机器学习学术速递[8.20]

AI 总结：该研究发现卷积序列标注器的归一化层可通过序列跨越路径提供全局上下文，在标签长序列场景中可替代大部分感受野的作用，且消融感受野模块会高估其贡献。

链接：https://arxiv.org/abs/2608.18576

机构：University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）

作者：Qing Tian

英文摘要：A convolutional sequence labeler's receptive field is routinely treated as the extent of the model's usable context: it sets dilation schedules, bounds streaming horizons, and underwrites locality claims. However, we show that this can be false: when a normalization layer computes statistics from the current input along the sequence at inference, those statistics open a sequence-spanning path that bypasses the convolutional receptive field to provide global context. We derive this from the layer's Jacobian (the criterion needs no experiment), and what the path carries has a closed form. On a synthetic labeling process with computable optima, the global summary that a sequence-spanning normalization encodes already supplies almost all of what a larger receptive field would buy where labels come in long runs: a network reaching 9 positions comes within 0.009 of the whole-sequence optimum, against a near-chance bound for its reach. Closing the path, by taking the same statistics per position, multiplies what enlarging the receptive field is worth by up to an order of magnitude on simulated genomes at every difficulty level tested and on real 1000 Genomes haplotypes. The same path also confounds attribution: ablating a trained network's receptive-field-enlarging blocks severs part of the path, overstating their contribution 8.3-16.1-fold relative to retraining from scratch. The substitution of normalization for receptive field fades as labels switch more often. Where labels run long, neither the receptive-field justification nor the ablation is wrong about its numbers, but both credit the wrong component.

AI 总结：本研究发现Transformer与Mamba架构虽微观机制不同，却存在相近的近边际慢模动力学，其集体红外组织具有普适性，为认知场理论提供了独立验证。

链接：https://arxiv.org/abs/2608.18592

机构：Electronics and Telecommunications Research Institute（电子通信研究院）

作者：Byung Gyu Chae

英文摘要：Whether distinct neural architectures develop common collective dynamics remains an open question. Recent analysis of Transformer language models revealed a nearly flat, weakly infrared-enhanced time-scale density of states (TDOS) associated with near-marginal long-memory dynamics. Here we test whether a closely related organization emerges in Mamba, whose selective state-space dynamics provides a fundamentally different microscopic mechanism. Mamba allows relaxation dynamics to be resolved at three levels: the intrinsic spectrum of the learned state-space generator, its input-conditioned selective rescaling, and the collective TDOS of the complete block measured from its Jacobian. These spectra are not identical: selective dynamics and the remaining block transformations substantially reorganize the microscopic relaxation hierarchy. Nevertheless, the full block develops a reproducible slow-mode continuum whose infrared sector becomes progressively better resolved with increasing sequence length. Cumulative analysis yields $\rho(\lambda)\sim\lambda^\beta$, with the long-sequence Mamba exponent stabilizing near $\beta_{\rm M}\simeq-0.17$. The corresponding memory dynamics follows $K(t)\sim t^{-(1+\beta)}$, close to the marginal $1/t$ regime. Despite fundamentally different microscopic dynamics, Transformer full-block spectra exhibit closely related infrared organization, with representative exponents of order $\beta_{\rm Tr}\sim-0.1$. These results separate explicit state-space memory from collective infrared organization and show that distinct sequence architectures can develop closely related near-marginal slow-mode dynamics. They extend infrared collective organization beyond Transformers and provide an independent test of the dynamical structure described by Cognitive Field Theory.

AI 总结：本文构建智能电表能耗预测的9种深度时间序列模型实证基准，评估历史输入长度、预测时域等因素的影响，发现深度学习模型优于经典基线，轻量级架构性价比高，架构差异仅在特定场景显著。

链接：https://arxiv.org/abs/2608.18675

机构：Linköping University（林雪平大学）

作者：Behnaz Kavoosighafi, Maria Eidenskog, Wiktoria Glad, Katerina Vrotsou

英文摘要： Accurate forecasting of energy consumption is important for the efficient operation of power systems, with direct implications for operational costs, energy management, and system maintenance. Due to the availability of extensive high-resolution consumption data from smart meters, data-driven methods have been used for short-term and long-term forecasting. However, their comparative performance on real-world smart meter data is still not well studied. In this paper, we present an empirical benchmark of nine modern deep learning models for time-series forecasting, including linear, MLP-based, convolutional, and Transformer architectures. We evaluate these models on two publicly available smart meter datasets. Our analysis focuses on three factors that strongly affect forecasting performance: the length of historical input, the prediction horizon, and the choice of model architecture. We show that extending the historical context improves accuracy, but only up to a saturation point, after which additional input provides limited benefit. In contrast, accuracy decreases as the prediction horizon increases. We also investigate the trade-off between prediction accuracy and computational complexity, and assess the statistical significance and practical magnitude of performance differences across models. Our results show that deep learning models consistently outperform classical baselines, while lightweight architectures achieve relatively similar performance at significantly lower computational cost. Additionally, architectural differences only become meaningful at longer forecasting horizons and on more heterogeneous datasets. Finally, a subgroup analysis across geodemographic and household categories shows that model choice has limited impact for most population segments.

AI 总结：FedLNS是一种服务器端联邦学习框架，通过层归一化签名筛选恶意更新，在200个客户端、40%目标操纵下，对三类模型均实现优于基线的测试困惑度。

链接：https://arxiv.org/abs/2608.18736

机构：Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg（卢森堡大学安全、可靠性与跨学科研究中心（SnT））； Carnegie Mellon University（卡内基梅隆大学）； Edith Cowan University（埃迪斯科文大学）； TU Berlin（柏林工业大学）

作者：Kai Li, Jong-Ik Park, Carlee Joe-Wong, Wei Ni, Falko Dressler

英文摘要：Federated training enables language models to learn from distributed private text, but the server cannot directly verify the local supervision or optimization process that produces each client update. A malicious client can therefore train on corrupted targets, introduce incorrect context-token associations, and degrade the global model through repeated aggregation. Such degradation can also increase the risk of unreliable or hallucinatory generation. We propose Federated Learning with Normalization Signatures (FedLNS), a server-side framework for lightweight malicious-update screening. FedLNS represents each client update through changes in trainable normalization-layer parameters and screens suspicious updates against a robust, history-aware cross-client reference. Because the signatures are extracted at the server from the returned local models, FedLNS requires no additional client-to-server parameter or metadata exchange compared to standard federated learning (FL) methods. After screening, the retained full-model updates can be aggregated using standard FL or another compatible aggregation rule. FedLNS requires no raw client data, trusted server dataset, labeled attack examples, or separately trained detector. Experiments on GPT-style, BERT-style, and LLaMA-style models trained from scratch with 200 clients show that, under 40% population-level target manipulation, FedLNS achieves lower test perplexity than the strongest of six baselines for all three architectures under both IID (independently and identically distributed) and non-IID data partitions.

AI 总结：GEAR是一种两阶段蒸馏框架，可将表格基础模型蒸馏为轻量级预测器，在TALENT和TabArena上的实验显示其能显著降低推理开销并提升AUC，性能优于多种基准模型。

链接：https://arxiv.org/abs/2608.18849

作者：Qi Qin, Jiajie Zhu, Dali Chen, Yuzhao Zhang, Jia-Xing Han, Yu Su, Peng Zhang, Ying Yan, Yifan Sun

英文摘要：Tabular foundation models (TFMs) achieve strong performance through in-context learning, but context-dependent inference imposes substantial latency and memory costs, hindering large-scale deployment. We propose GEAR (\emph{Generative Expansion and Real Anchoring}), a modular two-stage framework that distills TFMs into lightweight MLP or tree-based predictors that can be deployed on commodity CPUs. Stage 1 uses synthetic covariates solely as teacher-query locations and trains the student on soft TFM targets, expanding coverage beyond observed rows. Stage 2 re-anchors the student to the target distribution using real labels and out-of-fold teacher predictions, whitch avoids self-labeling leakage. We further derive a risk certificate characterizing the trade-off between generated-query volume and generator fidelity. Experiments on TALENT and TabArena demonstrate the broad applicability of GEAR. Two-stage MLPs outperform supervised MLPs by 1.81--2.00 AUC points on binary tasks and 1.19--1.35 points on multiclass tasks, with additional gains over real-data-only distillation of 1.76--2.19 and 2.09--2.40 points, respectively. On binary tasks, the gains also transfer to LightGBM and XGBoost, and all three student families outperform CatBoost, the strongest non-TFM baseline, in mean AUC. Ablations show gains beyond longer training or alternative warm starts, greater stability from staged than mixed optimization, and generator-dependent diminishing returns as query volume increases. Finally, GEAR reduces median inference time by 57--2866 times and peak prediction memory by 1.9--3.3 times, while retaining higher AUC than matched supervised baselines.

AI 总结：本研究针对多教师在线蒸馏（M-OPD）的能力不平衡问题，提出 Open-MOPD 框架，通过三种机制将提升空间恢复率从 35.6% 提升至 83.4%，并开源了相关方案与评估套件。

链接：https://arxiv.org/abs/2608.19098

机构：SIA-Lab of Tsinghua AIR and ByteDance Seed（清华大学AIR与字节跳动种子SIA实验室）； Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）； Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）

作者：Huan-ang Gao, Haohan Chi, Yong Yan, Shiyuan Feng, Hanlin Wu, Zheng Jiang, Bingxiang He, Wei-Ying Ma, Ya-Qin Zhang, Hao Zhou

英文摘要： Multi-teacher on-policy distillation (M-OPD) has emerged as a promising paradigm for consolidating domain-specialized reinforcement learning (RL) experts into a single generalist student via dense, token-level reward supervision. Despite its practical success, the optimization dynamics governing multi-teacher capability integration remain poorly understood, and open, rigorously reproducible recipes are conspicuously lacking. In this work, we establish a controlled M-OPD benchmark on SmolLM3-3B-Base with oracle routing, isolating capability integration from routing ambiguity. Our investigation reveals a pronounced capability integration gap: standard M-OPD captures only 35.6% of the available headroom relative to a domain-routed oracle ensemble, with concise tasks such as instruction following suffering severe degradation and premature stagnation. Crucially, we show that this failure stems not from gradient conflict, but from a severe misallocation of the token-level optimization budget. This pathology is driven by three orthogonal factors: structural sequence-length disparities across domains, dynamic convergence drift due to non-uniform learning rates, and multi-step reward staleness from asynchronous policy updates. To resolve these imbalances, we introduce Open-MOPD, a principled framework incorporating token-share balancing, gap-aware dynamic budget allocation, and student reward refresh. Together, these mechanisms systematically restore cross-domain balance, elevating headroom recovery from 35.6% to 83.4% in a single deployable student. We fully open-source our end-to-end post-training recipe, training trajectories, and evaluation suites on an academically accessible hardware budget.

AI 总结：针对城市区域表示中缺失数据的语义价值被忽略问题，提出缺失感知区域表示模型MARCUS，将缺失视为城市信号，在悉尼和纽约租金预测任务上较基线显著降低MAE，性能最优。

链接：https://arxiv.org/abs/2608.18546

机构：The Property Investors Alliance（房地产投资者联盟）

作者：Chenya Huang, Bin Liang, Zhidong Li, Yuxi Lu, Kunqi Li, Justin Wang, Fang Chen

英文摘要：Multimodal urban data has expanded the applications of urban region representation learning, such as functional zone identification and real estate appraisal, but also introduces challenges caused by data incompleteness. Existing studies usually handle missing data through imputation, treating missingness as noise while ignoring its potential semantic value. To address this issue, we propose MARCUS, a missing-aware region representation model that treats missingness as a contextual urban signal. MARCUS models missingness in three stages: Intra Learning jointly encodes observed features and missing patterns, Inter Learning estimates modality reliability to guide cross-modal interaction, and Fusion uses missing-aware and time-aware gating to generate the final region embedding. We apply MARCUS to rent prediction, a task with long-term trends and seasonal fluctuations, using real-world datasets from Sydney and New York. Experimental results show that MARCUS achieves state-of-the-art performance, reducing MAE by 51.35% on Sydney and 12.62% on New York compared with the best baselines. Additional experiments, including an imputation-based ablation study and randomized additional-missingness analysis, further demonstrate the effectiveness of the proposed method.

AI 总结：本研究提出MorphoGP框架，通过ContourCluster模型分类潮汐海滩形态，结合高斯过程专家与门控网络预测平衡海滩剖面，在中国沿海180余个海滩数据上使测试RMSE降约59.3%，为海岸管理提供数据驱动工具。

链接：https://arxiv.org/abs/2608.18558

机构：Fudan University（复旦大学）； Shanghai Academy of AI for Science (SAIS)（上海人工智能科学研究院）； East China Normal University（华东师范大学）； Third Institute of Oceanography, Ministry of Natural Resources（自然资源部第三海洋研究所）； Xiamen University（厦门大学）

作者：Xi Wu, Yanqing Wei, Hang Yin, Pengze Li, Hongshuai Qi, Xi Chen

英文摘要：The prediction of equilibrium beach profiles under tidal influence is of fundamental importance for sustainable coastal development, informing shoreline protection strategies and managing coastal ecosystems under changing environmental conditions. However, it remains challenging due to the highly nonlinear interactions among wave, tide, and sedimentary processes. Traditional empirical and numerical models often exhibit limited adaptability across diverse coastal environments, with especially pronounced limitations in beach systems where tidal processes are important. To improve data-driven prediction under these conditions, this study proposes MorphoGP, a unified category-specific Gaussian process framework for predicting equilibrium beach profiles (EBPs) under tidal influence. The framework first introduces a ContourCluster model based on contrastive learning to classify tide-influenced beach morphologies automatically. Within each morphological category, a specialized Gaussian process expert learns statistical associations between environmental descriptors including waves, tides, and sediments and the beach profile's shape. A Gating Net then integrates the outputs of all experts through a probabilistic weighting mechanism to produce the final prediction. Evaluated on data from over 180 beach profiles from tide-influenced coasts along the Chinese coast, MorphoGP achieves improved predictive performance compared with conventional and deep learning models, reducing the test RMSE by about 59.3\% compared with the best baseline and achieving a final RMSE of 0.297 m. The proposed framework provides a physically informed, data-driven tool for equilibrium beach-profile prediction under tidal influence and coastal management, while stronger process-level physical coupling remains an important direction for future development.

AI 总结：该研究针对低预算跨筒仓联邦主动学习，发现同分布数据查询选择更具挑战性，提出基于联邦表示学习的新框架，性能优于现有方法。

链接：https://arxiv.org/abs/2608.18634

机构：School of Computer Science and Engineering（计算机科学与工程学院）； The Hebrew University of Jerusalem（耶路撒冷希伯来大学）

作者：Liam Mohr, Daphna Weinshall

英文摘要：Federated Active Learning (FAL) addresses the dual challenges of data privacy and label scarcity, where the absence of a global data view introduces additional hurdles for coordinated query selection. We study cross-silo FAL in the low-budget regime, where annotation decisions are most critical. We characterize, both theoretically and empirically, a heterogeneity reversal: in low-budget settings, homogeneous (IID) data requires stronger coordination to avoid redundant queries, whereas heterogeneous data naturally promotes diversity; this trend reverses at higher budgets. Thus, in contrast to the standard federated learning (FL) narrative where heterogeneity is a primary challenge, we show that IID settings are more challenging for query selection in FAL. Motivated by these findings, we propose a new FAL framework that utilizes federated representation learning to align client data in a shared embedding space. This enables the server to perform globally coordinated active selection over optionally obfuscated client embeddings, while annotation remains local to each client. Although our framework operates in the more challenging low-budget regime, it achieves performance that surpasses existing FAL methods even when they are given substantially larger annotation budgets, demonstrating the value of centralized coordination under privacy constraints.

AI 总结：该研究提出计算框架，从协作VR游戏带时间戳对话检测团队过程阶段，经评估其可识别连贯阶段结构，为分析协作活动提供透明可迁移方法。

链接：https://arxiv.org/abs/2608.18660

机构：School of Business, Technical University of Applied Sciences Augsburg（奥格斯堡应用技术大学商学院）； Data Science und Autonome Systeme Technologietransferzentrum (TTZ)（数据科学与自主系统技术转移中心）

作者：Qing Huang, Jianing Zhang, Pooja Pol

英文摘要：Collaborative virtual reality (VR) environments make team communication observable as it unfolds, but conventional transcript analyses often summarize entire trials or divide them into fixed temporal windows. Such approaches can obscure changes in team communication and coordination over time. This article presents a computational framework for detecting and interpreting dynamic team-process phases from timestamped dialogue in a collaborative VR game. The framework uses late chunking to generate context-aware transcript representations, aggregates them into temporal chunks, and applies penalized Gaussian-kernel change-point detection to identify semantic transitions in team communication. After boundary detection, term frequency--inverse document frequency (TF-IDF), non-negative matrix factorization (NMF), and representative transcript segments provide structured evidence for phase interpretation. A locally deployed large language model (LLM) uses in-context learning to generate initial interpretations that are subsequently reviewed by humans. Independently recorded interaction logs are then aligned with the detected phases to examine corresponding task-action patterns. The evaluation compares representations, pooling strategies, segmentation methods, parameter settings, reviewed phase interpretations, and phase-aligned interaction profiles. The results show that the framework identifies coherent and interpretable phase structures while preserving traceability to the underlying transcript evidence. The correspondence between transcript-derived phases and interaction behavior further supports their relevance for analyzing collaborative activity. The framework therefore offers a transparent and transferable approach for studying temporal changes in teamwork from timestamped transcripts across collaborative task settings.

