to complete the maneuver, revealing a trade-off between safety, joining effectiveness, and decision efficiency. An external safety controller effectively prevents collisions, although its interventions may reduce joining efficiency. The results highlight the importance of jointly considering safety and efficiency when designing RL-based controllers for CAV platoon joining in mixed traffic.

AI 总结：该研究针对RL-for-LLM范式，分析主流后训练算法框架，构建RLM并行策略分类体系，提炼实用指南并概述开放方向，以推动开发高性能可扩展的高性价比RLM。

链接：https://arxiv.org/abs/2608.27046

机构：ETH Zurich（苏黎世联邦理工学院）

作者：Maciej Besta, Leonard Schmidt, Lara Nonino, Robert Gerstenberger, Pierre Pang, Patrik Okanovic, Ales Kubicek, Tiancheng Chen, Baraq Lipshitz, Torsten Hoefler

英文摘要：Reinforcement Learning with Verifiable Rewards (RLVR) and other RL-style post-training paradigms have been used for aligning large language models (LLMs) with reasoning standards. The resulting recent Reasoning Language Models (RLMs) such as DeepSeek-R1, o3, and Kimi k1.5 show that such RL-style post-training ("RL-for-LLMs") can substantially improve chain-of-thought reasoning, long-horizon planning, and self-correction. However, the computational footprint of these systems is massive: state-of-the-art RLM training requires millions of GPU-hours and tightly coupled multi-model pipelines that stress modern hardware far beyond classical supervised LLM training. This makes RLM training as much a parallel and distributed systems problem as an algorithmic one. In this work, to facilitate developing RLMs that are simultaneously high-performance, scalable, and cost-effective, we first systematize the RL-for-LLM paradigm and provide a compute-centric analysis of prominent post-training algorithmic frameworks: Proximal Policy Optimization (PPO), Group Relative Policy Optimization (GRPO), as well as their variants. Second, we develop a taxonomy of intra- and inter-model parallelism strategies for RL-for-LLMs, covering both traditional techniques (data, tensor, pipeline, sequence, context, and expert parallelism) as well as novel forms of parallelism and optimization techniques for multi-model RLM training, for example disaggregated placement, stage fusion, hybrid parallelism, and asynchronous execution. We harness the work-depth model of parallel computing to make our taxonomy and its insights rigorous and portable. Finally, we analyze existing RLM frameworks and we distill practical guidelines and outline open research directions for building scalable, fast, and cost-effective RLMs.

AI 总结：该研究提出情感偏好作为目标优先级调节的概念，构建含多目标强化学习内部控制器与外部偏好生成器的框架，经实验验证其偏好函数表现优于固定偏好与手工设计偏好策略。

链接：https://arxiv.org/abs/2608.27072

机构：School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）

作者：Shiqi Liu, Yihua Tan, Hu Fu, Guanyu Qi

英文摘要：A core question in decision-making for agents is whether the relative priorities of competing lower-level objectives can be determined by emotional preferences autonomously generated by higher-level goals, rather than being externally prespecified. Under changing external environments and evolving internal states, emotions play an important functional role in regulating the relative priorities of competing goals. Inspired by the goal-directed theory of emotion, this paper studies how such preference regulation can be computationally realized through reinforcement learning. We first propose a conception of emergent emotional preference: a high-level goal autonomously induces state-dependent preferences over competing lower-level objectives. This conception is built upon a framework consisting of a multi-objective reinforcement learning inner controller and an outer preference generator. The inner controller provides a repertoire of preference-conditioned goal-directed behaviors, while the outer preference generator learns a mapping from the current state to objective preferences through reinforcement learning on a high-level goal. We operationalize emotional preference as a state-dependent regulation of relative goal priorities that emerges through optimization. Furthermore, we characterize the policy space induced by preference regulation and derive an upper bound on the optimality gap in terms of the representation error of the inner behavioral repertoire. We show that the gap vanishes when the optimal policy can be represented by the available preference-conditioned policies. Experiments in self-constructed multi-objective exploration environments show that the learned preference function exhibits contextual priority switching, graded trade-offs, and temporal persistence, and outperforms the evaluated fixed-preference and handcrafted-preference strategies.

AI 总结：针对机器人人群导航中现有方法难以表征多样化短期避障策略的问题，提出PDPO框架，生成短程动作块并引入边界约束，在基准测试中取得更好导航成功率。

链接：https://arxiv.org/abs/2608.27158

机构：Institute for Numerical Simulation（数值模拟研究所）； University of Bonn（波恩大学）

作者：Wendong Li, Jochen Garcke

英文摘要：Robot crowd navigation requires safe and efficient decision-making under dense, dynamic, and multimodal human--robot interactions. Existing reinforcement-learning methods typically output a single reactive action at each timestep, which limits their ability to represent diverse short-term avoidance strategies. We propose Planning Diffusion Policy Optimization (PDPO), an offline-to-online reinforcement-learning framework that uses a diffusion policy to generate short-horizon action chunks for crowd navigation. PDPO is first pretrained on collision-avoidance demonstrations and then fine-tuned online with PPO by treating the denoising process as an internal decision process. During execution, the policy generates a five-step action chunk and applies it in a receding-horizon manner. Furthermore, we observe an evaluation artifact in common crowd-navigation benchmarks: without explicit boundary constraints, learned agents may leave the valid domain and bypass dense crowds. To address this, we introduce a setting in which boundary violations are treated as collisions. Experiments show that PDPO obtains an improved success rate over strong baselines, and ablations demonstrate that action chunks are especially important for the modified bounded benchmark.

AI 总结：本文提出GRAS方法，通过降方差提议与自适应重采样温度改进离散扩散模型无训练奖励对齐，在调控DNA和蛋白质设计任务中表现优于现有无训练方法，效果接近或超越奖励微调模型。

链接：https://arxiv.org/abs/2608.26585

机构：Gwangju Institute of Science and Technology (GIST)（光州科学技术院）

作者：Kwanyoung Kim

英文摘要：Discrete diffusion models have become a strong, widely adopted class of generators for sequence data, and steering them toward a downstream reward at inference time, without any retraining, is increasingly important. Such training-free steering is done by gradient guidance, by search, or by combining the two. We study the combined regime and identify two weaknesses in how it is usually run: the guided proposal estimates its gradient from a single noisy sample, and the search then resamples particles at a fixed temperature that ignores how rewards spread across each denoising step. We address both with a small set of changes that add no denoiser cost. For the proposal, we lower the estimator variance with a Rao-Blackwellized reveal for differentiable rewards and a leave-one-out baseline for non-differentiable ones; for the search, we standardize the per-step values into a group-relative advantage and prove it collapses to a single active ingredient, an adaptive resampling temperature. We call the resulting method Guided Reduced-variance proposals and Adaptive Selection (GRAS). GRAS is simple yet effective: across regulatory DNA and protein design it attains the best training-free reward, outperforming prior training-free methods and matching or surpassing a reward-fine-tuned model, and it remains effective even for non-differentiable rewards.

AI 总结：本研究提出一种基于自生成数据增强的扩散引导的物理感知生成方法，解耦控制方程评估与扩散模型训练采样，可显著降低生成物理信号的偏差，且与现有物理约束扩散方法结合效果更佳。

链接：https://arxiv.org/abs/2608.26748

机构：The University of Tokyo（东京大学）； School of Engineering（工学院）

作者：Akira Osaka, Naoya Takeishi, Takehisa Yairi

英文摘要：Diffusion models can be used to generate spatiotemporal signals of physical phenomena, such as time-series images of fluid dynamics. However, a major limitation of standard diffusion models is that they do not incorporate constraints derived from the underlying physical laws. Consequently, generated samples may appear visually plausible while deviating substantially from the true dynamics. In this study, we propose a simple yet effective physics-informed approach based on diffusion guidance with self-generated data augmentation. The proposed method learns the data distribution conditioned on the degree of deviation from the physically correct dynamics and generates samples by explicitly setting the deviation condition to be zero. The method decouples the evaluation of the governing equations from the diffusion model training and sampling processes, avoiding the need to solve the governing equations at every iteration of the denoising process. This design makes the method applicable to problems requiring computationally expensive numerical simulations and enables faster sample generation. Experimental results demonstrate that the proposed model not only significantly reduces the deviations compared with standard diffusion models but also achieves further reductions when combined with existing physics-constrained diffusion methods.

AI 总结：该研究提出格罗莫夫-蒙日流匹配方法，通过构造感知结构的商耦合，在小积分预算下提升图与分子生成质量，且兼容标准置换等变架构。

链接：https://arxiv.org/abs/2608.26961

机构：Institute of Mathematics, Technische Universität Berlin（柏林工业大学数学研究所）； Institut Camille Jordan, INSA Lyon（里昂国立应用科学学院卡米尔·乔丹研究所）

作者：Moritz Piening, Christian Wald

英文摘要：Graphs are invariant under node permutations, motivating the use of permutation-equivariant architectures in generative models. In flow matching, however, symmetry may also enter the source--target coupling: once graph pairs are compared up to node relabeling, the natural Wasserstein geometry is that of the graph quotient space. The Euclidean quotient metric of this space coincides with the Gromov--Monge distance, obtained by optimally relabeling the nodes. We develop this perspective theoretically, showing that quotient couplings can be lifted to aligned representatives without additional cost and that symmetrization yields equivariant flow-matching minimizers, including for categorical endpoint prediction. In practice, exact Gromov--Monge alignment is intractable, so we construct minibatch couplings using efficient Gromov--Wasserstein-type relaxations and lower bounds for the inner node alignment, optionally combined with an outer assignment between graphs. The resulting procedure changes only the training coupling and is compatible with standard permutation-equivariant architectures. Across continuous graph and categorical molecular generation, these structure-aware couplings substantially improve sample quality at small integration budgets, while our scaled-up molecular models remain competitive under conventional many-step sampling.

AI 总结：本研究提出一种基于RSS的概率路径重建方法，实现了对38毫克低功耗设备的景观尺度追踪，精度达10-15米，可用于欧洲熊蜂归巢飞行的追踪研究。

链接：https://arxiv.org/abs/2608.27152

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

作者：Christopher J. Noroozi, Joseph L. Woodgate, Michael Mangan, Michael T. Smith

英文摘要： Applications in fields such as movement ecology, Internet of Things or robotics share the need for systems that localize devices that are too small and power constrained to implement GNSS (Global Navigation Satellite Systems). Alternative low-power localization methods often rely on only measurements of RSS (Received Signal Strength) to infer the AoA (Angle of Arrival) of a transmitted radio frequency signal, but are limited by range and the power demand of the large number of RSS measurements required to infer an accurate AoA. In this paper we address these issues with a novel RSS-based method for tracking ultra lightweight and low-power moving receivers across a complex landscape, achieved by using a minimal number of RSS measurements from simple rotating high-gain transmitters with a range of 300m, and applying probabilistic modelling to infer their AoA. The receiver's movement path is then modelled using a Gaussian process and reconstructed using doubly stochastic variational inference, resulting in approximately 15m accuracy tracking of receivers weighing 38mg (including power source) over a scalable landscape range while consuming less than 180uW, increased to approximately 10m accuracy at less than 600uW by taking more RSS measurements. We anticipate that this method will support fields such as the behavioural study of flying insect species, which we demonstrate by applying the system to track Bombus terrestris nest return flights.

AI 总结：该研究针对大型语言模型预训练优化器Muon，证明带有限牛顿-舒尔茨迭代的Muon可通过平滑极映射提升非光滑非凸优化的收敛性，其样本复杂度达最优，且优于采用精确极因子更新的Muon。

链接：https://arxiv.org/abs/2608.26288

机构：The University of Tokyo（东京大学）； RIKEN（理化学研究所）

作者：Mingyi Li, Taira Tsuchiya

英文摘要：Muon has emerged as a strong optimizer for the matrix-valued parameters in large language model pretraining, approximately orthogonalizing its momentum with a few Newton-Schulz iterations. Existing theory either replaces this iteration with the exact polar factor it approximates, or treats its finite depth as an approximation error, and thus the iteration Muon actually runs can only hurt the guarantees. We show that finite Newton-Schulz can instead be beneficial for nonsmooth nonconvex optimization. To this end, we analyze Muon through the online-to-nonconvex conversion, which views the update rule as an online learner and converts its regret bound into a stationarity guarantee. The finite Newton-Schulz iteration smooths the discontinuous polar map into a Lipschitz map of the singular values, and Muon with finite Newton-Schulz can be regarded as an online learner with a smoothed spectral potential. This smoothing is exactly what the conversion needs: we prove that a Newton-Schulz depth growing only logarithmically in the target accuracy suffices for convergence to stationary points in nonsmooth nonconvex optimization, whereas Muon with the exact-polar update may fail to converge. The resulting sample complexity bounds match the best-known guarantees for nonsmooth nonconvex optimization and are optimal for smooth nonconvex optimization up to problem-dependent factors. The argument extends beyond Newton-Schulz to general spectral maps with the same smoothing property.

