机器学习学术速递[8.17]

AI 总结：本文提出激活剪枝融合框架APM，通过激活引导选择源模型的显著组件并注入目标模型，无需训练和显式语义对齐，在16个基准上将3B目标模型平均准确率从55.5%提升至60.6%。

链接：https://arxiv.org/abs/2608.13596

作者：Jiahe Fan, Si Chen, Yinghao Hou, Aiyuan Zhang, Hong Xie

英文摘要：Heterogeneous model fusion seeks to combine models that differ in tasks, initializations, architectures, or scales. We study an underexplored cross-scale setting: improving a small recipient language model with a stronger donor despite substantial architectural mismatch. We ask whether useful capabilities can be transferred without explicit neuron-wise semantic alignment. Building on the observation that truncating a large model to a smaller architecture and injecting it with a tiny mixing weight can already improve the recipient, we propose Activation-Prune-Merge (APM), an activation-guided framework for cross-scale fusion. APM constructs task-conditioned activation maps on the donor, selects salient layers, hidden dimensions, attention heads, and MLP neurons to prune it to the recipient architecture, and injects the resulting donor slice into the original recipient using a micro interpolation coefficient. This formulation treats the donor as a source of concentrated functional components rather than requiring precise structural transplantation. Across 16 benchmarks spanning reasoning, mathematics, code generation, instruction following, and classification, APM improves the overall average accuracy from 55.5% to 60.6% over the original 3B recipient. RTE accuracy increases from 64.3% to 82.3%, QNLI from 52.3% to 65.7%, and BoolQ from 70.8% to 79.2%. Analyses of injection ratios and sequential multi-stage fusion further suggest that activation-guided extraction improves the quality of the transferable donor slice while preserving the small-ratio fusion regime. These results provide evidence that cross-scale heterogeneous fusion can succeed without explicit semantic alignment when the donor contribution is sufficiently concentrated and carefully selected.

AI 总结：针对带在线请求的动态多车场车辆路径问题，提出事件驱动的Transformer深度强化学习框架，经多场景基准测试，该学习策略在部分指标上弱于最强启发式算法，无单一方法在所有维度最优。

链接：https://arxiv.org/abs/2608.13799

机构：Louisiana State University（路易斯安那州立大学）

作者：Faezeh Ardali, Gerald M. Knapp

英文摘要：This paper presents an event-driven learning and benchmarking framework for the Dynamic Multi-Depot Vehicle Routing Problem with progressively revealed requests and evolving vehicle states. Masked MLP and Transformer policies are trained through behavior cloning and proximal policy optimization. Deterministic feasibility masking prevents invalid vehicle--request assignments, while fixed-prefix/flexible-suffix route commitments protect completed, active, and near-term decisions and separately measure vehicle reassignment and resequencing. The learned policies are compared with dynamic insertion heuristics and time-limited rolling-horizon optimization. In a 20-scenario policy benchmark, all methods completed every request without invalid actions, but nearest feasible achieved the lowest mean objective and outperformed the learned policies in routing quality, waiting time, stability, makespan, and runtime. Across five independent training runs, PPO had little average effect on the MLP and improved the Transformer on average, although with greater seed variability. Under the common protocol, nearest feasible achieved the lowest combined objective and route disruption, whereas rolling horizon achieved the lowest waiting times and makespan at substantially higher computational cost. The learned policies retained millisecond-level decisions and transferred to instances with up to 80 requests without retraining, but did not outperform the strongest heuristic. No single method was best across routing efficiency, service responsiveness, stability, and online computation.

AI 总结：针对联邦多模态医疗AI的客户端与样本级模态异质性问题，提出MedMix框架，通过模态上下文感知路由、共识引导路由对齐与客户端自适应专家聚合，在多模态医疗数据集上取得最优平均F1值，严重异质性下提升显著。

链接：https://arxiv.org/abs/2608.13911

机构：KAIST（韩国科学技术院）； NTU Singapore（新加坡南洋理工大学）

作者：Adiba Orzikulova, Dong Min Kim, Jaehong Yoon, Sung-Ju Lee

英文摘要： Federated multimodal medical AI faces modality heterogeneity at both the client and sample levels: clients may systematically lack access to specific modality types, while individual records within the same client may contain different partial modality subsets. Sparse Mixture-of-Experts (MoE) architectures are a promising remedy for modality-adaptive computation, but their use in federated learning is fragile under cross-client modality heterogeneity, where locally learned routing policies can diverge across clients and drive experts toward incompatible specializations. Different clients may assign the same observed modality configuration to different experts, or train similarly indexed experts on different missing-modality configurations, causing standard aggregation to misalign or overwrite the expert specialization that sparse MoEs are intended to learn. To address this challenge, we propose MedMix, a semantic-alignment framework for federated multimodal sparse MoEs that coordinates cross-client routing and expert specialization using modality context. At the client side, MedMix uses modality-context-aware routing to guide expert selection using each token's modality identity, position, and incompleteness context. Across clients, it uses consensus-guided routing alignment to construct server-side consensus anchors for shared modality patterns and align local routing distributions across clients. Complementing these routing mechanisms, client-adaptive expert aggregation leverages client-specific modality-pattern prototypes to match and aggregate functionally similar experts across clients. Experiments on real-world multimodal medical datasets show that MedMix achieves the best average F1 across diverse modality heterogeneity and modality incompleteness settings, with especially clear gains under severe heterogeneity.

AI 总结：该研究针对联邦生物信号学习的隐私与效率挑战，提出混合量子启发式柯尔莫哥洛夫-阿诺尔德网络（HQKAN），在两类心电数据集上较MLP实现参数与通信成本降低，且分类性能更优。

链接：https://arxiv.org/abs/2608.13914

机构：National Taiwan University（台湾大学）； National Center for High-Performance Computing（国家高速计算机中心）； National Institutes of Applied Research（应用研究院）； Brookhaven National Laboratory（布鲁克海文国家实验室）； Korea Advanced Institute of Science and Technology（韩国科学技术院）； Beth Israel Deaconess Medical Center（贝斯以色列女执事医疗中心）； Harvard University（哈佛大学）； National Yang Ming Chiao Tung University（国立阳明交通大学）； National Center for Theoretical Sciences（国家理论科学中心）

作者：Chun-Hua Lin, Samuel Yen-Chi Chen, Yu-Chao Hsu, Kuo-Chung Peng, Jiun-Cheng Jiang, Chi-Sheng Chen, Tai-Yue Li, Nan-Yow Chen, En-Jui Kuo, Hsi-Sheng Goan

英文摘要：Electrocardiogram (ECG) recordings are sensitive biomedical data, limiting the ability of hospitals and wearable devices to share raw signals for centralized model training. Federated learning addresses this practical privacy constraint by enabling collaborative model training while keeping raw biosignal data at their respective sources. However, federated ECG classification remains challenging due to limited client-side samples, imbalanced arrhythmia labels, and non-independent and identically distributed (non-IID) data across clients. These constraints require classifiers that are both communication-efficient and robust to cross-client distribution shifts. In this work, we evaluate a hybrid quantum-inspired Kolmogorov-Arnold network (HQKAN) against a multilayer perceptron (MLP) for five-class arrhythmia classification on the MIT-BIH dataset and three-class classification on the INCART dataset under federated averaging (FedAvg). Across multiple client configurations, HQKAN improves most aggregate and minority-class metrics while using 37.35% fewer trainable parameters and reducing communication cost by 24.89% on MIT-BIH; on INCART, it achieves corresponding reductions of 44.81% and 36.41%. These results indicate that HQKAN offers a compact, communication-efficient and robust alternative to the MLP baseline for privacy-aware federated learning on biosignal data.

AI 总结：针对小批量解码下MoE模型专家权重加载的瓶颈，提出DeaMoE架构，通过专家分组共享参数与两阶段路由策略提升效率，在多款模型及显卡上实现显著速度提升。

链接：https://arxiv.org/abs/2608.14385

机构：University of Science and Technology of China（中国科学技术大学）； Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）； Shanxi University（山西大学）

作者：Zewen Jin, Shen Fu, Zeping Duan, Shannon Wang, Weihao Wu, Chengjie Tang, Congkun Ai, Ping Gong, Zijian Dai, Youhui Bai, Cheng Li

英文摘要：Mixture-of-Experts (MoE) models have been widely adopted in real-time interactive applications such as coding assistants, real-time audio-video interaction systems. To meet the extremely low response latency requirements of these scenarios, practitioners commonly employ small-batch decoding, under which MoE inference becomes memory-bound and is severely bottlenecked by expert weight loading. However, this bottleneck has received limited attention, and existing solutions such as post-training weight compression or fine-grained expert design during pre-training either degrade model accuracy or introduce additional computation and communication overhead. To tackle this issue, we propose DeaMoE, a decoding-efficient MoE architecture, in which the experts are grouped into several departments, and the experts belonging to the same department share most parameters since they come from the same professional field, and additionally each expert contains a few private parameters to reflect its uniqueness. Moreover, we design customized two-stage routing strategy for DeaMoE to avoid redundant loading, under which DeaMoE greatly improves the efficiency during LLM decoding. Compared with vanilla MoE, DeaMoE reduces per-step loaded weights by up to 50.9% and achieves up to 1.33 end-to-end TPOT speedup for the pre-trained 7B model on A40, and up to 2.00x and 1.97x peak speedup for DeepSeek-V3 on A40 and H100 in microbenchmarks.

AI 总结：本研究提出基于神经元门控与混合激活的NAS方法，通过连续松弛优化架构空间，在MNIST、CIFAR-10上实现紧凑架构的高性能，优于DARTS，可优化过度参数化架构。

链接：https://arxiv.org/abs/2608.14443

机构：IIT Kanpur（印度理工学院坎普尔分校）； IIM Ahmedabad（印度管理学院艾哈迈达巴德分校）； Krishnamurthy Tandon School of AI（克里希纳穆尔蒂坦登人工智能学院）

作者：Abhishek Shukla, Ankur Sinha, Faiz Hamid

英文摘要： Neural Architecture Search (NAS) is naturally formulated as a bilevel optimization problem, where the upper-level optimizes the architecture using validation performance and the lower-level trains network parameters using training loss. However, NAS is computationally expensive due to discrete architectural decisions, exponentially growing search spaces, and the high cost of training candidate architectures. This work develops a general bilevel optimization framework for NAS across diverse architectures, including MLPs, CNNs, RNNs, and Transformers, to identify compact architectures with strong predictive performance. We propose three scalable formulations that replace discrete neuron- and activation-level decisions with continuous relaxations, enabling differentiable optimization over otherwise combinatorial architecture spaces. These formulations give rise to three NAS methods: NAS based on Neuron Gating (NAS-NG), NAS based on Mixed Activation (NAS-MA), and NAS based on Neuron Gating and Mixed Activation (NAS-NGMA). Experiments on MLPs and CNNs using MNIST and CIFAR-10 show that the proposed methods consistently identify compact architectures with competitive or improved predictive performance. On MNIST, NAS-NGMA achieves 98.68% test accuracy with 7.69M MLP parameters, while NAS-NG achieves 99.63% accuracy with only 0.26M CNN parameters. On CIFAR-10, the proposed methods consistently outperform vanilla DARTS. Further experiments demonstrate that NAS-NG can optimize substantially over-parameterized and literature-optimal architectures, improving accuracy while reducing parameters. These results establish relaxed bilevel optimization as a scalable alternative to discrete NAS and provide a general framework for efficient neuron- and activation-level architecture optimization.

AI 总结：本文提出LP-NAS框架，将线性规划应用于可微分NAS，其变体在CIFAR等数据集上的搜索与评估阶段均优于DARTS及其多种变体，且架构可迁移至ImageNet。

链接：https://arxiv.org/abs/2608.14472

机构：IIT Kanpur（印度理工学院坎普尔分校）； IIM Ahmedabad（印度管理研究所艾哈迈达巴德分校）

作者：Abhishek Shukla, Ankur Sinha, Faiz Hamid

英文摘要：Neural Architecture Search (NAS) aims to automate neural network architecture design, reducing reliance on human expertise. Among the various NAS methods, differentiable NAS has gained prominence due to its efficiency and accuracy compared to conventional NAS approaches. Since differentiable NAS relaxes the architecture search space into a continuous domain, it is possible to apply principles from continuous optimization to NAS. In this paper, we propose Linear Programming-based NAS (LP-NAS), a mathematical programming-based framework for differentiable NAS that is applicable to a wide range of continuous search spaces. LP-NAS formulates a linear program (LP) using the validation-loss gradient and the training-loss Hessian to compute an architecture update direction that improves generalization while preserving the optimality of the model parameters. By following this LP-derived descent direction, LP-NAS efficiently navigates the architecture search space, leading to faster and more effective architecture optimization. We introduce two computationally efficient variants of LP-NAS, namely S-LP-NAS and R-LP-NAS. Applying LP-NAS to the Differentiable Architecture Search (DARTS) search space results in two algorithmic variants, S-LP-DARTS and R-LP-DARTS. Both variants achieve faster convergence and significantly higher validation performance during the early search iterations than the standard DARTS algorithm. Extensive experiments on CIFAR-10 and CIFAR-100 show that LP-DARTS outperforms standard DARTS in both the architecture search and evaluation phases. Additionally, we compare our approach with several DARTS variants (P-DARTS, PC-DARTS, and STO-DARTS) on the CIFAR-10 dataset and demonstrate its effectiveness. Furthermore, we validate the transferability of the discovered architectures through experiments on the ImageNet dataset.