AI 总结：本文提出SIGMA框架，结合LLM实现自适应交通信号多目标控制，在SUMO仿真中较基准控制器降低等待与排队时长、提升通行量，且具备鲁棒性与统计可靠性。

链接：https://arxiv.org/abs/2608.18263

机构：Indian Statistical Institute（印度统计研究所）； Sorbonne University Abu Dhabi（阿布扎比索邦大学）； Sorbonne Center for Artificial Intelligence（索邦人工智能中心）； SQC & OR（统计质量控制与运筹学研究室）

作者：Pratham Payra, Jagadish B, Tanmay Sen, Tanujit Chakraborty

英文摘要：Traffic signal control is a complex sequential decision-making problem requiring real-time adaptation and trade-offs among throughput, delay fairness, signal stability, and emergency vehicle priority. Existing RL methods often fix objectives, ignore dynamic priority changes, and fail to generalize across geometrically similar this http URL propose SIGMA (Symmetry-aware, Intelligent, Geometric, Multi-objective Adaptive traffic control), an RL framework enhanced with a large language model (LLM) for adaptive objective tuning and orientation-invariant learning. SIGMA converts natural-language emergency commands into priority vectors for a multi-objective actor-critic controller, avoiding manual reward engineering. Rotational augmentation improves transferability across four-way intersections, while offline-to-online learning ensures stable initialization and gradual adaptation to changing this http URL define reliability properties covering emergency service levels, graceful degradation under LLM failures, and demand sensitivity, validated via bootstrap statistics. Evaluated in SUMO on four Kolkata-based urban intersections against fixed-time, actuated, and DQN controllers, SIGMA reduces average/emergency waiting times and queue lengths, and boosts throughput. Ablation studies confirm robustness to component failures and geometric rotations. Overall, SIGMA offers a reliable, language-guided, multi-objective traffic control system with statistical reliability assurance.

AI 总结：SingularClip是一种定期裁剪权重矩阵奇异值的方法，可缓解训练中因奇异值各向异性增长导致的神经网络可塑性丧失问题，在两类学习任务上性能优于基线。

链接：https://arxiv.org/abs/2608.18319

机构：University of Toronto（多伦多大学）； Vector Institute（向量研究所）； Mila（米拉研究所）； Polytechnique Montréal（蒙特利尔理工学院）

作者：Tyler Kastner, Nimrod De La Vega, Amir-massoud Farahmand

英文摘要：Neural networks trained on nonstationary tasks frequently lose the ability to fit new targets, a phenomenon referred to as loss of plasticity. We identify a novel source of plasticity loss due to the growing anisotropy of weight matrices' singular values during training, and analyze this phenomenon both empirically and theoretically. To mitigate this issue, we introduce SingularClip, a procedure that periodically clips the singular values of all weight matrices. We show that SingularClip performs strongly against baselines across a range of tasks in both continual supervised learning and deep reinforcement learning.

AI 总结：该研究提出VSPG算法，以单位范数超向量表示离散动作，通过优势加权超向量捆绑更新动作，可实现样本高效学习且推理内存不增加，还证明其动作选择在随机比特翻转下稳定，连接了三类方法并提供鲁棒性保证。

链接：https://arxiv.org/abs/2608.18404

机构：University of California, Irvine（加州大学欧文分校）； Intel Corporation（英特尔公司）； Johns Hopkins University（约翰斯·霍普金斯大学）； Northeastern University（东北大学）

作者： Ryozo Masukawa, Sanggeon Yun, SungHeon Jeong, Hyunwoo Oh, Raheeb Hassan, Pietro Mercati, Nathaniel D. Bastian, Mahdi Imani, Mohsen Imani

英文摘要：We answer this question with Vector-Symbolic Policy Gradient (VSPG), a discrete-action actor that represents each action by a unit-norm hypervector and scores it by similarity to the encoded state. Under the standard softmax policy-gradient surrogate, we prove that its update is exactly advantage-weighted hypervector bundling followed by normalization, and therefore supports standard advantage estimators. We further show that each trained action hypervector is a fixed-size compressed kernel memory, storing an advantage-weighted kernel expansion over visited states and transferring evidence according to the encoder-induced similarity. This provides a concrete mechanism that can support sample-efficient learning without increasing inference-time memory. Finally, for bipolar action memories, we prove that greedy action selection is stable under random bit flips, with failure probability decaying exponentially in the hypervector dimension. VSPG thus connects VSA action memories, log-linear policy gradients, and kernel policy search while providing a quantitative robustness guarantee.

AI 总结：本研究提出持续推理环境，针对持续RLVR中顺序训练性能低于MTRL的问题，提出CPR方法利用共享推理，使模型平均达到MTRL级性能。

链接：https://arxiv.org/abs/2608.18574

机构：State Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室（BIGAI））； Beijing Institute of Technology（北京理工大学）； Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）； State Key Lab of General AI, School of Intelligence Science and Technology, Peking University（通用人工智能国家重点实验室、北京大学智能科学与技术学院）

作者：Lirui Luo, Guoxi Zhang, Hongming Xu, Rongqing Li, Cong Fang, Lifeng Fan

英文摘要：Reinforcement learning with verifiable rewards (RLVR) commonly post-trains reasoning models on multiple tasks, while rerunning multitask RLVR (MTRL) as new tasks are added makes capability expansion costly. We therefore study continual RLVR, which updates the existing model as each task arrives. The central question is whether a model updated this way can perform as well as a jointly trained model. To answer this question, we introduce Continual Reasoning Gym, a continual-RLVR environment that organizes text and visual reasoning tasks into five task sequences. In this setting, we identify two key observations: Sequential RLVR exhibits modest forgetting, yet its final performance remains below that of MTRL. To understand the latter, we decompose final performance and show that forgetting accounts for only part of the gap. To explain the former, we identify shared reasoning: transferable reasoning structure allows training on one task to support others on average. We therefore introduce Continual Prompt Replay (CPR), which harnesses shared reasoning to improve learning on the arriving and future tasks by replaying previous-task prompts and regenerating their responses with the current policy. On average, only CPR reaches MTRL-level performance.

AI 总结：该研究针对强化学习奖励设计瓶颈，提出MLREF框架，通过模块池复用奖励组件，结合三种优化机制，在17个任务上实现比强基线更优且更稳定的性能。

链接：https://arxiv.org/abs/2608.18827

机构：Institute for Interdisciplinary Information Sciences Tsinghua University（清华大学交叉信息研究院）

作者：Chenglin Liu, Xun Wang, Ruishuo Chen, Zhuoran Li, Longbo Huang

英文摘要：Reward function design remains a bottleneck in reinforcement learning. While large language models (LLMs) have enabled automated reward generation, existing methods generate and revise reward functions as monolithic programs, making it difficult to reliably preserve and reuse effective components discovered in earlier iterations, leading to unstable performance across iterations. To address this, we propose Module Level Reward Evolution Framework (MLREF). At the core of MLREF is a module pool, a persistent repository of reusable reward components. MLREF treats the module pool as the primary optimization object: the pool evolves across iterations by accumulating successful modules, refining underperforming ones, and reusing proven components; while reward functions are constructed as linear combinations of modules drawn from this pool. To drive this evolution, MLREF integrates three mechanisms: reflection-based refinement, hybrid credit assignment, and a merge strategy with rollback, which together improve the effectiveness and robustness of reward optimization. Experiments on 17 tasks show that MLREF outperforms strong baselines by 25.2% in locomotion and 6.6% in manipulation, with more stable optimization dynamics.

AI 总结：本文针对现实非凸校园拓扑下的毫米波基站最优部署问题，将其建模为马尔可夫决策过程，通过对比四种深度强化学习方案，发现地理划分多智能体DDPG在密集场景中性能更优、可实现全覆盖且收敛高效。

链接：https://arxiv.org/abs/2608.19049

作者：Omar Rady, Mohamed Ayman, Ali Arafa, Mohamed Shalma

英文摘要：Deep reinforcement learning (DRL) has recently gained a great attention due to its real-time adaptation and effectiveness in complex optimization problems. This paper investigates the optimal deployment of millimeter-wave (mmWave) base stations (BSs) in a realistic, non-convex campus topology. The optimization problem is NP-hard, due to the non-convex, non-smooth nature of the max-min fairness objective. To overcome these constraints, we formulate the BS placement as a Markov Decision Process (MDP) and systematically benchmark four DRL schemes: a discrete single-agent Deep Q-Network (DQN), a spatially partitioned Multi-Agent DQN, a continuous single-agent Deep Deterministic Policy Gradient (DDPG), and a geographically partitioned multi-agent DDPG framework. Numerical evaluations reveal that the multi-agent DDPG approach substantially outperforms single-agent in dense scenarios. Additionally full coverage is achieved, and a fairness Jain's index of 0.94 is obtained. Finally, the multi-agent demonstrates highly efficient computational convergence of dense scenarios with $400$ users.

AI 总结：PGFS++是一种感知合成的强化学习框架，通过优化反应模板与库存构建模块的应用，在改进分子目标性质的同时保留输出多样性，解决了PGFS+的奖励作弊问题。

链接：https://arxiv.org/abs/2608.19121

机构：Graphcore（格洛科普（Graphcore））； University of Cambridge（剑桥大学）

作者：Boqiao Zhang, Godbless James, Sai Krishna Gottipati, Andrew Fitzgibbon

英文摘要：Improving molecular properties, such as drug-likeness or binding affinity, is a recurring task in early-stage drug discovery. However, molecules optimized in an unconstrained chemical space have limited practical value if they cannot be synthesized. Policy Gradient for Forward Synthesis (PGFS) is a synthesis-aware reinforcement learning method for molecular improvement, but its use of reactant embedding prediction makes reactant selection indirect, which, as we show, limits learning effectiveness. We first develop PGFS+, in which reaction templates and second reactants are represented by trainable embedding lookup tables. Combined with a more effective scoring function and RL algorithm, PGFS+ significantly improves the desired property. However, it exposes a reward-hacking failure mode: a powerful reactant search can map diverse input molecules to the same high-reward magnet molecule, improving the reward while collapsing the output diversity. We therefore introduce PGFS++, a synthesis-aware reinforcement learning framework for input-specific molecular improvement. Given an input molecule, PGFS++ treats it as the start of a forward-synthesis trajectory, applies learned reaction templates with compatible in-stock building blocks, and produces a molecule with improved target properties, an explicit synthesis route, and structural similarity to the input. Experiments on molecular improvement tasks show that PGFS++ improves target properties while preserving high output diversity.

AI 总结：针对非马尔可夫环境下霍克斯驱动随机微分方程的随机控制问题，提出Hawkes-CT DDPG算法，通过马尔可夫化近似实现无模型学习，并在三类核上与离散时间强化学习方法对比。

链接：https://arxiv.org/abs/2608.19151

机构：UC Berkeley（加州大学伯克利分校）

作者：Tomasz R. Bielecki, Thibaut Mastrolia, Haoze Yan

英文摘要：We study stochastic control of multivariate Hawkes-driven stochastic differential equations with machine learning algorithms in a non-Markovian setting. Due to the path dependence of the memory of the Hawkes intensity, this problem does not fall within classical stochastic control theory outside particular Markovian kernels. We first develop a finite-dimensional Markovianization procedure and algorithm to approximate multivariate Hawkes processes with mixtures of exponential kernels. We prove the convergence of the Markovianized approximation of the Hawkes process, its intensity, and the value of the problem to the original non-Markovian processes and the value of the primal problem. We then formulate continuous-time deterministic policy gradient learning on the Markovianized approximation of the problem, called Hawkes-CT DDPG. We propose a model-free algorithm to solve the non-Markovian Hawkes-driven optimization by observing only the event times of the process, the realization of the solution to the SDE, and a chosen set of decay filters, while the Hawkes kernel coefficients remain unknown. We compare our continuous time reinforcement learning Hawkes-CT DDPG method with discrete time reinforcement learning techniques under three different types of kernels: simple exponential, Erlang, and power-law kernels.

AI 总结：该研究提出DCGCNet模型，可实现任意导联的鲁棒心房颤动检测，在跨数据集评估中AUC均超0.98，性能达到新基准。

链接：https://arxiv.org/abs/2608.18451

机构：Information Center, The People’s Hospital of Baoan Shenzhen（深圳市宝安区人民医院信息中心）； School of Computer Science and Engineering, South China University of Technology（华南理工大学计算机科学与工程学院）； Department of Cardiology, The People’s Hospital of Baoan Shenzhen（深圳市宝安区人民医院心内科）； Institute for Advanced Study, Shenzhen University（深圳大学高等研究院）

作者：Hongtao Li, Jia Wei, Guoyao Li, Yuchen Lei, Guangnian Ma, Jia Xiao, Yuanjun Lai, Shuzhen Lv, Xueqiang Ouyang

英文摘要：\textbf{Background and Objective}: Reliable atrial fibrillation (AF) detection from electrocardiogram (ECG) signals remains challenging in real-world clinical settings due to variable lead configurations, cross-dataset domain shifts, and pervasive physiological and technical artifacts. So we develop a robust and generalizable deep learning model for accurate AF detection.\\ \textbf{Methods}: We propose the Dual-Codebook Graph Collaborative Network (DCGCNet), a novel end-to-end vector-quantized variational autoencoder that jointly performs AF classification and ECG reconstruction. DCGCNet introduces two key components: (1) a Local-Global Contrastive Module for learning noise-invariant representations, and (2) an Adaptive Codebook Vector Quantizer that dynamically refines codebook prototypes to better align with input data distributions, thereby preventing codebook collapse and enhancing generalization.\\ \textbf{Results}: DCGCNet achieves state-of-the-art performance in standard intra-dataset 12-lead evaluation and demonstrates exceptional cross-dataset generalization across seven diverse settings, consistently attaining AUC > 0.98 in all cases. Furthermore, it maintains high diagnostic accuracy under realistic noisy conditions, including baseline wander, powerline interference, and EMG artifacts.\\ \textbf{Conclusions}: DCGCNet establishes a new benchmark for robust, generalizable, and noise-resilient AF detection, showing strong potential for deployment in real-world clinical environments.

AI 总结：本文提出张量场模型（TFMs），将其应用于生成状态流形，采用流匹配训练，可提升性能并通过可重用条件表示实现的分摊采样加速生成。

链接：https://arxiv.org/abs/2608.18808

机构：Evercot AI

作者：Alexander Strunk, Roland Assam

英文摘要： This paper introduces Tensor Field Models (TFMs), realization-level Mathematical Structures in which a learned Operator maps a product of admissible component-section families to a prescribed family of time-dependent tangent sections on a Generative State Manifold. Analytic and dynamical restrictions are encoded through the choice of admissible families rather than imposed by the root definition. Constructed, component-separable, and Tensor Bundle TFMs provide structured refinements of this common object. In the conditional realizations considered here, a structured condition $c=(c_1,\ldots,c_n)$ is mapped componentwise to a reusable collection $\mathbf H_c=(H_{c_1}^{(1)},\ldots,H_{c_n}^{(n)})$. In the architectures evaluated here, the component representations remain distinct and are combined only by the Field Operator to produce the generated Vector Field. All learned models are trained using Flow Matching. Experiments show that TFMs can improve performance and that amortized sampling enabled by reusable condition representations can accelerate generation.

AI 总结：本研究构建基于FEM的电磁线圈设计代理建模与优化框架，对比EI-BO、COBYLA、BOBYQA等算法，发现优化器表现与FEM评估预算相关，不同方法在仿真驱动设计中各有优势。

链接：https://arxiv.org/abs/2608.18903

机构：University of Oxford（牛津大学）

作者：Yucheng Liu

英文摘要：This work evaluates surrogate-assisted optimization of a seven-parameter current-excited coil--core benchmark subject to geometric, manufacturing, and separate core and copper mass constraints. A Python--MPh--COMSOL workflow couples a two-dimensional axisymmetric finite-element method (FEM) model to a Matern 5/2 Gaussian-process (GP) probabilistic surrogate. Here, physics-constrained denotes a design problem evaluated by a governing-equation FEM model and restricted by explicit physical, geometric, manufacturing, and material-allocation constraints; it does not denote a physics-informed GP architecture. Sequential Bayesian optimization (BO) ranks candidates using expected improvement (EI), and every reported incumbent is verified by FEM. Five paired runs show that optimizer ranking depends on the available FEM-evaluation budget: EI--BO improves rapidly at small continuation budgets, COBYLA is stronger at the earliest checkpoint, and BOBYQA attains the highest mean terminal response. A retrospective finite-pool study further finds no robust endpoint advantage of EI over posterior-mean ranking on this smooth response surface. The broader result is that early progress, terminal response, information use, and wall-clock cost can favor different methods in simulation-driven design. A selected-design check at a common total current preserves the observed BOBYQA--COBYLA--EI-BO ordering. The conclusions nevertheless remain conditional on this axisymmetric benchmark and do not establish a fixed-current optimum, fixed-power performance, or electrical-efficiency superiority.

AI 总结：本研究提出SRGAN超分辨率框架，将EBSD分析通量提升25倍，优于经典插值方法，可高效获取高精度电池电极微观结构数据，助力材料研发与工业应用。

链接：https://arxiv.org/abs/2608.19117

作者：John Mangum, Andrew Glaws, Francois Usseglio-Viretta, Steven Spurgeon, Donal Finegan

英文摘要：Quantitative microstructural characterization of Li-ion battery electrode materials using electron backscatter diffraction (EBSD) has been proven as a critical method for optimizing cell performance. However, the inherently slow nature of EBSD can hinder the throughput of analyses needed for statistical representation of a material microstructure being developed. This work demonstrates a machine learning super-resolution framework using a generative adversarial network (SRGAN) to significantly increase EBSD throughput. The SRGAN model was trained on EBSD data of LiNixMnyCozO2 (NMC) cathode particles to computationally enhance low-resolution datasets and its performance is compared against classical interpolation methods across various upscaling factors (2x to 12x). Both qualitative image metrics and quantitative microstructural analysis verified that the SRGAN systematically outperformed classical methods, particularly in preserving small grains and maintaining realistic grain boundaries. We demonstrate that a 5x upscaling factor, corresponding to a 25x speed-up in acquisition time or a 25x larger field of view, is practical while maintaining acceptable accuracy in key metrics like grain size and shape. For instance, at 5x upscaling, relative errors were +5.7%, +8.2%, and -14.6% on grain area-equivalent diameter, grain maximum sphere-inscribed diameter, and grain boundary length, respectively. The SRGAN methodology developed in this work significantly enhances the efficiency of EBSD acquisition for more statistically robust microstructural dataset, enabling EBSD as a high-throughput characterization tool for materials research and industrial process development.