AI 总结：该研究针对通信约束下去中心化学习的公平性等挑战，提出融合个性化、公平性与高效通信的DMFL-SQ算法，在CIFAR-10等数据集上验证其能减少通信并维持性能、提升公平性。

链接：https://arxiv.org/abs/2608.26493

机构：School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology（瑞典皇家理工学院电气与计算机科学学院）

作者：Krishnendu S. Tharakan, Carlo Fischione

英文摘要：Decentralized learning systems aim to collaboratively train models across multiple clients without relying on a central coordinator. While decentralization improves scalability, privacy, and robustness, it also exacerbates three fundamental challenges: statistical heterogeneity across clients, fairness in client-level performance, and stringent communication constraints. This raises a natural question: \emph{how fair can decentralized learning be under limited communication?} We address this question by presenting a unified framework for decentralized learning under communication constraints, bringing together graph-based personalization, agnostic fairness, and compressed event-triggered communication. Specifically, we propose a new algorithm DMFL-SQ, a decentralized multi-task learning algorithm that couples personalized model training over a communication graph with an agnostic mixture fairness objective, while reducing communication through sparsification, quantization, and event-triggered synchronization. We establish convergence guarantees for general non-convex objectives and show that DMFL-SQ achieves an $\mathcal{O}(T^{-1/2})$ rate in expected squared Moreau-envelope stationarity despite sparse, quantized, and event-triggered communication. We further derive PAC-Bayes generalization guarantees for the fairness-aware mixture objective. Experiments on CIFAR-10 and the real heterogeneous MUSMET EEG dataset demonstrate that DMFL-SQ substantially reduces communication while maintaining predictive performance and improving fairness across clients. Together, our theoretical and empirical results show that personalization, fairness, and communication efficiency can be jointly achieved in decentralized learning while preserving the dominant convergence rate.

AI 总结：该研究解决统计学习理论中三个开放问题，证明多分类学习无法简化为恰当学习，恰当学习存在亚线性误差必要条件，且正则化不是通用学习器，同时给出SRM可学习性的充分条件。

链接：https://arxiv.org/abs/2608.26516

机构：University of Chicago（芝加哥大学）； Northwestern University（西北大学）

作者：Julian Asilis, Shaddin Dughmi, Vatsal Sharan, Alec Sun, Shang-Hua Teng, Chang Wang

英文摘要： Two of the most fundamental questions in statistical learning theory are the following: which prediction problems are learnable, and how should they be learned? For the former, elegant answers often take the form of combinatorial dimensions. The latter question, however, has proved considerably more elusive: all known general-purpose multiclass learners rely on intricate orientations of exponentially large one-inclusion structures, and familiar algorithmic principles such as proper learning and regularization remain poorly understood. Motivated by prior work, we ask whether learning reduces to proper learning---possibly over a larger hypothesis class---and whether proper or improper multiclass learning can ultimately be captured by suitable regularizers. Our primary results answer both questions negatively, resolving three open problems from prior work. First, we exhibit a learnable multiclass problem that cannot be embedded in any properly learnable class, meaning learning cannot be reduced to proper learning by enlarging the hypothesis class. Second, we demonstrate that proper learning can require training error and characterize this phenomenon precisely: every properly learnable class admits a proper learner making $o(m)$ errors on samples of size $m$, but every prescribed sublinear scale $a_m=o(m)$ is necessary for some properly learnable problem. Third, regularization is not a general learner: we exhibit a properly learnable class that cannot be learned by any Structural Risk Minimization (SRM) learner, and a learnable class that cannot be learned by any local regularizer. We complement these impossibility results with a positive theory that gives two sufficient conditions for SRM learnability and characterizes SRM representability through integrability of revealed preferences.

AI 总结：该研究针对LLMs带来的AI与人类文本区分难题，提出利用人类写作样本改述机器生成文本的策略，推导收敛速率并分析有限样本下的相关缩放关系。

链接：https://arxiv.org/abs/2608.26797

机构：Truth Audit Labs

作者：Jaee Ponde, Aritra Das, Mihir More, Debayan Gupta

英文摘要：The rapid improvement of LLMs has made distinguishing AI-generated text from human writing a pressing problem. This challenge is further amplified by paraphrasing tools designed to make machine-generated text appear more "human". We study how access to human writing samples can be used to strategically paraphrase machine-generated responses toward the human distribution. Under a multi-sample setting with human and machine responses to the same prompts, we show that repeated paraphrasing moves the machine distribution toward the empirical human distribution under simple mixing and stability conditions. Our results derive an explicit convergence rate, extend the analysis to a finite-sample setting, and characterize how the required number of human samples and paraphrasing rounds scale with the desired error.

AI 总结：针对多模态学习中强模态坍塌导致模型难超单模态基准的问题，提出反向非对称融合（IAF）方法，在三类基准上验证其可保留主导模态性能且最高提升单模态基准8.25%

链接：https://arxiv.org/abs/2608.26879

机构：Imperial College London（帝国理工学院）； California Polytechnic State University（加州州立理工大学）

作者：Mary Ogbuka Kenneth, Foaad Khosmood, Abbas Edalat

英文摘要：Fusing multiple modalities is expected to improve model performance. However, on the MultiHuSE dataset, early, late, and symmetric attention fusion often fail to outperform the best unimodal baseline (text). Pathway isolation of a symmetric attention fusion model reveals that the text-pathway accuracy drops from 74.9% to 56.4% after fusion in one such setting, indicating that the dominant modality can be degraded during integration. We term this strong-modality collapse and argue that it helps explain why some multimodal models fail to surpass unimodal baselines. We propose Inverted Asymmetric Fusion (IAF), which avoids forcing mutual attention across modalities. The dominant modality is preserved by passing through fusion unchanged, while weaker modalities attend to it as a contextual anchor. Before fusion, weaker modalities are strengthened using Modality-Aware Knowledge Distillation. We evaluate IAF on three benchmarks with different modality hierarchies: text-dominant datasets (MultiHuSE, UR-FUNNY) and an audio-visual-dominant dataset (MUStARD). Pathway isolation shows that IAF preserves the dominant modality's internal accuracy at its unimodal ceiling across all tested configurations, whereas symmetric fusion degrades it by up to 18.5% on MultiHuSE. IAF improves over the strongest unimodal baseline by up to 8.25%.

AI 总结：该研究针对最佳N采样的奖励黑客攻击与偏好数据隐私问题，提出PrivBoN和PrivITP方法，实现差分隐私推理时对齐，经实验验证其性能优于原有策略。

链接：https://arxiv.org/abs/2608.26324

机构：Indian Institute of Technology Kanpur（坎普尔印度理工学院）

作者：Ishi Jain, Nandini Bhattad, Sayak Ray Chowdhury

英文摘要：Best-of-N (BoN) sampling is the simplest and most widely deployed inference-time alignment strategy, but it suffers from two distinct problems: reward hacking, in which the selected response exploits errors in the proxy reward model, and the absence of any privacy protection for the sensitive human preference data used to train that reward model. We show that a single intervention-adding calibrated noise to reward scores before selection-resolves both. Our first result, Private Best-of-N (PrivBoN), establishes that Gumbel noise at an appropriate scale simultaneously provides $\epsilon$-differential privacy and implements KL-regularized alignment. Whenever the privacy budget exceeds a critical threshold $\epsilon^*$, the privacy-mandated noise is the regret-optimal regularization, and privacy imposes zero additional alignment cost-matching the information-theoretic skyline of Huang et al. (2025). Because $\epsilon^*$ depends on an unknown coverage coefficient, we introduce Private Inference-Time Pessimism (PrivITP), which combines $\chi^2$-regularized rejection sampling with a two-phase Gaussian mechanism. PrivITP achieves ex-post $(\epsilon,\delta)$-DP with a privacy cost independent of the number of responses $n$, cleanly decouples the regularization parameter from the privacy parameter, and attains the skyline up to a noise-inflation term. Experiments across several language models, datasets, and reward models confirm our results: PrivBoN and PrivITP are scaling-monotonic (unlike BoN, which degrades past a critical $n$), and PrivITP matches or outperforms PrivBoN at equivalent privacy levels, with the largest gains in the strong-privacy regime.

AI 总结：本文提出基于NASA C-MAPSS数据集的联邦RUL估计基准FedCMAPSS，定义五类任务模拟工业挑战，评估多种联邦优化算法，为联邦预测性维护提供标准基础。

链接：https://arxiv.org/abs/2608.26433

机构：University of Catania（卡塔尼亚大学）

作者：Amelia Sorrenti, Matteo Pennisi, Concetto Spampinato, Simone Palazzo

英文摘要：Data-driven prognostics and health management has emerged as a key enabler for Industry 4.0, yet the development of robust remaining useful life (RUL) estimation models is often limited by the scarcity of run-to-failure data. While federated learning offers a promising paradigm to collaboratively train predictive models without sharing sensor data, research efforts have operated so far in the absence of a common evaluation framework. To address this gap, this paper introduces FedCMAPSS, a benchmark for federated RUL estimation based on the commonly-used NASA C-MAPSS dataset. We define a set of five standardized tasks designed to simulate real-world industrial challenges, ranging from ideal IID settings to extreme statistical heterogeneity, and conduct a systematic evaluation of state-of-the-art federated optimization algorithms across multiple neural architectures. By establishing reproducible baselines and making the source code and data splits publicly available, this work aims to provide a standard foundation for developing and comparing federated predictive maintenance solutions.

AI 总结：本文针对差分隐私模型合并的几何障碍，提出几何感知框架DP-Merging，可提升差分隐私任务模型可合并性，在保留隐私保障的同时改善私人合并模型性能。

链接：https://arxiv.org/abs/2608.26655

机构：Xidian University（西安电子科技大学）； Tianjin University（天津大学）

作者：Jin Liu, Junkang Liu, Ning Xi, Yinbin Miao, Dawei Wei, Ke Cheng, Jianfeng Ma

英文摘要：Model merging promises to construct a single multi-task model from independently fine-tuned task models without accessing the original task data. This makes it attractive when task data cannot be centralized, but released task models may still leak private fine-tuning data. Differential privacy (DP) provides a principled mechanism for limiting such leakage, yet its effect on model merging remains poorly understood. In this paper, we study the geometry of differentially private model merging and identify two geometric obstacles that make private task models difficult to merge: \emph{local sharpness}, which makes task losses sensitive to the parameter displacement induced by merging, and \emph{reference drift}, which measures the displacement of private task models from the shared pretrained initialization and amplifies cross-task interference. Based on these observations, we propose \textbf{DP-Merging}, a geometry-aware framework that improves the mergeability of differentially private task models. DP-Merging uses a DP-compatible sharpness-aware objective to guide each private task model toward flatter loss regions, and a reference-based alignment regularizer to keep task models close to the shared pretrained initialization. We derive a merge-gap upper bound showing that reducing local curvature and reference drift tightens the bound on the loss increase induced by merging. Experiments on vision and language tasks across multiple privacy budgets show that DP-Merging consistently improves private merged-model performance while preserving the privacy guarantees of the underlying DP fine-tuning procedures.

AI 总结：NeuronFuzz是一种安全神经元引导的LLM安全评估白盒模糊测试框架，通过利用安全神经元激活值生成反馈，在21个模型上实现了高越狱发现率和零样本迁移能力，性能优于基线方法。

链接：https://arxiv.org/abs/2608.26222

机构：University of Bristol（布里斯托尔大学）

作者：Zhiyuan Xu, Muhammad Firhard Roslan, Joseph Gardiner, Sana Belguith, Lichao Wu

英文摘要：Safety evaluation is critical for assessing whether aligned Large Language Models (LLMs) remain robust against jailbreak attacks. Existing automated testing methods, however, largely rely on response-level feedback: each candidate prompt typically requires generating a target-model response to evaluate its attack effectiveness. This process is expensive and, more importantly, provides only sparse guidance on strongly aligned models, where most candidates are rejected with the same failure outcome. This paper presents NeuronFuzz, a white-box fuzzing framework that exploits internal safety neurons as continuous execution feedback for LLM safety evaluation. A SafetyOracle converts safety-neuron activations into a continuous safety alarm score that serves as feedback for fuzzing and can be obtained during prefill, eliminating response generation from the fuzzing loop. To construct the SafetyOracle, NeuronFuzz uses template-invariant harmful and benign inputs and stability-aware selection to identify a compact set of safety neurons whose activations capture harmful-intent recognition. Moreover, since the safety alarm score is differentiable, NeuronFuzz uses its gradients to identify safety-sensitive template positions and a masked language model to generate fluent, context-compatible mutations while preserving original harmful payload and avoiding additional optimization variables. We evaluate NeuronFuzz across 21 text and multimodal models. Across five white-box source models, it achieves a 76-100% jailbreak discovery rate, outperforming baselines by up to 48 percentage points. Its optimized templates further transfer zero-shot to open-weight and six proprietary target models, achieving average ASR and top-5 ensemble ASR (EASR) of 69.6%/92.6% and 44.1%/60.0%, respectively.