AI 总结：Rollplex是一种跨阶段GPU空间共享运行时，通过解耦RL后训练的参考与训练阶段、优化内存与并行度，提升VLMs后训练的GPU利用率与训练速度。

链接：https://arxiv.org/abs/2608.14498

机构：HKUST（香港科技大学）； Alibaba Inc（阿里巴巴公司）

作者：Hanfeng Lu, Tianyu Feng, Suyi Li, Yuheng Zhao, Wei Gao, Shaopan Xiong, Ju Huang, Siran Yang, Jiamang Wang, Lin Qu, Wei Wang

英文摘要：Vision-language models (VLMs) enable embodied agents to reason and act from visual observations and language instructions. Reinforcement learning (RL) post-training enhances these capabilities using task feedback, but current on-policy RL runtimes execute rollout, reference scoring, and actor training in strict serial phases. While effective for text-only RL, this phase-granular execution is wasteful for VLMs, where processing dense video inputs and prompt prefixes occupies a large fraction of each phase. Because prefix processing is independent of the generated response, it can be run alongside rollout decoding, which leaves GPU compute capacity underutilized, without breaking synchronous on-policy semantics. We present Rollplex, a runtime that decomposes the reference and training phase and moves the prefix computation into the rollout decode window. Realizing this schedule requires more than concurrent kernel launches: naive colocation of Qwen2.5-VL-32\,B requires roughly 165\,GiB per GPU, while rollout and training prefer different tensor-parallel (TP) degrees and weight layouts. Rollplex addresses these constraints with two mechanisms. Phase-aware memory management controls HBM residency according to producer--consumer lifetimes. Parallelism-aware weight sharing uses the same physical storage for layout-compatible tensors across distinct TP degrees and reconstructs only incompatible tensors, avoiding a complete second actor copy. On 32 H800 GPUs, Rollplex achieves $1.23\times$--$1.30\times$ speedup over serial colocation and $1.57\times$--$2.24\times$ over disaggregation under the same GPU budget, while preserving the synchronous RL update.

AI 总结：针对现有表格学习方法难以捕获食谱数据分层与序列依赖的问题，提出分层Transformer架构RecipeNet，在多类食谱任务上性能优于现有表格模型，为食谱表示学习提供了新方案。

链接：https://arxiv.org/abs/2608.14505

机构：Arizona State University（亚利桑那州立大学）； Applied Materials（应用材料公司）； University of Illinois Chicago（芝加哥大学伊利诺伊分校）

作者：Pin-Yen Huang, Sachin Chhabra, Prasanth Sai Gouripeddi, Abhinav Kumar, Baoxin Li

英文摘要：Recipe data arises in domains such as materials synthesis, pharmaceutical formulation, and industrial manufacturing, where procedures are represented as ordered sequences of steps containing heterogeneous structured fields. Existing tabular learning methods typically flatten this structure into fixed-schema representations, limiting their ability to capture hierarchical field interactions and procedural dependencies. We propose RecipeNet, a hierarchical Transformer architecture that encodes field-level interactions within each step and sequential dependencies across steps through stacked Transformer encoders. Experiments on multiple recipe datasets and tasks demonstrate that RecipeNet consistently outperforms existing tabular models, highlighting the value of hierarchical and sequential modeling for recipe representation learning.

AI 总结：本研究针对对撞机异常检测的可解释性与能量依赖问题，提出ORCA两阶段框架，通过对比学习结合自编码器实现更优的信号灵敏度与可解释性，为对撞机异常搜索提供新途径。

链接：https://arxiv.org/abs/2608.13652

机构：Stanford University（斯坦福大学）； SLAC National Accelerator Laboratory（SLAC国家加速器实验室）

作者：Haoyi Jia, Sagar Addepalli, Julia Gonski

英文摘要：Generic event-level anomaly detection for collider physics has two recurring problems: anomaly scores are hard to interpret, and they correlate strongly with energy scale and object multiplicity. We present Organized Representation via Contrastive learning for Anomaly detection (ORCA), a two-stage framework that first learns an embedding space via supervised contrastive learning across a diverse set of physics processes, then runs a standard autoencoder in that space to generate event-level anomaly scores. On a simulated dataset consistent with conditions at the High-Luminosity Large Hadron Collider, ORCA delivers significant gains in both breadth and depth of sensitivity to new physics signals with respect to a baseline autoencoder architecture. Beyond improved sensitivity, the contrastive embedding makes the anomalous sample interpretable: because known processes occupy distinct regions of the space, a maximum-likelihood template fit to the embedding distributions can attribute events in an anomalous sample to template physics processes with quantified uncertainties. We demonstrate that the fit accurately recovers injected signal yields, including for signals excluded from the training of the embedding, and characterizes signals absent from the template library through the known processes they most resemble. These results establish ORCA as a route to interpretable anomaly detection-based searches at colliders, where the embedding geometry carries higher dimensional physics information compared to standard one-dimensional output fits, enhancing downstream statistical analysis.

AI 总结：该研究针对大地测量需求提出连通子空间聚类问题，证明其难度，设计启发式算法，在海平面数据实验中表现优于对比方法，可应用于多类空间时间序列场景。

链接：https://arxiv.org/abs/2608.14215

机构：Heinrich Heine University Düsseldorf（海因里希·海涅杜塞尔多夫大学）； University of Cologne（科隆大学）； University of Bonn（波恩大学）； University at Buffalo（纽约州立大学布法罗分校）

作者：Johanna Hillebrand, Jan Höckendorff, Jürgen Kusche, Kelin Luo, Heiko Röglin, Melanie Schmidt, Christian Sohler, Bernd Uebbing

英文摘要：Constrained optimization extends classical optimization by integrating side information, making it widely applicable across scientific and engineering domains. Consider a setting where we measure variables at different physical locations. When grouping these measurements, we often want clusters that are both internally similar and physically coherent. Thus, we have a constrained clustering problem where the constraint models coherence. Motivated by an application in geodesy, where contiguous regions of the sea surface must be identified for principal component analysis, we introduce the Connected Subspace Clustering problem: given high-dimensional points and a connectivity graph, partition them into $k$ connected clusters, minimizing their total squared distance to the clusters' best-fit $m'$-dimensional affine subspaces. We prove that, even for $m' = 0$ and a grid graph with holes, the problem is NP-hard to approximate within $\Omega(n^{1/2-\varepsilon})$ for every $\varepsilon>0$, where $n$ is the number of measurements. We then introduce an efficient Lloyd-style heuristic that alternates subspace fitting with an iterative merging procedure to enforce connectivity. Our method returns exactly $k$ connected regions by construction, whereas unconstrained methods leave up to $1{,}966$ disconnected fragments at higher cost. In a study of 160 configurations on global sea level time series, our merging-based repair is the strongest of four strategies in $73.75\%$ of cases, and consistently outperforms competitors such as (connected) Ward's method across all tested cluster counts. The resulting regions isolate signals aligning with climate indices such as the El Nino-Southern Oscillation and Indian Ocean Dipole. Although developed for geodesy, the approach applies to other spatially embedded multivariate time series, such as climate fields, remote sensing, neuroimaging, and sensor networks.

AI 总结：本研究提出“冒名者”预文本任务，利用跨实体特征置换学习物理一致性，经ERA5-Land数据评估，该任务与现有SSL目标结合可提供互补信息，为科学基础模型提供新自监督来源。

链接：https://arxiv.org/abs/2608.14372

作者：Aleksei Rozanov, Arvind Renganathan, Vipin Kumar

英文摘要：Scientific data often describe entities whose features are jointly governed by the laws of physics, yet existing self-supervised learning (SSL) objectives largely ignore this physical coherence. We introduce imposter, a discriminative pretext task that replaces subsets of an entity's features with real observations donated by another entity and trains the encoder to identify the swapped features. Because every donated value is individually plausible, the task can only be solved by learning cross-feature physical dependencies. We evaluate the proposed objectives on global ERA5-Land reanalysis data using 21 environmental variables and assess the learned representations on seven downstream tasks spanning climate classification, carbon flux estimation, and streamflow prediction. Our study includes, to our knowledge, the first systematic comparison of self-supervised objectives for land-surface modeling under a shared architecture and pre-training budget. We find that the most effective pretext task depends on the downstream task family rather than any single objective's superiority, and that imposter provides complementary information when combined with existing SSL objectives. These results suggest that physical coherence is a valuable new source of self-supervision for scientific foundation models.

AI 总结：本文将时尚穿搭生成形式化为约束集成生成，提出统一序列组合模型与潜在扩展蒙特卡洛树搜索机制，在多数据集上实现了时尚穿搭生成任务的最优性能。

链接：https://arxiv.org/abs/2608.13888

机构：Laboratory for Artificial Intelligence in Design（人工智能设计实验室）； Hong Kong Polytechnic University（香港理工大学）； The University of Queensland（昆士兰大学）

作者：Kaicheng Pang, Xingxing Zou, Ruohan Xu, Waikeung Wong

英文摘要：The task of synthesizing stylistically coherent fashion outfits from massive item libraries, known as fashion outfit generation, remains a non-trivial challenge, primarily due to the non-monotonic and implicit nature of aesthetic compatibility, coupled with the exponentially large combinatorial search space. In this paper, we formalize this task as Constrained Ensemble Generation (CEG) and model it as a finite-horizon deterministic Markov Decision Process. To address CEG in fashion, we propose the Unified Sequential Composition Model (USCM), which jointly models set-level compatibility and latent composition intents. Guided by USCM's learned priors, a Latent Expansion Monte Carlo Tree Search (LE-MCTS) mechanism is proposed to handle item retrieval during composition, balancing local aesthetic synergy with global structural balance. Extensive experiments on the Polyvore Outfits dataset, along with zero-shot evaluations on the iFashion and PolyvoreU datasets, demonstrate that our framework achieves state-of-the-art performance across independent human preference evaluations, automated aesthetic proxies, and structural validity metrics for constrained fashion outfit generation.

AI 总结：针对电网拓扑控制的组合空间与约束问题，研究受AlphaZero启发的模型方法，发现优化的AlphaZero达98.43%生存能力，需结合领域启发式、二元奖励与受限观测空间。

链接：https://arxiv.org/abs/2608.14114

机构：Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）

作者：Lukas Zetto, Benjamin Schäfer, Qiong Huang

英文摘要：As the integration of volatile renewable energy sources increases the strain on modern power grids, the use of Reinforcement Learning (RL) for autonomous topological reconfiguration has emerged as a promising research field to keep strained grids stable and operational. Compared to traditional redispatching measures, topological actions offer a cheaper and more cost-effective way to manage grid congestion. However, their implementation is hindered by a vast combinatorial action space and strict operational constraints. This paper investigates the effectiveness of model-based AlphaZero-inspired approaches that utilize Monte Carlo Tree Search (MCTS) for proactive grid management. We systematically evaluate how reward functions, observation density, and search guidance influence an agent's survivability. Our results demonstrate that the optimized AlphaZero approach achieves a peak survivability of 98.43%, significantly outperforming the proximal policy optimization (PPO) variant. We find that conducting the MCTS without guidance from a prior learned policy or value function can enhance training efficiency, and that a straightforward binary survival reward provides more effective search guidance than complex, multi-objective functions. Our findings demonstrate that while AlphaZero is a powerful framework for topological control, pure reinforcement learning is not sufficient; rather, an effective and reliable system requires a 'minimalist' integration of domain-specific heuristics, binary rewards, and a restricted observation space of line loads.

AI 总结：本研究首次将改进的JAMPR深度强化学习模型用于求解带容量和时间窗约束的取送货路径问题，可为中小规模问题提供快速最优解，为超大规模问题提供快速次优解。

链接：https://arxiv.org/abs/2608.14156

机构：Moscow State University（莫斯科国立大学）； Space Research Institute of RAS（俄罗斯科学院空间研究所）

作者：Andrew Soroka, Alex Meshcheryakov, Sergey Gerasimov

英文摘要：The task of constructing vehicles optimal routes for pickup and delivery of goods is one of most promising tasks in the context of global urban population growth. Although this kind of problems with small size can be solved by various classical approaches, a fast (or realtime) route optimizer under the constraints of the real world (such as capacity and time windows constraints) for medium-large size problems still remains a highly challenging task. In this work we, for the first time, successfully applied a deep Reinforcing Learning approach (modified JAMPR model) to solve Pickup and Delivery problem with Capacity and Time Window constraints (CPDPTW). We obtained a robust model that gives a fast optimal solution for problems of small and medium size, and gives fast suboptimal solution for problems of larger (> 200) size.

AI 总结：该研究针对量子多臂老虎机和量子线性老虎机，证明了新的极小极大下界，并提出了改进维度依赖的基于设计的消除算法，解决了Wan等人提出的相关问题。

链接：https://arxiv.org/abs/2608.14319

机构：The Chinese University of Hong Kong（香港中文大学）； Xidian University（西安电子科技大学）

作者：Maoli Liu, Zhuohua Li, John C.S. Lui

英文摘要：We study quantum multi-armed bandits (QMAB) and quantum linear bandits (QLB) in the model of Wan et al. [2023], where the learner queries each arm or action through a quantum reward oracle or its inverse. Prior work gives algorithms over horizon $T$ with regret $O(K\log T)$ for QMAB with $K$ arms and $O(d^2\operatorname{polylog} T)$ for $d$-dimensional QLB. This leaves open whether the $K\log T$ scale is unavoidable and whether the $d^2$ dependence can be improved. We prove the first minimax lower bounds of $\Omega(K\log(T/K))$ for QMAB and $\Omega(d\log(T/d))$ for finite-action QLB, resolving the question raised by Wan et al. [2023] of whether regret independent of $T$ is achievable. At the heart of our argument is a high-confidence single-arm quantum testing lower bound for distinguishing a fixed reward mean from an interval of alternatives, proved by the polynomial method and a Remez-type inequality for trigonometric polynomials. A bandit-to-testing reduction then lifts it to the QMAB lower bound, while a linear embedding gives the finite-action QLB lower bound. Complementing the lower bounds, we give a design-based elimination algorithm for finite-action QLB. When the action set has size $\operatorname{poly}(d)$, its regret is linear in $d$, improving the prior $d^2$ dependence and matching our lower bound up to polylogarithmic factors. The algorithm couples a low-bias low-variance quantum mean estimator with a small-support $G$-optimal design through a query allocation matched to the design weights. The design-based elimination reduces the dimension dependence from $d^2$ to $d^{3/2}$ when using Quantum Monte Carlo estimates. The low-variance estimator then makes reconstruction error aggregate through variance rather than worst-case absolute error, removing the remaining $\sqrt d$ factor.