AI 总结：针对时间序列插补的现有方法存在的局限性，提出MDTIM模型，引入随机离散化技术，在多种基准上的实验显示其鲁棒性和可扩展性优于现有基线方法。

链接：https://arxiv.org/abs/2608.19119

机构：Seoul National University（首尔大学）

作者：Dongbin Kim, Seungyun Lee, Geonwoo Shin, Jaewook Lee

英文摘要：Time series imputation is a crucial area for reliable time series analysis, yet it remains challenging due to the complex temporal dynamics and noise of real-world data. Existing approaches, however, exhibit two limitations: missing and observed values are embedded within the same representation space without explicit structural separation, and continuous diffusion-based methods are trained to predict added noise rather than the original signal. To address these, we propose the Masked Diffusion Time-series Imputation Model (MDTIM), which leverages the training paradigm of masked diffusion model for imputation tasks. The MASK token is structurally orthogonal to valid observations, and the model directly predicts the original values, naturally aligning both the representation and the learning objective with the imputation task. To bridge the gap between discrete masked diffusion and the continuous, ordinal nature of time series, we further introduce Stochastic Discretization, which maps continuous values to ordinal-aware tokens while preserving continuous dynamics. Our experiments on diverse benchmarks confirm that MDTIM achieves superior robustness and scalability, consistently outperforming state-of-the-art deterministic and generative baselines across various missing scenarios.

AI 总结：该研究提出桥接图模型（BGMs），定义马尔可化间隙作为生成模型桥到解码器压缩的不可约损失，通过实验验证其可作为桥和耦合设计的训练前诊断工具。

链接：https://arxiv.org/abs/2608.19144

机构：Columbia University（哥伦比亚大学）

作者：Tiantian Zhang

英文摘要：Continuous-time generative models are often built from endpoint-conditioned bridges, but generation requires a different object: a non-anticipative Markov decoder that only observes the current state and time. We identify this bridge-to-decoder compression as a structural bottleneck shared by diffusion models, flow matching, rectified flow, Schrödinger bridges, and field-based generative models. We introduce the \emph{Markovization gap}, the time-integrated conditional variance of the bridge velocity given the Markov state. It is the MMSE of predicting endpoint-conditioned motion from the information available to a sampler, and it measures an irreducible loss incurred before any neural network is trained. To make this bottleneck comparable across model families, we define \emph{Bridge Graphical Models} (BGMs), which separate endpoint coupling, bridge law, Markovian projection, and current-preserving dynamics representation as independent design choices. The same formalism also represents Poisson and electrostatic models as field-line bridge kernels with a corresponding field-line Markovization gap. Across synthetic, latent, and pixel-space pilots on CIFAR-10 and Fashion-MNIST, a feature-space proxy gap estimated in minutes before training ranks design choices in the same direction as downstream training loss and FID under fixed architecture, bridge, sampler, and compute. These results support the Markovization gap as a pre-training diagnostic for bridge and coupling design.

AI 总结：该研究针对深度学习中稳定性边界的过往公式未捕捉优化器依赖性的问题，推导了基于定向海森矩阵与梯度对齐得分的新稳定性边界公式，揭示了优化器平衡时间与空间预算的独特作用。

链接：https://arxiv.org/abs/2608.18415

机构：Seoul National University（首尔大学）； Computer Vision Lab, ASRI（ASRI计算机视觉实验室）

作者：Jaerin Lee, Kyoung Mu Lee

英文摘要：The edge of stability refers to a phenomenon in deep learning with gradient-based optimizers where the Hessian eigenvalues of the loss remain stable above a threshold that the classical descent lemma predicts to be unstable. Previous works formulate the edge of stability with respect to the maximum Hessian eigenvalue and the learning rate. However, we observe that many first-order methods, including gradient descent, significantly violate the stability bound predicted by these theories by a factor as large as $\times 21.1$. Moreover, this deviation turns out to be systematic and highly dependent on the underlying optimizer, which is not captured by previous formulations. This calls for a new formulation of the stability threshold, which we derive from the directional Hessian and the gradient-alignment score with respect to the actual update taken by the optimizer, rather than the maximum curvature mode. Our new formulation of the realized edge of stability not only removes optimizer-dependent offsets and provides more consistent predictions of the stability threshold, but also introduces new diagnostic tools that reveal the unique role of the optimizer in actively balancing between the temporal and spatial budgets in first-order optimization.

AI 总结：针对老年人跌倒风险识别的静态方法无法适配动态个性化风险因素，本文提出PAFIR框架，将自适应特征选择建模为强化学习问题，在PEER试验数据上验证其能更有效捕捉特征模式，实现动态个性化跌倒风险预防。

链接：https://arxiv.org/abs/2608.18450

机构：University of Central Florida（中佛罗里达大学）； Arizona State University（亚利桑那州立大学）

作者：Chang Liu, Ladda Thiamwong, Yanjie Fu, Rui Xie

英文摘要：Falls among older adults represent a major public health challenge driven by complex, time-varying interactions across multiple risk domains. Effective fall risk factor identification requires learning from heterogeneous longitudinal data while accounting for sparse and delayed fall-related outcome events. However, existing approaches are largely static and fail to adaptively model evolving, individualized risk factors across modalities and time. We propose PAFIR, a Personalized and Adaptive Feature selection framework for fall risk Identification and pRevention, which formulates adaptive feature selection as a reinforcement learning problem over longitudinal multimodal health data. PAFIR jointly models structural dependencies among correlated assessment variables and temporal dynamics in wearable-derived physical activity data, and learns adaptive selection policies across repeated study visits using reward signals derived from sparse fall incidence outcomes. We apply PAFIR to data from the Physio fEedback Exercise pRogram (PEER) cluster-randomized trial. Experimental results demonstrate that PAFIR more effectively captures longitudinal and structural patterns of feature relevance than state-of-the-art baselines, and enables dynamic, subject-specific feature selection. By adapting selected features over time, PAFIR supports more timely and personalized fall prevention strategies.

AI 总结：本文针对自适应随机量化未考虑后续熵编码的精度损失问题，提出ECASQ方法，给出最优与GPU友好近似动态规划方案，实验表明其精度接近最优且速度优势显著。

链接：https://arxiv.org/abs/2608.18147

机构：University College London（伦敦大学学院）； VMware Research by Broadcom（博通旗下VMware研究院）； Harvard University（哈佛大学）

作者：Ran Ben Basat, Yaniv Ben-Itzhak, Michael Mitzenmacher, Shay Vargaftik

英文摘要： Adaptive stochastic quantization (ASQ) is a recently introduced quantization approach that optimizes the Mean Squared Error (MSE) for a given input while preserving unbiasedness. It is designed to alleviate the communication and memory bottlenecks of modern data and machine learning workloads, including model, gradient, and KV-cache compression and nearest-neighbor search. Further, practical systems can then compress quantized data with a lossless entropy encoder. However, existing unbiased methods, including ASQ, choose their quantization values without considering this later encoding stage, leaving accuracy on the table. We formulate the Entropy Constrained Adaptive Stochastic Quantization (ECASQ) problem, which jointly selects adaptive quantization values to minimize MSE under an entropy budget and an unbiasedness constraint. We give an optimal dynamic program with $O(sd^2)$ time and $O(d^2)$ space for a length-d vector and at most s quantization values, and a GPU-friendly approximate dynamic program with $O(sd^2)$ time and $O(d)$ space. The approximation guarantees that the solution has an MSE no larger than the optimal solution that uses one fewer bit of entropy per entry. We also provide an iterative refinement procedure for the approximation solution that, in our experiments, yields near-optimal results while retaining a substantial speed advantage over our solver for the optimal solution.

AI 总结：本文提出基于Tsetlin机的NILM框架，解决传统NILM难在MCU部署的问题，在REDD数据集上实现高分类精度，模型体积小、推理延迟低，适配MCU嵌入式应用。

链接：https://arxiv.org/abs/2608.18780

作者：Tianhang Tan, Han Wu, Tousif Rahman, Shengyu Duan, Alex Yakovlev, Rishad Shafik

英文摘要：Non-Intrusive Load Monitoring (NILM) systems estimate individual appliance energy consumption from a single aggregate meter, without requiring separate sensors for each device. By installing a single meter that measures a building's total electricity consumption, NILM algorithms can determine the active status of each appliance. However, traditional NILM systems use computationally intensive optimization algorithms to process offline data, limiting their capability for on-device deployment, where sensitive household data must be processed locally. This paper proposes a Tsetlin Machine (TM)-based NILM framework, targeting real-time applications on resource-constrained microcontrollers (MCUs), enabling privacy-preserving edge deployment. The problem is reformulated as a classification task, and the proposed approach achieves an average precision of 90% and recall of 96% for two-appliance classification, and 77% precision and 80% recall for four appliances on the REDD dataset. The trained model occupies only 18 KB of flash memory and achieves an inference latency of 0.43 ms on an ESP32, demonstrating its suitability for embedded NILM applications on MCUs.

AI 总结：该研究针对细粒度分层分类的结构化歧义问题，提出H$^2$EDL模型，其在FGVC-Aircraft等数据集上使校准误差较交叉熵基线降低约一半，改进在深层级和大训练预算下更显著。

链接：https://arxiv.org/abs/2608.18185

作者：Yuanye Liu, Xiahai Zhuang

英文摘要：Fine-grained recognition often involves hierarchical label spaces, where a model may be confident about a coarse semantic concept while remaining uncertain among its descendant classes. Such structured ambiguity requires uncertainty representations that capture both fine-grained classes and intermediate concepts. However, existing tools each capture only half of it: flat evidential classifiers quantify total ignorance with a single vacuity on the leaf frame, and hierarchical classifiers propagate point probabilities with no notion of evidence. Hyper-opinions would unify the two, but their general form is exponential in the label count, and existing hyper-evidential networks either require composite labels to be supplied in the training data or read them off an unstructured weight pattern, with no principled notion of which composites deserve mass. We observe that the taxonomy itself is the missing hyperdomain. Its subtrees and leaf singletons form a linear-size focal family, and one local Dirichlet opinion per branching node induces every composite mass in closed form. The resulting model, H$^2$EDL, can be interpreted in two complementary ways using the same set of parameters. From a prediction perspective, it functions as a hierarchical classifier that preserves consistency across different levels of the label tree. From a probabilistic perspective, it defines a valid tree-structured hyper-opinion, where the mass assigned to each node represents the belief that reaches that node but does not provide sufficient confidence to further specialize into its descendants. On FGVC-Aircraft and DERM12345, H$^2$EDL reduces calibration error by approximately half compared with cross-entropy baselines, with the improvement becoming more pronounced at deeper hierarchy levels and under larger training budgets.

AI 总结：

链接：https://arxiv.org/abs/2608.18330

作者：Tianxin Zhou, Ruixi Lin

英文摘要：Whether input-dependent ("dynamic") combination of a regression model pool beats the best static blend depends on the shift and is rarely known before deployment. Can a small labeled target-domain probe tell us when reallocating trust across regions of the input space will pay off? We answer this with $\widehat{D}_{\mathrm{CF5}}$, which estimates from the probe the cross-fitted gain of the regionwise convex combination over the best static convex blend: the realizable value of deciding, region by region, whom to trust. Across a frozen suite of 12 dataset-shift pairs (spatial, temporal, domain, feature-cluster), $\widehat{D}_{\mathrm{CF5}}$ predicts realized regionwise test gains with dataset-level Spearman $+0.98$ (95% CI $[+0.83, +1.00]$; $p=5\times10^{-5}$), including two cases overturning preregistered expectations. The relationship holds in a 16-pair sensitivity analysis (Spearman $+0.83$), whereas alternative probe diagnostics reach at most $+0.66$. This contrast isolates regional trust reallocation: correlation is $+0.98$ for regionwise-convex gain, but $+0.01$ for smooth covariate-dependent stacking after affine correction. A controlled generator shows dynamic gains arise from the interaction of shift heterogeneity and local competence, increase with shift severity, and become realizable between 128 and 256 probe labels in the tested grid. The Probe-Validated Ensemble Selector chooses among a static affine stacker and dynamic realizers, deploying a candidate only when a held-out lower confidence bound clears the static-convex floor. In a preregistered prospective batch, it matched or improved the floor in all 12 runs; two deployments reduced test risk by 11% and 16%, while the gate rejected a candidate whose un-gated deployment incurred $>30\times$ the static loss. We release OpenRegShift, a reproducible evaluation harness for regression ensembles under distribution shift.

AI 总结：本文提出SIMPLE模型，将多视图推理预训练为可复用过程，在多视图与多组学基准上，其冻结变体具竞争力，轻量级适配器校准性能领先。

链接：https://arxiv.org/abs/2608.19115

机构：Hong Kong Baptist University（香港浸会大学）； Zhejiang University（浙江大学）

作者：Jielong Lu, Zhihao Wu, Jiajun Yu, Zhaoliang Chen, Haishuai Wang

英文摘要：Modern pretrained encoders make representations from heterogeneous views increasingly reusable, but the procedure that determines view utility and combines evidence is still relearned for each downstream task. Consequently, knowledge about view relevance, complementarity, reliability, and missingness is repeatedly discarded rather than transferred across tasks. We therefore reformulate multi-view learning as learning a reusable, task-conditioned inference procedure rather than a fixed fusion function. Based on this perspective, we propose SIMPLE, a prior-fitted multi-view in-context learner that predicts query labels by conditioning on a small labeled support set. Since existing real-world datasets cover only a limited range of view configurations and task structures, we construct a controllable synthetic task prior in embedding space. It generates diverse support-query episodes with varying class structures, shared and view-specific factors, representation geometries, cross-view dependencies, reliability levels, missingness patterns, and distribution shifts. A hierarchical inference architecture then performs reasoning within views, across views, and across support and query samples. Experiments on multi-view and multi-omics benchmarks demonstrate that the frozen variant of SIMPLE achieves competitive performance without updating the inference backbone, while lightweight adapter calibration attains leading performance on most evaluated datasets. Together, the results under frozen, one-shot, and missing-view settings support the central hypothesis that multi-view reasoning itself can be pretrained and reused, while lightweight adapter calibration provides task-specific alignment when needed.

AI 总结：本文提出Lévy注意力算子，可在单次前向传播中以闭式形式输出连续时间序列预测的不确定性，在t-PatchGNN等任务上表现优于蒙特卡洛dropout，且计算高效。

链接：https://arxiv.org/abs/2608.19171

机构：Cyprus University of Technology（塞浦路斯理工大学）； Ethical AI Novelties

作者：Sotirios P. Chatzis, Loukas Papadoulas

英文摘要：Deep models for irregularly-sampled time series answer queries at arbitrary continuous timestamps, yet report nothing about how far each answer should be trusted. We show the attention layer itself can close that gap: with the right stochastic formulation, the pass that makes each prediction also reports, in closed form and at no extra cost, how far it should be trusted. We introduce Lévy Attention, a cross-attention operator whose output is a stochastic integral against an inhomogeneous Poisson random measure: query-key compatibilities assemble an intensity over a continuous (time x channel) index space, the measure scatters atoms under it, and the output averages an interpolated value field at those atoms. In expectation it reduces to a mollified cosine-kernel attention, so it replaces a softmax layer and trains with exact gradients. What softmax discards, the Poisson construction preserves in closed form: the evidence $\Lambda_q$ (total compatibility mass) and the disagreement $\mathrm{tr}\,\Sigma_V(q)$ (value spread). An exact variance identity makes their combination $\hat\sigma(q)=\sqrt{\mathrm{tr}\,\Sigma_V(q)\,\varphi(\Lambda_q)}$ the root-mean-square deviation of the sampled operator, emitted by the deterministic pass with no trained head. Empirically, disagreement carries the signal, while the evidence factor swings from uninformative on dense data to strongly informative on sparse. On t-PatchGNN the operator swap costs at most 5.6% accuracy against a matched control and nothing on the sparsest dataset. The free disagreement signal improves on 20-pass MC dropout across matched five-seed suites, and $\hat\sigma$ scales a calibrated Gaussian whose zero-sample CRPS beats a fifty-draw sampler; a split-conformal wrapper reaches nominal coverage at every level, and one pass ranks 3,383 unseen patients by trust in 1.4 seconds.

AI 总结：本文提出基于FitLayout的网页视觉感知表示与机器学习平台，支持数据集准备、机器学习输入获取，可用于训练图神经网络识别网页关键内容元素，保障结果可复现。

链接：https://arxiv.org/abs/2608.18727

机构：Brno University of Technology（布尔诺理工大学）； Faculty of Information Technology（信息技术学院）

作者：Radek Burget, Radek Hranický

英文摘要：Applying machine learning to web pages is challenging due to the need to interpret HTML together with associated resources and perform rendering to obtain a meaningful visual and layout-aware representation. As a result, machine learning over web content remains comparatively underexplored. In this paper, we present a platform for visual-aware representation and machine learning over web pages based on the open-source rendering tool FitLayout. The platform provides a server capable of rendering web pages, explicitly capturing their visual and structural properties in an RDF-based representation, and persisting the rendered documents in an integrated storage. The processing pipeline is controlled via a REST API, while SPARQL queries are used to retrieve structured data suitable as input for machine learning algorithms. By explicitly modeling rendered web pages, including fine-grained layout details, the platform enables dataset sharing and supports the reproducibility of experimental results. The architecture supports the complete dataset preparation workflow, from web page collection and rendering through preprocessing and annotation of content elements to downstream learning tasks. We further provide a Python client library that integrates the platform with standard machine learning workflows. As a demonstration, we show how rendered web pages can be transformed into graph-based representations and used to train graph neural networks for recognizing key content elements, illustrating both the applicability of the approach and the reproducibility of the results.

AI 总结：该研究针对动态图嵌入中图自编码器未考虑节点结构异质性的问题，提出含NC-LID正则化等的三种基于距离的GAE变体，经多数据集实验证实其可提升重构性能。

链接：https://arxiv.org/abs/2608.18762

机构：University of Novi Sad（诺威萨大学）

作者：Aleksandar Tomčić, Miloš Savić, Miloš Radovanović

英文摘要：Graph autoencoders (GAEs) are widely used for learning representations of dynamic graphs. However, their optimisation objectives typically do not take structural heterogeneity across nodes into account. We propose three distance-based GAE variants that incorporate structural penalties into the reconstruction loss. All variants share a two-layer Graph Convolutional Network encoder and a Euclidean-distance decoder trained with distance-based reconstruction objectives. We extend sparsity-corrected loss with two node-level regularization terms: (i) a hub penalty based on degree centrality, and (ii) a penalty based on Natural Community Local Intrinsic Dimensionality (NC-LID). The paper is motivated by prior evidence linking high NC-LID to reduced embedding quality. The proposed methods are designed to emphasize reconstruction errors for structurally ambiguous nodes. Experiments on multiple dynamic graph data sets show that incorporating NC-LID-based regularization consistently improves reconstruction performance over the baseline without structural regularization and the method using hub-aware regularization. These findings highlight NC-LID as a useful structural signal for enhancing distance-based graph autoencoders in dynamic settings.