AI 总结：CG4AI是带线性约束的AI模型训练的列生成框架，通过主LP、定价子问题和割平面程序实现，在MNIST和SNDLIB网络上验证，可生成可行预测器且准确率优于单模型基线。

链接：https://arxiv.org/abs/2608.26375

机构：Huawei Technologies Ltd., France Research Center（华为技术有限公司法国研究中心）

作者：Youcef Magnouche, Abderrahmane Driouch, Sébastien Martin, Pierre Bauguion

英文摘要： Standard machine-learning training minimizes a loss function over a dataset, but does not guarantee that the resulting model will satisfy predefined rules or constraints on its outputs. In many real-world applications, ranging from autonomous systems to network routing, such guarantees are essential. We propose CG4AI, a framework that builds a convex combination of AI models while enforcing linear constraints on the combined output. A master linear program (LP) determines the optimal mixture weights, while a pricing subproblem generates new models guided by LP dual variables, focusing attention on the most violated constraints. A cutting-plane procedure extends feasibility guarantees beyond the training set. We apply CG4AI to two problems: (i) digit classification on MNIST, where we demonstrate four distinct uses of constraints, learning from constraints alone, improving adversarial robustness, correcting misclassified examples, and enforcing output relabeling; and (ii) the multi-commodity flow problem, where link capacity constraints are enforced on neural-network routing predictors. Experiments on MNIST and standard SNDLIB benchmark networks show that CG4AI reliably produces feasible predictors while achieving better accuracy than single-model baselines.

AI 总结：本文针对点云数据量大、含噪声及缺失信息，现有重建无不确定性量化的问题，提出全贝叶斯框架与适配的MCMC采样器，经合成及LiDAR数据实验，实现精确曲线重建与不确定性量化。

链接：https://arxiv.org/abs/2608.26490

机构：University of Tennessee（田纳西大学）

作者：Asir Intesar Tushar, Ioannis Sgouralis

英文摘要：Point-cloud data routinely captured by modern imaging and sensor technologies provide detailed geometric descriptions of objects and environments, but their analysis is hindered by large data volumes, localization noise, and missing information. In addition, existing point-cloud reconstruction pipelines typically return a single best-fit structure without uncertainty quantification. We introduce a fully Bayesian framework for representing point-cloud data and reconstructing closed curves, in which observed points are modeled as noisy perturbations of latent locations constrained to lie on the underlying curve that is regularized by a non-parametric prior. Posterior inference in our framework is carried out using a series of Markov chain Monte Carlo samplers tailored to point-cloud characteristics. Numerical experiments, including synthetic examples and real-world LiDAR datasets, show accurate reconstructions and quantified uncertainty over the recovered curves.

AI 总结：该研究提出基于低秩Householder展开的无输入梯度对抗训练方法，消除了对输入求导及内部最大化步骤，开销低且在小ℓ²预算下可匹配多步PGD对抗训练效果。

链接：https://arxiv.org/abs/2608.26963

机构：Washington University in St. Louis（圣路易斯华盛顿大学）

作者：Tiana C. Johnson, Donsub Rim

英文摘要：This work concerns adversarial training against the small-norm adversarial examples that arise from the inherent input instability of a trained deep neural network. Examples in this class are small as measured in the relative $\ell^2$-norm, and therefore lie in the neighborhood of the input on which the model acts approximately linearly, the regime in which the perturbation remains imperceptible. We first show that such examples can be computed directly from the trained network parameters, without input gradient iterations, by means of a linearization called the low-rank Householder expansion (LRHE). The expansion describes the composed affine map rather than any individual layer, and the directions it identifies are read from the activation pattern already available in the forward pass. We then propose a simple adversarial training scheme built on this construction. No differentiation with respect to the input is performed at any point: training requires only additional forward evaluations, with weight parameters updated by the standard backward pass, and the inner maximization of the usual min-max formulation is eliminated entirely. That such a regularizer exists is our main finding: the methods that dispense with the inner search all obtain their local geometry by differentiating with respect to the input, and we show this is not necessary. The regularizer costs the equivalent of $2.8$ PGD steps per epoch, an $8.7\times$ reduction relative to 40-step adversarial training on MNIST and below the cost of 3-step training. The resulting models match three-step PGD adversarial training for relative $\ell^2$ budgets $\varepsilon \le 0.02$ and 40-step training for $\varepsilon \le 0.012$, falling away beyond, consistent with the locality of the expansion.

AI 总结：针对多步CSI预测中现有方法缺乏校准不确定性估计的问题，提出TRACE-CRC方法，通过轨迹自适应策略实现可靠轨迹级覆盖，且不确定性球更小，避免了覆盖不足问题。

链接：https://arxiv.org/abs/2608.27124

机构：Chalmers University of Technology（查尔姆斯理工大学）

作者：Kiarash Rezaei, Mehdi Sattari, Javad Aliakbari, Tommy Svensson, Paolo Monti, Carlos Natalino

英文摘要：Reliable prediction of time-varying channel state information (CSI) is essential for efficient wireless communication. Each CSI frame is a matrix-valued representation of the wireless channel response, and a sequence of CSI frames forms a temporal channel trajectory. Modern deep learning-based CSI predictors, however, often provide only point predictions and lack calibrated uncertainty estimates. This limitation is particularly problematic in multi-step CSI prediction, where the target is a sequence of future CSI matrices, and downstream decisions such as beamforming or scheduling may fail if any part of the predicted trajectory is unreliable. We propose trajectory-adaptive calibration and error profiling with conformal risk control (TRACE-CRC), a method for trajectory-aware uncertainty quantification in multi-step CSI prediction. TRACE-CRC constructs Frobenius-norm uncertainty balls around predicted CSI matrices and controls the risk that at least one future frame is uncovered. Instead of calibrating each future step independently, TRACE-CRC combines future-step-dependent error profiling, trajectory difficulty stratification, and learn-then-test (LTT) risk control. Empirically, TRACE-CRC achieves reliable trajectory-level coverage with substantially smaller uncertainty balls than conservative multi-step corrections, while avoiding the trajectory undercoverage of compact stepwise and adaptive conformal baselines.

AI 总结：该研究针对带属性标签图学习的传统图神经网络的静态属性表示局限，提出SLM条件分层关系路由架构，结合拓扑GNN与参数高效SLM实现可解释的语义集成，提升图学习的预测能力。

链接：https://arxiv.org/abs/2608.26132

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

作者：Michal Podstawski

英文摘要：Labeled property graphs combine relational structure with heterogeneous textual and categorical properties attached to both nodes and relationships. Conventional graph neural networks typically represent these properties as static feature vectors, limiting their ability to determine which semantic evidence should influence message propagation for a particular prediction target. We propose SLM-Conditioned Hierarchical Relation Routing, an architecture that integrates a small language model directly into graph message selection. A topology GNN provides a stable structural representation and prediction anchor. For each target node, incident messages combine the neighbor's structural state, node-property encoding, relationship-property encoding, and relationship type. A parameter-efficient SLM processes structured graph soft tokens and produces a target-conditioned routing query. This query first selects relevant messages within each relationship type and subsequently routes information across relation-level summaries. The resulting representation provides a bounded residual update to the topology anchor, preserving structural evidence while allowing contextual semantic information to modify the prediction. The architecture supports interpretable analysis at both the neighbor and relationship-type levels and provides a general mechanism for integrating language-derived semantics into property-rich graph learning.

AI 总结：针对GNN因敏感同质性导致的结构偏见问题，提出轻量级架构无关的SF-GNN框架，通过识别并过滤易产生偏见的边，在多基准数据集上实现更优的公平性-准确率权衡。

链接：https://arxiv.org/abs/2608.26437

机构：Molly Wardaguga Institute for First Nations Birth Rights, Charles Darwin University（查尔斯·达尔文大学莫莉·瓦达古加原住民生育权研究所）； The University of Sydney（悉尼大学）

作者：Haohui Lu, jiyuan Tian, Fangyu Zhou, Shahadat Uddin

英文摘要：Graph neural networks (GNNs) can exhibit unfair behavior even when sensitive attributes are excluded from node features, because graph topology and message passing propagate group-correlated signals under sensitive homophily. Existing fairness-aware GNN methods mainly constrain representations or prediction distributions at a global level, without explicitly controlling the local structural pathways through which biased information propagates during aggregation. We propose Subgraph Filtering for Fair Graph Neural Networks (SF-GNN), a lightweight and architecture-agnostic framework that mitigates structural bias at its source. SF-GNN identifies bias-prone edges by combining sensitive homophily with structural propagation amplifiers, including hub participation and triadic closure. It then incorporates stochastic edge filtering into each message-passing step to selectively downweight or remove these edges while preserving the remaining graph structure. Training further incorporates a statistical-parity regularizer with a warm-up schedule to stabilize optimization. Experiments on five benchmark datasets show that SF-GNN achieves consistent fairness improvements while maintaining competitive predictive performance, leading to a better fairness--accuracy trade-off than recent fairness-aware GNN baselines.

AI 总结：针对扩展共享单车系统的冷启动预测与公平资源分配挑战，提出公平感知图神经网络FairGIN，通过三类组件实现高精度需求预测并降低收入差距。

链接：https://arxiv.org/abs/2608.26451

机构：University of Exeter（埃克塞特大学）

作者：Man Luo, Yixuan Zhao

英文摘要：Bike-sharing systems are an important component of low-carbon urban mobility, but continued expansion creates challenges in both cold-start prediction and equitable resource allocation. Newly deployed stations lack historical ridership records, causing a mismatch between training and inference for graph-based models on evolving networks. Historical demand may also encode structural inequalities, as lower ridership in low-income neighborhoods can reflect limited infrastructure access rather than weak latent demand. Models trained directly on such data may therefore reinforce existing mobility disparities. We propose FairGIN, a fairness-aware graph neural network for demand prediction in expanding bike-sharing systems. FairGIN integrates three components. Expansion-Simulated Increment Training stochastically simulates network expansion during training to reduce the cold-start distribution gap. Attention-Based Knowledge Transfer combines station-adaptive temperature scaling with orthogonal embedding alignment to transfer representations from data-rich existing stations to data-sparse new stations. Fairness-Aware Optimization introduces income-stratified regularization and an equity-calibrated deployment score to support more inclusive station placement. Experiments on NYC and Seattle demonstrate that FairGIN achieves state-of-the-art predictive accuracy across diverse expansion scenarios while substantially reducing income-based disparities without compromising overall system efficiency.

AI 总结：本研究提出神经回归模型LitEm及协同训练框架，使直推式知识图谱嵌入模型可预测数值属性，在多数据集上取得优异性，还提升了双线性模型的链接预测性能。

链接：https://arxiv.org/abs/2608.26729

机构：Heinz Nixdorf Institute, Paderborn University（帕德博恩大学海因茨·尼克斯多夫研究所）

作者：Rupesh Sapkota, Louis Mozart Kamdem Teyou, Moshood Yekini, Caglar Demir, Axel-Cyrille Ngonga Ngomo

英文摘要： In recent years, transductive knowledge graph embedding models have been applied to tasks such as link prediction and query answering. Although knowledge graphs often contain rich numerical attributes, most embedding models neglect them, limiting their ability to represent real-world knowledge graphs with diverse information. In this work, we propose a neural regression model (LitEm) that enables transductive knowledge graph embedding models to predict numerical attributes within knowledge graphs. Experimental results demonstrate that LitEm achieves the best or second-best results on most attributes across FB15K-237, YAGO15K, DB15K, and Mutagenesis. Furthermore, we propose a co-training framework that jointly trains state-of-the-art transductive knowledge graph embedding models with LitEm, which improves link prediction performance mainly for bilinear models and simultaneously enables them to predict numerical attributes. In addition, the literal-awareness evaluation demonstrates that co-training helps models to encode and exploit attribute information in a "literal-aware'' manner, suggesting that the observed gains are not merely due to additional parameters. We publicly release our implementation at this https URL.