AI 总结：本文从路径空间视角统一了扩散模型RL算法的原理，推导得到降方差值梯度形式，提出多样本KDE估计器和尺度受限权重族，在SD3.5-M等模型上验证了方法有效性并优于基线。

链接：https://arxiv.org/abs/2608.14430

机构：State Key Laboratory of General Artificial Intelligence（通用人工智能国家重点实验室）； School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）； ByteDance（字节跳动）

作者：Yixian Xu, Yuanrui Zhang, Shengjie Luo, Liwei Wang, Di He

英文摘要：Reinforcement learning (RL) post-training provides a direct way to align diffusion models with human preferences and task-specific rewards. However, current RL algorithms for diffusion models remain fragmented: reverse-trajectory methods rely on discretized likelihood ratios, whereas forward-matching methods train on reward-labeled noising versions of the rollout samples. This paper shows that these seemingly different losses arise from a single path-space principle. Starting from the regularized diffusion-RL objective, we use importance sampling between sampling SDEs to obtain an explicit policy-gradient estimator on trajectory space. The estimator contains the stochastic Itô integral underlying Flow-GRPO-type updates; we derive an equivalent variance-reduced value-gradient form that recovers the forward-matching structure of AWM and DiffusionNFT. This identifies the empirical gap between these method families as a variance-reduction effect rather than a difference in RL principle. The derivation yields a unified design space organized by value-gradient estimation, weight functions, and sampling choices. Within this space, we propose a multi-sample KDE value-gradient estimator that reuses rollout groups, together with scale-bounded weight families that retain stable existing recipes while excluding singular ones. Experiments on SD3.5-M and Qwen-Image models validate the variance-reduction explanation and show that the resulting recipe improves over prior diffusion-RL baselines.

AI 总结：本文提出一种对抗学习方法，将无分类器引导调度建模为密度比估计问题，训练判别器与轻量生成器，在文本到图像生成基准上优于启发式CFG调度及现有动态引导学习方法。

链接：https://arxiv.org/abs/2608.14038

机构：Google（谷歌公司）； Google DeepMind（谷歌DeepMind）； Gatsby UCL（盖茨比伦敦大学学院）

作者：Ashwini Pokle, Alexandre Galashov, Arnaud Doucet, Mauricio Delbracio, Valentin De Bortoli

英文摘要：Modern text-to-image diffusion models rely on classifier-free guidance (CFG) to achieve high image fidelity and text alignment. However, CFG typically applies a static, global scale across all timesteps, samples, and conditions -- a choice that is generally suboptimal and can introduce artifacts, as different states may benefit from different levels of guidance. While time-varying schedules are known to improve quality, designing them by hand is non-trivial and application-dependent. In this paper, we learn the guidance schedule as a function of diffusion time, conditioning and the current noisy sample, in order to better align sampled images with the text prompt. We frame this as a density ratio estimation problem: a discriminator is trained to estimate the time-dependent log-density ratio between the true and guided marginal distributions, while a lightweight generator network predicts the optimal, state-dependent guidance scale. Empirically, our approach outperforms both heuristic CFG schedules and prior methods for learning dynamic guidance on text-to-image generation benchmarks.

AI 总结：PPAPlace是一种时序驱动的可微代理模型，以全局布线后标签训练，通过双流预测器结合图注意力与空间卷积，在ChiPBench测试电路上较分层基准显著提升WNS与TNS并保持功耗和可布线性。

链接：https://arxiv.org/abs/2608.13790

机构：University of Alberta（阿尔伯塔大学）

作者：Ruogu Chen, Jie Han

英文摘要：Macro placement significantly affects a chip's post-route performance, power, and area (PPA). Most placement methods optimize half-perimeter wirelength (HPWL) as the primary objective. However, recent benchmarking shows a near-zero correlation between HPWL and post-route timing metrics such as the worst negative slack (WNS) and total negative slack (TNS). As a result, all six evaluated artificial intelligence (AI) placers degraded PPA relative to the hierarchical baseline. Recent efforts have tried to train cross-stage predictors to close this gap. However, existing methods focus on macro-only representations and use pre-route metrics as training labels. A label fidelity study of ten circuits at four design flow stages reveals that HPWL and pre-route timing poorly reflect final post-route timing rankings. In contrast, post-global-routing achieves the best balance between final timing fidelity and label generation cost-effectiveness. Based on this finding, PPAPlace is a timing-driven differentiable surrogate predicting post-route PPA from macro and standard-cell placements. The surrogate is a dual-stream predictor that combines graph attention over the chip netlist with spatial convolution over the placement grid. It is trained on post-global-routing labels. The predicted WNS and TNS gradients flow end-to-end back to cell coordinates. PPAPlace exploits these gradients in two ways: as a co-objective injected into an analytical placer's optimization loop (PPAPlace-CoOpt), and as a post-placement refinement step that adjusts macro positions via projected gradient descent (PPAPlace-Refine). On five ChiPBench test circuits excluded from training, PPAPlace improves average WNS and TNS by 22\% and 51\% over the hierarchical baseline while preserving power and routability, using the same predictor without test-circuit retraining. Code is available at this https URL.

AI 总结：该研究提出变分布朗核梯（VBKL）框架，分离非线性递归字典构建与线性变分叠加，推导了相关泛化界与误差界，实验显示其在有限数据下的精度-复杂度权衡表现良好。

链接：https://arxiv.org/abs/2608.13882

机构：Faculty of Engineering, Free University of Bozen-Bolzano（博尔扎诺自由大学工程学院）

作者：Mahdi Mohammadigohari

英文摘要：Claims about the benefit of depth depend on the complexity assigned to a representation. We introduce the \emph{Variation Brownian Kernel Ladder} (VBKL), a path-atomic function-space framework that separates nonlinear recursive dictionary construction from linear variation superposition. Starting from linear projections, each atom recursively composes unit-ball profiles from the Brownian reproducing kernel Hilbert space; the full VBKL space is then the signed-measure variation hull of the completed dictionary. We identify each recursive dictionary as a union of Brownian pullback RKHS balls and establish variation-controlled Hölder regularity, compactness and attainment, and strict growth with depth under a local non-degeneracy condition whose trace lies in the support of the input measure. For associated finite lower-support architectures, we derive Rademacher and generalization bounds through Brownian quadratic chaos, signed threshold traces, and VC entropy. We also construct two-stage approximants by discretizing the outer measure and the selected outer Brownian profiles, obtaining an $M^{-1/2}+m^{-1/2}$ error bound, a sharp interpolation constant $\sqrt{A/2}$, and at most $2M$ active outer-profile basis contributions per evaluation. Controlled experiments illustrate the approximation mechanisms and indicate a favorable limited-data accuracy--complexity trade-off.

AI 总结：该研究针对联邦学习的通信瓶颈与信道损伤问题，提出基于极化码的跨层方案，通过不等错误保护特性优化量化比特与码长，实验显示其性能优于无编码及LDPC基准，可增强联邦学习的鲁棒性与效率。

链接：https://arxiv.org/abs/2608.13961

机构：School of Information Science and Engineering, Southeast University（东南大学信息科学与工程学院）； National Mobile Communications Research Laboratory, Southeast University（东南大学国家移动通信重点实验室）

作者：Han Xiao, Wei Kang, Nan Liu

英文摘要：Federated learning (FL) enables collaborative model training across distributed devices without sharing raw data; however, it faces significant communication bottlenecks and channel impairments in practice. Conventional network layer treatments either idealize the channel as error free or apply equal error protection (EEP) to transmitted model updates, failing to account for the inherently unequal importance of quantization bits within a single local model. To address this limitation, we propose a cross layer polar code based FL scheme that leverages the unequal error protection (UEP) property of polar codes under finite block lengths. Specifically, the proposed design selectively protects more significant quantization bits, thereby mitigating the detrimental effects of channel noise. We further provide a rigorous convergence analysis of the proposed scheme, deriving an upper bound on the convergence gap, which we then jointly optimize over the number of quantization bits and the polar code block length across all training iterations. Experimental results demonstrate that both constant and variable block length configurations of our polar code based scheme consistently achieve substantial performance gains over uncoded and LDPC-based EEP benchmarks, with the advantage becoming increasingly pronounced as the channel quality deteriorating. These findings confirm the efficacy of our cross-layer design in enhancing FL robustness and efficiency under realistic channel conditions.

AI 总结：该研究将模型合并的参数选择转化为黑箱多目标优化问题，提出MOBO-Merge框架，经实验验证其在多数场景下优于随机搜索，为模型合并提供了高效的搜索方案。

链接：https://arxiv.org/abs/2608.14264

机构：Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）

作者：Utkarsh Agarwal, Vamshi Bonagiri, Raul Astudillo, Monojit Choudhury

英文摘要：Model merging combines trained models directly in weight space, offering a compute-efficient alternative to additional fine-tuning. Selecting merge parameters is nevertheless difficult because downstream evaluations are expensive, gradients are unavailable, and source capabilities can conflict. We formulate merge-parameter selection as a black-box multi-objective optimization problem and introduce MOBO-Merge, a merge-operator agnostic framework that uses multi-objective Bayesian optimization to approximate the Pareto front under a limited evaluation budget. We evaluate Qwen3-4B and Llama-3.1-8B in two-model instruction-math and three-model instruction-math-code settings using Linear, SLERP, TIES, and block-wise merge operators. On held-out benchmark partitions, MOBO-Merge obtains higher mean hypervolume than random search in 11 of 12 reported comparisons. The gain is small for one-dimensional Linear interpolation but substantially larger for several TIES, block-wise, and three-objective searches. No merge operator is uniformly best: TIES leads in three of four family-setting combinations, whereas Block-Linear 4x is strongest for the Llama three-model merge. These results show that multi-objective Bayesian optimization is valuable as a search layer for expressive merge parameterizations.

AI 总结：CutClean是一种感知隐私的神经网络剪枝方法，通过辅助线性隐私头量化并消除私有属性泄露，在保持分类精度的同时实现高稀疏度，减少隐私信息流。

链接：https://arxiv.org/abs/2608.13773

机构：Télécom Paris, Institut Polytechnique de Paris（巴黎理工学院电信学院）； University of Genoa（热那亚大学）； Istituto Italiano di Tecnologia（意大利技术研究院）

作者：Leonardo Magliolo, Vito Paolo Pastore, Giuseppe Valenzise, Enzo Tartaglione

英文摘要： Neural networks are increasingly deployed in high-stakes applications with growing privacy leakage concerns. We show that this privacy leakage can occur even in the absence of representation imbalances that lead to traditional dataset biases. This poses significant privacy risks when deploying models that process sensitive attributes. In this context, we propose CutClean, a privacy-aware pruning method that allows to reduce privacy information flow through the network, while increasing its sparsity. Our approach employs auxiliary linear privacy heads placed at each network's block to quantify information leakage, and further applies increasing levels of sparsity to remove the private attribute leakage, measured in terms of the accuracy of the privacy head attached to the last block. Experiments on synthetic and real-world datasets demonstrate that our approach effectively minimizes private information flow while achieving high sparsity rates and preserving classification target accuracy.

AI 总结：QUASAR是一种QAT方法，通过训练循环中轻量级损失感知重构降低大语言模型量化损失下限，在2-4比特下优于现有方法，提升了低比特模型准确率。

链接：https://arxiv.org/abs/2608.13966

机构：Together AI； Cornell University（康奈尔大学）

作者：Vincent Counathe, Ben Athiwaratkun, Christopher De Sa, Tianyi Zhang

英文摘要：As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aware training (QAT) essential for preserving model quality. However, QAT computes the loss and surrogate gradients using a lossy reconstruction of latent full-precision weights, while applying updates to the latent weights themselves. This mismatch can lead to suboptimal training trajectories and a higher loss floor. Second-order PTQ methods mitigate a similar gap by minimizing loss-aware reconstruction error, but doing it once for a frozen model can take hours; repeating this process throughout QAT as the weights evolve is impractical. We introduce QUASAR, a QAT method that continuously performs lightweight, loss-aware reconstruction in the training loop to lower the loss floor and improve the resulting low-bit model. At each training step, QUASAR uses the exponential moving average of squared gradients as online saliency estimates, searches over a small set of clipping ranges, and fits affine dequantizers via saliency-weighted least squares. Our analysis shows that the loss-aware reconstruction error is the only reconstruction-dependent term in the QAT convergence bound and controls the loss of the final quantized model, establishing QUASAR's objective as a principled optimization target. QUASAR modifies only the training procedure and supports standard deployment formats, including integer quantization and NVFP4, with no inference-time changes or overhead. Across Qwen3 and Llama-3.1, QUASAR achieves the lowest held-out KL divergence among competitive QAT methods at 2, 3, and 4 bits, reducing KL by at least 10% at 3 and 4 bits and by 29% at 2 bits. At 2 bits, it improves average accuracy across eight tasks by 3.5-4.3 percentage points over strong QAT and PTQ baselines.