AI 总结：该研究将强表达能力彩票票假设推广至多关系和时序领域，证明参数充足的关系型图神经网络含维持1-RWL表达能力的稀疏子网络，还通过实验验证相关概率下界并分析预训练表达能力与模型性能的关联。

链接：https://arxiv.org/abs/2608.18819

机构：Faculty of Computer Science, University of Vienna（维也纳大学计算机科学学院）； Doctoral School Computer Science, University of Vienna（维也纳大学计算机科学博士学院）； CeMM Research Center for Molecular Medicine of the Austrian Academy of Sciences（奥地利科学院CeMM分子医学研究中心）； CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）； School of Electronic Engineering and Computer Science, Queen Mary University of London（伦敦大学玛丽女王学院电子工程与计算机科学学院）； Research Network Data Science, University of Vienna（维也纳大学数据科学研究网络）

作者：Lorenz Kummer, Samir Moustafa, Anatol Ehrlich, Franka Bause, Marco Nennstiel, Przemysław Andrzej Wałȩga, Nils Morten Kriege

英文摘要：Graph neural networks (GNNs) are widely used, but how parameter sparsity affects the expressivity of relational (RGNNs) and temporal (TGNNs) variants is poorly understood. The Strong Expressive Lottery Ticket Hypothesis (SELTH) posits the existence of sparse GNNs that preserve Weisfeiler-Leman (WL) expressivity on static graphs. We generalize this existence result to a probabilistic statement for multi-relational and temporal domains via the relational WL (RWL). We prove that sufficiently parameterized RGNNs contain sparse subnetworks that maintain 1-RWL expressivity and derive a lower bound on the probability that a random pruning yields such a subnetwork. We show that common TGNNs and cross-graph message passing schemes admit RGNN reformulations such that they inherit these guarantees and, moreover, that the expressivity of a sparse RGNN is connected to its optimization behavior under common update regimes. Experiments instantiate the bound, compare it to empirical probabilities on synthetic data, and study how pre-training expressivity relates to optimization and prediction quality metrics on temporal and molecular benchmarks.

AI 总结：针对企业AI智能体在非平稳环境中面临的过时知识问题，提出含三种记忆状态的可逆遗忘框架，实例化为滞后可逆记忆控制器，可减少过时信息影响且不混淆临时抑制与永久擦除，金融场景可验证其思路。

链接：https://arxiv.org/abs/2608.18177

作者：Nilutpaul Sarker Yash, Tirtho Roy, Ushashi Bhattacharjee

英文摘要：Continual learning has traditionally treated forgetting as a failure, emphasizing preservation of previously acquired knowledge as environments evolve. We argue that this objective is incomplete for enterprise AI agents operating in non-stationary environments, where customers, policies, tools, workflows, regulations, and market conditions change over time. Indiscriminate retention can allow obsolete knowledge to influence decisions, creating negative transfer and operational risk. We therefore propose reversible forgetting: a conceptual framework with three operational memory states: active, dormant, and retired, and a reactivation transition that can restore dormant knowledge when its relevance returns. We instantiate the framework as a Hysteretic Reversible Memory Controller that accumulates relevance evidence, uses asymmetric thresholds to prevent state oscillation, tests reactivation in shadow mode, and gates retirement through policy. The framework reduces the influence of obsolete information without conflating temporary suppression with permanent erasure. Finance illustrates the idea: knowledge useful under one market regime may become harmful under another yet regain relevance when similar conditions recur.

AI 总结：该研究针对物理学中域适应的假设不成立问题，提出自适应域适应方法，通过重加权模拟事件聚焦物理不匹配，并给出无标签模型选择规则以选择近最优操作点。

链接：https://arxiv.org/abs/2608.18190

作者：Ivan Kharuk (1 and 2) ((1) Institute for Nuclear Research of the Russian Academy of Sciences, (2) Moscow Institute of Physics and Technology)

英文摘要：Domain adaptation is widely used to make neural networks trained on simulations applicable to experimental data. Its premise is that the two domains differ only in nuisances, and that the quantity of interest is distributed identically in both. In physics neither assumption holds: simulations can be wrong about the physics, and the distribution of the target quantity - an energy spectrum, a redshift distribution - is often the measurement itself. We study the consequences of such mismatches on a toy air-shower benchmark in which a detector-response nuisance, a physical simulation shift, and an energy-spectrum shift can be switched on separately or together. Standard adversarial adaptation handles the conditional shifts, but once the two spectra differ it aligns them, replacing an uncontrolled bias by one anchored on the simulation prior. We present adaptive domain adaptation, which reweights the simulated events so as to focus domain adaptation on the genuine physical mismatch alone. Since the predicted spectrum depends on model training configuration, we provide a label-free model selection rule for selecting the near-the-best operation point.

AI 总结：本文提出基于交互作用的IPS指标，分析50个开源LLMs的提示敏感性，发现监督微调等四个因素可通过降低低阶交互作用的敏感性减少提示波动。

链接：https://arxiv.org/abs/2608.18539

机构：School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）

作者：Ruiyang Qin, Qingzhuo Wang, Tian Wang, Zhihua Wei, Wen Shen

英文摘要：The remarkable capabilities of large language models (LLMs) are often undermined by their instability. Even subtle and semantically irrelevant changes in prompts can cause dramatic fluctuations in performance, a phenomenon known as prompt sensitivity. Previous studies typically evaluate prompt sensitivity by comparing the LLM's final outputs when prompts change. However, such coarse-grained metrics fail to explain the internal reasons for prompt sensitivity. In this paper, we introduce interactions as a fine-grained tool to analyze prompt sensitivity of LLMs. Specifically, we decompose the output score of the LLM into a set of interactions. Each interaction represents a nonlinear relationship involving a set of input variables. We discover that subtle changes to prompts can trigger severe instability in interactions, even when the outputs of the LLM remain the same. To this end, we propose an Interaction-based Prompt Sensitivity (IPS) metric by quantifying changes in interactions when we introduce subtle changes to prompts. We apply the IPS metric to 50 open-source LLMs and uncover four factors that reduce the prompt sensitivity of LLMs, including supervised fine-tuning, increased model scales, dense architectures, and few-shot learning. More crucially, we discover a common mechanism by which these four factors reduce prompt sensitivity: all four factors tend to reduce the prompt sensitivity of low-order interactions (i.e., interactions involving few input variables).

AI 总结：该研究提出数据共观测是持续学习的第三维度，发现其可提升泛化性，且记忆重放不仅缓解遗忘还能引入共观测益处。

链接：https://arxiv.org/abs/2608.18803

机构：KU Leuven； ESAT； Bernoulli Institute（伯努利研究所）； University of Groningen（格罗宁根大学）

作者：Timm Hess, Abhishek Jha, Gido M. van de Ven, Tinne Tuytelaars

英文摘要：Efficient continual learning remains a fundamental challenge for deep neural networks. While catastrophic forgetting and loss of plasticity are widely considered the primary obstacles to overcome, we show that these two issues cannot fully explain the performance gap between naive sequential training and offline joint training. In this paper, we highlight data co-observation as a distinct factor influencing continual learning performance. By decoupling the constraints of separate data access from stability and plasticity, we systematically investigate the representational benefits gained by observing training data together. Empirically, we demonstrate a consistent performance difference between joint and separate training across both supervised and self-supervised paradigms in generic data-incremental "chunking" scenarios, whilst mitigating forgetting and controlling for plasticity. Our findings indicate that simultaneous observation of training data (co-observation) yields benefits to the learner's generalization that extend well beyond mere knowledge retention, and that this effect does not require a specific continual distribution shift. Furthermore, we contextualize prominent continual learning mechanisms through this lens: while distillation-based approaches act only as effective knowledge retention mechanisms, our results suggest that the empirical success of memory replay goes beyond the mitigation of forgetting, actively reintroducing the benefits of data co-observation into the learning process.

AI 总结：该研究提出工具链持续学习（HCL）范式，围绕冻结基础模型演化工具链，通过受保护演化机制缓解工具链级遗忘，在多任务实验中相对基准增益超10%，可调整稳定性-可塑性权衡。

链接：https://arxiv.org/abs/2608.19013

机构：University of Wollongong（卧龙岗大学）； Nanjing University（南京大学）

作者：Borui Kang, Jinrui Gu, Junhan Lv, Wenbin Li, Lei Wang, Yang Gao

英文摘要：Continual learning has largely been model-centric, treating model parameters as the state that changes with sequential experience. Modern agents can also adapt through a harness of prompts, memories, tools, skills, and routing rules. Because these contents jointly shape later execution, a harness update can disrupt previously reliable behavior even when the model is frozen. This raises a new question: how can an agent continually improve its state outside the model while retaining behavior acquired earlier? We formulate Harness Continual Learning (HCL), a new continual learning paradigm in which the harness evolves around a frozen foundation model, and define the resulting loss of earlier behavior as harness-level forgetting. We instantiate HCL with four execution-facing components: the Task Interface, Experience Memory, Capability Map, and Adaptive Router. We further introduce guarded harness evolution to separate update generation from state commitment. A Continual Optimizer proposes candidate harnesses from post-execution feedback, and a Continual Evaluator commits the resulting candidate harness only after checking current improvement, historical retention, and validity. Experiments on textual reasoning, multimodal perception, and open-world interaction demonstrate capability accumulation and failure recovery, with relative gains exceeding 10% over corresponding baselines in multiple settings. Component ablations assess the contribution of each harness component, while controlled retention sweeps reveal measurable harness-level forgetting and show that the stability--plasticity trade-off can be explicitly adjusted.

AI 总结：本研究推出ClosureBench基准，评估不同规模模型在组合图推理任务的表现，发现模型存在记忆效应、组合推理瓶颈，微调输出程序的模型可提升性能。

链接：https://arxiv.org/abs/2608.18242

机构：AIM Research Lab（AIM研究实验室）

作者：Stefano Goria (AIM Research Lab)

英文摘要：We introduce ClosureBench, a constructive benchmark for compositional graph-relational reasoning with programmatically verified ground truth. Unlike fixed-test-set benchmarks vulnerable to data contamination, ClosureBench generates instances on demand: each task's reference answer is computed by executing a program in the Ein tensor-logic language, ensuring machine-verified correctness. The benchmark spans 26 task categories at three compositional levels (L1-L3), with difficulty controlled along three independent axes: graph size, edge density, and query depth. We evaluate models from 1.5B open weights to frontier systems (o3, GPT-4.1, Gemini 2.5, Claude Sonnet 4) and report three findings. First, because the benchmark can always supply fresh instances, it measures memorisation directly: a model fine-tuned on a fixed test set shows a 19.3 percentage-point gap between its accuracy on seen and on fresh instances, which a static test set cannot reveal. We scope this to supervised fine-tuning on answer pairs, not pretraining contamination. Second, accuracy falls as graph size and query depth increase, and the two interact: models misread the graph from its natural-language description and then reason correctly over the wrong graph, so even the strongest frontier model degrades from atomic to compositional queries. This bottleneck is a property of the reasoning rather than the input format: it persists when the graph is given as a JSON edge list or an adjacency matrix instead of prose. Third, a 4B model fine-tuned to emit executable programs rather than answers stays nearly flat across compositional levels and approaches frontier accuracy (94.3% on held-out instances) at a fraction of the token cost. This holds for two program targets, Ein and Python+NetworkX, so it is a property of verified program synthesis rather than of one language.

AI 总结：该研究针对多弱相互作用组件的动力系统，提出对σ-代数而非张量化评分的降维方法，可避免线性掩码问题，用少量代数坐标恢复被遗漏组件，实现低样本预测。

链接：https://arxiv.org/abs/2608.18918

机构：Technion, IIT（以色列理工学院）； NVIDIA（英伟达公司）

作者：Mark Kozdoba, Shie Mannor

英文摘要：Dimension reduction for dynamical systems is standard practice, and the standard route is spectral: model the transfer (Koopman) operator by its leading modes. We show that on systems assembled from several weakly interacting components --- a structure common in physical and biological settings --- this may either require an exponential number of modes, or drop an entire component: the component is absent from the model rather than modeled coarsely, and no function of it can be predicted at any accuracy. We call this linear masking. The cause is that a rank-based model pays one coordinate per mode. We propose to score instead the $\sigma$-algebra the coordinates generate, so that products and powers come free and a component's cost is governed only by its generators rather than by all its interactions. The criterion is a $\chi^2$-divergence between the embedded present and future, and it carries a budget guarantee: twice the intrinsic dimension of the dynamics is enough coordinates for an embedding whose algebra carries the operator's entire spectrum, with its full infinite rank. In variational form the criterion admits off-the-shelf estimators, and restricting its critic to the bilinear class returns the VAMP score on the span, so rank-based methods are one end of the same family. We demonstrate the proposed objective on a composite of published benchmark systems. We exhibit examples where the rank-based methods completely miss the masked components at all ranks $k<100$, while ten algebra coordinates recover all of them. In addition, the resulting algebra representation supports predicting the masked components from few labels, while direct regression from the high-dimensional observation or from the VAMP features fail.

AI 总结：该研究指出表格机器学习基准的聚合指标忽视模型的数据集特定不可替代优势，提出以数据为中心的峰值性能前沿评估框架，建议基准进展需同时衡量聚合指标与模型对峰值性能集的扩展。

链接：https://arxiv.org/abs/2608.18919

机构：University of Mannheim（曼海姆大学）； University of Rostock（罗斯托克大学）； Technical University of Clausthal（克劳斯塔尔工业大学）

作者：Andrej Tschalzev, Stefan Lüdtke, Heiner Stuckenschmidt, Christian Bartelt

英文摘要：Tabular machine learning benchmarks typically summarize performance by averaging scores, ranks, or pairwise wins across datasets. Such aggregates are useful for selecting robust default models, but they can obscure a different question: which models are necessary to attain peak performance on particular datasets? We argue that benchmark evaluation should also consider the data-centric peak performance frontier, defined by the best statistically supported performance achieved on each dataset. From this perspective, a model may be irreplaceable, sufficient, redundant, or fallible depending on where it lies on the frontier relative to other models. Applying this framework to the TabArena benchmark, we find that common aggregation metrics are highly correlated and largely measure consistency and avoiding failures, while being much less aligned with dataset-level irreplaceability. Consequently, models performing decently across datasets without ever being the best choice are rewarded while models with unique dataset-specific strengths appear mediocre under aggregation. Hence, benchmark progress should be measured not only by improvements on aggregation metrics but also by whether new models expand the set of attainable peak performances across datasets.

AI 总结：该研究针对轻量级代理模型训练时加速器利用率低的问题，提出ERASE方案，通过分离子图反向传播与前向工作重叠，使大规模点击率模型训练吞吐量提升最高9.51%且保持性能稳定。

链接：https://arxiv.org/abs/2608.18469

机构：Carnegie Mellon University（卡内基梅隆大学）； Meta Inc.（元公司）

作者：Ergan Shang, Flavio Sales Truzzi

英文摘要： Lightweight proxy models enable rapid experimentation without repeatedly training frontier-scale systems, but their small kernels often leave modern accelerators underutilized. Conventional training compounds this inefficiency by scheduling the forward and backward passes as disjoint phases, so spare capacity in one cannot be filled by work from the other. We reinterpret the detachment mechanism of Forward-Forward (FF) as a scheduling primitive: given a local objective, detaching a block's output removes downstream gradient dependencies, making its backward pass ready when its forward pass finishes. ERASE launches each detached subgraph's backward pass early on a separate CUDA stream, overlapping it with subsequent forward work. Execution trace on a lightweight transformer demonstrates this overlap and its limit: a kernel that saturates the device leaves no capacity for concurrency. On a large-scale click-through-rate model, detaching six dense subarchitectures improves training throughput by up to $9.51\%$ while keeping normalized entropy close to the baseline.

AI 总结：提出物理展开混合神经算子（PU-HNO），通过三级级联结构逐步捕捉无线传播效应，在不同平面图上的实验中，其在图像质量和无线部署指标上均优于多种基线模型。

链接：https://arxiv.org/abs/2608.18495

机构：University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

作者：Rafid Umayer Murshed, Saif Ur Rahman, Mingyue Tang, Elahe Soltanaghai

英文摘要：Radio maps are essential for wireless decision-making tasks such as access-point placement, coverage planning, and localization, but their fine spatial details are governed by complex propagation effects and are costly to simulate accurately. Machine learning offers a path to high-fidelity radio-map prediction without running expensive high-fidelity simulations for every scene. However, generating high-quality training labels at scale is also difficult: the affordable labels come from finite-ray simulations, which are richer than low-fidelity inputs but carry residual Monte Carlo noise. We address this challenge with Physics-Unrolled Hybrid Neural Operator (PU-HNO), a three-stage cascade that predicts high-fidelity indoor radio maps from low-fidelity ray-tracing outputs and scene priors by progressively capturing reflection, diffraction, and scattering effects, rather than treating radio maps as generic images. We prove that, under conditionally unbiased label noise, the model can learn stable propagation structure and outperform its own training labels. Experiments across diverse floorplans show that PU-HNO outperforms image-to-image baselines, wireless learning models, and monolithic neural operators across both image-quality and wireless deployment metrics.