AI 总结：该研究针对文本属性图学习提出了检索增强的RTA框架，以标签感知的检索与传播替代传统结构消息传递，经多基准测试，其性能匹配或优于强基线且效率、鲁棒性更优。

链接：https://arxiv.org/abs/2608.26732

机构：Xiamen University（厦门大学）； Fudan University（复旦大学）； Central South University（中南大学）

作者：Jintang Li, Yuhong Chen, Ruofan Wu, Binli Luo, Jiayi Ji, Hui Li, Rongrong Ji

英文摘要：Graph neural networks (GNNs) are typically conceptualized as message-passing neural networks, yet it remains unclear why neighborhood aggregation reliably outperforms node-wise multilayer perceptrons (MLPs). Despite its empirical success, this paradigm can be computationally expensive and sensitive to imperfect graph structures. In this work, we present a retrieval-augmented view of GNNs: each layer makes predictions by applying an MLP to a node representation together with a permutation-invariant summary of retrieved graph context. Motivated by this perspective, we propose RTA, a simple MLP-based framework that replaces structural message passing with label-aware retrieval and propagation. We provide theoretical insights that (i) connect retrieval-based aggregation to softmax-attention message passing, and (ii) establish the robustness of retrieved-context supervision to mis-retrieved outliers. Experiments on multiple text-attributed graph benchmarks show that RTA matches or even outperforms strong GNN and graph LLM baselines while improving efficiency and robustness across diverse scenarios.

AI 总结：本研究针对关联聚类算法的直推式缺陷，提出基于图神经网络的归纳式关联聚类框架，可高效推广至新图，在归纳设置下推理时间大幅降低，还可作为图分类的高效池化层。

链接：https://arxiv.org/abs/2608.27153

机构：Sapienza University of Rome（罗马大学）； Intesa Sanpaolo AI Research（裕信银行人工智能研究院）； Bowling Green State University（鲍灵格林州立大学）

作者：Francesco Paolo Nerini, Francesco Bonchi, Arijit Khan, André Panisson

英文摘要：Correlation Clustering (CC) is a natural formulation of clustering in combinatorial optimization, which uses a graph representation of the input and does not require a pre-specified number of clusters. Given $n$ objects and a pairwise similarity function, the goal is to cluster the objects so that similar objects are put in the same cluster and dissimilar objects are put in different clusters. Despite its versatility, existing CC algorithms suffer from significant scalability issues and are inherently transductive: i.e., the algorithm must be executed from scratch for any new problem instance. In this work, we bridge this gap by leveraging Graph Neural Networks (GNNs) to solve Inductive Correlation Clustering, a novel generalization of the CC problem designed to handle unseen graph instances. By learning to exploit common structural patterns and node features during training, our framework generalizes to new graphs drawn from the same distribution with minimal computational overhead with respect to standard algorithms. We demonstrate the effectiveness and scalability of our approach through extensive experiments. Our framework not only excels in the inductive setting, e.g., lowering the inference time up to $5$ order of magnitude, while maintaining an approximation ratio within $~10\%$ of the best baseline solution, but also achieves competitive results on standard (transductive) CC benchmarks. Finally, we showcase a practical application of our framework as a learnable pooling mechanism for graph classification. Our results indicate that our method serves as an efficient pooling layer, enhancing the ability of GNNs to capture hierarchical structural information in networks.

AI 总结：本研究提出SimCast-S2S，一种基于气候模拟迁移学习的潜在扩散生成模型，通过变分自编码器的紧凑潜在空间与LoRA迁移学习，实现高效次季节降水概率预测，性能优于深度学习基线及ECMWF-S2S等业务系统。

链接：https://arxiv.org/abs/2608.26594

机构：University of Virginia（弗吉尼亚大学）； School of Data Science（数据科学学院）； Department of Environmental Sciences（环境科学系）

作者：Hiep V. Dang, Antonios Mamalakis

英文摘要：Subseasonal-to-seasonal (S2S) precipitation forecasting has substantial financial and societal impact, yet remains challenging because of weak predictive signals, high associated uncertainty, and the computational cost of operational systems, which constrains simulation fidelity. We introduce SimCast-S2S, a generative latent-diffusion framework for probabilistic S2S precipitation forecasting that addresses three major bottlenecks in data-driven prediction. First, because S2S prediction requires uncertainty quantification rather than only deterministic point forecasts, SimCast-S2S is the first data-driven system that uses a diffusion-based generative pipeline for S2S prediction, enabling effective sampling from the underlying conditional distribution. Second, since generating large probabilistic ensembles is computationally costly in physical space, SimCast-S2S instead operates in a compact latent space learned by variational autoencoders, enabling efficient large-ensemble generation. Third, diffusion models typically require large training datasets; SimCast-S2S overcomes this via transfer learning with low-rank adaptation (LoRA), pretraining on large ensembles of climate simulations before fine-tuning on limited reanalysis data. On reanalysis data, SimCast-S2S outperforms deep learning baselines, including convolutional neural networks and U-Net architectures. Notably, despite using only a subset of atmospheric input variables and no post-processing, bias correction, or calibration, SimCast-S2S remains competitive with, and in many cases outperforms, state-of-the-art operational systems such as the ECMWF-S2S baseline. These results indicate that latent generative modeling combined with simulation-to-reanalysis transfer learning offers an efficient and scalable path toward data-driven probabilistic S2S precipitation forecasting.

AI 总结：该研究首次将元学习与预训练应用于神经刺激响应建模，通过改进时间基函数模型，大幅降低预测失效，减少校准需求，为闭环神经刺激的临床部署提供了可行方案。

链接：https://arxiv.org/abs/2608.26649

机构：University of Washington（华盛顿大学）； Paul G. Allen School of Computer Science & Engineering（保罗·G·艾伦计算机科学与工程学院）； Center for Neurotechnology（神经技术中心）； Computational Neuroscience Center（计算神经科学中心）； Department of Electrical and Computer Engineering（电气与计算机工程系）； Department of Bioengineering（生物工程系）

作者：Matthew J Bryan, Daniel C Muir, Felix Schwock, Azadeh Yazdan-Shahmorad, Rajesh P N Rao

英文摘要：Objective: Model-based closed-loop neural stimulation holds promise for therapeutic applications ranging from Parkinson's disease to sensory restoration, but deployment has been limited by two obstacles: 1) forecasting models for predicting the consequences of stimulation fail catastrophically on a meaningful fraction of sessions, and 2) per-session calibration requirements are often incompatible with clinical constraints. We address both by demonstrating, for the first time, that meta-learning and pretraining can be applied to neural stimulation response modeling. Methods: Temporal basis function models (TBFMs) forecast state-dependent neural responses to stimulation. We extend TBFMs with cross-session pretraining using a novel architecture and algorithm based on model-agnostic meta-learning (MAML), evaluating them on 40 sessions of optogenetic stimulation in primary sensorimotor cortex of two non-human primates. Results: Meta-learning substantially reduces catastrophic forecast failure: for a 1k calibration set size, sessions with test R-squared < 0.05 drop from 16 of 40 (single-session training) to 1 (MAML-pretrained), and prediction intervals become significantly narrower (p < 0.05). Calibration requirements are reduced by 50-90% at matched accuracy, enabling experiments otherwise infeasible within clinical session-time constraints. Conclusion: Our results demonstrate that cross-session structure in stimulation responses is consistent enough to support pretraining, providing the first empirical evidence that meta-learning approaches are viable for neural stimulation. Significance: The robustness and sample efficiency gains directly address known obstacles to deploying model-based stimulation controllers. Our results motivate community efforts to assemble standardized multi-site stimulation datasets and to further explore meta-learning for robust closed-loop stimulation.

AI 总结：该研究发现扩展模型生成的蒸馏数据可使学生模型中教师的潜在特征更易被检测，且该效应跨多种场景存在，建议扩展数据时结合感知特征的整理与评估。

链接：https://arxiv.org/abs/2608.26958

机构：Shanghai Jiao Tong University（上海交通大学）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； Fudan University（复旦大学）

作者：Zhichen Dong, Zhixuan Liu, Yuyu Fan, Xiangtian Li, Shuyang Zhang, Chao Yang

英文摘要：Scaling model-generated data is usually viewed as improving distillation: more examples should increase coverage, reduce noise, and produce stronger students. We show a second effect: larger datasets can make subtle teacher-specific signals easier to detect in the trained student, even when examples are off-task and never mention the trait. In a controlled setup inspired by subliminal learning, a teacher induced to express a target trait generates restricted off-task data, such as number-only completions. Students trained on different amounts of independent off-task data are evaluated in a separate domain, with matched no-trait controls isolating target-specific transfer. Our main finding is that larger independent datasets make the teacher's induced trait stand out more clearly in the student's later behavior. Other plausible traits may also strengthen with scale, but the target usually grows more. When the small-scale student already favors the target, scaling mainly amplifies that behavior; when it favors a related or salient alternative, more data can shift behavior toward the intended trait. Analyses of learned LoRA updates show a parallel trend. These effects appear across model families, trait types, multi-trait settings, and cross-model transfer. Our results suggest that scaling generated distillation data should be paired with trait-aware curation and evaluation, even when the data appears off-task or benign.

AI 总结：该研究构建含10种英语口音的ABX-Accent基准，用自适应域归一化微调CPC模型，在跨说话人ABX分数上平均提升23.6%，相关数据指标将开源。

链接：https://arxiv.org/abs/2608.26992

机构：ENS（巴黎高等师范学院）； PSL university（巴黎文理研究大学）； CNRS（法国国家科学研究中心）； EHESS（高等社会科学研究学院）； Hebrew University of Jerusalem（耶路撒冷希伯来大学）

作者：Robin San Roman, Manel Khentout, Tu Anh Nguyen, Paul Michel, Yossi Adi, Emmanuel Dupoux

英文摘要：Representation learning has attracted great atten- tion and managed to reach good performances as a pretraining method for downstream tasks or as a first step towards unsu- pervised speech modeling. Yet, little is known about how such methods deal with out-of-domain speech and how could they be adapted in a few shot to new domains. This is important especially for accented speech where one observes a long tail of accents that diverge from the standard ones. We introduce ABX- Accent, a benchmark based on the AESRC dataset that features 10 different accents of English. It includes a small (< 10 hours) unlabelled training set in each of the accents and adaptations of the Zero Resources Challenge ABX evaluation metrics to each of the accents. We illustrate this benchmark with a baseline model that uses adaptive domain normalization to fine tune a pretrained Contrastive Predictive Coding model on the accents. This method is first developed on LibriSpeech using a male/female split. When applied to the new benchmark, the proposed method yields a relative improvement of 23.6% on across-speaker ABX scores on average compared to non adapted models. The data and metrics will be open sourced upon paper acceptance

AI 总结：本文提出FiUni框架，通过K-FAC近似的Fisher主子空间正交性检测批量级任务，结合LoRA实现参数高效适配，动态平衡知识共享与任务隔离，缓解LLM持续学习的灾难性遗忘，性能优于先进方法且参数更少。

链接：https://arxiv.org/abs/2608.27070

机构： School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）； The Hong Kong University of Science and Technology（香港科技大学）； Shandong University（山东大学）； Qilu Hospital of Shandong University（山东大学齐鲁医院）

作者：Dezheng Han, Anbang Zhang, Zhihao Zhu, Shuaishuai Guo

英文摘要：To mitigate catastrophic forgetting in downstream continual learning (CL) for large language models (LLMs), existing methods typically constrain parameter updates or introduce task-specific adaptation modules. However, these methods often rely on explicit task boundaries during training, limiting their applicability to realistic task-free scenarios. In this paper, we propose a \textbf{Fi}sher-guided \textbf{uni}fied (\textbf{FiUni}) framework for batch-level task detection and parameter-efficient continual adaptation. FiUni is motivated by a key observation about the Fisher information matrix (FIM) of pre-trained models: the orthogonality among the principal subspaces of its Kronecker-Factored Approximate Curvature (K-FAC) approximation, estimated from a small number of downstream task samples, can reflect the similarity between different tasks. Based on this observation, FiUni constructs FIM-derived frozen subspaces to guide low-rank adaptation (LoRA), while matching the Fisher principal subspace of each incoming batch window with historical subspaces. This enables FiUni to adaptively determine whether to reuse existing knowledge, expand a related subspace, or create a new subspace, dynamically balancing knowledge sharing and task isolation. Experiments show that FiUni can effectively infer latent batch-level task affiliations and achieve competitive performance against advanced task-aware CL methods with fewer trainable parameters.