AI 总结：该研究针对长上下文推理中KV缓存的内存瓶颈，提出注意力感知变换编码（AATC）方法，在多基准测试中实现约5.8倍压缩且保持近乎无损的准确率，优于基线方法。

链接：https://arxiv.org/abs/2608.14191

作者：Hannah Laus, Claudio Mayrink Verdun, Hao Wang, Flavio du Pin Calmon, Felix Krahmer

英文摘要：The key-value (KV) cache stores information from past tokens and is a major memory bottleneck in long-context inference. Existing quantization methods address this bottleneck by representing the KV cache uniformly with lower-precision data types and designing quantization schemes to minimize reconstruction error in the cache itself, without accounting for how that error propagates through attention mechanisms. We prove that, under a white-noise quantization model, the expected attention-aware distortion decomposes into additive key and value contributions that factor across tokens and channels. Building on transform coding and reverse water-filling, which are classical tools from signal processing and rate-distortion theory, we introduce Attention-Aware Transform Coding (AATC), which allocates bits over a calibration set to minimize attention-aware distortion. On Llama-3.1-8B-Instruct and Qwen-2.5-7B-Instruct, evaluated across LongBench, RULER, GSM8K, MMLU-Pro, and MATH-500, our method achieves near-lossless accuracy at approximately $5.8\times$ compression, whereas each baseline degrades in at least some settings.

AI 总结：本文为联邦提示学习（FPL）的全面综述，明确其与传统联邦学习及全模型联邦微调的差异，分析其多维度权衡与现存挑战，梳理全生命周期方法及防御机制，为该领域研究提供方向。

链接：https://arxiv.org/abs/2608.13844

机构：Cyberspace Institute of Advanced Technology, Guangzhou University（广州大学先进技术网络空间研究院）； Huangpu Research School of Guangzhou University（广州大学黄埔研究院）； Iwate Biotechnology Research Center（岩手生物技术研究中心）； Nanjing University of Posts and Telecommunications（南京邮电大学）

作者：Qinglin Yang, Chen Qiu, Hongyuan Zhang, Pengdeng Li, Yuan Liu, Zhihong Tian

英文摘要：Large language models (LLMs) have become core components of cloud-based intelligent services in academia and industry, yet their training and deployment are hindered by high computational costs, data centralization, and privacy concerns. Federated learning (FL) offers a decentralized training paradigm that enables clients to collaboratively train a learning model without sharing raw data, making it a promising solution for privacy-preserving LLM training and reasoning. This paper presents a comprehensive survey of federated prompt learning (FPL) to review recent advances in integrating the federated learning paradigm and large language models, answering the following research questions: RQ1: The fundamental motivations, characteristics, and enabling technologies of FPL, and how it differs from conventional FL and full-model federated fine-tuning; RQ2: The trade-offs FPL approaches exhibit in performance, communication efficiency, computational overhead, scalability, personalization, and heterogeneity handling; RQ3: The remaining security, privacy, robustness, and system challenges, along with key future research directions. To this end, we systematically examine existing FPL methods across the full model lifecycle: pre-training, fine-tuning, and practical applications, while discussing security, privacy, and robustness issues and summarizing existing defense mechanisms. Finally, we highlight open challenges and future directions, aiming to help readers understand how the insights drive research in FPL.

AI 总结：本研究针对岩土工程中不排水抗剪强度预测的数据缺失与变异性问题，采用高级插补法结合机器学习技术，构建MN增强型MHA-PNN概率间接模型，显著提升了预测精度与不确定性量化效果。

链接：https://arxiv.org/abs/2608.13934

作者：Haibin Xiong, Shaoheng Dai, Peng Lan, Xuzhen He, Chenxi Tong, Sheng Zhang, Daichao Sheng

英文摘要：Accurate prediction of undrained shear strength (su) is crucial for geotechnical design, but is often hampered by substantial uncertainty in traditional empirical methods. This study uses the CLAY/10/7490 global database to develop probabilistic indirect models to predict su based on Atterberg limits and piezocone cone penetration (CPTU) measurements. Firstly, the dataset has a high missing data rate and variability. We test three imputation methods - multivariate normal (MN), multiple imputation by chained equations (MICE), and miss forest (MF) - to fill the missing values. To validate their effectiveness, a Probabilistic Extreme Gradient Boosting (PXGB) model is developed, and the imputation methods are evaluated by comparing the PXGB's performance when trained on the imputed datasets against that on the original incomplete data. Secondly, the indirect model is built by integrating a multi-head attention (MHA) mechanism into an artificial neural network (ANN) to enhance information extraction from limited data, which leads to the MHA-based probabilistic neural networks (MHA-PNN) model. The models' performance, alongside a conventional MN-based prediction model, was evaluated using root mean square error (RMSE), coefficient of determination (R2), mean absolute percentage error (MAPE), conditional interval width (wCI), and coverage rate (CR). Results demonstrate that the proposed MN-enhanced MHA-PNN model substantially outperforms other models in both prediction accuracy and uncertainty quantification. These findings highlight the potential of this integrated strategy for building robust probabilistic indirect models in geotechnical applications, particularly when confronted with sparse and incomplete datasets.

AI 总结：该研究提出通用零样本预测框架MINT，通过轻量级嵌入注入等技术连接交易序列编码器与LLM，在交易预测问答任务中性能领先且资源消耗更低，证实紧凑交易嵌入更具优势。

链接：https://arxiv.org/abs/2608.14198

机构：Visa Inc.（维萨公司）

作者：Parameswaran Kamalaruban, Viktor Drobnyi, Maeve Madigan, Julia Rozanova, David Sutton, Stuart Burrell

英文摘要：Banks analyse sequential financial transaction data to perform many tasks, including fraud prevention, credit risk assessment and offer personalization. To improve the predictive accuracy of these tasks, Payments Foundation Models encode transaction sequence data as rich contextual embeddings, which can then be provided to task-specific models as features. However, these Foundation Models are not designed for flexible zero-shot reasoning across novel downstream prediction tasks, limiting their adaptability and utility. Existing LLM-based approaches to zero-shot prediction often fail to fully exploit the predictive signal within transaction data, while relying on costly text serialization or task-specific architectures that scale poorly. To address these limitations, we present the Multimodal Instruction Network for Transactions (MINT), a framework that connects a pretrained transaction sequence encoder to a decoder-only LLM through lightweight embedding injection, transaction-language alignment, and instruction tuning. We find that MINT achieves state-of-the-art predictive question-answering performance in both in-distribution and out-of-distribution questions, while substantially reducing input tokens, latency, and memory consumption compared to text-serialization baselines. Through comprehensive analyses of representations, alignment strategies, training data, and history length, we establish that compact transaction embeddings are a superior approach to transaction representation than text serialization for multimodal reasoning and zero-shot prediction tasks.

AI 总结：本文针对业务流程延迟检测的内在难度，分析14个事件日志后发现高延迟案例识别困难源于分布偏斜与不确定性，提出利用相关性的改进方法，为PPM研究提供新方向。

链接：https://arxiv.org/abs/2608.14367

机构：University of Mannheim（曼海姆大学）； SAP Signavio（思爱普 Signavio）

作者：Keyvan Amiri Elyasi, Lukas Kirchdorfer, Heiner Stuckenschmidt

英文摘要：The early detection of delayed cases in business processes is a critical capability for organizations. Predictive process monitoring (PPM) supports this task by using historical event logs to predict the remaining time of ongoing cases, enabling timely interventions to avoid missed deadlines and service level violations. Although remaining time prediction has advanced considerably through sophisticated deep learning architectures, little is known about the intrinsic difficulty of delay detection itself. Since performance is typically assessed using aggregate metrics, prior work provides limited insight into how models perform across the target distribution, especially on the operationally most critical cases with large delays. In this paper, we address this gap by analyzing the difficulty of delay detection. Across 14 event logs, we show that remaining times are typically strongly right-skewed, with only a small fraction of cases exhibiting large delays. Existing models capture the mode of this distribution well but perform poorly on high-delay cases. We further uncover pronounced heteroscedasticity, showing that predictive uncertainty increases with delay magnitude. Based on these findings, we evaluate approaches to mitigate the imbalance problem, but find only limited benefits, suggesting that the key underlying problem may not be imbalance but higher uncertainty associated with delayed cases. We show that this correlation can be exploited to substantially improve the identification of delayed cases. Overall, our work provides new insights into the sources of difficulty in delay detection and identifies uncertainty-aware modeling as a promising direction for future PPM research.

AI 总结：该研究提出HI-MGN，即MeshGraphNets的多尺度扩展，通过分层多尺度处理器与图插值网络，提升非结构化网格物理学习的精度并降低训练时间与内存使用，在三个基准测试中表现优于现有模型。

链接：https://arxiv.org/abs/2608.13827

机构：Samsung Electronics Co.（三星电子）； Sejong University（世宗大学）

作者：SiHun Lee, Dong-Hyuk Park, Taesoo Bang, Seung-Hoon Kang

英文摘要：Machine-learned physical surrogate models have become promising alternatives to mesh-based numerical solvers. Among them, graph neural networks (GNNs) are well suited for representing simulation meshes and learning nodal state evolution through message passing. However, conventional flat message passing becomes inefficient on large, high-fidelity meshes because information propagates only one hop per layer, requiring deep processors for long-range interactions and increasing computational cost, memory usage, and the risk of over-smoothing. To address this limitation, we propose Hierarchical Interpolating MeshGraphNets (HI-MGN), a multiscale extension of MeshGraphNets for efficient long-range communication on unstructured meshes. HI-MGN replaces the flat processor with a hierarchical multiscale processor that coarsens graphs using farthest-point sampling and Voronoi partitioning while preserving the original mesh topology. Message passing on coarse graphs enables information to travel over larger geometric distances with fewer layers, and a learned graph interpolation network reconstructs fine-resolution features. Across three structural and fluid benchmarks, HI-MGN achieves improved accuracy compared with MeshGraphNets and the Bi-Stride Multi-Scale GNN while reducing training time and peak memory usage. The results show that topology-aware hierarchical message passing and learned coarse-to-fine interpolation provide an effective and practical framework for scalable mesh-based physics surrogate modeling.

AI 总结：该研究针对GNN易利用非因果捷径导致分布外任务可靠性低的问题，提出架构无关的人在回路策略XIGL，结合主动学习优先选择含捷径的解释以降低反馈成本，经多种GNN架构验证其有效性。

链接：https://arxiv.org/abs/2608.14121

机构：VU Amsterdam（阿姆斯特丹自由大学）； University of Trento（特伦托大学）； UiT The Arctic University of Norway（挪威北极大学）

作者：Taraneh Younesian, Steve Azzolin, Antonio Longa, Francesco Ferrini, Vincenzo Marco De Luca, Stefano Teso

英文摘要：Graph Neural Networks (GNNs) can solve prediction tasks by unintentionally exploiting shortcuts---that is, edges, nodes, and features that correlate with but are not causal for the prediction---which compromise their reliability in out-of-distribution tasks. We introduce XIGL, an architecture-agnostic human-in-the-loop strategy for removing such shortcuts from GNNs. Our key insight is twofold. On the one hand, reliance on shortcuts can be detected by inspecting GNN explanations. On the other hand, once made aware of such shortcuts, sufficiently expert users can provide tailored corrective feedback, which helps deconfound the model. XIGL supports any query strategy; however, since corrective feedback can be expensive to acquire, we develop an active learning strategy for prioritizing explanations that are more likely to display shortcut behavior, lowering annotation and cognitive costs. We showcase the effectiveness of XIGL, including both existing and proposed explanation-based strategies, on several GNN architectures. Our implementation is available online.

AI 总结：针对深度时空交通预测模型透明度不足的问题，提出SGSAN模型，通过DDG、InfoNCE软耦合机制和解耦优化框架，实现高精度预测与内置可解释性。

链接：https://arxiv.org/abs/2608.14177

机构：University of California, Berkeley（加利福尼亚大学伯克利分校）； Tongji University（同济大学）

作者：Xuanmian He, Can Li, Wanjing Ma

英文摘要：Deep spatiotemporal models integrating graph convolutions and attention mechanisms have demonstrated excellent performance in network-level traffic flow prediction, owing to their exceptional ability to capture complex spatiotemporal dependencies. Despite their predictive success, deployment of such models in safety-critical urban systems remains constrained by their inherent lack of transparency. Existing post-hoc diagnostic methods often struggle with spurious correlations and fail to unveil the intrinsic decision-making mechanisms governing traffic dynamics, resulting in suboptimal interpretability and limited operational trustworthiness. To address these challenges, this paper proposes the Structure-Guided Spatiotemporal Attention Graph Neural Network (SGSAN). Departing from traditional architectures that rely on unconstrained adaptive graphs, SGSAN explicitly learns a static Directed Dependency Graph (DDG) to identify the invariant macroscopic propagation paths of traffic states. We further introduce an InfoNCE-based soft-coupling mechanism that anchors the model's dynamic spatiotemporal attention to this structural prior, offering a mechanistic account of the model's decision-making process while ensuring robust forecasting by aligning attention-based reasoning with identified macroscopic dependencies and preventing over-reliance on ephemeral local noise. Furthermore, a decoupled two-stage optimization framework is developed to resolve the fundamental conflict between structural discovery and predictive error minimization. Extensive experiments on multiple real-world datasets demonstrate that SGSAN achieves state-of-the-art predictive accuracy while providing built-in interpretability that organically aligns with the physical logic of traffic networks.

