机器学习学术速递[8.7]

AI 总结：该研究针对多模态指令多要求重要性不等的问题，提出PRISM四阶段数据合成框架，结合PRISM-Eval评估，提升多模态大模型的多规则优先级感知指令遵循能力。

链接：https://arxiv.org/abs/2608.05249

作者：Xiaomin He, Dongling Xiao, Jiahao Xie, Ruiqi Lu, Qianle Wang, Zhongbin Guo, Wanxuan Sun

英文摘要：Real-world multimodal instructions often bundle multiple requirements with unequal importance, yet most multimodal training data still reduce instruction following to answering one self-contained question. We study this gap through \textbf{rubric comprehension}, which casts the model not as a generator measured against rubrics but as an \textbf{executor} that follows them: given an image and a typed, prioritized rubric, the model must verify each rule before producing an overall judgment. To support this setting, we propose \textbf{PRISM}, a four-stage data synthesis framework that produces persona--task pairs, prefix-guided rule sets, quality-filtered rubrics, and structured verification traces. We further introduce \textbf{PRISM-Eval}, whose Loose and Strict metrics use deterministic matching against fixed labels and therefore require no inference-time judge model. With only 10K synthesized samples, PRISM lifts Qwen3-VL-4B from 9.5\% to 30.1\% Strict accuracy on PRISM-Eval while preserving average performance on general benchmarks, and the gains transfer to four additional open-source MLLMs across dense and MoE architectures, suggesting that structured rubric supervision is a scalable path toward multi-rule, priority-aware multimodal instruction following.

AI 总结：该研究提出一种可证明的端到端流程，通过观测谱滤波（OSF）的凸学习结合谱到LDS的蒸馏，从非线性动力学系统中提取事后最优线性状态空间模型，实验验证其性能优于或匹配直接训练基线。

链接：https://arxiv.org/abs/2608.05416

机构：Princeton University（普林斯顿大学）

作者：Liane Galanti, Devan Shah, Shlomo Fortgang, Elad Hazan

英文摘要：Can nonlinear dynamical systems be learned through a compact linear state-space representation, without directly solving a non-convex system-identification problem? We give a provable pipeline for doing so. Starting from observations of an unknown nonlinear dynamical system, we first learn an implicit spectral predictor using Observation Spectral Filtering (OSF), a convex method that competes with the best linear observer for the system. We then apply spectral-to-LDS distillation to convert this predictor into an explicit recurrent linear dynamical system. Our main theorem shows that the average prediction error of the distilled LDS decomposes into an exponentially-small distillation term and the OSF learning term governed by the Luenberger complexity of the best observer. The guarantee is dimension-free: it depends on observer complexity rather than on the latent dimension needed to represent the nonlinear system. To our knowledge, this yields the first end-to-end provable method for extracting a best-in-hindsight LDS representation of nonlinear dynamics through convex learning followed by provable distillation. Experiments on linear LDS benchmarks and MuJoCo behavior cloning show that the train-then-distill pipeline produces compact LDS predictors that match or outperform directly trained baselines.

AI 总结：本研究针对热锻造中工件直接跟踪不可靠的问题，提出结合深度学习视觉与事件驱动有限状态机的设备中心式工件定位框架，在实际工厂实现高事件检测准确率与可靠定位，支持可视化与定量分析。

链接：https://arxiv.org/abs/2608.05744

作者：Dohyeon Kong, Jaebong Cho, Hyunbo Cho

英文摘要：Continuous workpiece localization is essential for traceability and process coordination in hot forging, but direct tracking is unreliable because of extreme temperatures, surface degradation, and irregular routing. This study presents an equipment-centric framework that infers workpiece locations from handling equipment observed by multiple static 2D cameras. The framework estimates floorplan-space 3D equipment coordinates and recognizes grasp and release activities. Event-driven finite state machines validate these activities as discrete handling events and continuously update workpiece states and locations. A keypoint-guided attention mechanism integrated into a 3D convolutional neural network improves activity recognition by focusing on functionally relevant equipment regions. Evaluation in an operational hot forging factory achieved 100\% event detection accuracy within a 33-second tolerance window, a mean localization error of 317.8 mm, and a mean system latency of 21 seconds. The framework connects vision-based perception with interpretable event-driven reasoning and supports visualization of workpiece transfers and quantitative analysis of equipment operations.