AI 总结：Chart2SVG是融合图表语义令牌、Beagle+数据集与Chart Structure Graph的多模态大语言模型，可生成可编辑SVG，在图表重建与编辑任务中性能优于基线，助力智能可视化工具发展。

链接：https://arxiv.org/abs/2608.26544

机构：Renmin University of China（中国人民大学）； State Key Lab of CAD&CG, Zhejiang University（浙江大学CAD&CG国家重点实验室）； Shandong University（山东大学）； Microsoft Research（微软研究院）； Qwen Large Model Application Team, Alibaba（阿里巴巴通义大模型应用团队）； University of Technology Sydney（悉尼科技大学）

作者：Jinning Cui, Lu Chen, Haoyan Shi, Yue He, Chenglong Wang, Mengyu Zhou, Weidong Huang, Yunhai Wang

英文摘要：We present Chart2SVG, a multimodal large language model that converts static raster charts into structurally organized, semantically enriched SVGs that support programmatic editing. By incorporating chart-specific semantic tokens into a vision-language model, Chart2SVG captures both geometric primitives and their functional roles. To support robust structural recovery, we introduce Beagle+, a dataset of 33K canonicalized and structurally distilled chart samples. Our approach combines specialized training objectives with a rendering-aware post-training phase, producing SVGs that are both visually accurate and structurally consistent. To facilitate higher-level manipulations, we construct a Chart Structure Graph (CSG) that exposes visual dependencies, enabling tasks such as interactive exploration, chart repurposing, and layout reuse. Experiments show that Chart2SVG substantially outperforms baselines in reconstruction fidelity and downstream editing utility, advancing the development of intelligent and interactive visualization tools.

AI 总结：本研究对比多种AI方法，在三类风电场数据集上测试后发现，不同架构各有优势，RF BiLSTM混合模型获最佳预测精度。

链接：https://arxiv.org/abs/2608.26613

作者：Majid Masoumi, Asghar Dashtiy, Mohammad Dehghan, Mina Rajabi

英文摘要：This study provides a comprehensive benchmarking of conventional machine learning (ML), ensemble learning, deep neural networks, recurrent architectures, Transformers, graph based models, and hybrid ensemble deep learning approaches under complementary renewable energy scenarios. Three datasets are considered: a large scale WEC dataset, a 16 WEC dataset, and operational 10 min SCADA measurements at the Penmanshiel wind farm. For structured WEC layout data, tree ensembles exhibited a clear advantage over conventional ML and neural predictors because randomized partitioning and boosting efficiently captured nonlinear layout power interactions without requiring explicit feature representation learning. The Extra Trees was the strongest model, achieving considerable results. Relative to the MLP baseline, this corresponds to an approximately 63.7% reduction in MAE, demonstrating the suitability of randomized tree ensembles for high dimensional structured WEC data. Also, STGCN reduced the MAE to approximately 167.0 kW and achieved R = 0.93 by explicitly learning spatial and temporal turbine interactions. The best overall forecasting accuracy was obtained by the RF BiLSTM hybrid, with an MAE=150.5 kW. Compared with standalone LSTM, this represents an approximately 75% reduction in MAE, while improving on STGCN by approximately 10.0%. Finally, the experiments reveal that no single AI architecture is universally optimal: randomized and boosted ensembles are particularly effective for structured WEC surrogate modeling, graph networks become advantageous when explicit spatial interactions dominate, and ensemble recurrent hybrids provide the strongest balance when nonlinear tabular relationships and temporal dynamics coexist.

AI 总结：TEMPLAR Wales是含3757条威尔士定居点记录的地理参考环境-地名数据集，关联定居点框架与词汇、环境属性，经技术验证，为多领域研究提供可复用基础。

链接：https://arxiv.org/abs/2608.26970

机构：Cardiff University（卡迪夫大学）； Turkish Air Force Academy, National Defence University（土耳其空军学院，国防大学）

作者：Oktay Karakuş, Can Eyupoglu

英文摘要： Place names provide persistent records of how landscapes have been described and organised, but their quantitative reuse requires explicit separation between mapped places, lexical annotations and environmental measurements. TEMPLAR Wales is a georeferenced environmental-toponymy dataset comprising 3,757 settlement records across Wales. The resource links a reproducible settlement frame to deterministic lexical screening and settlement-level environmental attributes through stable identifiers. It contains 1,350 lexical detections across 1,294 settlements, generated from a frozen registry of 24 Welsh place-name elements, while retaining exact- and prefix-token matches and their provenance separately. Environmental attributes describe river and coastal proximity, elevation and local terrain context at multiple spatial scales, land cover and neighbourhood woody cover, with parallel terrain measurements derived from independent elevation products. The dataset is distributed as four relational tables accompanied by a field-level data dictionary, source-provenance register and licensing metadata. Technical validation confirms relational integrity, deterministic lexical reconstruction, documented environmental coverage, strong agreement between independent terrain sources and reproducible reconstruction of the frozen release. TEMPLAR Wales provides a reusable foundation for research in toponymy, linguistic geography, historical and environmental landscape studies, GIS and spatial data analysis without treating computational lexical detections as verified etymologies or contemporary environmental measurements as historical landscape reconstructions.

AI 总结：QuantumBoostNet作为经典-量子混合架构，通过双头部设计及分阶段训练，在心脏超声视图识别任务中优于现有模型，且在图像分类基准中表现更优、抗噪性更强，为专业医学成像的混合模型发展提供支撑。

链接：https://arxiv.org/abs/2608.27302

机构：Politehnica University Timişoara（蒂米什瓦拉理工大学）； University Hospital Müenster（明斯特大学医院）

作者：Mihai Udrescu-Milosav, Stefan-Alexandru Jura, Mihai Udrescu, Gerhard-Paul Diller

英文摘要：Accurate identification of the correct view or angle in cardiac ultrasound (echocardiogram) is a critical component of cardiologic imaging. This step is essential for precise anatomical interpretation, reliable measurement, and the reduction of clinical errors. Although computer vision has advanced significantly, most state-of-the-art models perform well on standard benchmarks but often yield suboptimal results in specialized medical imaging tasks due to the high level of noise present in the data. QuantumBoostNet, a hybrid classical-quantum architecture, is introduced to address these challenges. This model integrates a classical backbone with two heads: one classical and one quantum, with the quantum head implemented as a parametrized 10-qubit quantum circuit. Training occurs in two stages, with an adaptive transition between heads governed by a mixing parameter that monitors loss dynamics. Extensive experiments indicate that, despite the limited number of qubits that can be simulated, QuantumBoostNet consistently outperforms state-of-the-art classical and hybrid classical-quantum models in cardiac ultrasound view identification, achieving a relative improvement over the best competitor. QuantumBoostNet also demonstrates superior performance on established image classification benchmarks and exhibits robustness to noise. These findings support the continued development of hybrid classical-quantum models for specialized medical imaging applications.

AI 总结：针对时间序列预测模型缺乏语义知识的问题，提出基于CLIP的SAGE框架，通过双重利用CLIP实现多模态监督，在8个长期基准及M4数据集上取得最优精度。

链接：https://arxiv.org/abs/2608.26829

机构：Shanghai Jiao Tong University（上海交通大学）

作者：Haizhao Fan, Xinyi Le

英文摘要：Time series forecasting models operate on raw numerical sequences, lacking the semantic knowledge that domain experts implicitly leverage, such as the physical meaning of each variable, its statistical behavior, and its temporal dynamics. Recent efforts to bridge this gap fall into two camps. Some rely on large language models at inference time, which is computationally expensive. Others apply uniform textual prompts at the dataset level, ignoring the heterogeneous semantics across individual variates. We propose SAGE (Seeing and Augmenting with Grounded Encoding), an end-to-end CLIP-based framework that jointly models temporal, cross-variable, textual, and visual information. The CLIP text encoder processes frequency-enhanced patches and variable tokens, while gated residual paths inject variable-specific descriptions and statistical descriptors. In parallel, the frozen CLIP vision encoder aligns rendered series with temporal representations through a training-only contrastive objective. This dual use of CLIP adds complementary semantic and visual supervision without placing an LLM in the forecasting loop. Across eight long-term benchmarks and M4, SAGE achieves state-of-the-art accuracy. Ablations confirm complementary gains from multimodal alignment and variable-level knowledge.

AI 总结：研究针对LLM智能体时间序列根因归因性能缺乏受控评估的问题，推出TraceBench框架，评估了四个LLM智能体的表现并揭示其分析规律，相关资源已公开。

链接：https://arxiv.org/abs/2608.27182

机构：ETH Zürich（苏黎世联邦理工学院）； CSEM SA（CSEM公司）

作者：Tommaso Bendinelli, Artur Dox, Christian Holz

英文摘要：LLM agents are increasingly applied to anomaly detection and root-cause analysis in time-series observations collected from real-world systems; however, their performance on these tasks has not been systematically evaluated under controlled conditions. We introduce TraceBench, a simulation-based framework for generating controlled root-cause attribution tasks. In each generated task, an agent receives time-series observations produced by simulating a physical dynamical system and must determine whether a system parameter was altered during the simulation and, if so, which one. Using TraceBench, we generate tasks from three interpretable mechanical systems and systematically evaluate four LLM agents across controlled experimental conditions, yielding new insights into how these agents analyze time-series observations from dynamical systems. Our results show that agents benefit substantially from domain context and explore data primarily through numerical console output rather than visualizations. We also find that agents generally perform worse when required to produce a Python script that maps each time-series sample to a predicted root-cause label than when they submit predictions directly. We release our datasets, agent trajectories, experimental results, and a leaderboard on our website, this http URL.

AI 总结：本文针对二值化神经网络剪枝适配问题，提出基于PyTorch的专用框架及全局加权剪枝算法，在VGG11二值化模型上实现70%剪枝率且准确率不变，优于现有最优结果。

链接：https://arxiv.org/abs/2608.26233

机构：Polytechnique Montreal（蒙特利尔理工学院）

作者：Roan Rubiales, Jean Pierre David

英文摘要：Extreme compression of deep neural networks, up to full binarization, dramatically reduces memory footprint and arithmetic complexity, facilitating deployment on constrained edge hardware with field-programmable gate arrays (FPGAs) and microcontrollers. Although combining binarization with pruning promises additional efficiency gains, existing pruning strategies are ill-suited to binarized representations and rarely translate into meaningful hardware savings. We introduce a PyTorch-based, research-oriented framework that incorporates freezing and pruning mechanisms for designing and optimizing binarized neural networks. The framework enables rapid and reproducible evaluation of state-of-the-art approaches and the fast prototyping of new ones. Leveraging this framework, we propose a novel pruning method that accounts for the relative importance of learned parameters across abstraction levels. Such a global weighting mechanism consistently achieves a superior trade-off between model accuracy and pruning rate, achieving a 70% pruning rate on VGG11 with constant accuracy, while state-of-the-art results reach only 41% in the binarized setting.

AI 总结：针对标签传播在大规模高维数据集上的计算与内存局限，提出AMELS框架，通过代数多重网格求解器替代随机游走迭代，大幅减少运行时间且对超参数更鲁棒，可高效应用于大规模图像数据集。

链接：https://arxiv.org/abs/2608.26309

机构：Osnabrück University（奥斯纳布吕克大学）； Ruhr University Bochum（波鸿鲁尔大学）

作者：Antonia van Betteray, Jonathan Klees, Miriam Schäfers, Matthias Rottmann

英文摘要：Modern machine learning models rely on large amounts of labeled data. However, manual annotation of large-scale datasets is expensive and time-consuming. Label spreading is a semi-supervised learning technique that addresses this challenge by propagating information from a few labeled examples to a larger pool of unlabeled data. Despite its effectiveness, its application to large-scale, high-dimensional datasets is limited by computational costs and memory constraints. To address these limitations, we propose Algebraic Multigrid Acceleration for Efficient Label Spreading (AMELS), an efficient label spreading framework that improves scalability by fast construction of neighborhood graphs and the incorporation of algebraic multigrid solvers. The latter is an iterative solver that replaces the ordinary random walk iteration typically performed in label spreading. Due to the multilevel nature of algebraic multigrid solvers, AMELS spreads given label information across a graph of any size in a single multigrid cycle. We demonstrate that AMELS achieves significant runtime reductions compared to existing implementations while also being more robust to hyperparameter choices in terms of both runtime and classification accuracy. Our framework therefore enables efficient label spreading on large-scale image datasets and produces accurate labels even when only a few labeled samples are available.

AI 总结：该研究提出潜在诊断分类学框架，构建提示注入检测分类器并诊断其可信决策，实验发现分类器约77%高置信度决策对单标记移除不鲁棒，分两种失败模式并给出修复策略。

链接：https://arxiv.org/abs/2608.26423

机构：TrendAI™ Research（TrendAI™研究中心）

作者：Jaturong Kongmanee, Smile Thanapattheerakul

英文摘要：This paper proposes a framework for constructing a classifier as a safeguard layer, and for developing a complementary diagnostic that identifies which of the classifier's confident decisions can be trusted. This framework, the Latent Diagnostic Taxonomy, consists of (i) constructing a dimensionality-optimized classifier, in which the embedding dimensionality is empirically selected via cross-validated performance rather than fixed a priori, (ii) locating a relatively small set of latent support vectors (~ 29% of total training examples) representing influential prompts for identifying tokens that alter the classifier's predicted labels, and (iii) utilizing such tokens and their associated attack magnitudes for constructing a diagnostic taxonomy. This diagnostic taxonomy provides an end-to-end guideline for flagging prompts that require different treatments: rely Safely on the classifier's decision; flag Heuristic Bias and Heuristic Override cases; route Insufficient Context cases for further human/safety review. Applying the framework to a classifier trained on a public prompt injection dataset, we find that a substantial fraction of its confident decisions (~ 77%) are not robust to removing a single token, and that this brittleness separates into two distinct failure patterns: a confidence calibration failure and a genuinely exploitable shortcut. For each zone of the taxonomy, we also recommend strategies for remediating diagnosed prompts. We illustrate the framework as a series of steps, demonstrating how each step operates.