AI 总结：针对细胞计数数据异质性与非标准化导致机器学习难以应用的问题，推出开源基础模型CytoBERT，经5000万细胞数据预训练后可实现跨数据集迁移学习，为通用细胞计数分析提供新方案。

链接：https://arxiv.org/abs/2608.14414

机构：University of Rostock（罗斯托克大学）； Marburg University（马尔堡大学）； Hessian Center for Artificial Intelligence（黑森人工智能中心）

作者：Syed Abdul Haseeb Qadri, Bjarne C. Hiller, Felix Blanke, Vanja Sophie Cangalovic, Kutalmış Coşkun, Amin Mirzaei, Tom Siegl, Sebastian Bader, Thomas Kirste, Martin Becker

英文摘要： Cytometry measures the complex characteristics of single cells (e.g., counts and protein expression of immune cells) and is widely used across immunological research and clinical settings. However, cytometry data is highly heterogeneous and unstandardized due to experimental protocols and the choice of measured features. While machine learning methods hold the potential to gain deeper insights into cell biology, these challenges make them difficult to apply and transfer across studies. Recent advances in foundation models can alleviate these issues, but corresponding approaches are still scarce in this field. To address this, we provide CytoBERT, a publicly available, open-source, open-weight foundation model for single-cell cytometry data with variable marker panels. CytoBERT is pretrained in a self-supervised manner on a large-scale cytometry corpus (15 human datasets with heterogeneous marker panels and more than 50 million cells) curated through marker standardization, enabling it to learn transferable inter-marker relationships within cells. Fine-tuning CytoBERT for sample-level classification demonstrates that transfer learning across heterogeneous cytometry datasets is feasible, providing a starting point for scalable, generalizable cytometry analysis. Code is available at GitHub.

AI 总结：本文针对Muon优化器难以与LoRA结合用于低秩微调的问题，提出sMuon方法，经实验验证其在SFT和ReLoRA预训练中表现良好，可适度提升低秩微调性能。

链接：https://arxiv.org/abs/2608.14492

机构：University of Bristol（布里斯托大学）； School of Mathematics（数学学院）； School of Engineering Mathematics and Technology（工程数学与技术学院）； University of Bath（巴斯大学）

作者：Ben Anson, Conor Houghton, Edward Milsom

英文摘要：The Muon optimizer shows clear benefits versus alternatives when pretraining neural networks. However, it is used less frequently for parameter-efficient fine-tuning (PEFT). One potential reason is that the most common PEFT method, LoRA, does not naturally combine with Muon since it is not mathematically possible to orthogonalize the weight update given by a low-rank parameterization. In this paper, we address this issue by approximating the solution to a relaxed Muon objective in the low-rank setting via linearization and then least-squares. We provide an efficient implementation that uses matmul operations only, as opposed to more complex linear algebra decomposition routines. Our method, sMuon (small Muon), performs favourably across SFT and a ReLoRA pretraining experiment. While results are model- and eval-dependent, we find overall that using Muon for low-rank fine-tuning provides moderate performance improvements.

AI 总结：该研究指出少量编码基准的优化无法提升通用编码能力，通过案例研究验证了基准排名难泛化、跨任务迁移差等问题，呼吁采用差异化评估与持续基准维护。

链接：https://arxiv.org/abs/2608.13566

作者：Egor Shibaev, Vera Kudrevskaia, Timur Galimzyanov, Mikhail Evtikhiev, Ana Terna, Rastislav Rabatin, Timur Kudashev, Timofey Bryksin, Arina Puchkova, Patrik Bartak, Egor Bogomolov, Sergey Titov

英文摘要：Post-training papers, model cards, and blog posts often treat scores on a small set of coding benchmarks (e.g., SWE-bench and LiveCodeBench) as evidence of broad coding capability, both for research artifacts and user-facing systems. We argue that optimization for these benchmarks leads to measuring task-specific performance, creating a meaning gap between measured scores and claims of general coding ability. We examine this gap with a Django-based case study benchmark suite we create. Evaluating foundation models and checkpoints post-trained on SWE-bench trajectories, we find that benchmark rankings frequently fail to generalize. Post-trained checkpoints show little cross-task transfer, and SWE-bench optimization yields limited or no gains on our tasks or on LiveCodeBench. Similarly, fine-tuning on individual Django modalities fails to transfer. We conclude that a small number of benchmarks is insufficient for evaluating diverse models under benchmark optimization pressure. We encourage the community to use differentiated evaluation - holistic assessment for frontier models, multi-task suites for research, and human-in-the-loop studies for narrow task applications. Finally, we argue for creating a capability taxonomy and sustained benchmark maintenance, rather than one-off benchmark releases. Without reliable evaluation standards, engineers and researchers using LLMs and agents have to rely on insufficient evidence to make research, development, and deployment decisions.

AI 总结：针对符号回归进化特征构建中重要特征易丢失的问题，提出基于特征重要性的自适应保护机制，经98个回归基准数据集和2个信用分类数据集验证，可提升解质量与搜索效率。

链接：https://arxiv.org/abs/2608.14209

机构：Centre for Data Science and Artificial Intelligence（数据科学与人工智能中心）； School of Engineering and Computer Science（工程与计算机科学学院）； Victoria University of Wellington（惠灵顿维多利亚大学）； Business School, Sichuan University（四川大学商学院）； Michigan State University（密歇根州立大学）

作者：Hengzhe Zhang, Qi Chen, Bing Xue, Lean Yu, Wolfgang Banzhaf, Mengjie Zhang

英文摘要：Evolutionary feature construction has shown strong promise in symbolic regression by automatically discovering informative transformations of input features that enhance a simple base learner. However, existing approaches often lack explicit mechanisms to preserve important constructed features discovered during evolution, and valuable genetic material can be lost when genetic operators disrupt effective features. This paper introduces an adaptive protection mechanism that leverages feature importance metrics to selectively preserve constructed features during evolution. The mechanism provides stronger protection for more important constructed features while still allowing less important features to be modified and to incorporate useful building blocks from more important features. We evaluate the approach using multiple feature importance calculation methods and demonstrate its robustness across different base learners. Experimental results on 98 regression benchmark datasets show that the proposed mechanism consistently improves solution quality over baseline approaches, and experiments on two credit classification datasets demonstrate that the method also extends effectively to improve search effectiveness beyond symbolic regression.

AI 总结： 提出与威胁模型无关的CodeSIFT方法，利用影响函数检测受污染的代码生成提示批次，在3B至7B参数的三个代码LLM上，中高注入率下AUROC达0.98，性能优于静态分析基线。

链接：https://arxiv.org/abs/2608.14303

机构：The University of Oxford（牛津大学）

作者：Francesco Quinzan, Noor Munir, Yishun Lu, Stephen Roberts

英文摘要：Large language models (LLMs) are increasingly used for code generation, yet they remain vulnerable to prompts that elicit insecure implementations. Existing defenses typically rely on predefined threat models or known vulnerability patterns, limiting their effectiveness against novel attacks. We propose CodeSIFT, a threat-model-agnostic detection method that leverages influence functions to identify batches of prompts that induce anomalous model behavior. Rather than detecting specific vulnerabilities, CodeSIFT measures the parameter-space influence of generated code and uses a statistical test to determine whether a candidate prompt set deviates from a benign reference distribution. To evaluate our approach, we introduce two benchmark datasets covering a variety of vulnerabilities. We evaluate CodeSIFT on three open-weight code LLMs ranging from 3B to 7B parameters, achieving AUROC scores of up to 0.98 at moderate-to-high injection rates, while maintaining well-calibrated false positive rates and substantially outperforming static analysis baselines. These results suggest that influence-function-based detection is a promising direction for identifying malicious code-generation prompts without requiring prior knowledge of the underlying attack class.

AI 总结：针对现有合成表格数据生成方法难以处理多异构表格的局限，本文提出两阶段跨表格数据生成框架，结合扩散Transformer实现高保真合成数据生成，验证了其有效性。

链接：https://arxiv.org/abs/2608.14496

作者：Hao Yan, Lisa Pilgram, Dan Liu, Linglong Kong, Fida Dankar, Khaled El Emam

英文摘要：Cross-Tabular Data Generation (CTDG) seeks to learn a generative model from multiple heterogeneous tables and produce new synthetic tabular datasets. However, existing synthetic tabular data generation methods are largely restricted to single-input-table scenarios and struggle to effectively handle multiple heterogeneous tables with diverse feature sets. To address this limitation, we propose a two-stage framework for cross-tabular data generation. In the first stage, each heterogeneous raw table is transformed into a standardized statistical table with the same set of columns across all tables. Each statistical table captures the marginal distributions of the original columns and the pairwise correlations among them. In the second stage, a diffusion transformer model is trained to capture structural patterns across these homogeneous statistical tables and to generate synthetic statistical tables. Synthetic raw tables are subsequently reconstructed from the generated statistical tables via multivariate Gaussian sampling followed by an inverse probability integral transform. This two-stage CTDG framework enables the learning of a unified generative model from multiple heterogeneous tables and supports the generation of an unlimited number of realistic synthetic heterogeneous tables. Experimental results demonstrate high fidelity in the learned statistical representations and a favorable fidelity-diversity trade-off in the generated synthetic data, validating the effectiveness of the proposed approach.

AI 总结：该研究针对稀疏事件场景下标准神经算子的适用性局限，提出L-FNO随机神经算子，经8个合成基准和3个真实世界数据集验证，其在事件似然等指标上优于基线模型，为随机事件动力学建模提供有效方法

链接：https://arxiv.org/abs/2608.13562

机构：Tech University of Korea（韩国技术大学）

作者：Songhee Kang, Jihoon Kang

英文摘要：Modern operational systems face uncertainty even in routine conditions, where rare, bursty, and self-exciting events emerge from both exogenous covariates and endogenous event dynamics. Standard neural operators are typically trained as regression-style function-to-function models rather than conditional-intensity estimators, limiting their suitability for sparse event regimes. We introduce the Lorentzian Fourier Neural Operator (L-FNO), a stochastic neural operator that combines an FNO-style covariate path, Lorentzian spectral kernels for history-dependent excitation, and a likelihood-based training objective. We evaluate L-FNO on eight synthetic point-process benchmarks and three real-world datasets covering disease outbreak prediction and semiconductor fault or defect detection. L-FNO improves event likelihood, calibration diagnostics, and rare-event detection over regression- and likelihood-based neural operator baselines. These results show that structured spectral memory and likelihood-based learning provide effective inductive biases for neural operator models of stochastic event dynamics.

AI 总结：本文综述近期基于深度学习的药物-靶点结合亲和力预测方法，分析其优势、局限与研究缺口，指出当前方法存在数据集偏差等问题，探讨未来研究方向。

链接：https://arxiv.org/abs/2608.13797

机构：Prairie View A&M University（普雷里维尤农工大学）

作者：Jafin Khan, Md Hossain Shuvo

英文摘要： Computational approaches to drug discovery involve multiple sub-problems, and among them, drug-target binding affinity prediction plays an important role. Despite recent advances, accurately predicting binding affinity remains an open research area. The major objective of our paper is to perform a comprehensive review and comparative analysis of recent machine learning methods for drug-target binding affinity prediction, with a focus on identifying strengths, limitations, and research gaps. We review representative recent deep learning approaches that use common benchmark datasets and evaluation metrics, covering a range of neural network architectures and representation strategies. In addition, we analyze seven widely used benchmark datasets and commonly adopted evaluation metrics for drug-target binding affinity prediction. Our analysis indicates that although many methods report strong performance on standard benchmarks, their effectiveness is often influenced by dataset bias and limited evaluation settings. Furthermore, most methods exhibit reduced performance in cold-start scenarios, highlighting challenges in generalization. We identify several limitations of current approaches, including dataset imbalance, the lack of standardized evaluation, limited real-world applicability, and challenges in cold-start scenarios. We also discuss future research directions, including better dataset design, more robust evaluation methods, improved handling of cold-start problems, and the integration of multimodal representations.

AI 总结：该研究提出模型无关的RAEF方法，通过改进检索与聚合机制提升时间序列预测性能，其效果优于RAF，兼具高效性与竞争力，可替代微调用于时间序列预测的领域适配。

链接：https://arxiv.org/abs/2608.14054

作者：Juan Pablo Villa Serna, Rohan Asthana, Vasileios Belagiannis

英文摘要：Time series forecasting with pretrained foundation models has demonstrated strong zero-shot capabilities. However, achieving optimal performance on time series with short or negligible historical data in domain-specific applications typically requires adaptation via either fine-tuning or RAG. While fine-tuning is effective, it incurs substantial computational costs. This work explores RAG within univariate time series (Retrieval Augmented Generation) as a more efficient alternative, in particular RAF (Retrieval Augmented Forecasting), and introduces RAEF (Retrieval-Augmented Extended Forecasting), a model-agnostic method built upon RAF. RAEF incorporates key refinements to the retrieval and aggregation mechanisms: (1) direct retrieval in input-space rather than embedding-space, reducing inference overhead, and (2) concatenation-based aggregation that preserves temporal structure instead of averaging. Empirical evaluation across multiple benchmark datasets demonstrates that RAEF outperforms RAF in both accuracy and inference overhead. Furthermore, comprehensive comparisons with zero-shot and fine-tuned foundation models show that RAEF achieves competitive or superior performance to fine-tuning while avoiding its computational burden, establishing it as a practical and scalable approach for domain adaptation in time series forecasting.

AI 总结：本研究质疑扩散时间序列预测器迭代采样均有益的观点，提出无标签全局停止准则与伯努利时间步采样器，经八组真实数据集实验验证，可提升预测精度并加快推理速度。

链接：https://arxiv.org/abs/2608.14067

作者：Dat Nguyen-Cong, Luong Tran, Tung Kieu

英文摘要：Diffusion models offer a natural way to model uncertainty in time series forecasting, yet their iterative sampling process is often treated as a uniformly beneficial refinement procedure. Our study challenges this view by examining how forecast quality evolves throughout reverse diffusion. We find that general temporal structure is often recovered at relatively high noise levels, whereas continued low-noise refinement can introduce statistical drift and degrade the final forecast. Our analysis further suggests that this behavior explains why prior methods often favor relatively narrow diffusion architecture and schedule design. Building on this observation, we propose a label-free global stopping criterion that detects the optimal termination point, eventually speeding up inference and improving predictive accuracy. Additionally, since early stopping terminates inference in high-noise regions, we propose a Bernoulli timestep sampler that concentrates training on this region while preserving coverage of the full diffusion process. Extensive experiments conducted across eight real-world datasets demonstrate the superior performance of our method compared to existing approaches.