AI 总结：研究针对热带气旋预报的不确定性与高成本问题，提出物理约束生成式框架Tianmu-TC，该模型在全球各洋盆的预报性能优于权威系统，且在复杂场景下表现良好，计算成本显著更低。

链接：https://arxiv.org/abs/2608.18500

机构：College of Computer Science and Technology, Zhejiang University of Technology（浙江工业大学计算机科学与技术学院）； School of Computer Science and Engineering, Tianjin University of Technology（天津理工大学计算机科学与工程学院）； School of Earth Sciences, Zhejiang University（浙江大学地球科学学院）； School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）

作者：Shiqi Zhang, Pan Mu, Cheng Huang, Hanting Yan, Yuchao Zhu, Jinglin Zhang, Shengyong Chen, Shoujuan Shu, Cong Bai

英文摘要：Tropical cyclones (TCs) pose severe risks from strong winds and heavy rainfall. However, forecasting their track and intensity remains challenging due to chaotic atmosphere and the rapid amplification of initial condition errors, leading to growing forecast uncertainty. While numerical weather prediction (NWP) and deep learning models have made progress, they remain computationally demanding and often fail under complex meteorological scenarios. Here, we present Tianmu-TC, a physics-constraints generative framework for global TC forecasting. Trained on Western North Pacific data, Tianmu-TC leverages physics-constraints to generate controllable outputs with reduced uncertainty thus improving forecast reliability. Experiments show Tianmu-TC outperforms deterministic and ensemble meteorological artificial intelligence models and authoritative NWP systems such as ECMWF in global ocean basins, with significantly lower computational cost. We further show Tianmu-TC performs well in challenging scenarios such as data sparsity, anomaly tracks, rapid intensification and weakening. These findings suggest physics-constraints generative AI offers a promising approach for reliable, efficient global TC forecasting.

AI 总结：本文提出DCNO与DGNO两种多阶段神经算子学习框架，用于提升卷积积分计算精度与效率，经理论分析及数值实验验证，其性能优于传统求解器，还可扩展至多输入算子学习场景。

链接：https://arxiv.org/abs/2608.18851

机构：Eastern Institute of Technology（东方理工学院）； Wuhan University（武汉大学）； Tianjin University（天津大学）

作者：Zhiping Mao, Zhenye Wen, Yong Zhang, Xiaofei Zhao

英文摘要：Convolution integrals widely exist in applications, and to enable fast and accurate computations, this paper introduces two general multi-stage neural operator learning frameworks. The first, Deep Collocation Neural Operator (DCNO), is a supervised approach that iteratively refines the operator approximation by learning residuals from input-output data pairs. The second, Deep Galerkin Neural Operator (DGNO), is an unsupervised framework applicable when the target operator can be represented by a PDE, leveraging the weak form of the PDE residual for training. Both methods progressively construct basis operators through multiple training stages to enrich the approximation space, leading to significantly improved accuracy over standard one-shot operator learning. We provide theoretical analysis for their approximation capabilities and implement them for learning convolutions. Extensive numerical experiments demonstrate that both DCNO and DGNO achieve high accuracy, approaching machine precision under single float for convolution problems, and offer substantial efficiency gains for numerous queries or parametric variations compared to traditional solvers. We also extend these frameworks to handle multi-input operator learning scenarios involving variations in both the density and kernel of a convolution.

AI 总结：本文提出新的分子基础模型Monroe，通过多方面创新提升性能，在多个基准测试中表现优异，且其下游适应策略可推广至其他模型。

链接：https://arxiv.org/abs/2608.18982

机构：Graphcore（格弗科（Graphcore））； Max Planck Institute of Biochemistry（马克斯·普朗克生物化学研究所）

作者：Blazej Banaszewski, Andrew W. Fitzgibbon

英文摘要：Bioassay activity prediction is often data-limited because drug-discovery datasets rely on time-consuming and expensive wet-lab experiments for data generation and evaluation. This challenge has inspired recent research into molecular foundation models (MFMs), which aim to encode general-purpose chemical knowledge into molecular representations that generalize well in data-constrained scenarios. This paper presents Monroe, a new MFM with several innovations over the existing state of the art: increased scale allowing pre-training on over 81 million molecules from the PM6 quantum chemistry dataset; improved graph representation of stereochemistry; improved training losses including conformer denoising and embedding decorrelation; improved multi-task learning; and the use of a prior-data-fitted model (TabPFN) for downstream in-context prediction. Our evaluations use a principled pairwise comparison framework that measures statistically significant performance differences. Across established Polaris benchmarks, Monroe matches or exceeds existing MFMs, while on activity cliff benchmarks, designed to assess utility for molecular discovery, it achieves significant improvements over prior methods. Finally, ablation and transfer experiments show that PFN-based downstream predictors also substantially improve two leading existing models, MiniMol and CheMeleon, yielding new state-of-the-art variants we call MiniMol_PFN and CheMeleon_PFN, suggesting that our downstream adaptation strategy generalizes beyond Monroe. Source code is at this http URL.

AI 总结：该研究针对视觉在线策略蒸馏中在线展开成本高的问题，提出HB-SJD批量推测雅可比展开后端，仅替换学生展开后端，在LlamaGen上验证可降时间且保生成质量。

链接：https://arxiv.org/abs/2608.18183

机构：Shenzhen Key Laboratory of Internet Information Collaboration（深圳市互联网信息协同重点实验室）； Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））

作者：Bingqi Shan, Zhehao Yu, Kenhong Lin, Baoquan Zhang

英文摘要：Visual on-policy distillation (OPD) improves the training of compact visual autoregressive models by learning from trajectories generated by the current student. However, these online rollouts are still produced token by token with autoregressive decoding, which adds substantial cost to every on-policy training step. Speculative Jacobi Decoding (SJD) provides an alternative because it can process multiple tokens in parallel without an auxiliary draft model, but the original method is designed for single-sequence inference. We introduce HB-SJD, a batched SJD rollout backend for visual OPD. HB-SJD allows each image to advance independently according to its own decoding progress, while images at different sequence positions are still verified in batched model forwards. As images finish, HB-SJD switches between Full and Compact execution to reduce the cost of later rollout rounds. HB-SJD only replaces the student rollout backend and leaves the teacher, distillation objective, and optimization procedure unchanged. Experiments with LlamaGen show that HB-SJD substantially reduces rollout and end-to-end training time while preserving the generation quality of the distilled student.

AI 总结：该研究探讨医学与机器学习的生成类比，借鉴临床转化的认知与方法论正当性，提出一种新的ML可靠论，以解决ML在医学应用中的不确定性问题。

链接：https://arxiv.org/abs/2608.18186

作者：Emanuele Ratti, Lena Zuchowski

英文摘要：In the past few years, machine learning (ML) has been widely (and to an extent, successfully) implemented in medicine. However, uncertainties surrounding ML have made it difficult to establish the bases of its epistemic and methodological warrants. In the literature, a parallel has been drawn between medicine and ML, suggesting that we should model epistemic and methodological standards for ML on the standards of clinical translation. By developing tools from Hesse work, we characterise the nature of this parallel as a generative analogy between the process of clinical translation and the process of building ML systems. We identify more precisely the epistemic and methodological warrants of clinical translation that are typically only mentioned when appealing to the analogy, and we show in which sense such warrants apply analogically to the context of ML. In particular, we interpret warrants of clinical translation in reliabilist terms, and we show how this can inform a new form of ML reliabilism, which is distinct from (though compatible with) existing reliabilist accounts in philosophy of AI.

AI 总结：本系统综述分析2017-2023年55项研究，探究ML在ASD诊断治疗的应用，指出监督学习为主、深度学习作用扩大，需整合多模态数据并加强跨学科合作。

链接：https://arxiv.org/abs/2608.18188

作者：Rafael Muñoz-Terol, Jesús Peral, Sandra Amador, David Gil

英文摘要： Autism spectrum disorder (ASD) is a developmental disability characterized by challenges in social interaction and communication. As the causes of ASD remain unclear, identifying relevant features and hidden correlations is crucial for early diagnosis. This systematic review evaluates 55 studies from 2017 to 2023 on the application of machine learning (ML) techniques to ASD. The primary objective is to examine recent ML applications in ASD research, identifying trends, techniques, and datasets that enhance diagnosis and treatment. Supervised learning methods dominate, as they align well with ASD diagnostic needs; however, the role of deep learning is expanding with greater data availability. Emerging techniques based on hybrid methods, where unsupervised, deep learning, and fuzzy logic could be included, will be interesting to observe in the future. The review highlights key challenges and opportunities, particularly the need for models that can integrate complex data -such as genetic and clinical information- to improve diagnostic accuracy and treatment outcomes. Additionally, incorporating innovative data sources, like wearable devices and biometric sensors, could enable continuous and non-intrusive monitoring, providing a more holistic understanding of ASD. Findings emphasize that addressing current challenges requires interdisciplinary collaboration and expanded datasets tailored to ASD. Future ML models will benefit from broader multimodal data integration, enabling researchers to more comprehensively address the complexities of ASD.

AI 总结：ChiroEcho框架联合预测蝙蝠的属与物种，结合地理分布将欧洲蝙蝠自动分类覆盖从73%提升至85%，为解决未见过的细粒度类别问题提供了原理验证。

链接：https://arxiv.org/abs/2608.18191

机构：Naturalis Biodiversity Center（自然生物多样性中心）； Department of Cognitive Science and Artificial Intelligence, Tilburg University（蒂尔堡大学认知科学与人工智能系）； People and Nature Lab, University College London（伦敦大学学院人与自然实验室）； Leiden Institute of Advanced Computer Science, Leiden University（莱顿大学莱顿高级计算机科学研究所）

作者：Burooj Ghani, Welmoed Eversteijn, Milan van Hirtum, Juan Sebastián Cañas, Vincent J. Kalkman, Dan Stowell, A. Leonie Baier

英文摘要：Bats are key indicators of ecosystem health and are protected throughout Europe, making reliable population monitoring a conservation priority. Their cryptic nocturnal lifestyle makes passive acoustic monitoring essential, yet automated identification remains difficult as echolocation calls vary with behaviour and environment and overlap among species. We present a deep learning framework that jointly predicts species and genus and combines genus predictions with geographic species distributions at inference. When only one species of a predicted genus occurs in a region, the framework can resolve species absent from the learned taxonomy. This reframes geographic information as a means of extending, rather than constraining, a classifier's effective taxonomy. Using recordings spanning 35 European bat species, we evaluate closed-set classification, examine the instability of performance estimates for sparsely represented species, and conduct a controlled held-out proof-of-principle experiment. The rare-species analysis shows how limited evaluation data can obscure species-level performance, while the held-out experiment shows that genus predictions and location can recover labels unavailable to the species head. Geographic resolution extends operational coverage from 35 to 41 of the 48 native European bat species, increasing coverage from 73% to 85%. To our knowledge, this is the broadest operational coverage reported for automated European bat classification. More broadly, the bat framework provides proof of principle for resolving unseen fine-grained classes by combining coarse predictions with transparent external constraints.

AI 总结：该研究针对循环深度推理器的测试时迭代问题，提出通过控制算子动态状态实现深度安全，提升了数独等任务的外推准确率，为循环模型的可靠深度推理提供了准则。

链接：https://arxiv.org/abs/2608.18222

作者：Ivan Viakhirev, Kirill Borodin, Amirah Almutairi, Serguei Barannikov, Maxim Abramov, Grach Mkrtchian

英文摘要：Recurrent-depth reasoners aim to solve harder problems by iterating their update longer at test time, but additional iterations can improve, preserve, or degrade an answer. We show that a measurable property of the trained operator, its finite-time dynamical regime (estimated as settling, marginal, or drifting), indicates which of these occurs. We give a sufficient condition for depth-safety: once an operator's per-step displacement is small relative to the decoder margin, the decoded answer cannot change under further iterations. Empirically, on algorithmic tasks trained from $800$ unaugmented examples per difficulty tier, settling operators do not degrade with added depth, and on some tasks convert it into higher accuracy on harder unseen instances (Sudoku, $0.19$ to $0.34$ past the training horizon). A single terminal fixed-point objective moves the regime and the depth behavior together: removing it induces drift and removes the gains, and adding it to a generic recurrence yields depth-safe extrapolation on carry propagation. We give four operational criteria for useful test-time depth, use them to catalogue failure modes, and, as a consistency check, apply the same measurements to Huginn-3.5B, which falls in the non-settling family.

AI 总结：该研究针对循环语言模型，提出仅重复混合器、单次执行密集FFN的MixerLoop，在不同参数规模下验证其性能，可保留循环深度优势并降低计算量。

链接：https://arxiv.org/abs/2608.18230

机构：University of California, Santa Cruz（加州大学圣克鲁兹分校）

作者：Ruhai Lin, Yiyang Guo, Rui-Jie Zhu, Hao Ye, Jason K. Eshraghian

英文摘要：Looped language models improve reasoning and knowledge manipulation by applying shared computation repeatedly. Existing systems usually repeat an entire layer stack, although a mixer and a dense feed-forward network (FFN) perform different operations and have different costs. We ask a narrower question: what should loop? We view recurrence as repeated composition of a state update and argue that an application is valuable when it exposes a new cross-position influence direction that remains observable at the task readout. Iterative Transport Rank (ITR) describes the cumulative influence trajectory; marginal ITR describes the nonredundant influence contributed by successive applications. This view motivates MixerLoop, which repeats each Gated DeltaNet mixer while applying its dense FFN once. We compare MixerLoop with no recurrence and full-block recurrence at 15M and 110M parameters under the same data, initialization, and architecture. A finite context-off intervention tests whether later mixer applications produce distinct, non-negligible, and beneficial changes at the final language-model readout. MixerLoop surpasses FullLoop on aggregate CORE at 15M and retains 41.5% of its CORE improvement at 110M while reducing recurrent-backbone projection FLOPs by 45.9%. These results show that the benefits of recurrent depth can be retained without repeatedly executing the dense FFN.

AI 总结：本研究用DBN与Bi-GRU处理MV3轨迹分类问题，DBN编码静态快照，Bi-GRU实现四类轨迹近乎完美分离，可实时感知MV3动态 regime，为意见动力学模型临界转变检测提供分层架构。

链接：https://arxiv.org/abs/2608.18235

作者：Mauricio A. Valle, Gonzalo A. Ruz

英文摘要： In this work, we investigate whether the latent representations learned by a Deep Belief Network (DBN) and a Bidirectional Gated Recurrent Unit (Bi-GRU) can discriminate among four dynamically distinct trajectory types in the three-state majority vote model (MV3): approach from disorder, approach from order, departure to disorder, and departure to order. The DBN, pre-trained in an unsupervised manner on static equilibrium samples via a Gaussian-Bernoulli Restricted Boltzmann Machine input layer and architecture $784 \to 4096 \to 225 \to 81$, encodes each lattice snapshot into an 81-dimensional latent vector. A t-SNE analysis of the DBN latent space reveals only partial separation of the four trajectory types, reflecting the fact that a model trained on static configurations cannot fully resolve directional temporal structure. A two-layer Bi-GRU classifier, trained on sequences of DBN-encoded snapshots of length $T = 50$, achieves near-perfect separation of all four trajectory types in its hidden state space, as confirmed by t-SNE visualization on both training and test sets. Furthermore, a sliding-window application of the trained Bi-GRU to continuous MV3 dynamics demonstrates its ability to sense the system's current dynamical regime in real-time. These results establish a principled hierarchical architecture for detecting and classifying critical transitions in agent-based opinion dynamics models.

AI 总结：该研究针对生物与人工神经网络表征对齐的不对称问题，开发整合谱正则化与双向预测性分析的计算框架，调控表征几何使双向预测性获55%相对提升，证明可通过调控表征几何调节双向对齐。

链接：https://arxiv.org/abs/2608.18244

机构：University of Toronto（多伦多大学）； KITE Research Institute（KITE研究所）； University Health Network（大学健康网络）

作者：Samuel Kostousov, Abhinn Kaushik, Brokoslaw Laschowski

英文摘要：Recent work has shown that representational alignment between biological and artificial neural networks is asymmetric: model representations predict neural responses much better than neural responses predict model representations. This asymmetry raises the question of whether representational geometry contributes to bidirectional representational alignment. We hypothesized that steering representational geometry during training can systematically influence bidirectional alignment. To test this hypothesis, we developed a computational framework that integrates spectral regularization with bidirectional predictivity analyses. As an initial demonstration, we evaluated our framework using self-supervised contrastive vision models. Steering the spectral geometry of the learned representations substantially increased reverse predictivity with modest reductions in forward predictivity, yielding a 55% relative improvement in bidirectional predictivity. These improvements were accompanied by reduced effective dimensionality and a reorganization of the shared representational subspace, within which forward and reverse predictivity became approximately symmetric at intermediate spectral exponents. Overall, these findings demonstrate that representational geometry can be systematically steered to modulate bidirectional representational alignment between biological and artificial neural networks.

AI 总结：本研究针对Qwen3模型开展OPSD实验，分析OPSD的性能提升源于参考信息还是基础模型的推理行为，发现性能提升与参考信息的契合度无可靠关联。

链接：https://arxiv.org/abs/2608.18271

机构：FirstPrinciples

作者：Samyak Shrestha, Alexander Tessier

英文摘要：On-policy self-distillation (OPSD) trains a student on its own responses using token-level supervision from the same model conditioned on privileged reference information. We investigate whether performance gains from OPSD show that the student learned the information in the reference or instead reflect recovery of reasoning behavior already present in the base model. We perform OPSD experiments on science and mathematics datasets using Qwen3 models ranging from 1.7B to 8B. Our analysis framework separates the supervision induced by the reference from the supervision provided by the teacher without the reference and measures how each aligns with changes in the student's predictions. The correct reference does not provide a consistent performance benefit across teacher generation modes, model sizes, and training datasets. Students can improve without the correct reference, and a solution from another problem can outperform the correct solution on several mathematical reasoning benchmarks. The student's predictions align more strongly with the base model's thinking behavior than with the supervision induced by the reference, but controls constructed from other problems reproduce much of both alignments. Moreover, stronger alignment attributable to the correct reference does not reliably coincide with a greater performance benefit from the reference. Performance gains and distributional alignment alone therefore cannot determine how privileged reference information contributes to student learning in OPSD.