AI 总结：本文提出NeoTriFuse框架，将缺失值作为可靠性信号动态调整模态贡献，联合优化死亡率与住院时长预测，在新生儿死亡率风险预测任务中取得优异性能。

链接：https://arxiv.org/abs/2608.26436

机构：The University of Sydney（悉尼大学）； Charles Darwin University（查尔斯达尔文大学）； Molly Wardaguga Institute for First Nations Birth Rights（莫莉·沃达古加原住民生育权利研究所）

作者：Jiyuan Tian, Qincheng Shen, Ye Lin, Yu Gao, Haohui Lu

英文摘要： Neonatal mortality risk prediction from bedside monitoring data remains challenging due to extreme class imbalance, heterogeneous clinical risk factors, multi-scale temporal dynamics, and substantial missingness. We propose NeoTriFuse, a reliability-aware multimodal fusion framework for missingness-heterogeneous neonatal monitoring data. Unlike conventional multimodal approaches that treat missingness primarily as a preprocessing issue, NeoTriFuse models missingness as an explicit reliability signal that dynamically modulates modality contributions during fusion. The framework integrates static perinatal variables, local-global temporal encoders, and patient-level statistical summaries through reliability-guided gating mechanisms, while jointly optimizing mortality prediction and an auxiliary length-of-stay objective. NeoTriFuse achieves competitive performance, with an F1 score of 0.6736 +/- 0.0216 and an AUROC of 0.9454 +/- 0.0056. Ablation studies indicate that the local-global temporal architecture and patient-level summary branch contribute most substantially to predictive performance, while reliability-aware gating provides additional improvements on threshold-dependent metrics under heterogeneous observation completeness. Sensitivity analyses further suggest stable performance across nearby hyperparameter settings. Overall, the findings support reliability-aware multimodal fusion as a practical approach for neonatal mortality prediction under realistic clinical missingness conditions.

AI 总结：该研究针对广域网分布式训练的带宽、延迟等瓶颈，提出结合多播、在线FPGA的系统方案与基于拓扑的旋转团同步调度算法，在九城市DoubleZero网络拓扑上验证可缩小与同位置训练的性能差距。

链接：https://arxiv.org/abs/2608.26453

作者：Nihar Shah, Ben Blier

英文摘要：Distributed training across a wide area network (WAN) is challenging, as continuous parameter exchange by islands of compute is constrained by limited bandwidth, high latency, and uneven topology. We propose making the network an active participant in training. On the systems side, such networks should leverage (i) multicast technology to replicate outbound traffic and (ii) in-line FPGAs to aggregate inbound traffic, to ease egress and ingress bottlenecks. These technologies are used for training across workers within a data center, but this paper extends them to the WAN. On the algorithms side, we develop an optimization framework that produces rich synchronization schedules (namely, rotating cliques of islands) around the underlying network topology and these technologies, to maximize information exchange. Finally, we illustrate this on a nine-city topology modeled on the DoubleZero network, a live programmable WAN equipped with both technologies, and show how the optimal schedules shift with the network's capabilities. Together, these can narrow the gap to the gold standard of colocated training.

AI 总结：该研究针对合并模型家族提出BAJ方法，利用预训练基础模型的越狱风险，通过最小-最大优化生成可迁移的对抗性后缀，在多种设置下均实现高迁移成功率且能抵御现有防御。

链接：https://arxiv.org/abs/2608.26506

机构：RIKEN AIP（理化学研究所先进智能项目）； Institute of Science Tokyo（东京科学大学）； Zhejiang University（浙江大学）

作者：Yu Zhe, Yixin Tan, Junhao Wei, Wang Chen

英文摘要：Model merging enables combining multiple fine-tuned models without additional training, but its safety implications remain poorly understood. Prior work primarily attributes merging risks to unsafe constituent models, implicitly assuming that merging individually aligned models preserves safety. In contrast, we show that model merging reveals a previously overlooked jailbreak risk rooted in the pretrained foundation model, even when all constituent models are individually safety-aligned. Motivated by this observation, we study a new threat setting where an attacker constructs jailbreak prompts that generalize across merged models sharing the same pretrained backbone, without access to the exact merging coefficients or constituent checkpoints. To exploit this phenomenon, we propose \textbf{Basin-Aware Jailbreak (BAJ)}, which formulates jailbreak generation as a min--max optimization over the merging space to produce transferable adversarial suffixes across merged model families. Experiments across diverse backbones and merging settings show that BAJ achieves consistently high transfer success rates and remains effective under existing defenses.

AI 总结：该研究针对带Xavier初始化的宽随机tanh神经网络，通过分离最高阶导数线性项等方法，得到与深度无关的一阶导数界及多项式增长的混合导数界，还推导了欧几里得Lipschitz常数等相关高概率界。

链接：https://arxiv.org/abs/2608.26526

作者：Josef Dick, Michael Feischl, Fabian Zehetgruber

英文摘要：We establish high-probability bounds for mixed input derivatives of wide random neural networks whose activation derivatives satisfy a factorial growth bound. Our main result specializes these estimates to $\tanh$ networks with Xavier initialization. A direct deterministic analysis based on Euclidean operator norms of the weight matrices yields derivative bounds that generally grow exponentially with the depth. We show that this growth can be substantially improved for sufficiently wide Gaussian networks by isolating the term that is linear in the highest-order derivative and controlling the corresponding tangent directions by measurable finite nets. For scalar-output $\tanh$ networks with Gaussian weights and Xavier initialization, we prove that there exist constants $C,C_0,C_1>0$ such that, whenever the common hidden width satisfies $n \geq C\left(L^3n_0^2(1+\log n_0)+L^2\left(1+\log(L/\eta)\right)\right)$, then, with probability at least $1-\eta$, the estimate $\left|D^u\mathcal{R}_{\Phi^{(L)}}(x)\right| \leq C_0 |u|! (C_1L)^{|u|-1}\prod_{j\in u}\beta_j(\eta,n_0)$ holds simultaneously for every non-empty $u\subseteq[n_0]$ and every $x\in[0,1]^{n_0}$. Thus, the first-order derivative bound is independent of the depth, while a square-free mixed derivative of order $|u|$ grows at most polynomially as $L^{|u|-1}$, apart from the coordinate factors. As consequences, we obtain high-probability bounds for the Euclidean Lipschitz constant and for weighted Sobolev norms of the network realization. The latter connect the derivative estimates to quasi-Monte Carlo integration and indicate how such regularity can enter the analysis of QMC-based training.

AI 总结：本研究提出建模可量化性的框架，基于初筛特征预测后续剂量反应分析的效价可量化性，实现精准分流以优化药物筛选的资源分配。

链接：https://arxiv.org/abs/2608.26538

机构：Rice University（莱斯大学）

作者：Sean Lim

英文摘要： High-throughput drug screening relies on low-cost primary assays to prioritize compounds for more expensive dose-response profiling, where potency is ultimately quantified. Current screening strategies largely focus on identifying compounds that will confirm biological activity on follow-up, implicitly assuming that confirmed activity will also yield a usable potency estimate. However, confirmed biological activity in screening does not necessarily translate into a quantifiable potency, because active compounds can still fail to produce a reportable dose-response estimate. We therefore present a framework for modeling quantifiability, whether follow-up testing will yield a usable potency estimate, as a distinct triage objective from biological activity. Quantifiability was strongly predictable from the preceding low-cost screen, with most predictive information arising from the observed screening features rather than molecular structure. Response-based predictors remained robust on previously unseen chemical scaffolds and generalized across held-out assay-mechanism families, while the probability of successful quantification varied strongly with response amplitude and assay context. These findings establish experimental measurability, distinct from biological activity, as a predictable property of screening outcomes and show that quantifiability-aware triage can improve the allocation of costly dose-response profiling capacity.

AI 总结：本研究针对多模态大语言模型超低比特量化的性能损失问题，提出Residual Fallback Quantization框架，可有效恢复MXFP4、HiF4量化下的性能，缩小与BF16基线的差距。

链接：https://arxiv.org/abs/2608.26581

机构：Huawei（华为）

作者：Tanzila Rahman, Mehran Taghian Jazi, Yunke Peng, Zhuang Ma, Anandharaju Durai Raju, Yao Wang, Xing Huang, Hei Yi Mak, Shadan Golestan, Hoang Le, Yonghan Dong, Wei Guo, Yaoyuan Wang

英文摘要：Low-bit quantization offers a promising avenue for reducing the computational and memory demands of Multimodal Large Language Models (MLLMs). Recent hardware support for low-precision formats, ranging from MXFP8 to ultra-low-bit formats such as MXFP4 and HiF4, has accelerated research into efficient MLLM training and deployment. In this work, we present a systematic study of these quantization schemes in representative MLLMs that span both video generation and reasoning tasks. Our analysis shows that MXFP8 achieves near-lossless performance, whereas aggressive 4-bit quantization leads to significant degradation. Through extensive ablations, we identify activation quantization as the primary source of this performance loss, contributing substantially more than weight quantization. Motivated by this observation, we propose Residual Fallback Quantization (RFQ), a lightweight activation reconstruction framework that supplements the primary ulta-low-bit activation representation with an auxiliary quantized residual pathway. By explicitly modeling and compensating for quantization errors, RFQ improves activation fidelity while preserving the efficiency advantages of ultra-low-bit computation. RFQ requires no architectural modifications and incurs negligible computational overhead. Extensive experiments on Wan2.2 and Qwen3-VL demonstrate that RFQ consistently recovers a substantial portion of the performance lost under the quantization of MXFP4 and HiF4, significantly narrowing the gap to BF16 baselines across both generation and 4 reasoning benchmarks. Our findings establish activation quantization as the dominant bottleneck in ultra-low-bit MLLMs and highlight residual-based activation reconstruction as an effective and practical strategy for robust 4-bit deployment.

AI 总结：J-Zero是从零数据出发的统一挑战者-求解器-评判器协同进化框架，在可验证与不可验证领域均优于基线，且迭代10次后仍能持续改进。

链接：https://arxiv.org/abs/2608.26582

机构：KAIST（韩国科学技术院）

作者：Gyouk Chu, Myeongho Jeon, Eunho Yang

英文摘要：Self-evolving language models have recently emerged as a promising path toward superintelligence, with the advantage of reducing the cost of human supervision. While considerable progress has been made in verifiable domains, self-evolution in unverifiable domains remains substantially less explored. We propose Judge co-adaptation from Zero data (J-Zero), a unified Challenger--Solver--Judge co-evolution framework that supports self-improvement across both domains. The Challenger and Solver co-evolve through an adversarial interaction: the Challenger generates increasingly difficult tasks, while the Solver learns to produce higher-quality responses to them. In parallel, the Judge co-adapts using preference pairs whose ordering is known in advance from how each response was produced, i.e., the Solver's answer over the Challenger's, and its decomposed-and-recombined answer over its one-shot answer, rather than from the Judge's own scores. J-Zero outperforms the baselines by an average of 4.2 points on verifiable and 8.0 points on unverifiable domains, and continues to improve through at least ten iterations, whereas the baselines degrade after two.

AI 总结：本文针对随机SCAFFOLD，在一维同质客户端等条件下证明客户端平均无法消除系数非零时的客户端无关O(γ²)稳态偏差，数值实验验证了相关结论。

链接：https://arxiv.org/abs/2608.26765

机构：National Chung Hsing University（国立中兴大学）

作者：Yi-Ping Tang, Guan-Ju Peng

英文摘要： Existing constant-step analysis of stochastic \Scaf{} identifies a leading $O(\gamma/N)$ stationary mean bias and shows that higher-order bias can persist as the client count increases, but does not identify the first client-independent contribution at coefficient level. For full-participation stochastic \Scaf{} with one-dimensional homogeneous clients, fixed local-step count $H$, and bounded additive gradient noise, we prove, uniformly over $N\ge2$, $$ \begin{aligned} \mathbb{E}_{\pi_{\gamma,N,H}}[x]-x^\star ={}& -\frac{f'''(x^\star)\sigma^2}{4f''(x^\star)^2}\frac{\gamma}{N}\\ &- \frac{f'''(x^\star)\sigma^2}{12f''(x^\star)} \frac{(H-1)(5H-1)}{H}\gamma^2 +O_H\!\left(\frac{\gamma^2}{N}+\gamma^3\right). \end{aligned} $$ Hence client averaging suppresses the leading $O(\gamma/N)$ bias but does not remove the client-independent $O(\gamma^2)$ component when its coefficient is nonzero. The mechanism is indirect: although the direct control contribution cancels pathwise in the linear global average, the controls still alter within-round local trajectories and their second moments. Fresh gradient noise and persistent control fluctuations therefore generate local second-moment corrections that nonquadratic curvature converts into stationary mean bias. The coefficient vanishes for quadratic objectives. Numerical experiments are consistent with the predicted coefficient, its persistence as client count increases, and the stated joint remainder. The result is restricted to the one-dimensional homogeneous fixed-$H$ setting.