AI 总结：针对1000只美股每小时收益预测出现的预测崩溃现象，本文分析其成因，提出CalibRank目标函数平衡校准与排名，在Finance1K上提升了截面相关性。

链接：https://arxiv.org/abs/2608.14106

作者：Shu Wan, Miles Ma, Hank Zhu, Guangqi Liu, Stephen Wang, Qingsong Wen, Huan Liu

英文摘要：When forecasting hourly returns for 1,000 US equities, we observe an unexpected phenomenon: predictions become nearly flat and show poor stock ranking, as measured by cross-sectional correlation. We call this forecast collapse. Surprisingly, the phenomenon largely disappears when forecasting trading volume under the same setting. We investigate forecast collapse across time-series foundation models (TSFMs), twelve deep-learning forecasting models, and 97 public benchmark configurations, and find that it is closely tied to target predictability. We identify two distinct reasons behind it: low predictability limits the amplitude of calibrated point forecasts, while per-series objectives leave cross-series structure unidentified. These findings reveal a calibration-ranking tradeoff: optimizing squared error leads to flat predictions, whereas directly optimizing cross-sectional correlation improves ranking but can inflate forecast amplitude by more than an order of magnitude. To address this tradeoff, we introduce CalibRank, a simple objective that balances calibration and ranking. On Finance1K, CalibRank nearly triples cross-sectional correlation while keeping amplitude close to the target, and improves correlation on all tested models. Our results reveal a blind spot in conventional time-series evaluation: per-series metrics can hide failures in cross-series structure needed by downstream decisions.

AI 总结：针对欧拉与拉格朗日流体动力学表示的不匹配问题，提出可迁移潜算子TLO，在五个基准测试中于两类任务均优于现有神经算子，经微调后性能进一步提升。

链接：https://arxiv.org/abs/2608.14120

作者：Meng Li, Chuqi Chen, Zhengqing Gao, Xi Zhou, Xiao Sun, Yang Xiang, Huaxi Huang

英文摘要： Lagrangian modeling is vital to fluid dynamics, as it characterizes particle transport and complements the Eulerian this http URL, Lagrangian trajectories are less commonly available than Eulerian fields, while most neural operators are trained and evaluated primarily in the Eulerian representation. This mismatch motivates a new learning problem: can a model trained solely on Eulerian observations generalize zero-shot from Eulerian field prediction to Lagrangian particle rollout, without Lagrangian supervision or task-specific adaptation? To address this problem, we propose the Transferable Latent Operator (TLO), which learns a unified flow representation shared by Eulerian field prediction and Lagrangian particle rollout. TLO decouples latent flow evolution from coordinate-dependent decoding: querying the evolving latent representation at fixed spatial coordinates yields Eulerian fields, whereas querying velocities at particle positions and recursively updating these positions enables Lagrangian rollout. Across five fluid-dynamics benchmarks, TLO consistently outperforms existing neural operators in both Eulerian field prediction and zero-shot Lagrangian rollout, with further gains from limited Lagrangian fine-tuning.

AI 总结：本文提出经典深度玻尔兹曼机（DBM）作为表格型异常检测的互补能量模型，实验显示其与自编码器融合后在两个基准数据集上性能显著提升，为该领域提供了新的有效工具。

链接：https://arxiv.org/abs/2608.14186

机构：Meijo University（名城大学）

作者：Junichiro Niimi

英文摘要：Tabular anomaly detection is dominated by classical density-proxy methods (Isolation Forest, OCSVM, LOF), reconstruction-based detectors (Autoencoders, VAEs), and modern non-parametric scorers (COPOD, ECOD, Deep SVDD), all of which approximate the inlier distribution only indirectly; explicit energy-based models are largely absent. Motivated by the recent revival of EBMs in deep learning (e.g., Energy-Based Transformers, JEPA), we revisit the classical Deep Boltzmann Machine (DBM) for this task and hypothesize that its mean-field energy combines more effectively with a reconstruction-based score than same-lineage pairs do. We evaluate a two-hidden-layer DBM on two tabular benchmarks spanning distinct domains (UCI Bank Marketing and NSL-KDD) against eight classical and modern baselines across twenty random seeds. The DBM mean-field energy matches the strongest baseline (the Autoencoder) on Bank Marketing and statistically beats it on NSL-KDD, while significantly outperforming the remaining seven on both datasets. When fused with the Autoencoder via rank fusion, the DBM energy yields a statistically significant improvement on both datasets (AUROC=+0.014, p<0.01 on Bank Marketing; +0.002, p<0.001 on NSL-KDD); every non-DBM-derived base model instead fails to improve or significantly degrades the AE-paired ensemble. Our position is that classical EBMs, exemplified by the DBM, deserve a place in the tabular anomaly detection toolbox as a non-redundant complementary view to the reconstruction-based scores that dominate current practice.

AI 总结：本文针对XGBoost易受垂直异常值和杠杆点影响的问题，提出基于鲁棒回归估计量的MM-XGBoost两步方法，实现了鲁棒性与预测精度的最优权衡。

链接：https://arxiv.org/abs/2608.13590

机构：KU Leuven（鲁汶大学）

作者：Iris Aragón Mladosich, Christophe Croux

英文摘要：XGBoost is a very popular and powerful method for prediction. It iteratively fits simple decision trees to the residuals of the previous step. An efficient and scalable implementation is available. The standard loss function for XGBoost is the quadratic loss, but a Huber loss can also be used. In this paper, we study the robustness of XGBoost and show that its performance can be affected by vertical outliers and leverage points. To address this, we explore alternative loss functions, based on M-, S-, and {\tau} -estimators from robust regression. Our results indicate that a two-step procedure, referred to as MM-XGBoost, provides the best trade-off between robustness and prediction accuracy.

AI 总结：本研究在三种噪声场景下对比不确定性采样与随机采样，发现其标签效率受数据集、预算等因素影响，未找到结构化错误定位带来普遍额外惩罚的证据。

链接：https://arxiv.org/abs/2608.13601

作者：John Myron Uy

英文摘要：Active learning can reduce labeling cost by selecting informative examples, but the most uncertain examples may also be the hardest to label correctly. This study tests whether uncertainty sampling fails because it acquires more corrupted labels or because errors concentrated in difficult regions are especially harmful. Margin-based uncertainty sampling is compared with random sampling under clean labels, random classification noise (RCN), and bounded difficulty-dependent noise on three public binary tabular datasets. The design uses 100 paired seeds, nine expected noise rates from 0 to 0.30, annotation budgets from 20 to 120, and logistic regression with regularization re-selected by cross-validation at every budget. An exposure-matched RCN control aligns mean final acquired corruption, while a clean-label extension reaches budget 400. Under clean labels, uncertainty sampling improved normalized balanced-accuracy area under the learning curve by 1.09 to 1.77 percentage points on all datasets. Difficulty-dependent noise reduced this advantage more than RCN at six of eight rates on Breast Cancer Wisconsin, but at no tested rate on Banknote Authentication or MAGIC Gamma Telescope. Exposure-matched analyses found no corrected evidence for a universal additional penalty from structured error location. On clean MAGIC data, uncertainty sampling improved balanced accuracy while reducing average precision and true-positive rate at fixed false-positive rates. Thus, uncertainty sampling was label-efficient, but its apparent robustness depended on dataset, budget, noise structure, and evaluation metric.

AI 总结：本文提出KRPRVFL模型，结合RVFL效率与KRP准则鲁棒性，引入协作学习机制，经UCI和KEEL数据集实验，其在分类任务中性能优于基线模型。

链接：https://arxiv.org/abs/2608.13628

机构：Indian Institute of Technology Indore（印度印多尔理工学院）

作者：A. Quadir, A. Rahaman, Mushir Akhtar, M. Tanveer

英文摘要： Random vector functional link (RVFL) networks are lightweight and fast neural models that offer efficient training and strong generalization through randomized hidden-layer weights and direct input-output connections. However, conventional RVFL models are sensitive to noisy labels, outliers, and imbalanced data, which limits their performance in real-world applications. To address these challenges, we propose the kernel risk-sensitive mean p-power based RVFL (KRPRVFL) model, which integrates the computational efficiency of RVFL with the robustness of the kernel risk-sensitive mean p-power (KRP) criterion. By replacing the standard least-squares objective with a KRP-based loss, KRPRVFL adaptively reduces the influence of corrupted or unreliable samples during training, resulting in improved stability and generalization. Additionally, a collaborative learning mechanism is introduced to enable adaptive interaction among model components, further enhancing robustness in complex and noisy environments. The proposed framework also leverages kernel-induced feature mapping to capture nonlinear relationships without requiring explicit hidden-layer selection, maintaining both efficiency and scalability. Extensive experiments on UCI and KEEL benchmark datasets demonstrate that KRPRVFL consistently outperforms baseline models in terms of accuracy, robustness, and statistical significance, highlighting its effectiveness as a fast, scalable, and reliable solution for challenging classification tasks.

AI 总结：该研究针对线性注意力长上下文下的存储项干扰问题，提出查询衍生擦除方向（QED），可提升检索性能并在S-NIAH-1上使可用上下文长度约翻倍。

链接：https://arxiv.org/abs/2608.13668

作者：Dhruman Gupta, Aritra Das, Debayan Gupta

英文摘要：Linear attention keeps a state of fixed size. At long context, many stored items share this state, and interference between them degrades retrieval. Gated DeltaNet-2 (GDN-2), like every delta-rule model before it, derives its erase vector from the key of the current token. However, the interference in its reads is measured through the query, and the erase step cannot reach it. We introduce the Query-derived Erase Direction (QED). QED adds a second erase direction derived from the query and orthogonal to the key. In the fast-weight view, a key-directed delta edit cannot change the key-orthogonal part of a read. It uses the editable part to cancel old-state content measured along the query. It also improves retrieval at every length past the training window, and it about doubles the usable context length on S-NIAH-1.

AI 总结：该文梳理2018-2026年语言模型进展，发现2024年末后编码能力年提升近6倍、能力-成本曲线崩溃，专用模型成趋势，Qwen 2.5数学测试及置信度工具验证了相关结论，研究材料全公开。

链接：https://arxiv.org/abs/2608.13675

作者：Pranav Kumar Kaliaperumal

英文摘要：Between October 2018 and July 2026 AI models progressed from simple systems like BERT to massive agents that solve complex math and write software. The ability to resolve real coding issues improved by nearly six times per year since late 2024. During this time costs dropped sharply with OpenAIs budget model GPT 5 point 6 Luna matching flagship capabilities for just one to six dollars per million tokens beating older versions at a fraction of the price. Top performance is now split across specialized models as Claude Opus 5 leads in frontend coding Claude Fable 5 excels at repository level coding and GPT 5 point 6 Sol dominates terminal tasks. In a grade school math test using the Qwen 2 point 5 model basic methods solved 58 of 100 problems while advanced sampling solved up to 79. A confidence ranking tool correctly identified 47 right answers in its top 50 choices proving highly useful for sorting tasks with all research materials made fully public.

AI 总结：本研究提出EEG-PRISM，一种无需修改脑电基础模型的事后归因方法，可将其归因分数映射至频谱、空间域，能定位癫痫发作区、自闭症生物标志物等，提升脑电基础模型的可解释性。

链接：https://arxiv.org/abs/2608.13676

机构：Johns Hopkins University（约翰斯·霍普金斯大学）； Boston University（波士顿大学）

作者：Deeksha M Shama, Punnisa Amornsirikul, Archana Venkataraman

英文摘要：Objective: Foundation models represent the next advancement in AI for EEG analysis; however current explainable AI techniques provide attribution scores in the time-channel input space, which is mismatched to clinical intuition about EEG. Thus, there is a critical need for a universal method that can extend the interpretability of any foundation model to alternative and physiologically relevant domains without modifying or retraining the underlying model. Methods: EEG-PRISM leverages linear transformations and established backpropagation rules to map time-channel attribution scores into alternative domains. We derive mappings to the frequency domain via an invertible DFT and to the source domain via an approximately invertible EEG generative model. We evaluate EEG-PRISM in simulated and real data, assessing recovery of ground-truth phenomena across domains with five foundation models and four AI explainers. Results: In simulation, EEG-PRISM achieves near-perfect spectral recovery and 69.2% spatial accuracy. In epilepsy, EEG-PRISM correctly determines that delta-theta activity is most salient and correctly localizes the seizure onset region with 50% accuracy. In autism, EEG-PRISM localizes the predictive delta-alpha biomarkers to frontal and temporal regions, consistent with prior work. Conclusion: EEG-PRISM is a theoretically-grounded post-hoc attribution method with accurate mapping into the spectral and spatial domains. It supports window-level analysis of transient events (e.g., seizures) and group-level identification of clinically relevant biomarkers (e.g., autism), thus advancing interpretable EEG foundation models. Significance: This work enables physiologically-grounded interpretation of EEG foundation models and supports clinically relevant insights such as event localization and biomarker identification.

AI 总结：本研究提出 SAGE 机制，利用注意力熵估计的块级不确定性调整基于 Transformer 的脉冲神经网络的训练代理梯度斜率，在 CIFAR-10/100 上实现最高 1-2% 的稳定准确率提升，保留原始架构且部署成本不变。

链接：https://arxiv.org/abs/2608.13702

机构：University of South Dakota（南达科他大学）； USD Artificial Intelligence Research Lab（南达科他大学人工智能研究实验室）

作者：Kiran Nair, Rodrigue Rizk, KC Santosh

英文摘要：Spiking neural networks (SNNs) offer an energy-efficient alternative to conventional deep neural networks by exploiting sparse event-driven computation, but their training remains challenging because the non-differentiable spike function requires surrogate gradients whose fixed shape may be suboptimal across layers and training stages. In this work, we introduce SAGE, an uncertainty-modulated surrogate-gradient mechanism for Transformer-based SNNs. SAGE estimates block-level uncertainty from normalized self-attention entropy and uses this signal to adapt the surrogate-gradient slope during training while leaving the inference model unchanged. By modulating only the training-time surrogate parameter, the proposed method preserves the original architecture and deployment cost while improving optimization flexibility. Experiments on CIFAR-10/100 demonstrate that SAGE achieves improved accuracy over fixed-surrogate baselines, with results up to 1-2\% consistent gains across multiple simulation time steps. These results highlight the potential of attention-derived uncertainty as a lightweight training signal for adaptive surrogate-gradient learning in transformer-based SNNs.