AI 总结：该研究探究自预训练（SPT）对Transformer在医疗时间序列诊断任务的影响，发现SPT可提升分类准确率0-6个百分点，是无需修改架构的通用有效策略。

链接：https://arxiv.org/abs/2608.06122

机构：Università Campus Bio-Medico di Roma（罗马生物医学大学校园大学）； Umeå University（于默奥大学）； Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）； ELLIS Institute Tübingen（埃利斯研究所蒂宾根分所）

作者：Omar Coser, Antonio Orvieto, Paolo Soda, Loredana Zollo

英文摘要：Inspired by recent evidence that transformer architectures benefit from Self-PreTraining (SPT) on long-context benchmarks, we investigate whether similar gains extend to multimodal, multivariate, and even simple univariate medical time series. Our objective is to assess the impact of SPT on the performance and scalability of transformer-based models across diverse medical applications, particularly under limited data conditions. We evaluate transformer architectures on three representative medical time-series tasks: rehabilitation robotics (Camargo dataset), stress detection (Non-EEG Stress), and Parkinson's disease detection (Gait Parkinson's Disease). Models are trained either from scratch or through SPT using four masking-based objectives designed to promote temporal and cross-modal representation learning, and we systematically vary model depth to examine how capacity interacts with pre-training benefits. Across datasets and configurations, SPT consistently improves classification accuracy by 0-6 percentage points depending on masking strategy, dataset and architecture, with gains observed not only in multivariate settings but also when models are restricted to simple univariate inputs. The improvements increase for deeper models that can better exploit the enriched temporal representations learned during pre-training. These findings indicate that SPT is a simple and general strategy that enhances transformer performance on medical time-series tasks without requiring task-specific architectural changes, supporting its potential to improve robustness and accuracy in data-limited clinical settings.

AI 总结：本研究提出基于注意力的 Surv-IPTB 模型，将生存数据的 IPTB 估计转化为二分类问题，通过成对患者比较处理右删失数据，在合成非线性数据集上优于 T-learner、S-learner 等基线模型，可用于个性化治疗获益评估。

链接：https://arxiv.org/abs/2608.06288

机构：Higher School of Artificial Intelligence Technologies（人工智能技术高等学院）； Peter the Great St.Petersburg Polytechnic University（彼得大帝圣彼得堡理工大学）

作者：Lev V. Utkin, Stanislav K. Kogan, Andrei V. Konstantinov

英文摘要：This work presents a novel attention-based framework for estimating the Individual Probability of Treatment Benefit (IPTB) in survival analysis contexts. The proposed model, called Surv-IPTB, directly quantifies the probability that a specific patient will experience extended survival time under treatment versus control. We reformulate IPTB estimation as a binary classification problem, leveraging pairwise patient comparisons across treatment and control cohorts. The framework incorporates a principled handling of right-censored observations through imprecise probability representations, where uncertain treatment effects are characterized by interval-valued probabilities. An attention mechanism with learnable query-key transformations enables flexible, data-driven aggregation of pairwise comparisons, while simultaneously learning soft class probabilities for censored cases. Through extensive experiments on synthetic datasets with complex nonlinear structures, including spiral, bell-shaped, and circular feature spaces, we demonstrate that our approach maintains robust performance across varying censoring rates and treatment effect strengths. The model consistently outperforms meta-learner baselines (T-learner and S-learner) equipped with random survival forests, Cox proportional hazards, and Beran estimators, particularly in challenging nonlinear scenarios where conventional methods exhibit significant degradation. The results establish the proposed attention-based framework as a scalable and statistically principled solution for personalized treatment benefit assessment in survival settings. The code implementing the model is publicly available.

AI 总结：针对工业场景中故障诊断标注数据稀缺的问题，提出自监督学习方法SAP，通过欠采样振动数据创建折叠频谱训练Transformer重构展开频谱，在CWRU数据集上验证其结合线性探测的效果优于全监督训练。

链接：https://arxiv.org/abs/2608.05705

作者：Victor Gialis, Maxime Metz, David Esteve, Abdenour Soualhi

英文摘要：Deep learning is a new way for machinery fault diagnosis but requires extensive labeled data, a scarce resource in industrial settings. We propose Spectral Aliasing Pretext (SAP), a self-supervised learning method that pretrains models on unlabeled vibration data by exploiting spectral aliasing. We deliberately undersample signals to create folded spectrum, then train a Transformer to reconstruct the original unfolded spectrum. This pretext task forces the model to learn frequency-domain invariants characteristic of mechanical faults, without potentially destructive augmentations. Experiments on the CWRU dataset show that SAP learns stable and highly discriminative representations. In a linear probing setting, SAP quickly achieves very high classification performance with only a small fraction of labeled data and low variance. In contrast, full fine-tuning, including fully supervised training, does not lead to more stable or better results. Overall, these findings suggest that SAP combined with linear probing can be more effective and reliable than fully supervised training for fault diagnosis with limited labeled data.