AI 总结：该研究针对测试时聚合提出无候选控制方法，在数学基准测试中探究候选条件作用对准确率的影响，发现多正确候选时提升、全错时降低，明确了其效果边界。

链接：https://arxiv.org/abs/2608.18379

机构：ETH Zurich（苏黎世联邦理工学院）

作者：Guiv Farmanfarmaian

英文摘要：When every candidate is wrong, correct-candidate selection is unavailable, yet the aggregation call can still solve the problem afresh. A correct aggregate answer may therefore reflect recombination, fresh solving, or both. For efficient test-time reasoning, the relevant question is whether candidate context adds value beyond the additional generation pass. We introduce the missing candidate-free control under the same maximum output-token allowance and stratify by the number of correct candidates. Across AIME-2025 and HMMT-2025 with Qwen3-4B, candidate conditioning improves accuracy when multiple candidates are correct ($\Delta_{\mathrm{cand}}$(c2+) = +0.290), lowers accuracy when every candidate is wrong ($\Delta_{\mathrm{cand}}$(c0) = -0.123), and remains unresolved in the one-correct regime. The c2+ and c0 conclusions survive a conservative correction for the adaptive two-benchmark procedure. Under this counterfactual, the interpretation of all-wrong recovery reverses at this scale: conditioning on an all-wrong candidate pool lowers accuracy relative to a fresh solve. Original-format matching and placebo results characterize the failures descriptively but leave their mechanism unresolved. Within a separate structured intervention, explicit answer fields causally steer outputs toward their values; masking yields no measurable accuracy improvement, and equivalence with the original format was not established. The evidence is limited to one Qwen3-4B family, two mathematics benchmarks, first-answer-truncated candidate fragments, and single-pass prompted aggregation.

AI 总结：该研究针对VLA模型推理成本高的问题，提出RoleSub方法，通过角色条件子令牌路由压缩视觉和语言表示，在匹配视觉-KV预算下多数场景优于仅令牌控制，结合压缩后总KV仅为原始的9.2-11.3%且控制性能强。

链接：https://arxiv.org/abs/2608.18410

机构：Futurewei Technologies（未来智能技术公司）

作者：Wei Jiang, Wei Wang

英文摘要：Vision-Language-Action (VLA) models process long multimodal token sequences, making inference expensive in both memory and computation. Existing efficiency methods mainly reduce visual tokens, but aggressive token pruning becomes fragile because removing a token discards its entire representation. Sub-token compression provides a complementary alternative by retaining more tokens while reducing their value width. However, directly applying sub-token compression to VLA policies is less effective because information important for perception, language understanding, and control is distributed differently across the multimodal representation. We introduce Role-Conditioned Sub-Token Routing (RoleSub), which learns how to compress the value representations of retained tokens. After visual token reduction, RoleSub partitions each retained value representation into groups in an orthogonal space and uses a lightweight router to determine which groups should be preserved. The routing decision is conditioned on the token representation, a learned latent role representation, and language context. The same mechanism can also be applied to language values, allowing visual and language representations to be compressed without removing additional tokens. We evaluate RoleSub on OpenVLA-OFT-7B across the four LIBERO suites. At matched visual-KV budgets, RoleSub outperforms a trained token-only control in 33 of 36 settings, with the largest gains under aggressive compression. Combining visual and language compression reduces total KV to 9.2--11.3% of the original while retaining strong control performance on most tasks. These results show that reducing the representation within retained tokens provides an effective complement to token pruning for aggressive VLA compression.

AI 总结：本研究从机制可解释性视角探究LLaMA 3.1 8B，通过构建需捕捉结构的数值序列任务，发现其可无监督计算存储一阶差分，还揭示其通过类诱导回路机制完成数值推理。

链接：https://arxiv.org/abs/2608.18419

机构：Northeastern University（东北大学）； EmbodyX Inc.（EmbodyX公司）

作者：Rahul Chowdhury, Timothy A Rupprecht, Senhao Cao, Jiahao Liu, Octavia Camps, David Bau, Pu Zhao, Yanzhi Wang

英文摘要：Recent work has shown that large language models (LLMs) exhibit strong numerical sequence modeling capabilities and show promise in time-series prediction. While LLMs display in-context learning capabilities, the mechanisms with which they accomplish time-series prediction remain unclear. Specifically, whether they truly understand the underlying structure, which at a minimum requires reasoning over first differences in the sequence of numbers. To study this, we investigate Llama 3.1-8B from a mechanistic interpretability point of view. Mechanistic interpretability is an emerging field concerned with the reverse engineering of the algorithms learned by neural networks such as LLMs. To assess Llamas' numerical sequence modeling capabilities and to facilitate our mechanistic interpretability analysis, we create a sequence modeling task that cannot be solved without picking up structural cues. Specifically, we sample n random numbers and repeat them with an offset. We find that Llama displays strong performance on our tasks suggesting that it can pick up on the underlying structure. To understand the mechanisms that allow it to do so, we perform probing experiments and activation patching based counterfactual analysis. Probing reveals that the model computes and stores first differences in its internal representations without explicit supervision, indicating that it tracks structural information about the sequence. Activation patching reveals that Llama retrieves the relevant first-difference with a mechanism similar to an induction circuit and subsequently adds it to the current value. Notably, our work represents one of the first studies to identify this form of concept induction in LLMs.

AI 总结：本研究针对数据中心高能耗问题，提出基于LLM的预测调度系统，经合作验证可降低32%能耗、30%等待时间，为数据中心可持续运行提供实用方案。

链接：https://arxiv.org/abs/2608.18503

机构：The University of Sydney Business School, The University of Sydney（悉尼大学商学院，悉尼大学）； University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）； Purdue University（普渡大学）

作者：Hanzhao Wang, Jingxuan Wu, Yumeng Li, Yu Pan, Guanting Chen

英文摘要：The growing demand for AI-driven workloads, particularly from Large Language Models (LLMs), has raised concerns about the significant energy and resource consumption in data centers. This work introduces a novel LLM-based predictive scheduling system designed to enhance operational efficiency while reducing the environmental impact of data centers. Our system utilizes an LLM to predict key metrics such as execution time and energy consumption from source code, and it has the potential to extend to other sustainability-focused metrics like water usage for cooling and carbon emissions, provided the data center can track such data. The predictive model is followed by a real-time scheduling algorithm that allocates GPU resources, aiming to improve sustainability by optimizing both energy consumption and queuing delays. With fast inference times, the ability to generalize across diverse task types, and minimal data requirements for training, our approach offers a practical solution for data center scheduling. This framework demonstrates strong potential for advancing sustainability objectives in AI-driven infrastructure. Through our collaboration with a data center, we achieved a 32% reduction in energy consumption and a 30% decrease in waiting time.

AI 总结：针对物联网环境下MLaaS客户端为黑盒的漂移检测难题，提出MPDD模型与APDDM机制，实验显示二者可显著提升检测准确率、降低漏检率。

链接：https://arxiv.org/abs/2608.18555

机构：Curtin University（科廷大学）； Umeå University（于默奥大学）

作者：Deepak Kanneganti, Sajib Mistry, Sheik Mohammad Mostakim Fattah, Erik Elmroth, Aneesh Krishna, Monowar Bhuyan

英文摘要：Machine Learning as a Service (MLaaS) is a powerful cloud paradigm enabling data-driven intelligent applications in Internet of Things (IoT) environments, widely adopted across healthcare, smart homes, and industry due to its cost-effectiveness. However, the dynamic nature of IoT frequently alters data distributions, affecting MLaaS stability, while periodic MLaaS updates further introduce performance drift. Unlike traditional ML systems, MLaaS clients operate as black-box users without access to internal data or parameters, making drift detection particularly challenging. To address this, we propose a novel MLaaS Performance Drift Detection framework for IoT environments. The framework first employs an MLaaS extraction model that learns service behavior from input-output pairs and identifies prediction-influenced features. Building on this, the proposed MLaaS Performance Drift Detection (MPDD) model jointly captures variations in input data and MLaaS behavior. We further design an Adaptive-Temporal Performance Drift Detection Mechanism (APDDM) that dynamically adjusts monitoring frequency based on behavioral and data variations, enabling timely drift detection for effective service management. Extensive experiments on real-world datasets demonstrate that MPDD achieves up to 22-25% accuracy improvement over baseline drift detection methods. APDDM provides an average accuracy gain of approximately 4% and reduces the miss detection rate by around 9% compared to fixed-interval monitoring.

AI 总结：本研究提出参数高效的混合时间卷积网络NanoSleep，解决单通道EEG睡眠分期分类中模型体积大的问题，经实验验证其在准确率与效率间实现平衡，适用于资源受限设备

链接：https://arxiv.org/abs/2608.18571

机构：School of Computing, Wichita State University（威奇托州立大学计算学院）

作者：S M Asif Hossain, Shruti Kshirsagar

英文摘要：Sleep stage classification from single-channel electroencephalography (EEG) is essential for wearable and home-based sleep monitoring. However, many deep learning models achieve high accuracy at the cost of large model sizes, which limits their deployment on resource-constrained devices. In this work, we present NanoSleep, a compact hybrid temporal convolutional network for automatic sleep stage classification. NanoSleep combines a learnable Sinc-convolutional front end, a dual-branch feature extractor that fuses multi-scale temporal and spectral representations, a gated dilated temporal convolutional backbone with channel recalibration, and a conditional random field for sequence-level decoding. We further employ a weighted calibrated focal loss to address class imbalance. We evaluate NanoSleep on the Sleep-EDF and Sleep-EDF-Expanded datasets using subject-wise cross-validation. The proposed model consistently outperforms six representative baseline methods, and an ablation study confirms the contribution of each major component. These results demonstrate that NanoSleep provides an effective balance between accuracy and efficiency, making it well suited for wearable devices, home-based sleep monitoring, and resource-constrained clinical applications.

AI 总结：该研究发现引导式蛋白质语言模型存在流形外坍塌问题，提出无需训练的马氏过滤方法，可低成本提升生成序列的属性得分与结构合理性，且可跨引导方法迁移。

链接：https://arxiv.org/abs/2608.18597

机构：Duke University（杜克大学）； Cornell University（康奈尔大学）； University of Wisconsin--Madison（威斯康星大学麦迪逊分校）

作者：Shuibai Zhang, Xinchi Liu, Fred Zhangzhi Peng, Zhihan Yang, Shutong Wu, Yingzi Ma, Jiawei Zhang

英文摘要：Protein language models are widely used priors for protein sequence design, and a growing body of work controls them at inference time as an alternative to fine-tuning. Such guidance faces a dilemma: mild enough to preserve natural activation statistics, it barely moves the property; strong enough to move it, the generations become progressively harder to fold. We show the failure has a specific and cheaply detectable signature, an off-manifold collapse of the model's own representations. Guided activations fall toward a region statistically indistinguishable from random amino-acid input, and the sequences degenerate to low complexity, yet the property oracle being optimized can still score these generations as a success. The optimized oracle can therefore fail to witness the collapse and, for solubility, can actively reward it, whereas structure and composition expose the failure. Because the failure is already visible in a finished candidate, we detect it at the output rather than modify the generator. We introduce a cheap density prior over natural protein activations and keep only the candidates that remain typical under it, a training-free post-hoc step we call Mahalanobis filtering. At matched guidance settings it improves both the property score and the structural plausibility of the sequences it keeps at negligible cost, without touching the generator, and transfers across different guidance methods. We release the activation statistic at this https URL

AI 总结：本文针对受噪声保护的文本嵌入，提出感知去噪的反演方法DAEI，突破双重噪声陷阱，在反演性能上大幅优于基线，挑战了高斯扰动可防嵌入隐私泄露的假设。

链接：https://arxiv.org/abs/2608.18610

机构：Monash University（莫纳什大学）； The University of Queensland（昆士兰大学）； Northeastern University（东北大学）

作者：Yubo Wang, Shujie Cui, James Bailey, Hongzhi Yin, Wenyu Liang, Min Tang, Shiyue Qin, Weiqing Wang

英文摘要： Dense text embeddings are widely used in data mining, retrieval, and downstream machine learning systems due to their compact and semantically rich representations, but recent embedding inversion attacks have shown that they can expose substantial information about the original text, leading to serious privacy leakage risks. A common defense is to release perturbed embeddings by adding Gaussian noise, which is simple yet effective against standard inversion attacks and does not significantly degrade embedding utility for downstream tasks. However, it remains unclear whether such noise-protected embeddings are sufficiently safe against adaptive attackers that explicitly account for the perturbation process. In this paper, we study text embedding inversion in a noise-protected setting, where the attacker can observe only noisy embeddings and has no access to clean embedding targets. We first analyze why existing generative inversion methods fail under this setting and identify a "Double Noise Trap", which fundamentally prevents standard generative inversion models from achieving high-quality reconstruction. To address this challenge, we propose DAEI, a denoising-aware embedding inversion pipeline that combines a residual denoising autoencoder with generative text inversion where the denoiser is trained in an unsupervised manner using Stein's unbiased risk estimate to enable denoising from noisy observations alone. Extensive experiments show that DAEI achieves approximately 154\% relative improvement in BLEU over the existing generative inversion baseline, while also improving token-level F1 and ROUGE-L by 32--60\%. The promising inversion performance of DAEI challenges the prevailing assumption that simple Gaussian perturbation is sufficient to prevent sensitive information leakage from embedding representations.

AI 总结：本研究提出一种模块化可扩展的故障概率建模框架，整合多源地理空间数据开展植被与雷击相关电力线资产风险建模，可支持公用事业级网络韧性规划。

链接：https://arxiv.org/abs/2608.18611

机构：SA Power Networks（SA电力网络公司）

作者：Artur Sokolovsky, Bhavik Merai, Moe Jafari, Muen Chen

英文摘要：Electric power networks are increasingly exposed to weather-sensitive failure mechanisms that require asset-level, spatially explicit risk modelling for effective intervention planning. This study contributes a modular, robust, and explainable probability-of-failure (PoF) modelling framework for utility asset management. The central contribution is an asset-level architecture that can be scaled to new environmental data sources and additional PoF types without reworking the underlying pipeline. This is particularly relevant for industry settings, where risk models must remain operationally maintainable while adapting to changing data availability, asset-management priorities, and climate-driven hazard conditions. We demonstrate the framework for vegetation-related and lightning-related failure modes using a harmonised geospatial machine-learning pipeline. The implementation integrates multi-source predictors, including topography (SRTM), vegetation condition (MODIS Normalised Difference Vegetation Index - NDVI), lightning climatology (LIS VHRMC), OpenStreetMap-derived proximity features, and utility operational records. The resulting architecture is computationally efficient, operationally extensible, and suitable for utility-scale deployment. It provides actionable asset-level risk stratification for inspection prioritisation, vegetation management, asset hardening, and resilience planning, supporting earlier intervention and more climate-resilient network operations.

AI 总结：ProxyGuard通过两种模式控制随机数据发布机制的错误，在注册研究中提升了直接模式的功效，且可审计Rice--TVAE等机制。

链接：https://arxiv.org/abs/2608.18643

机构：New York University（纽约大学）； Queens College（皇后学院）

作者：Dipesh Tharu Mahato, Pramod Dhungana

英文摘要：Researchers often choose a proxy dataset from many releases, transformations, or seeds. Search can make an invalid release appear adequate, while one adequate release does not establish that its generator is reliable. ProxyGuard controls both errors using prespecified bounded risks and a sealed target set. Named-release mode corrects for multiplicity and certifies specific releases. Direct shared-target mode evaluates independent mechanism draws on a common target, lower-bounds their favorable-score rate, and subtracts a bound on favorable scores contributed by invalid releases. Conditional on the target, release scores are independent, yielding a finite-sample mechanism-reliability guarantee without independent target batches or assumptions on release-level $p$-value dependence. We show that the mean-only penalty is sharp and derive a smooth-score certificate with additive target concentration. In a registered three-requirement study, direct mode raises power from 5.6\% to 64.2\% at reliability 0.95, while named mode remains stronger under high-signal evidence. Prospective audits span full-pipeline Rice--TVAE, which retrains on every draw, and a non-tabular text mechanism.

AI 总结：本文提出面向可扩展向量架构的FlashAttention-V，将其集成到ggml并在多模型与平台上评估，该方法在预填充、解码阶段均实现显著加速，但Q8_0量化线性层的结构性瓶颈制约了长向量可扩展性。

链接：https://arxiv.org/abs/2608.18656

机构：Chalmers University of Technology（查尔姆斯理工大学）； University of Glasgow（格拉斯哥大学）

作者：Sonia Rani Gupta, Nikela Papadopoulou, Miquel Pericàs

英文摘要：Inference with transformer models on CPUs is increasingly important, especially for Small Language Models (SLMs), where vector architectures are emerging as a promising execution substrate. The attention module is a major bottleneck due to high memory bandwidth requirements; FlashAttention mitigates this by fusing operations to improve data locality and reduce intermediate memory traffic. In this paper, we present FlashAttention-V, a blocked FlashAttention for scalable vector architectures that adapts efficiently from short to very long vectors by exploiting parallelism across attention heads, inter-head packing to enable efficient utilization of vector lengths beyond the head dimension, and improving vector register utilization and memory access locality. We integrate FlashAttention-V into ggml within this http URL and evaluate it on TinyLlama, Llama 3.2, Qwen2.5, and Pythia-410M using gem5 and a Banana Pi BPI-F3. On the Banana Pi BPI-F3, we confirm that loop reordering and loop unrolling across attention heads are effective optimization principles, scaling performance gains with larger models and most pronounced with short contexts and during decoding. Simulation-based analysis shows that FlashAttention-V achieves 22x-42x speedup over scalar FlashAttention at 512-bit VL in prefill, with an additional 2x-2.5x gain scaling to 64 lanes and 4096-bit VL. During decode, FlashAttention-V achieves 8x-11x speedup using 512-bit vector lengths over scalar FlashAttention, with performance showing diminishing sensitivity to vector width and lane count due to single-token, memory-bound execution. We further identify structural bottlenecks in Q8_0 quantized linear layers that limit arithmetic amortization under long-vector execution, consistent across RVV and Arm SVE, indicating that current quantization formats pose a fundamental challenge to long-vector scalability.