AI 总结：本文针对推理任务的监督微调，发现数据选择的效果依赖模型容量与训练时长，高似然数据适配小型模型早期训练，低似然数据利于大型模型长期训练，提出需结合模型容量与计算预算选择数据。

链接：https://arxiv.org/abs/2608.13721

机构：Virginia Tech（弗吉尼亚理工大学）

作者：Cuong Dang, Hoang Anh Just, Ruoxi Jia

英文摘要：In reasoning supervised fine-tuning, candidate responses for the same instruction can differ substantially in how well they match the student's current distribution. Recent likelihood-based response selection methods suggest that responses closer to the student distribution provide more effective supervision, motivating the hypothesis that high-likelihood responses may generally be preferable for fine-tuning. In this paper, we revisit this intuition and show that the value of likelihood-based data selection depends critically on model capacity and training duration. Through controlled experiments on mathematical reasoning, using students ranging from 1.5B to 8B parameters and supervision generated by stronger teacher models, we observe a clear \emph{capacity-dependent} ``{\color{SMALLCOLOR}\textbf{Fast-Fit}} / {\color{LARGECOLOR}\textbf{Slow-Gain}}'' pattern. High-likelihood data provides faster and more stable early improvements, especially for smaller models, but low-likelihood data becomes increasingly beneficial for larger models when training is allowed to continue longer. To explain this phenomenon, we analyze learning dynamics, showing that small models often fail to absorb low-likelihood supervision and instead fall into shallow or repetitive behaviors, while larger models are better able to move toward the teacher distribution under such data. We further provide a capacity-constrained theoretical view of distillation that clarifies how data difficulty, data span, and student capacity jointly govern transfer. Overall, our findings show that effective data selection for reasoning should be aware of model capacity and computing budget rather than based on a single universal preference for high-likelihood supervision.

AI 总结：该研究验证了vLLM中INT8线性内核（CUTLASS与Triton）的可互换性，定位到差异源于累加器后的缩放应用与输出舍入，提出的干预措施可恢复端到端逐位一致，还揭示了FP8 GEMM差异的不同特征并发布相关一致性检查流程。

链接：https://arxiv.org/abs/2608.13756

机构：Krixvon（克里克斯冯公司）

作者：Teng-Ruei Chen

英文摘要：Two GPU kernels implementing the same scaled INT8 GEMM interface are usually treated as interchangeable. We test that assumption: holding the checkpoint, prompts, hardware, inference engine, decoding, and quantization configuration fixed, we swap only the INT8 linear kernel (CUTLASS versus Triton) inside vLLM. At 1.7B each arm reproduces itself bit-for-bit across cold restarts, yet the arms agree on no sequence in any end-to-end comparison we ran (0/8, 0/16, and 0/64). What makes this more than a benchmark discrepancy is an integer alibi: for shared INT8 operands under a verified no-overflow bound, the INT32 dot product is exact and order-independent, so the accumulator cannot be the source of any difference. Feeding both kernels identical operands from every linear layer of Qwen3-1.7B and 8B (196 and 252 layers), we find bit-identical outputs under power-of-two scales, confirming a pinned prediction list 196/196 and 252/252 (pre-registered at 1.7B, pinned but not blind at 8B), and observed differences of at most one bfloat16 spacing under the checkpoints' real scales. This localizes the divergence to scale application and output rounding after the exact accumulator. Applied as a probe checkpoint, the same intervention restores end-to-end bitwise agreement (8/8 and 16/16 sequences). Cross-implementation FP8 GEMM shows a different signature: both the prevalence and the magnitude of differences grow with reduction depth, while the INT8 fraction stays at parts per million and within one spacing over a 64x range of K. Teacher-forced replay ties layers to tokens: flips concentrate at small logit margins, which predict flip risk with ROC-AUC 0.94 on 16,384 positions. We will release the pre-registration, per-layer predictions, manifests with kernel-selection evidence, and a conformance procedure that turns these controls into a concrete check for kernel interchangeability.

AI 总结：本研究针对现有基于滚动的分子跃迁路径采样（TPS）控制方法不稳定且依赖随机种子的问题，提出FS-TPS和LaS-TPS两种随机策略，在三种生物分子系统上验证其可提升跃迁成功率与路径质量并降低初始化敏感性。

链接：https://arxiv.org/abs/2608.13800

作者：Jingqian Liu, Yu-Hsiang Wang, Yanru Qu, Ge Liu

英文摘要： Transition path sampling (TPS) aims to efficiently generate rare molecular transition trajectories between metastable states and is essential for understanding biomolecular mechanisms. Beyond traditional molecular dynamics (MD)-based sampling, machine learning has become central to state-of-the-art TPS. One major class of methods learns control forces during explicit MD rollouts. By preserving the underlying molecular dynamics, these methods tend to produce more physically plausible trajectories than endpoint-conditioned generators that construct paths directly. However, rollout-based control methods have been reported to exhibit unstable and strongly seed-dependent performance. We recast rollout-based control as learning a path-space proposal distribution and investigate stochasticity placement as a design choice for improving exploration and optimization robustness. We develop two stochastic policies: FS-TPS, which directly parameterizes a state-dependent Gaussian distribution over the control policy output, and LaS-TPS, which samples a compact latent control variable and decodes it into structured, cross-atom-correlated force variation. We conduct extensive multi-seed experiments on three biomolecular systems of increasing size: alanine dipeptide, chignolin, and BBL, a fast-folding protein. Stochastic policies consistently improve transition success and path quality over deterministic-policy baselines while substantially reducing sensitivity to random initialization.

AI 总结：本研究针对LLM生成样本质量异质性问题，提出基于句子嵌入空间欧氏距离的几何过滤框架，结合软加权机制提升小样本文本分类性能，在多任务、多模型及多配置下均表现优异。

链接：https://arxiv.org/abs/2608.13866

作者：Benjamín Schindler, Gonzalo A. Ruz

英文摘要：Large language models (LLMs) can generate synthetic training data for text classification, but the quality of generated samples is heterogeneous: some fall in correct class regions of the embedding space while others land in peripheral or cross-class zones. We propose a geometric filtering framework that evaluates each LLM-generated sample by its Euclidean distance to real class examples in a sentence embedding space, selecting only geometrically consistent candidates. A soft weighting mechanism transforms filter scores into sample weights for classifier training. Evaluated across 13 datasets, 5 classifiers, 10 augmentation methods, and over 6,700 configurations, our method achieves +2.61 percentage points (pp) over SMOTE ($p<0.0001$, Cohen's $d=0.95$, 88.9% win rate). The approach generalizes to named entity recognition (+9.26pp, 100% win rate) without filter modification, and is robust across 5 LLMs from 4 providers. A key finding is that the simplest distance-based filter consistently outperforms complex multi-criteria alternatives.

AI 总结：本文提出基于低秩二阶密度投影的高维非参数变点检测方法，利用低秩矩阵CUSUM等技术实现变点精确检测，在高维数据实验中表现优异。

链接：https://arxiv.org/abs/2608.13922

机构：North Carolina State University（北卡罗来纳州立大学）； Georgia Institute of Technology（佐治亚理工学院）

作者：Guoqing Zhang, Zhaixin Chen

英文摘要：Detecting distributional changes in high dimension is difficult when neither the pre-change nor post-change density is parametrically specified. We introduce a representation-based approach that retains all degree-at-most-two density information while replacing density estimation by matrix mean estimation. For observations in $[-1,1]^d$, a symmetric feature matrix $H_2(X)\in\R^{(d+1)\times(d+1)}$ is constructed so that $M(f)=\E_f H_2(X)$ is an isometric encoding of the degree-two orthogonal projection of the density. We scan matrix CUSUMs after rank-$r$ truncation, exploiting the low rank of the projected jump rather than sparsity of individual coordinates. The resulting \LRD{} estimator has a tent-shaped population objective and a nonasymptotic operator-norm analysis whose leading stochastic term scales as $\sqrt{rd\log(nd)}$. For multiple changes, we give a seeded narrowest-over-threshold procedure and prove exact recovery by an induction that preserves an isolating interval for every undetected change. A cross-fitted scalar refinement learns the changing low-rank direction on one fold and localizes on the other, attaining $\widetilde O_{\Pp}(\kappa^{-2})$ error; a matching Le Cam lower bound shows optimality up to logarithms. A geometrically $\beta$-mixing extension follows from a dependent matrix Bernstein inequality. Experiments with ambient dimension up to $200$, a three-change $d=100$ sequence, and a $128$-feature human-activity benchmark show that the method remains computationally practical and accurately detects pure dependence changes that are invisible to mean CUSUMs.

AI 总结：本文提出CForce方法，通过一致性强制提升dLLMs的并行解码性能，在LLaDA模型上实验证实其在高并行解码预算下可优化速度-质量权衡。

链接：https://arxiv.org/abs/2608.13925

机构：Shanghai Jiao Tong University（上海交通大学）； Ant Group（蚂蚁集团）

作者：Yuji Ren, Chenkai Xu, Zhuocheng Gong, Jianguo Li, Zhijie Deng

英文摘要：Diffusion large language models (dLLMs) accelerate language generation by predicting multiple masks in a single forward pass. However, existing dLLMs can suffer from unreliable predictions in early denoising stages under aggressive parallelism strategies, leading to errors that can propagate to later stages. To tackle this issue, we present Consistency Forcing (CForce) for dLLMs, a distillation method to force the mask predictions of early stages to align with those of later stages. CForce trains the model on pre-collected self-rollout trajectories, thereby improving training-inference alignment. We introduce Confidence Adaptive KL Divergence as a distillation objective to conjoin the merits of forward and reverse KL. We further provide a theoretical analysis for the consistency objective to explain why CForce can approximately minimize the prediction error of early stages. Critically, the same formulation applies to both mask-to-token decoding and edit-capable decoding; in the edit-capable case, later token-to-token refinements provide additional supervision for earlier masked-state predictions. Experiments on non-edit and edit-capable LLaDA models show improved speed-quality trade-offs, especially under high-parallelism decoding budgets. Code is available at: this https URL.

AI 总结：针对混合迭代生成模型训练后量化易引发模型崩溃的问题，提出HyGenQ框架，通过分层聚类解耦与缩放重校准，成功将其量化至8位精度且性能优于现有方法。

链接：https://arxiv.org/abs/2608.13932

机构：Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）； University of Illinois Chicago（伊利诺伊大学芝加哥分校）

作者：Jing Gao, Junyi Wu, Wei Wang, Yan Yan, Yao Zhao

英文摘要： Iterative Generative Models (IGMs) span autoregressive and diffusion paradigms, and hybrid variants that couple them can achieve remarkable image-generation fidelity. However, their iterative inference incurs substantial computational overhead, making Post-training Quantization (PTQ) appealing for acceleration, while directly applying vanilla PTQ to hybrid IGMs can trigger model collapse. By analyzing these failures, we identify two critical challenges: Excessive Outliers (EOs) in the activations create an irreconcilable trade-off between preserving normal precision and covering EOs, resulting in severe degradation in generation quality; Amplified Anomalies (AAs) arising unpredictably from minor quantization errors, create a mismatch between calibration and inference, thus iteratively triggering model collapse. To address these challenges, we introduce HyGenQ, a PTQ framework for hybrid IGMs. HyGenQ comprises Hierarchical Cluster Decoupling (HCD) and Scaling Recalibration (SR). HCD identifies and decouples outlier channels via a multi-stage clustering process, effectively isolating EOs while maintaining normal value precision, thereby alleviating performance degradation. SR scales AAs beyond Gaussian Bound, thereby avoiding model collapse caused by aggressive truncation. Extensive experiments demonstrate that HyGenQ successfully quantizes representative hybrid IGMs to 8-bit precision (W8A8), significantly outperforming existing baselines and validating its robustness across different model families.

AI 总结：该研究建立偏序上上下文学习的理论，明确开放世界假设下的完备三分法，表征开放世界教学数的最大值，利用坐标-序等价性得到精确表示边界，为偏序上的上下文学习提供理论支撑。

链接：https://arxiv.org/abs/2608.14004

机构：Indian Statistical Institute（印度统计研究所）

作者：Faizanuddin Ansari, Debanjan Dutta, Swagatam Das

英文摘要：In-context learning is commonly formalized as inference from examples of a function. Partial orders instead combine transitivity, antisymmetry, and incomparability, so a finite prompt may not determine a queried comparison. We develop a theory of in-context learning on partial orders that separates logical identifiability, prompt teaching cost, structural complexity, and the exact capacity of a formal coordinate-decoder class. A version-space semantics makes background knowledge and open- versus closed-world assumptions explicit. For finite open-world prompts with positive and negative comparisons, we prove an exact completion trichotomy: after taking the reflexive transitive closure of the positive demonstrations, a query is forced true, forced false because every true completion creates a cycle or violates a negative demonstration, or remains genuinely ambiguous. For a known $n$-element universe, we characterize the open-world teaching number as the number of covers plus a blocker-set hitting number, prove that its maximum over all $n$-element posets is $n(n-1)$ and is uniquely attained by the antichain, and identify the blocker term as the exact cost of open-world rather than complete-Hasse semantics. We formalize prompt-dependent $s$-coordinate decoders and use the classical coordinate-order equivalence to obtain an exact representation boundary: dimension at most $s$ is necessary and sufficient, while width at most $s$ is a convenient sufficient condition.