AI 总结：该研究针对普通体积采样结合选定未加权最小二乘的场景，建立了中心化系数协方差的Loewner包络，分析了其Sharp性、可达性及相关几何性质，明确了证书非空的条件。

链接：https://arxiv.org/abs/2608.26877

作者：Kihun Rhee

英文摘要：Prior analyses by Derezinski and Warmuth established all-size sampling identities, selected-OLS unbiasedness, and inverse moments for ordinary volume sampling, while their exact arbitrary-fixed-response loss and prediction-covariance formulas are at the rank-size endpoint s=d. We establish a Loewner envelope for centered coefficient covariance for every full-rank fixed pool, response, and legal budget d <= s <= m under ordinary indexed fixed-size volume sampling followed by selected unweighted least squares; its coefficient is globally sharp over the full-rank class. Global sharpness does not determine attainability on the pool in hand. Under positive loss, strict-interior budgets, and no coloops, a feature-only margin nu_A gives the exact fixed-design spectral phase: nu_A > 0 if and only if the normalized spectral envelope is strict for every compatible residual, whereas nu_A = 0 if and only if some compatible residual is spectrally tight; the same zero-margin residual is tight at every strict-interior budget. A residual-augmented change of measure supplies the response-aware mechanism and a one-sided quantitative slack bound, while support saturation proves the attainment direction. Critical equal-leverage geometry interprets the boundary, and sound lower certificates yield conservative same-primitive cardinality decisions. Frozen-feature examples show that the certificate is nonvacuous and measure the fixed-pool cost of its authorized reduction. The claims concern conditional centered, full-Gram-whitened coefficient covariance, not population generalization.

AI 总结：针对内存有限设备上的自回归小型语言模型，提出结合信息保留与吞吐量增益的复合层重要性度量，可调整速度-质量权衡，预测加速比误差约4%，性能优于部分同类方法。

链接：https://arxiv.org/abs/2608.26926

作者：Artem Safronov

英文摘要：Small language models (sLLMs) are nowadays hosted on devices with limited memory and computational budget. In an autoregressive setup, inference is memory-bandwidth bound: uniform quantization is often detrimental to such models, since their architecture has limited redundancies and only a few layers are not very sensitive to lower precision. We propose a composite metric that combines two orthogonal criteria: information retention (measured in terms of a normalized SQNR-based coefficient) and throughput gains (modeled using a roofline-based latency analysis). By profiling Gemma 3 1B, we find that Feed-Forward Network blocks and the embedding matrix are the most promising targets for acceleration. For each candidate, we estimate a normalized quality score based on simulated quantization and a normalized speed score based on roofline modeling with no actual execution needed. We combine the two scores in a composite priority coefficient, allowing us to tune the trade-off between speed and quality as needed. Our metric is general and can be used to prioritize individual blocks, their projection sublayers, or transformer layers as a whole. We evaluate our approach on several model architectures, showing that our estimates have at around 4% prediction error for the accelerated speedup. We find that our method generally allocates more resources to the most expressive layers compared to evolutionary search, specialized accelerators, or Shapley-value-based approaches that require expensive approximate inference. Our analytical approach makes sLLM quantization a predictable engineering task.

AI 总结：Packora是一种基于流的生成式分子晶体结构预测模型，支持多组分与有机金属晶体，在结构生成和排序基准上优于基线，在6项生成基准中获最佳匹配预算覆盖率。

链接：https://arxiv.org/abs/2608.26962

机构：Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）

作者：Nayoung Kim, Kiyoung Seong, Sungsoo Ahn

英文摘要：Molecular crystal structure prediction (CSP) is important in pharmaceuticals, agrochemicals, and organic electronics, where subtle differences in molecular conformation and packing can strongly affect material properties. We present Packora, a flow-based generative model for molecular CSP that jointly predicts atomic coordinates and the lattice from molecular graphs. Packora supports multi-component and organometallic crystals and can condition on any subset of molecular conformers, stereochemical labels, and space-group information within a single model. Inspired by the CCDC CSP blind test, we evaluate generation and ranking separately, using generation to isolate generator quality and ranking to measure end-to-end performance under a common relaxation and ranking pipeline. We also systematically study architecture, training, conditioning, inference, and scaling, identifying an effective design based on cacheable pairwise reasoning, training objective and numerical solver choices, conditioning dropout, and balanced scaling of pairwise and single representations. Packora outperforms the baselines on both structure generation and ranking benchmarks, achieving the best matched-budget coverage across all six generation benchmarks, as well as higher experimental-form recovery, lower experimental-form ranks, and faster convergence in ranking.

AI 总结：本研究分析3757个威尔士定居点名称，发现含高地地形元素的名称对应位置显著更高，加入地形名称极性可降低空间均方误差，证实定居点名称保留了当地地形信息。

链接：https://arxiv.org/abs/2608.26978

机构：Cardiff University（卡迪夫大学）； National Defence University（国防大学）； Turkish Air Force Academy（土耳其空军学院）

作者：Oktay Karakuş, Can Eyupoglu

英文摘要： Landscapes are named, but whether names retain measurable environmental information beyond broad geographic structure is rarely tested. We analysed 3,757 Welsh settlements using a frozen, source-audited 24-element lexical framework, preregistered outcome-specific models and geographically structured validation. The central comparison contrasted 101 settlements carrying high-terrain elements (\textit{bryn} or \textit{mynydd}) with 139 carrying low-terrain elements (\textit{cwm} or \textit{pant}). High-terrain names occupied locations 24.4 m higher relative to their 2-km surroundings (95\% CI, 10.8--38.1 m; Holm-adjusted $p$ = 0.00137). The association remained positive across prespecified 1-, 2- and 5-km neighbourhood definitions and was reproduced using an independently produced elevation source (24.1 m; 95\% CI, 10.6--37.6 m). Adding terrain-name polarity to a non-lexical spatial and settlement baseline reduced geographically held-out mean squared error by 4.63\%, 6.22\% and 7.30\% under 10-, 25- and 50-km spatial blocking, respectively, although improvement varied among held-out regions. River-related names provided weaker, directionally consistent evidence, while the preregistered woodland model was non-estimable. Residual spatial structure, unresolved name language and the absence of independent external replication limit interpretation. Selected Welsh settlement-name categories therefore retain measurable information about present-day terrain within Wales, without establishing individual etymology, causal naming, historical environmental memory or transferability to other naming systems.

AI 总结：本文针对任务关系未知的网络场景，提出从分布式数据学习任务图的分散式两阶段策略，实现合作式多任务扩散学习，性能优于非合作学习且逼近真实图基线。

链接：https://arxiv.org/abs/2608.26989

机构：Imperial College London（帝国理工学院）

作者：Zirui Wan, Stefan Vlaski

英文摘要：This paper investigates decentralized multitask learning over networks when the underlying task relationships are unknown. While existing graph-regularized multitask frameworks typically assume a known structure, practical settings often require learning inter-task dependencies directly from distributed data. We propose a decentralized two-phase strategy that first estimates a generalized graph Laplacian from noisy non-cooperative stochastic gradient iterates, and subsequently exploits the learned graph to enable cooperative multitask diffusion learning. This framework is motivated by a Gaussian Markov random field prior, which gives rise to a decentralized maximum likelihood estimator for the graph Laplacian. The analysis quantifies the Laplacian estimation error and its propagation to the steady-state performance of the multitask diffusion recursion, and introduces a topology sensitivity index to capture the effect of network heterogeneity. Simulation results corroborate the theoretical findings and demonstrate that cooperation enabled by the learned task graph significantly improves performance over non-cooperative learning, while approaching the true-graph baseline when the estimation stepsize is sufficiently small.

AI 总结：本文针对DPO中β同时控制逆偏好噪声尺度与优化步长的纠缠问题，提出居中-软plus重构方法，使两种效应可独立调整，消除损失值跨β不可比性。

链接：https://arxiv.org/abs/2608.27032

作者：Ivan Kruzhilov

英文摘要：Direct Preference Optimization (DPO) is a widely used objective for aligning language models from preference data, with the coefficient $\beta$ commonly interpreted as controlling the KL constraint to a reference policy. We show that $\beta$ entangles two distinct roles: it governs the effective inverse preference-noise scale and simultaneously rescales the optimization dynamics, coupling this scale with the effective step size. As a consequence, at a fixed learning rate the achieved policy deviation is non-monotone in $\beta$: it vanishes in a dead zone at small $\beta$, reaches a peak at an intermediate value, and decreases again for larger $\beta$. Moreover, standard DPO loss values are not comparable across $\beta$: runs with nearly identical loss curves can differ several-fold in KL divergence from the reference model. This entanglement obscures the role of $\beta$, increases sensitivity to hyperparameter choices, and complicates learning-rate scheduling. We propose a centered-softplus reformulation that is argmin-equivalent to DPO for $\beta>0$, while making the inverse preference-noise-scale and learning-rate effects explicit and independently tunable. The normalized centered-softplus objective also admits a continuous $\beta\to0$ endpoint that reduces to a linear preference-margin objective.

AI 总结：本文提出一种柔性主动肌电接口，结合机器学习实现词级无声语音识别，在30词词汇分类中达97.2±1.3%平均准确率，可用于嘈杂隐私敏感环境的无人机控制。

链接：https://arxiv.org/abs/2608.27048

作者：Yuta Kurotaki, Shusuke Yamakoshi, Reitaro Yoshida, Yutaka Isoda, Tamami Takano, Yuji Isano, Yusuke Miyake, Kentaro Kuribayashi, Hiroki Ota

英文摘要：Silent speech recognition (SSR) provides an alternative communication pathway in the absence of audible speech. However, conventional approaches are limited by the need for constant facial attachment, privacy concerns, and unstable signal acquisition. Here, we propose a soft, active electromyography (EMG) interface that enables word-level SSR using machine learning. Worn on the hand, the device uses a fingertip electrode that can be positioned near the lips to acquire EMG signals only when needed. The interface integrates liquid metal (LM) interconnects, transparent flexible printed circuit (FPC) electrodes, and elastomer encapsulation to ensure high mechanical stability during finger motion. A deep neural network trained on these stable signals achieved a mean accuracy of 97.2 $\pm$ 1.3% across three subjects in classifying a 30-word vocabulary, demonstrating robust linguistic discrimination. Furthermore, real-time drone control validates the practicality of this approach in noisy and privacy-sensitive environments where conventional voice recognition fails. This study highlights the potential of soft, wearable EMG systems as secure and intuitive human-machine interfaces.

AI 总结：本研究针对算法交易中股票信号生成的制度鲁棒性问题，通过贝叶斯优化训练表格型深度学习模型，结合XGBoost与TabNet构建的混合集成模型取得了优异的投资表现。

链接：https://arxiv.org/abs/2608.27076

机构：University of Exeter（埃克塞特大学）

作者：Joshua Le Grice

英文摘要：Algorithmic trading now represents a market exceeding $20 billion, where even marginal gains in signal robustness can translate into economically significant returns. Existing evaluations of equity prediction models do not explicitly target regime robustness during hyperparameter selection. Five model classes are trained on daily observations from approximately 300 large-cap US equities over eleven years, with Bayesian optimisation configured to target trading performance across three statistically different market regimes. Regime-robust hyperparameter selection is associated with out-of-sample generalisation, as signal precision remains above the random baseline across all four quarters of the test period, and portfolio performance slowly degrades under simulated input noise before collapsing beyond a defined threshold. No individual tabular deep learning architecture outperforms gradient-boosted trees, but combining XGBoost and TabNet using rank aggregation produces a Hybrid ensemble with an annualised return of 51.26%, a Sharpe ratio of 2.44, and a statistically significant CAPM alpha of 0.423 (p = 0.011). A near-zero beta indicates this outperformance is driven by stock selection, not market exposure. Alternative data plays a secondary role once technical and fundamental features are accounted for, as well as contributing more strongly on the short side than the long, and varies by model class. An interactive application makes these results explorable in real time, with live data integration the remaining step toward practical deployment.