AI 总结： 该研究提出RP1方法，将良好搜索规则强化到神经规划器中，可改进多步计划，在多个机器人任务中性能优于手工搜索算法，且效率更高。

链接：https://arxiv.org/abs/2608.18669

机构：Pantheon Industries（万神殿工业公司）

作者：Armin Sommer, Jannik Schilling

英文摘要：Humans solve complex problems by constructing plans and mentally simulating their outcomes with an internal model of the world. Machine learning has produced world models that similarly predict the outcomes of action sequences, but the improvement of candidate plans still isn't fully learned. Current planners are either hand-designed, distilled from a hand-designed optimizer, or learned only to inform an amortized policy rather than to revise the plan itself. We introduce the Reinforced Planning, a method based on the idea that search can be learned by reinforcing good search rules into a neural planner. Our implementation RP1 learns both how to evaluate imagined outcomes through a critic, as well as how to improve multi-step plans through an optimizer trained fully offline from imagined world-model roll-outs. To our knowledge, RP1 is the first method to fully learn how to improve multi-step plans. Furthermore, it can be trained independently of and attached to any pretrained latent world model. Across visual navigation, arm reaching, and robotic manipulation on two world-model backbones, RP1 substantially outperforms hand-designed search algorithms, reaching near-perfect success in several settings while using $1,000 \times$ less world-model rollouts and being up to $67 \times$ faster than the strongest alternative under concurrent planner inference.

AI 总结：本研究对比多种ML分类器在UCI、Kaggle心脏病数据集上的性能，发现SVM在UCI数据集、Simple Cart在Kaggle数据集上表现最优，经调参的ML模型可辅助心脏病早期诊断。

链接：https://arxiv.org/abs/2608.18687

作者：Sami Ullah, Muhammad Mohsin Khan

英文摘要：Heart disease remains the leading cause of mortality globally, necessitating early and accurate detection to improve patient outcomes. This research focuses on the predictive analysis of heart disease using machine learning (ML) techniques, comparing the performance of multiple classifiers to identify the most accurate and least error-prone method. Two datasets from UCI and Kaggle repositories were utilized, each containing 14 attributes related to heart health indicators. Techniques including J48, Naive Bayes, Logistic Regression, Simple Cart, Bagging, Decision Stump, AdaBoost, Artificial Neural Networks, and Support Vector Machine (SVM) were applied. Evaluation metrics such as Mean Absolute Error (MAE), Relative Absolute Error (RAE), accuracy, precision, recall, and F-measure were used for performance comparison. Results revealed that SVM achieved the highest performance on the UCI dataset, while Simple Cart performed best on the Kaggle dataset, offering the highest accuracy and lowest error rates. The research work concludes that ML models, when properly tuned and validated, can significantly assist in the early diagnosis of heart disease, offering critical support for clinical decision-making. Future work may involve hybrid approaches and the use of more recent datasets to further improve prediction accuracy.

AI 总结：本研究运用深度学习预测欧盟27国2030年碳排放，发现其排放量将超目标35%，电力部门减排达标但交通部门进展不足，呼吁加强干预与能源信息建设。

链接：https://arxiv.org/abs/2608.18690

机构：Politecnico di Milano（米兰理工大学）； CMCC Foundation - Euro-Mediterranean Center on Climate Change（CMCC基金会-欧地中海气候变化中心）； RFF-CMCC European Institute on Economics and the Environment（RFF-CMCC欧洲经济与环境研究所）； NOVA School of Science and Technology（NOVA科学技术学院）； NOVA University Lisbon（里斯本NOVA大学）； CENSE—Center for Environmental and Sustainability Research（CENSE环境与可持续发展研究中心）； CHANGE—Global Change and Sustainability Institute（CHANGE全球变化与可持续发展研究所）

作者：Jacopo Ghirri, Carlos Rodriguez-Pardo, Lara Aleluia Reis, Massimo Tavoni

英文摘要：The European Union has committed to reducing greenhouse gas emissions 55% below 1990 levels by 2030, but whether current trends are compatible with this ambition remains uncertain. We apply deep learning to high-resolution socioeconomic and sectoral data across EU27 member states till 2023 to project sectoral CO$_2$ trajectories under current trends, extrapolating observed sectoral momentum without assuming changes in the pace or effectiveness of the policy environment beyond what is already reflected in historical data. We project that EU27 emissions will exceed the 2030 target by 35% (620 Mt CO$_2$ shortfall), with only a small minority of countries on trajectories consistent with the bloc's commitments. While the Power sector achieves target-consistent reductions driven by the renewable transition, Mobility shows minimal progress and accounts for over a third of total emissions by 2030, reflecting a structural inertia across member states rather than geographically concentrated lag. Our findings indicate that substantial additional intervention is required to close Europe's ambition-implementation gap, and call for establishing up-to-date energy information in Europe.

AI 总结：本研究评估SelF-Rocket用于机电故障多类诊断，提出其多变量扩展方法，在两个基准数据集上对比ROCKET类方法，证实该方法的准确率-延迟权衡最优且在挑战性数据集上表现出色。

链接：https://arxiv.org/abs/2608.18716

机构：University of Artois（阿图瓦大学）； LSEE； LGI2A

作者：Mouhamadou Mansour Lo, Mouad Talbaoui, Gildas Morvan, Mathieu Rossi, Fabrice Morganti, David Mercier

英文摘要：Diagnosing faults in rotating machinery is essential for ensuring the reliability of industrial processes. Random convolutional kernel-based Time Series Classification (TSC) methods, such as ROCKET and its variants, provide an attractive trade-off between predictive performance and computational efficiency. In this work, we evaluate SelF-Rocket for the multi-class diagnosis of both mechanical and electrical faults and introduce, as a new contribution, a multivariate extension of the original method. The proposed approach is compared with leading ROCKET-based methods on two public benchmark datasets, MaFaulDa (mechanical faults) and ITSC-UDG (stator inter-turn short circuits), under both univariate and multivariate settings. Experimental results show that SelF-Rocket achieves the best overall accuracy-latency trade-off among the evaluated methods, obtaining the highest classification performance on MaFaulDa while remaining highly competitive on the more challenging ITSC-UDG dataset.

AI 总结：该研究针对潜在世界模型中MPC规划的决策度量对齐问题，提出两种秩一致性诊断指标，开发DA-LeWM模型，验证其可加快收敛并提升在线成功率，改善潜在MPC的几何结构。

链接：https://arxiv.org/abs/2608.18746

作者：Jiawei Wang, Ke Rui, Yushen Zuo, Yichun Feng, Minglei Li

英文摘要：JEPA-style latent world models can use Euclidean distance to a goal latent as the cost for model-predictive control (MPC). Strong decoding of task variables, however, does not guarantee that this particular cost ranks candidate action sequences by real task progress. We call the latter property \emph{decision-metric alignment}. We introduce Plan-Real Spearman, which measures latent--real rank agreement on random plans, and CEM-stage Spearman, which measures the same agreement as cross-entropy-method (CEM) search concentrates its proposal. We analyze sufficient conditions under which latent distance preserves real-cost rankings, identifying encoder distortion, terminal rollout error, and candidate margins as the controlling quantities. Guided by the observed empirical alignment gap, DA-LeWM augments LeWM with inverse-dynamics and demonstration-conditioned goal-action heads. Across all our experiments, DA-LeWM accelerates convergence and achieves higher online success than LeWM, while probe scores remain similar. These results show that action-conditioned objectives improve the geometry used by Euclidean-cost, CEM-based latent MPC.

AI 总结：该研究针对隐私保护协同学习，提出带噪锚点对齐的几何数据扰动方法，在MNIST、CelebA实验中，其隐私-效用权衡优于对私有数据添加噪声的方案。

链接：https://arxiv.org/abs/2608.18749

机构：University of Tsukuba（筑波大学）； Graduate School of Science and Technology, University of Tsukuba（筑波大学大学院理工学研究科）； Institute of Systems and Information Engineering, University of Tsukuba（筑波大学系统情报工程学系）； Center for Artificial Intelligence Research, Tsukuba Institute for Advanced Research (TIAR), University of Tsukuba（筑波大学筑波高等研究院人工智能研究中心）

作者：Keiyu Nosaka, Yamato Suetake, Yuichi Takano, Yukihiko Okada, Akiko Yoshise

英文摘要：Geometric Data Perturbation (GDP) enables one-shot, privacy-preserving collaborative learning: each participant applies a distance-preserving transformation to its private data and uploads only the resulting representation to a central analyst. We study GDP under analyst-participant collusion, in which the analyst combines all uploaded representations with the private data and transformations disclosed by colluding participants to recover a non-colluding participant's private data. Participant-specific independent transformations resist this attack but map participants' data into incompatible representation spaces, degrading downstream model performance. Shared-anchor alignment from Data Collaboration (DC) analysis restores compatibility and improves utility, but we show that disclosing the DC anchor matrix enables exact recovery of non-colluding participants' private data even in the presence of collusion. Adding noise directly to the private-data representations mitigates this vulnerability but substantially reduces utility. We propose adding noise to the anchor representations instead. Each participant independently transforms its private data and the shared anchor matrix, perturbs only the resulting anchor representation, and uploads both representations in a single round. Using the noisy anchor representations, the analyst aligns the private-data representations by solving a Generalized Orthogonal Procrustes Problem. We characterize alignment and recovery errors, specialize a conservative sufficient condition for convergence of the alignment to our setting, and analyze three recovery attacks. Experiments on MNIST and CelebA show that, across the evaluated attacks and deployment settings, anchor noise achieves higher learning accuracy than private-data noise at comparable measured leakage, yielding a more favorable privacy-utility trade-off under the specified collusion model.

AI 总结：该研究提出解释一致性得分（ECS）作为公平性感知指标，以糖尿病视网膜病变筛查为案例，发现不同族裔群体预测性能有差异但解释一致性较高且与性能差异无显著关联，说明预测公平性与解释一致性是模型行为的互补维度，推动公平性评估拓展至预测性能之外。

链接：https://arxiv.org/abs/2608.18759

机构：Hertie Institute for AI in Brain Health（赫蒂脑健康人工智能研究所）； University of Tübingen（蒂宾根大学）； Tübingen AI Center（蒂宾根人工智能中心）

作者：Kerol Djoumessi, Philipp Berens

英文摘要：Fairness in medical imaging is commonly evaluated through subgroup performance metrics, yet it remains unclear whether models rely on consistent visual evidence across demographic groups. This work introduces the Explanation Consistency Score (ECS), a fairness-aware metric based on Jensen-Shannon divergence that quantifies the similarity of attribution maps across subgroups. Using diabetic retinopathy screening as a case study, ECS is evaluated globally and within disease severity. Experiments reveal that while predictive performance differs across ethnic groups, explanation consistency remains relatively high and shows no significant association with performance disparities. These findings suggest that predictive fairness and explanation consistency capture complementary dimensions of model behavior, motivating fairness evaluations that extend beyond predictive performance.

AI 总结：该研究针对AI对齐中服务不足用户的问题，提出CurriPO方法，通过构建树状课程设置适配多样化用户目标，在个性化连续控制任务上使群体满意度达最强基线的1.2-2.1倍且缩短训练时间。

链接：https://arxiv.org/abs/2608.18770

作者：Taehyung Kim, Jongeun Choi

英文摘要： Learning a reward model from human feedback and optimizing a policy against it is one approach to aligning AI systems with individual users. From a fairness perspective, existing work improves such alignment by developing data-efficient and accurate reward models that capture minority preferences despite scarce data. We push this line of inquiry one step further and argue that data-efficient and accurate per-user reward models are not sufficient: users whose reward models are difficult to \textit{optimize} at the policy level can become a new underserved group. We start from the observation that one user's reward model can be easy to optimize from the initial policy while another's is not. We argue that, given a sufficiently diverse user population, a curriculum naturally emerges between easy- and hard-to-optimize reward models. Building on this insight, we propose CurriPO, which grows a tree-structured curriculum to accommodate diverse user-specific objectives, covering the population in a single traversal. Specifically, CurriPO automatically constructs a curriculum over diverse user reward models, allowing it to branch from the existing curriculum and reuse reward models previously incorporated into the curriculum. To the best of our knowledge, this is the first work to explicitly exploit multi-user structure to address optimization in AI alignment. Extensive experiments on personalized continuous control in a simulated environment show that CurriPO achieves $1.2$--$2.1\times$ the population satisfaction of the strongest baseline while substantially reducing training time. Additional analysis attributes much of this improvement to the users left underserved by conventional optimization.

AI 总结：该研究提出新型图生成框架GraphK，通过编码器-采样器-解码器结构及KDTree边预测实现可变大小图生成，在合成与真实数据集上性能优于现有方法。

链接：https://arxiv.org/abs/2608.18777

机构：Ataturk University（阿塔图尔克大学）； Istanbul Technical University（伊斯坦布尔理工大学）； Memorial University（纪念大学）

作者：Resul Tugay, Eren Oluğ, Elif Ak, Sule Gunduz Oguducu

英文摘要：Graph generation models have advanced significantly with deep learning, yet they remain limited in scalability, flexibility, and ability to model underlying structures. We present GraphK, a novel encoder-sampler-decoder framework for graph generation that overcomes these challenges through structural flexibility and computational efficiency. Unlike autoregressive approaches constrained by vocabulary size (i.e. number of nodes in graph generation), GraphK allows for both upscaling (generating graphs with more nodes than the input) and downscaling, providing a flexible control over output graph size. By learning permutation-invariant latent representations and sampling new node embeddings via maximum likelihood estimation, GraphK generalizes across graph sizes and structures. For edge generation, we employ edge prediction with a KDTree-based top-k neighbor search in the latent space, reducing computational cost. Based on the manifold smoothness assumption, our method effectively captures graph properties. Experiments on synthetic and real-world datasets show that GraphK outperforms existing methods, accurately learns graph structures, and generates synthetic graphs without explicit definitions.

AI 总结：该研究提出重复优化器重采样（ROR）方法，在单次训练中搜索最优优化器，仅需穷举训练的24%-35%量，即可在多任务上接近最优固定优化器性能，实现高效自适应优化器选择。

链接：https://arxiv.org/abs/2608.18810

机构：insureAI； ETH Zürich（苏黎世联邦理工学院）

作者：Ronald Richman, Mario V. Wüthrich

英文摘要：An optimizer is usually chosen before training a deep neural network and then kept fixed. Treating optimizer choice as a hyperparameter could boost performance, but it requires several complete training runs and discards all but the winner. Repeated Optimizer Resampling (ROR) instead searches during one evolving run. Every $b$ epochs, each candidate optimizer scouts from the current model weights for $s$ epochs. The best scout continues for the remaining $b-s$ epochs, and that completed segment becomes the new incumbent if it improves the validation objective. This design allows the preferred optimizer to change as training progresses. We compare two variants of ROR on MNIST, Fashion-MNIST, and two motor insurance claim-count models. Nine fixed optimizers and both ROR variants are evaluated with the same ten seeds. One-epoch ROR uses 24\% to 35\% of the aggregate training needed to identify the best fixed optimizer exhaustively and remains close to that optimizer on all four tasks. These results support short scouting as a practical way to search over optimizers without completing every candidate run.

AI 总结：该研究针对40例患者，对比不同图拓扑的图学习模型，发现Region-Bridge-$c$拓扑在致痫灶定位中表现最优，证明图构建需明确评估。

链接：https://arxiv.org/abs/2608.18887

机构：University of Cincinnati（辛辛那提大学）； Cincinnati Children’s Hospital Medical Center（辛辛那提儿童医院医疗中心）

作者：Daniel Wendelken (1), Brian Ervin (2), Ravindra Arya (2), Ali A. Minai (1) ((1) University of Cincinnati, Cincinnati, USA, (2) Cincinnati Children's Hospital Medical Center, Cincinnati, USA)

英文摘要：The epileptogenic zone (EZ) is the brain region that generates seizures in an individual, and is the target of epilepsy surgery. Localizing the EZ from stereo-EEG (sEEG) recordings supports surgical planning, but manual interpretation is time-consuming and focuses on seizure recordings. Graphical learning models of resting-state functional connectivity among the recorded brain regions are an attractive alternative, but depend crucially on the network topology chosen for the model. We present a controlled study of graph-based models to explore how graph topology affects EZ localization from resting-state sEEG in 40 patients. Using the same simple learnable model and leave-one-patient-out evaluation, we compare dense graphs, anatomy- and geometry-informed priors, budgeted sparsification methods, and learned sparsification, including the proposed Region-Bridge-$c$ topology. To compare graph constructions fairly, we control the number of incoming edges per node and vary graph sparsity. At $\approx 30\%$ edge retention, Region-Bridge-$c$ achieves the highest observed mean PR-AUC ($0.371\pm0.015$; ROC-AUC $0.743\pm0.010$) while using $\approx 69\%$ fewer edges than Dense (PR-AUC $0.349\pm0.014$). Spatial-$k$ is competitive, whereas random pruning requires near-dense retention. Learned sparsification benefits from anatomical node metadata but, on average, does not surpass the best fixed prior. Across all topologies, the best choice varies by patient. These results suggest that graph construction should be evaluated explicitly rather than treated as fixed preprocessing.

AI 总结：该研究分析难解优化问题算法的有限尺寸行为，发现其收敛到理论界的过程极为缓慢，中间情形下局部算法性能优于渐近预测，表明复杂算法设计仍具重要性。

链接：https://arxiv.org/abs/2608.18910

机构：LAAS–CNRS； Universidad de San Andrés（圣安德烈斯大学）； SISSA（国际高等研究学院）； International Center for Theoretical Physics（国际理论物理中心）

作者：Ali Hussaini Umar, Jean Barbier, Matthieu Jonckheere, Manuel Sáenz

英文摘要：Hard combinatorial optimization problems, many of which are NP-hard, present fundamental algorithmic challenges. Average-case analysis on random instances has emerged as a powerful framework for understanding typical algorithmic performance beyond worst-case guarantees. A substantial body of work has established negative results: for sufficiently hard instances (often controlled by the underlying graph connectivity/constraints density), no known polynomial-time algorithm can significantly outperform naive heuristics in the double asymptotic limit where both problem size and constraints density tend to infinity. We revisit this picture by studying the finite-size behavior of some optimization algorithms across easy, intermediate, and hard regimes. Through rigorous analysis of large-graph asymptotics combined with numerical experiments on canonical problems (maximum independent set and maximum $K$-SAT), we demonstrate that while algorithms do eventually converge to theoretically predicted bounds, this convergence can be remarkably slow. In the intermediate regime where instances are already highly constrained, local algorithms achieve solutions substantially better than their predicted performance in the high-constraint-density limit. This gap between finite-regime and asymptotic behavior has important practical implications: sophisticated algorithmic design remains crucial even when asymptotic theory predicts inevitable failure.