AI 总结：该研究探讨了添加正确数据可能损害学习性能的问题，定义插入稳定学习器可免疫于该问题，证明交闭类别具插入稳定性，且学习器与类别的适配性是关键而非单纯的类别或学习器优劣。

链接：https://arxiv.org/abs/2608.14020

作者：Joseph Sankoorikal Johny

英文摘要：Adding data known to be correct ought to be safe. Not always. Larsen, Pabbaraju and Shetty model the failure with a monotone adversary, which reads an i.i.d. training sample and may append as many further examples as it likes, provided the target hypothesis labels them all. Mehrotra has since settled the cost, showing that for classes of VC dimension d >= 2 no learner can guarantee expected error better than Theta((d/n)log(en/d)), a logarithmic factor above the clean PAC rate. Because that rate is a worst case over all classes, it says nothing about which classes actually suffer the penalty, and the answer turns on the learner. We call a learner insertion-stable if feeding it more correctly labeled examples can only shrink the region where it errs. Such learners are immune to the adversary, since on any given sample the risk after insertions never exceeds the risk on the clean part alone, however much is added and however cleverly it is chosen. High- probability guarantees carry over unchanged, and because Closure is insertion-stable every intersection-closed class keeps its clean rate of E[Err] <= (21d+34)/n. Immunity is not something the classical dimensions can predict. Two classes can agree on VCdim = Ldim = 2 and still split, one at Theta(1/n) and the other at Theta(log(en)/n), while intervals have unbounded Littlestone dimension and are immune anyway. On Mehrotra's hard class we prove more than the failure of a single algorithm, showing that no monotone permutation-invariant compression scheme of any finite size attains the clean rate. The question is therefore not whether a class is hard, nor whether a learner is good, but whether the two suit each other. Given an insertion-stable learner that is optimal on clean data, correct additions are free, and without one the cost belongs to the class, so changing the learner will not avoid it.

AI 总结：针对带删失需求的单仓库多门店系统，提出资源自适应原始对偶学习框架，获对数级预期悔值，优于现有策略，且经数值实验验证性能良好。

链接：https://arxiv.org/abs/2608.14096

机构：School of Management, Fudan University（复旦大学管理学院）

作者：Jiameng Lyu

英文摘要： The one-warehouse multi-store (OWMS) system is a fundamental inventory network in which a nonreplenishable warehouse allocates shared stock across multiple stores over time. Existing OWMS learning policies are built around a fixed target calibrated to the initial average resource rate, but such a fixed-target architecture cannot re-center after realized sales change the remaining resource available per future period. We develop Resource-Adaptive Primal-Dual Learning, a new learning framework that tracks the primal-dual resolving path with censored demand as the remaining-resource state evolves. In each period, the current resource rate indexes the target store allocations and dual variable, while censored sales provide gradient estimates for updating both. The analysis combines expected-sales geometry with a moving-target argument to yield logarithmic expected regret, improving on the state-of-the-art square-root-order guarantees of existing OWMS learning policies. The underlying design and analytical ideas may inform other online learning problems with depleting shared resources. Numerical experiments further demonstrate good finite-horizon performance of a practical variant across different horizon lengths and inventory regimes.

AI 总结：该研究针对存在撒谎神谕的m元序列预测场景，分别为随机与对抗环境提出算法并建立了遗憾的对数上界。

链接：https://arxiv.org/abs/2608.14102

机构：IIT Bombay（印度理工学院孟买分校）

作者：Puspabeethi Samanta, Nikhil Karamchandani, Jayakrishnan Nair

英文摘要：We consider the problem of sequential prediction of an $m$-ary sequence, where at each epoch, (i) the environment selects an outcome from an $m$-ary alphabet, (ii) the learner selects a probability distribution over the same alphabet (unaware of the outcome generated by the environment), and finally, (iii) the learner incurs a cost that depends on the probability assigned to the outcome. The cost function we consider captures the complexity of predicting the outcome generated by the environment, in a scenario where the aforementioned prediction is performed via comparative queries to a lying oracle. We consider both stochastic and adversarial environments, propose algorithms for both settings, and establish logarithmic upper bounds on their regret.

AI 总结：本文针对带现实约束的车辆路径问题，开发了Smart Routes平台，对比SCIP、LKH、JAMPR等方法，发现深度学习与经典启发式算法在大规模问题上比精确求解器SCIP更高效且解质量接近。

链接：https://arxiv.org/abs/2608.14140

机构：Moscow State University（莫斯科国立大学）

作者：Andrew Soroka, German Mikhelson, Alexander Mescheryakov, Sergey Gerasimov

英文摘要：The problem of route optimization with realistic constraints is becoming extremely relevant in the face of global urban population growth. While we are aware of approaches that theoretically provide an exact optimal solution, their application becomes challenging as the problem size increases because of exponential complexity. We investigate the Capacitated Vehicle Routing Problem with Time Windows (CVRPTW) and compare solutions obtaining by exact solver SCIP with heuristic algorithms such as LKH, 2-OPT, 3-OPT, the ORTools framework, and the deep learning model JAMPR. We demonstrate that for problem of size 50 deep learning and classical heuristic solutions became close to SCIP exact solution but requires less time. Additionally for problems with size 100, SCIP exact methods around 13 times slower that neural and classical heuristics with the same route cost and on around 50% worse for the first feasible solution on the same time. To conduct experiments, we developed the Smart Routes platform for solving route optimization problems, which includes exact, heuristic, and deep learning models, and facilitates convenient integration of custom algorithms and datasets.

AI 总结：针对表格基础模型（TFMs）公平性未被充分探索的问题，本研究提出FairTFM训练策略，将公平约束融入TFMs训练，在132个公平任务上实现公平性提升且保持竞争力准确性。

链接：https://arxiv.org/abs/2608.14211

机构：ÉTS Montréal（蒙特利尔高等技术学院）； Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）； Layer 6 AI（第六层人工智能公司）； University of Calgary（卡尔加里大学）； CIFAR（加拿大高级研究所）

作者：Patrik Kenfack, Jesse C. Cresswell, Anthony L. Caterini, Samira Ebrahimi Kahou, Ulrich Aïvodji

英文摘要：Tabular Foundation Models (TFMs) have emerged as leading methods for tabular predictive tasks, leveraging in-context learning to predict on new data without task-specific training. Despite the increased use of TFMs in high-stakes decision-making, their fairness properties remain largely unexplored. In this work, we incorporate fairness constraints directly into TFM training, enabling fair predictions in a single forward pass. Our approach addresses two key challenges: limited access to sensitive attributes in training data, and the incompatibility of existing fairness techniques with the in-context learning paradigm. We propose FairTFM, a scalable training strategy based on synthetic fairness tasks and a fairness-aware architecture using a gradient reversal layer, which encourages the model to learn representations invariant to sensitive attributes. Experiments on 132 fairness tasks show consistent improvements in fairness while maintaining competitive accuracy.

AI 总结：提出无需训练的AutoSchema框架，用于异构知识图谱的智能体文本转SPARQL的实时模式接地，在多项生物医学KGQA等任务中优于TogoMCP，可支持未记录RDF图谱。

链接：https://arxiv.org/abs/2608.14228

机构：The University of Tokyo（东京大学）； National Institute for Materials Science（国立材料科学研究所）； RIKEN Center for Advanced Intelligence Project（理化学研究所高级智能项目中心）

作者：Yiming Zhang, Koji Tsuda

英文摘要： Life science knowledge graphs make large collections of structured data available through SPARQL, but each resource uses its own schema, identifiers, and links. TogoMCP helps language model agents query these resources by providing curated Metadata Interoperability Exchange files. Creating and maintaining these files still requires language model assisted drafting, validation, and manual review. We study \emph{live schema grounding}, where an agent obtains the schema evidence needed for a question directly from the current endpoints. We present \textsc{autoschema}, a general framework for live schema grounding that requires no training. It inspects live schemas, maps entity names in a question to graph identifiers, explores relation paths, and finds possible connections between resources during iterative query construction. We use TogoMCP as our main comparison framework. We evaluate \textsc{autoschema} on Resource Focused Biomedical KGQA, Multi Resource Biomedical KGQA, Longitudinal Biomedical Semantic QA over BioASQ Task B, and Chemistry Knowledge Graph Transfer to a previously undocumented RDF graph. \textsc{autoschema} improves mean factoid accuracy over TogoMCP in the biomedical KGQA tasks and gives consistent gains in the longitudinal BioASQ evaluation. It also reduces iteration budget exhaustion and uses fewer tool calls on average in the core evaluation. The transfer study gives preliminary evidence that live schema grounding can support irregular and previously unseen graphs without first creating a curated schema file.

AI 总结：该研究提出多种适用于SVM和神经网络的新型凸损失函数，结合粒子群优化算法求解原始SVM问题，经嵌套交叉验证实验，发现新型损失函数对部分数据集的泛化性能无显著影响。

链接：https://arxiv.org/abs/2608.14288

机构：DAIS

作者：Filippo Portera

英文摘要：We propose multiple new convex losses for SVM and Neural Networks, applied to binary classification tasks. While there are practical limitations in exploiting them with the dual SVM models, we are able to use them with SVM primal formulation and Neural Networks. In detail, the primal SVM problem with the modified losses has been solved with the Particle Swarm Optimization algorithm. We prove that the proposed losses are a generalization of the standard loss, and we experiment them with several small data-sets. This preliminary study shows that using pattern correlations inside the loss function could in theory enhance the generalization performances on some data-sets. To evaluate the performance of each loss, we adopt a Nested Cross-Validation procedure. Results show that generalization measures are the same with or without the new losses.

AI 总结：该研究提出一种无训练的非参数时空轨迹预测方法，无需GPU和学习参数，在数据充足时精度与57M参数Transformer相当，数据稀缺时性能显著更优，可从少量历史数据部署到新区域。

链接：https://arxiv.org/abs/2608.14349

机构：Amazon Web Services（亚马逊网络服务）

作者：Michael Fore, Akshay Jain, Justin Downes, Rohan Pradhan, Duncan Botti

英文摘要：We present a training-free method for multi-modal trajectory prediction that achieves comparable accuracy to a 57M-parameter transformer while requiring no GPU and zero learned parameters. The method builds a transition table of historical state-to-next-position pairs and retrieves neighbors using a product kernel over spatial proximity, bearing, speed, and temporal context. Two inference modes operate over this shared representation: diversity-penalized sampling produces trajectories covering distinct plausible routes, while beam search finds the highest-likelihood path. On the TrAISformer benchmark (Danish Maritime AIS), our method achieves competitive accuracy at full data availability and dramatically outperforms the transformer in data-scarce regimes---remaining stable down to 10% of training data where TrAISformer degrades catastrophically. This enables deployment in new geographic regions from an order of magnitude less historical data, and with no GPU training.

AI 总结：本研究提出用无需重复训练的随机权重平均（SWA）替代高成本的深度集成，结合数据增强实现等方差增强，经多模型数值实验验证了其有效性。

链接：https://arxiv.org/abs/2608.14373

机构：Chalmers University of Technology and the University of Gothenburg（查尔姆斯理工大学与哥德堡大学）； Umeå University（于默奥大学）

作者：Longde Huang, Axel Flinth, Jan E. Gerken

英文摘要：The symmetries of a learning task have become an important factor in designing modern deep learning solutions. Data augmentation is a straightforward and effective way of incorporating symmetries into a generic neural network. Recent results show that infinitely large deep ensembles show perfect symmetry when trained on augmented data. However, since training ensembles requires repeating the training process many times, this method is costly. In this work, we study stochastic weight averaging (SWA) as an alternative ensembling technique that does not require repeated training runs. We analyze SWA by approximating the stochastic training trajectory at the end of training with an Ornstein--Uhlenbeck process. We show that in the infinite-width limit, SWA on augmented data provides an equiviariance boost that goes beyond what could be expected from the performance increase due to SWA alone. We verify our results with extensive numerical experiments on numerous models spanning computer vision and graph classification with both discrete and continuous symmetries.

AI 总结：研究发现幂采样存在悖论，即提升正确轨迹概率却降低下游推理性能，归因于剂量与覆盖不匹配，提出修复后的支持保留幂采样器可逆转损失并优于标准多采样推理。

链接：https://arxiv.org/abs/2608.14420

机构：State Key Laboratory of General Artificial Intelligence, Peking University（北京大学通用人工智能 State Key Laboratory）

作者：Haohui Yang, Jiaxing Sun, Xiujun Ma

英文摘要：Power Sampling sharpens a language model's distribution over complete generation trajectories, offering a verifier-free way to improve reasoning at inference time. It also has the potential to serve as a general-purpose front end for a broad range of downstream sampling methods. However, we uncover a striking paradox: Power Sampling can drive more probability mass toward correct trajectories while degrading the downstream inference it is intended to enhance. Using self-consistency as a representative case, we observe accuracy drops of up to 18.5 percentage points across models and reasoning benchmarks. We trace this paradox to two mismatches. Dose mismatch arises because a fixed exponent induces drastically different amounts of distributional change across problems. Coverage mismatch arises because global sharpening concentrates mass on a narrow set of dominant paths: high pass@k, often interpreted as evidence of preserved diversity, can therefore coexist with the loss of broad reasoning-path support required for downstream aggregation, search, and selection. Guided by this diagnosis, we replace uniform trajectory exponentiation with a deformation-controlled, support-preserving Power target that calibrates sharpening across problems while limiting the suppression of moderate-probability paths. In a same-budget instantiation with weighted self-consistency, the repaired sampler reverses the losses caused by global Power and outperforms standard multi-sample inference across reasoning benchmarks.