AI 总结：该研究针对有向图学习的非对称传播算子，基于锥瑞利框架开发了面向学习的谱认证、灵敏度分析与自适应控制方法，在有向Cora网络实验中可降低特定谱水平且不影响测试准确率。

链接：https://arxiv.org/abs/2608.27122

机构：Institute of Mathematics with Computing Centre, Ufa Federal Research Centre of the Russian Academy of Sciences（俄罗斯科学院乌拉尔联邦研究中心数学与计算中心研究所）

作者：Yavdat Sh. Il'yasov, Nur F. Valeev

英文摘要：Directed graph learning naturally leads to trainable nonsymmetric propagation operators with distinct right and left spectral structures. Building on the two-sided cone Rayleigh framework for generalized pencils \[ B_\theta-\lambda G, \] we develop a learning-oriented methodology for spectral certification, sensitivity analysis, and control without requiring symmetry, nonnegativity, or cone preservation. In the positive-orthant setting, computable lower and upper cone bounds provide an a posteriori enclosure of a distinguished cone level, while smooth soft-min/max surrogates preserve rigorous one-sided bounds with explicit approximation errors and remain differentiable with respect to the trainable parameters. For a simple interior level, the right and left modes satisfy \[ D\lambda_C(B)[H]=v_C^T H u_C, \] yielding first-order optimal graph-supported interventions under prescribed perturbation budgets and motivating adaptive spectral control. Numerical experiments demonstrate the applicability of the approach beyond cone-preserving operators and in directed learning settings. Signed nonsymmetric perturbations reveal a transition from interior eigenpairs to boundary complementary quasi-pairs, including non-spectral cone levels, while controlled experiments show that symmetrization can remove predictive information carried solely by edge direction. On the directed Cora citation network, adaptive recomputation of the right--left sensitivity reduces the distinguished spectral level by approximately $21.5\%$ under a cumulative edge-weight reduction budget of $0.5\%$, with no observed change in test accuracy for the trained model and data split considered.

AI 总结：针对演化交互图中同伴效应估计难题，提出DynaNet-DR估计器，通过受控对比框架实现双重稳健性，半合成基准及MathOverflow观测研究验证了其良好估计精度。

链接：https://arxiv.org/abs/2608.27187

机构：Adelaide University（阿德莱德大学）

作者：Xiaojing Du

英文摘要：Peer effects are difficult to estimate when interaction graphs evolve because pre-assignment network history, dynamic peer exposure, and post-assignment network change have distinct causal roles. We introduce a controlled contrast framework that indexes potential outcomes by own treatment, temporally aggregated peer exposure, and a post-assignment evolution summary. Differences between the resulting means define own-treatment, peer-exposure, controlled network-evolution, and joint controlled contrasts rather than a mediation decomposition. We develop the Dynamic Network Doubly Robust estimator, DynaNet-DR, which combines a temporally factorized propensity with normalized augmentation. Under consistency, summary sufficiency, sequential exchangeability, positivity, nuisance convergence, and weak dependence, its canonical estimator is consistent when either the outcome regression or the propensity estimator is consistent. The reported implementation adds representative-score prediction, fixed clipping, and finite-sample stabilization. Semi-synthetic benchmarks on fixed real temporal graph sequences show favorable estimation accuracy among methods targeting the full profile. These benchmarks assess summary-indexed contrasts rather than counterfactual edge generation, and the MathOverflow study is an observational illustration under the stated assumptions.

AI 总结：本文针对结构化SVM，通过构造最小反例，证明公共测地线条件无法保证其费希尔一致性，并对树度量分类得出argmax一致性仅当树为路径的结论。

链接：https://arxiv.org/abs/2608.27203

机构：Tsinghua University（清华大学）

作者：Jintao Fei, Jiangying Luo

英文摘要： A known necessary condition for Fisher consistency of the structured support vector machine requires the task loss to be a metric for which every output triple has a common geodesic point. We show that this condition is not sufficient for the canonical coordinate-wise argmax decoder. A four-output unit star admits an exactly optimal score vector whose maximizers are all strictly non-Bayes, and four outputs are minimal among metrics satisfying the condition. We then completely classify positively weighted tree metrics whose vertex set is the output space: argmax consistency holds if and only if the tree is a path. The failure on branching trees is confined to boundary distributions; every tree retains the argmax property at every full-support distribution. Among metrics satisfying the common-geodesic condition, five outputs are necessary and sufficient for a full-support counterexample; $K_{2,3}$ is the smallest member of an infinite $K_{m,n}$ family. We additionally give a full-support counterexample for the three-dimensional Hamming cube. All optimality claims have exact primal-dual certificates. The counterexamples expose a concrete decoder gap: in this polyhedral setting, an embedding can guarantee the existence of a calibrated link without validating a prescribed argmax link on every surrogate-risk minimizer.

AI 总结：该研究针对冬小麦施氮推荐，发现机器学习作为预测器表现不佳，需作为标准建议的利润导向修正，可减少利润损失，还可用于减排定价。

链接：https://arxiv.org/abs/2608.27205

机构：University of Sheffield（谢菲尔德大学）

作者：Xulong Wang, Po Yang

英文摘要：Nitrogen rates for winter wheat are set before the season, under unknown prices and weather. The standard UK advice does not respond to prices, yet recent price swings moved the most profitable rate by tens of kilograms per hectare. Machine learning is often proposed as the fix. However, it is usually judged on prediction accuracy, and accurate prediction does not by itself make the recommended rate more profitable. Our insight is to score nitrogen advice directly by the profit it forgoes on measured yield response curves. We build a test bench on 892 such curves from two long running UK experiments, and sweep the nitrogen to grain price ratio to cover all price scenarios. On this bench, machine learning fails as a predictor. No model recovers the best rate within farm tolerance, and the benchmark noise shows none can. At normal prices, every model also loses to the standard advice on profit. The gain sits elsewhere. A simple correction step applied after the model cuts profit losses by a quarter, while better models and extra features give no gain. The same frozen correction cuts losses by 43% at the second site without any retraining. A hybrid of standard advice plus a damped correction removes bias and trims rare large losses. The same price sweep also prices emission cuts, at a cost comparable to current carbon prices. Machine learning therefore pays as a profit scored correction to standard advice, not as its replacement.

AI 总结：本文提出Circuit Condensation方法，通过训练后处理将模型行为的因果电路集中，在4种行为8个模型的实验中大幅缩减电路规模，且能保留任务性能，可用于提升机械可解释性的电路分析效率。

链接：https://arxiv.org/abs/2608.27254

机构：George Mason University（乔治梅森大学）

作者：Sai Adith Senthil Kumar

英文摘要：One approach to mechanistic interpretability explains behavior through circuits: the components and connections that carry it. Frozen discovery often returns hundreds of edges, making them hard to inspect, compare, or verify exhaustively. We introduce Circuit Condensation, which post-trains models to concentrate behaviors into smaller causal graphs. Each round prunes low-attribution edges and trains a low-rank adapter to match the original through what remains, retaining the cut only if task performance and general capability survive. Across four behaviors and eight models, condensed circuits are smaller than the strongest frozen baseline in 30 of 32 settings, by $8.1\times$ on average and up to $316\times$. Repeating the search without weight updates produces larger circuits in 29 of 32 settings, showing that weight updates, rather than search alone, drive the reduction. Testing every subset of 19 circuits finds 11 that cannot be reduced and reveals removable edges in the rest. Pair ablations expose dependencies between edges, showing that their effects cannot be understood independently. On indirect object identification, condensation isolates 24 heads, 17 of them with documented roles, against 61 heads and 36 undocumented ones for the matched frozen circuit: a sufficient sub-circuit of the published mechanism rather than a reconstruction of it. The resulting circuit tracks the original model's next-token distribution and predicts its errors.

AI 总结：该研究提出隐式演化算子网络（LEON）作为WAMs的新型转移实现架构，通过算子结构建模隐式演化，在两类WAM范式下均提升了闭环性能与鲁棒性，确立了转移实现的重要性。

链接：https://arxiv.org/abs/2608.27259

机构：School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）； Principia AI

作者：Xiaoxiao Lu, Yunlong Dong, Jiahao Shi, Ye Yuan

英文摘要：World Action Models (WAMs) augment robot policies by predicting how task-relevant scene states may evolve under interaction. Recent WAMs increasingly perform such prediction in latent representation spaces, avoiding full appearance-level generation while preserving control-relevant information. Yet latent transitions are commonly realized with Transformer-based predictors whose inductive structure is centered on token interaction rather than temporal evolution. We study transition realization as an architectural choice distinct from predictive representation and prediction-policy coupling. We introduce the Latent Evolution Operator Network (LEON), which models latent evolution in a learned observable space through context-modulated operator-based propagation and additive forcing. Grounded in the controlled Koopman generator view of evolution, LEON organizes context-dependent transition variation around a shared evolution-operator structure while retaining a complementary path for additive change. Controlled dynamical systems verify the resulting evolution-specific inductive bias and the complementary roles of operator propagation and forcing. Across two WAM formulations that integrate latent prediction into the policy differently, LEON improves closed-loop performance and robustness while remaining effective under full transition replacement. These results establish transition realization as a consequential architectural choice in latent WAMs.

AI 总结：该研究针对块式生成的拒绝率，提出信息下限与模型差距的分离方法，在多领域目标上揭示了模型性能瓶颈，明确了短距离条件作用与生成质量的差异。

链接：https://arxiv.org/abs/2608.27339

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

作者：Xinwei Qiang, Xiang Fang, Chang Chen, Yue Guan, Yufei Ding

英文摘要：Block drafters propose several tokens in one forward pass, before earlier target tokens are realised. Their rejection mixes two losses: missing within-block path information and imperfect modelling of observable information. Accepted length cannot distinguish them. We separate the two with an information floor, the minimum expected rejection at a specified conditioning order; rejection above this floor is the model gap. Estimating both from target rollouts across four domains, four open-weight targets, and a frontier API target yields three findings. First, the all-parallel floor reaches $0.286$ at the final slot on Qwen3-4B, limiting even the best proposal to $71\%$ per-slot acceptance. Second, one realised token removes $86$--$100\%$ of this floor, a locality also recovered by an independent mutual-information analysis. Third, current drafters remain far above their floors: the final-slot model gap accounts for $43$--$64\%$ of DFlash rejection and $85$--$92\%$ of DSpark's oracle-conditioned rejection. These findings separate the value of short-range conditioning from proposal quality.

AI 总结：本文研究用于LLM推理的进化策略（ES），发现ES比GRPO有更广泛的推理覆盖范围，开发了结合两者优势的GRPO-ES策略，还揭示了ES的功能稀疏性等特性，确立其为独特的推理后训练范式。

链接：https://arxiv.org/abs/2608.27351

机构：Southern University of Science and Technology（南方科技大学）； National University of Singapore（新加坡国立大学）； Harbin Institute of Technology, Weihai（哈尔滨工业大学（威海））； Huawei Noah’s Ark Lab（华为诺亚方舟实验室）； City University of Hong Kong（香港城市大学）

作者：Yunpeng Ba, Zhi Zheng, Yue Xie, Jiaqing Li, Xialiang Tong, Tao Zhong, Mingxuan Yuan, Zhichao Lu, Xuyang Wu, Zhenkun Wang

英文摘要：Evolution Strategies (ES) have recently emerged as a memory-efficient post-training paradigm for LLM reasoning. However, the optimization behavior of ES remains understudied, making it hard to define its advantage scope compared to mainstream post-training paradigms (e.g., Group Relative Policy Optimization (GRPO)). By systematically investigating ES dynamics and mechanisms, this paper first identifies a performance advantage of ES over GRPO, theoretically and empirically showing that ES can lead to broader reasoning coverage, thereby better exploiting the reasoning capabilities of pretrained LLMs. Theoretically, we show that verifier-projected Jensen-Shannon diversity across the ES population is helpful to higher Pass@K performances. Empirically, unlike GRPO, which exhibits entropy collapse, ES improves Pass@1 while attaining higher Pass@K than GRPO. We further develop a sequential GRPO-ES training strategy that combines GRPO's strength in Pass@1 with ES's gains in Pass@K. Second, we find that despite substantial whole-model parameter drift, the task-performance gains of ES are only contributed to a sparse subset of larger-magnitude updates. This functional sparsity suggests that large parameter movement need not imply widespread functional change, and held-out evaluations further show that it does not necessarily lead to catastrophic forgetting. Finally, we study how hyperparameter design affects the effectiveness of ES, demonstrating that ES requires a smaller population size in a larger LLM. These findings position ES as a distinct reasoning post-training paradigm rather than a less effective, memory-efficient alternative to GRPO.