AI 总结：该研究提出CDSP流水线将投资委员会会议记录转化为金融特征，经实验其结合句子嵌入与CDSP特征的模型预测准确率达73%，证实专家审议含前瞻性金融信息。

链接：https://arxiv.org/abs/2608.18911

机构：Franklin Templeton Investments（富兰克林邓普顿投资公司）； Blend360（Blend360公司）； Santa Clara University（圣克拉拉大学）

作者：Vivek Batra, Kristin Chen, Sanjiv Das, Samuel Judge, Harshad Khadilkar, Sukrit Mittal, Amir Nasrollahzadeh, Daniel Ostrov, Jacob Sisk

英文摘要：We introduce the CDSP (context-conditional deliberation signal pipeline), converting an investment committee's meeting transcripts into structured predictive features. CDSP segments the meeting transcripts into topical chunks, assigns asset-class context labels using a large language model (LLM), maps financial keywords to a pre-determined taxonomy of labels, and constructs complementary features: sentiment polarity and mention frequency. This feature engineering framework is applied to a dataset spanning 48 monthly committee meetings to predict if global equities will perform better or worse than global bonds in the following month. In experiments with engineered features, raw transcript text, sentence embeddings, and combined representations, the prediction accuracy ranges from 62% to 73%, compared to always choosing stocks, which outperforms bonds 60.4% of the time. The best (73% accurate) model combines sentence embeddings with engineered CDSP features, achieving a 0.73 F1 score (although this is not statistically significant compared to always choosing stocks). Sentiment carries a stronger signal than mention frequency for several taxonomy categories. These findings suggest that experts' deliberations may contain forward-looking information that context-aware NLP can extract.

AI 总结：针对跨网络因果效应迁移的空白，提出TranCE双重鲁棒算法，经半合成基准与真实实地实验验证，可有效估计存在干扰时跨网络的可迁移因果效应。

链接：https://arxiv.org/abs/2608.18932

作者：Xiaojing Du, Jiuyong Li, Lin Liu, Debo Cheng, Jixue Liu, Thuc Duy Le

英文摘要：Estimating causal effects under network interference typically assumes that the network used for training and the network used for deployment coincide. In practice, an intervention is run on one population while the question of interest concerns a different population, and the two generally differ in topology, node-covariate composition, and spillover pathways. Transporting a causal effect across networks is therefore a data-fusion problem that no existing algorithm solves. We employ a selection diagram, extended to the network setting so that covariate shift and structural network shift enter as separate selectors, and derive from it a transport formula for the direct, spillover, and total effects in the deployment population. Each formula makes explicit which interventional mechanism is assumed invariant and which observational distribution must be reweighted. We then turn the formulas into TranCE (Transported Causal Effects), a doubly-robust algorithm combining an interventional outcome model, a domain density-ratio correction, and cross-fitted inference. Extensive experiments on two semi-synthetic benchmarks derived from real-world social networks and on a fully real weather-insurance field experiment, where the transported effects are checked against held-out randomized estimates, confirm the effectiveness of our approach. Our findings have the potential to improve intervention strategies in networked systems, particularly in social networks and public health.

AI 总结：该研究提出改编自Penrose张量表示法的图形符号，可直观呈现可解释AI架构的全局视图并与PyTorch einsum代码一一对应，还绘制了Steerling-8B的架构图并转换为代码。

链接：https://arxiv.org/abs/2608.18936

机构：IBM Research（IBM研究院）

作者：Pietro Barbiero

英文摘要： Designing, implementing, and comparing interpretable architectures requires a formal language to represent them. The most common representations fall short in one of two ways. Symbolic equations give no global view of an architecture at a glance. Probabilistic graphical models and flowcharts do not describe actual tensor manipulations, thus hiding key insights and limiting reproducibility. To close this gap, we introduce a graphical notation for designing interpretable AI architectures, adapted from Penrose tensor notation. This graphical notation gives a global view of an architecture and maps one to one onto PyTorch einsum code. We first use this notation to describe architectures that are interpretable by construction, including concept bottlenecks, sparse probes, prototype networks, neural additive models, and mixtures of linear models. We then diagram the key architectural components of Steerling-8B, a frontier interpretable language model. The diagram yields global insights into the architecture (e.g., showing that Steerling is a residual model), a geometric interpretation of each individual operation, and a direct translation into 33 lines of PyTorch code.

AI 总结：该研究针对单步逆合成的一对多特性，提出Top-K提示范式，构建超大规模反应数据集训练C3LM，结合特定奖励机制在基准上达最优性能，为逆合成系统提供新方向。

链接：https://arxiv.org/abs/2608.18940

机构：Insilico Medicine AI Limited（英矽智能人工智能有限公司）； Insilico Medicine Canada Inc.（英矽智能加拿大公司）； Insilico Medicine Hong Kong Ltd.（英矽智能香港有限公司）

作者：Bogdan Zagribelnyy, Ivan Ilin, Nikita Bondarev, Maksim Kuznetsov, Mathieu Reymond, Vladimir Aladinskiy, Alex Aliper, Alex Zhavoronkov

英文摘要：Single-step retrosynthesis is a central component of computer-aided synthesis planning, yet its intrinsically one-to-many nature is poorly captured by single-answer evaluation and benchmarking protocols. To address this, we introduce Top-K prompting as a robust training and inference paradigm to better capture diverse, plausible reaction predictions. We compile CREED-CCV-2+USPTO-XL, an ultra-large-scale dataset of ~45.6 million verified reactions to train the C3LM (Chemistry Constraint-Consistent Language Model). By integrating fine-tuning with ChemCensor-based and novelty-oriented rewards, our model achieves state-of-the-art performance on the OOD URSA-expert-2026 benchmark. Further analysis of reaction uniqueness shows that LLMs and conventional models explore complementary reaction spaces, motivating ensemble-based retrosynthesis systems. Overall, our results establish Top-K, plausibility-aware training as a practical new direction for robust future LLM-based synthesis planning.

AI 总结：本研究针对PPG信号肤色分类准确率低的问题，采用模糊准确率结合三种机器学习方法，发现PPG信号可在1类误差内准确预测肤色，为肤色与PPG信号的关联提供了有力证据。

链接：https://arxiv.org/abs/2608.18969

机构：National Physical Laboratory（国家物理实验室）； Mittelhessen University of Applied Sciences（中黑森应用科学大学）； Institute of Metrology of Bosnia and Herzegovina（波斯尼亚和黑塞哥维那计量研究所）

作者：Padmini Krishnadas, Urs Hackstein, Alen Bosnjakovic, Philip J. Aston

英文摘要：We consider the problem of classification of skin tone using photoplethysmography (PPG) signals with labels of the ordinal six-class Fitzpatrick skin tones. A typical accuracy for this task is a poor 40-55 %. However, the labels are subjectively determined by comparing the skin with a colour chart, and hence contain widespread small-scale inaccuracies. By working with a "fuzzy accuracy", which deems a prediction of skin tone class to be correct if its difference from the labelled class is not greater than one, much higher accuracy is obtained which provides more convincing evidence that skin tone can be accurately predicted from PPG signals. Three machine learning approaches were used, namely deep learning or tree-based approaches on raw PPG signals, deep learning on image representations of the signals generated by the Symmetric Projection Attractor Reconstruction (SPAR) method, and machine learning on features extracted from the signals. The first method also employed a fuzzy version of the cross entropy loss function, which gave the best results. Tree-based models on raw signals give accuracies up to 55 % and higher fuzzy accuracies up to 96 %, while deep learning models on the SPAR images obtained lower results of 44 % accuracy and 85 % fuzzy accuracy. The machine learning on PPG features gave similar results to the SPAR method with accuracy of 42 % and fuzzy accuracy of 87 %. We have shown that classification of skin tone using PPG signals is possible with high fuzzy accuracy which implies that our modelling approach enables accurate prediction of skin tone class within at most one class of the observer's choice of class, from which we conclude that PPG signals are affected by skin tone in a discernible way.

AI 总结：该研究针对S-JEPA，通过两个对照实验发现，软目标的非最大概率到GMM分量的映射对编码器表示有显著影响，而非仅概率结构决定表示。

链接：https://arxiv.org/abs/2608.19084

作者：Wenxuan He, Yunpeng Li, Shan Liang

英文摘要：S-JEPA uses soft Gaussian mixture model (GMM) posteriors instead of hard cluster labels to preserve uncertainty. It remains unclear whether the probability values alone are sufficient, or whether it also matters which GMM components receive the non-maximal probabilities. We test this with two matched controls. FIXED-RANDPERM keeps the top-1 component and probability together with the multiset of non-maximal probability values, but reassigns those non-maximal values using a mapping fixed for each physical frame. UNIFORM-TAIL keeps the top-1 component, its probability, and total non-maximal mass but distributes that mass uniformly. Across three independent seeds, REAL SOFT outperforms both controls on two frozen Encoder readouts. It provides better recovery of the original GMM tail and greater accessibility of spectral dynamics over short time scales after controlling for the complete spectrum of the current frame. In two exposure experiments, both readouts improved overall as more frames retained the original mapping. We also descriptively follow one Phase 2 trajectory after the switch to the online GMM. These results show that the numerical probability structure of the soft target does not fully determine the learned Encoder representation. The mapping of non-maximal probabilities to GMM components also matters.

AI 总结：该研究将梯度提升集成的叶值视为坐标，提出精确对比解释方法，构建的追索方法在表格数据集上精度高，在信用数据集上表现优于基线，且能生成可执行的建议。

链接：https://arxiv.org/abs/2608.19127

作者：Emanuele Luzio

英文摘要： A gradient-boosted ensemble predicts by summing one leaf value per tree. Read those values as coordinates rather than as intermediate results, and every instance becomes a point in R^M on which the model acts linearly: the score is the sum of the coordinates. This small change of view makes contrastive explanation exact. The difference between two instances is a vector that is identically zero wherever they share a leaf, so the gap between a rejected applicant and an accepted one is carried by a handful of coordinates, each traceable to a real split in a real tree. Nothing is fitted, sampled, or assumed additive in features -- the additivity is already there, in the right space. We build a recourse method on this representation and evaluate it on five tabular datasets under repeated cross-validation. Its recommendation reconstructs the model's own decision to 6.2 x 10^-15, so an auditor can re-check the arithmetic without the model. On the credit datasets it is Pareto-non-dominated on effort against realism. And when recommendations are restricted to changes the subject could actually make -- not their age, not a settled delinquency -- it retains 58% of its validity where the strongest baseline retains 41%, a distinction the standard evaluation cannot see because it never asks whether a recommendation can be carried out.

AI 总结：针对少重复脑-图像检索精度骤降问题，本文提出NEAR框架，通过锚定神经与视觉表征实现性能提升，减少对重复采集的依赖，逼近实际部署要求。

链接：https://arxiv.org/abs/2608.19128

作者：Zhenyao Cui, Siyuan Kan, Dingkun Liu, Dongrui Wu

英文摘要：Decoding visual information from brain signals probes neural representations and enables neuro-rehabilitation and dream decoding. Recent brain-to-image retrieval approaches have achieved promising performance, typically by averaging many (up to 80) neural trials per image, requiring repeated stimulus presentation that increases latency, cost, and user burden. When only one or a few repetitions are available, the retrieval accuracy drops sharply. This drop is commonly attributed to query noise because averaging suppresses noise and increases signal stability. However, we find a non-transitive alignment pattern: the low-repetition query signal and the image representation each align with the high-repetition center, but not directly with each other. This pattern shows that query noise is only part of the problem and that gallery placement also affects retrieval. We therefore propose a neural-anchor-based retrieval (NEAR) framework that treats the high-repetition center as an anchor and approaches it from both sides: a denoiser pulls the noisy query toward the true anchor, and a small network predicts each candidate's pseudo anchor from its image and pulls the image toward it. Across four datasets spanning EEG, MEG and fMRI, NEAR consistently improved retrieval in the few-repetition regime. On THINGS-EEG2, it improved 200-way Top-1 accuracy by 5.7 and 9.3 percentage points respectively, when averaging one and four repetitions. By anchoring neural and visual representations, NEAR reduces reliance on repeated acquisition and brings neural retrieval closer to real-world deployment.

AI 总结：本研究针对无标签跨主体EEG到图像检索性能差的问题，提出SCORE框架，通过源训练与部署时坐标对齐，在两个基准上显著提升检索准确率，推动脑视觉解码的实际应用。

链接：https://arxiv.org/abs/2608.19134

作者：Zhenyao Cui, Siyuan Kan, Siyang Li, Ziwei Wang, Dongrui Wu

英文摘要：Accurate visual decoding can reveal how the brain represents visual information and recover perceived content from neural signals such as electroencephalography (EEG), with potential for neural communication. However, current EEG-to-image retrieval methods perform far below their within-subject counterparts for new users without labeled calibration, limiting real-world deployment. To understand this gap, we analyze EEG features across subjects and find that different subjects preserve similar relationships among concepts but express them along different coordinate directions. We therefore propose Subject Coordinate Recovery (SCORE), a target label-free framework combining recovery-aware source training with coordinate alignment at deployment. During training, SCORE aligns source subject EEG with a common image space and simulates unseen-subject recovery through source-only episodes. At deployment, with both encoders frozen, SCORE selects reliable EEG-image landmarks through hubness-corrected matching and estimates an orthogonal transformation to recover target EEG coordinates without source data or target labels. In 200-way retrieval on two public benchmarks, SCORE outperforms the unadapted baseline for every target subject and achieves the best overall accuracy. It reaches 53.23%/83.55% and 12.01%/32.16% Top-1/Top-5 on THINGS-EEG2 and Alljoined-1.6M, respectively, surpassing the strongest baselines by 17.45/15.70 and 3.08/4.62 percentage points. Without target labels or encoder updates, SCORE brings brain-based visual decoding closer to robust, practical, low-latency deployment across users.

AI 总结：本研究通过对32个GPT-2模型的小规模预训练反事实实验，测量单示例注入对模型的短期影响，发现该影响会在训练后期衰减，且未检测到长期显著差异。

链接：https://arxiv.org/abs/2608.19168

机构：Arizona State University（亚利桑那州立大学）； Williams College（威廉姆斯学院）

作者：Zachary Speck, Asa Shepard

英文摘要： A single training example's contribution to a finished model is normally estimated rather than measured, because measuring it takes two expensive full pre-training runs that differ in one row of one batch. We ran that counterfactual 24 times at a small scale. We trained 32 GPT-2 models at 124M parameters from scratch on OpenWebText, over four conditions and eight seeds. At step 200 of 9,536, at peak learning rate, we replaced one row of a 256-row batch with a fixed context injection carrying a 194-token passage. The three injected conditions are: 1. fluent prose with a corpus-attested subject, 2. fluent prose with a fabricated subject matched to it within 0.14% on full-batch gradient delta, and 3. random keyboard characters. The fourth condition is an uninjected twin. The passage is learned from one exposure and then decays. Fifty steps after injection, the arm that saw a passage predicts it better than the arm that did not by 0.039 and 0.044 nats of cross-entropy on the passage, at eight of eight seeds with p < $10^{-4}$. At the final step we do not detect that difference for either passage, at p = 0.25 and p = 0.71, against minimum detectable effects of 0.025 and 0.079 nats, nor between the two passages, at p=0.54. Every geometric measure we report is taken after that decay. Our pre-registered contrast on interpolation loss barrier is +0.0068 with p = 0.509, against a minimum detectable effect of 0.032 barrier units. Held-out cross-entropy is $-0.00044$ with p = 0.310. Per-layer centered kernel alignment does not detectably separate any condition at any layer. Weight displacement reaches 44.1% of the seed-to-seed Euclidean distance and is 92% settled by the midpoint of training, while the barrier reaches 3.0% of the seed-to-seed barrier. Those two figures sit roughly 15 times apart, and that is a lower bound. The injection relocates the model within its basin without moving it out.

AI 总结：该研究针对长上下文推理中 OPD 的教师-验证器分歧问题，提出 GC-OPD 方法，结合验证器结果优化 OPD，在五个长上下文基准上显著提升 Qwen3 模型性能。

链接：https://arxiv.org/abs/2608.19181

机构：Tsinghua University（清华大学）； Beijing University of Posts and Telecommunications（北京邮电大学）； OpenBMB

作者：Zhu Zhang, Jixun Wang, Xiaoang Xu, Xiaorong Wang, Zihan Zhou, Zhiyuan Wang, Shuo Wang, Chaojun Xiao, Yuezhi Zhou

英文摘要：On-policy distillation (OPD) trains a student on its own responses using dense token-level guidance from a stronger teacher. In long-context tasks, however, token-level teacher support can favor locally plausible responses that omit evidence distributed across the input or violate global task constraints. Task-specific verifiers, in contrast, evaluate task completion at the response level and may return graded rewards that reflect partial success. We diagnose this mismatch on fixed responses from two representative long-context evidence-aggregation tasks. Across longer input ranges, trajectory-level OPD scores become progressively less aligned with verifier rewards, indicating teacher-verifier disagreement. Motivated by this observation, we introduce Group-Calibrated On-Policy Distillation (GC-OPD). GC-OPD separately normalizes verifier rewards and trajectory-level OPD scores within each rollout group and uses their difference as a signed teacher-verifier disagreement residual. Relative-advantage-based credit assignment (RACA) distributes this trajectory-level residual across tokens according to their relative OPD advantages while preserving the original OPD signal. Across five long-context benchmarks, post-training with GC-OPD raises the five-benchmark averages of the official Qwen3-4B and Qwen3-8B checkpoints from 29.08 to 40.47 and from 35.12 to 44.65, respectively. Vanilla OPD reaches 39.31 and 43.56 under the same setup. Controlled ablations show that the signed residual is more effective than either an additional OPD-derived term or direct group-normalized verifier reward addition, while RACA further improves over uniform token allocation. Together, these results demonstrate that group-relative residual calibration can incorporate verifier outcomes without discarding dense token-level guidance. Code is available at this https URL.