AI 总结：本研究对比评估Random Forest替代模型、LIME及主成分分析等聚类模式检测方法，发现其无法稳定识别全部注入模式，凸显现有工具的不足，推动专用方法开发。

链接：https://arxiv.org/abs/2608.05880

作者： Benjamin Connor, Anna Jurek-Loughrey, Lu Bai, Muhammad Fahim

英文摘要：Interpreting clustering outcomes remains a fundamental challenge in data analysis, particularly in domains such as healthcare where meaningful patterns must be extracted from high-dimensional data. While numerous explainability techniques exist, they are primarily designed to assess feature importance or provide local instance-level explanations rather than to identify structured patterns present within clusters. This work presents a comparative evaluation of commonly used post-hoc analysis methods for pattern detection in clustering results. To enable controlled evaluation, we introduce a suite of synthetic datasets in which predefined patterns are systematically injected. Three widely used techniques are evaluated: a Random Forest surrogate model with permutation feature importance, LIME (Local Interpretable Model-agnostic Explanations), and principal component analysis. Results demonstrate that although each method can successfully recover relevant features, none consistently detects all injected pattern types. These findings high- light a critical gap between existing explainability tools and the requirements of pattern-level cluster interpretation, motivating the development of dedicated pattern detection methodologies.

AI 总结：BioM-JEPA通过预测图连接基因块的聚合表示学习单细胞嵌入，在CellBench任务中实现最低扰动响应误差，微调与保留嵌入吞吐量优于scFoundation，为单细胞表示学习提供新预测单元。

链接：https://arxiv.org/abs/2608.05928

机构：Westlake University（西湖大学）； Centre for Artificial Intelligence and Robotics (CAIR), Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences (HKISI-CAS)（中国科学院香港创新研究院人工智能与机器人中心）； Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）； University of Chinese Academy of Sciences (UCAS)（中国科学院大学）

作者：Yuhao Wang, Zelin Zang, Yuxuan Liu, Zhen Lei, Stan Z. Li

英文摘要：Single-cell transcriptomes are sparse observations of coordinated biological programmes, yet most self-supervised models learn by reconstructing individual genes. Here we present BioM-JEPA, a joint-embedding predictive architecture that instead predicts aggregate representations of graph-connected gene blocks defined by protein-association and corpus-derived coexpression evidence. A student network infers each target-block representation from the remaining genes in a cell, while a slowly updated teacher supplies the corresponding target from the full observed gene set. Under the reported extraction procedure, block-level prediction produced embeddings with higher effective rank and weaker association with detected-gene depth in the tested diagnostics than token-prediction, random-block and reconstruction controls. Across CellBench tasks, frozen BioM-JEPA embeddings retained expression, pathway and neighbourhood information and achieved the lowest aggregate perturbation-response error among the evaluated models. Representation diagnostics were also consistent with canonical pancreatic programmes and compositional relationships between genetic perturbations. Linear attention avoids constructing a quadratic gene-by-gene attention matrix; in a matched one-epoch hPancreas experiment at batch size 8, BioM-JEPA provided 5.75-fold higher fine-tuning throughput and 3.76-fold higher held-out embedding throughput than scFoundation. Together, these results support graph-connected gene blocks as useful prediction units for JEPA-style representation learning in single-cell biology.

AI 总结：本研究提出RxnCLF，一种基于凝聚反应图的自监督对比反应基础模型，经170万Pistachio反应预训练后，在多类产率预测基准上均优于基线模型，展现出良好泛化潜力。

链接：https://arxiv.org/abs/2608.06259

机构：Discovery Chemistry, Merck & Co., Inc.（默克公司发现化学部门）

作者：Yiting Zheng, Cheng Fang, Anthony Donofrio, Haote Li

英文摘要：Reaction yield prediction remains challenging because labeled data are scarce and reaction space is both combinatorially large and sparsely populated, limiting the generalization of existing reaction representations. String-, fingerprint-, and graph-based reaction encodings only partially capture chemical transformations, making accurate prediction difficult for reactions with complex substrates. We propose reaction contrastive learning foundation (RxnCLF), a self-supervised contrastive framework for reaction representation learning. RxnCLF is built on a condensed reaction graph (CRG) that unifies reactant and product information into a single graph, enabling the model to learn explicit and enriched transformation structure rather than disconnected graphs. Pretrained on 1.7 million Pistachio reactions, RxnCLF learns a compact and continuous latent space that captures both reaction-center features and broader side chain contexts, making it transformation-aware and chemically interpretable. Fine-tuned on multiple yield prediction benchmarks, including Buchwald-Hartwig, Pd-catalyzed BH coupling, and proprietary HTE C-N coupling and amide formation datasets, RxnCLF consistently outperforms graph and sequence-based baselines, improving R2 and achieving the best performance overall. Our results highlight the promise of CRG-based RxnCLF as a scalable reaction foundation model, with the potential to generalize across broader reaction spaces and support diverse downstream reaction informatics tasks, including regioselectivity prediction, enantioselectivity prediction, and reaction condition optimization.

AI 总结：该研究针对零售投资者缺乏个性化税务感知投资组合管理的问题，开发了一款集成FastAPI后端等组件的应用，采用三阶段强化学习系统生成推荐，经集成测试后提供预部署验证。

链接：https://arxiv.org/abs/2608.05255

作者：Ramin Pishehvar

英文摘要： Retail investors lack access to the kind of personalized, tax-aware portfolio management that institutional clients take for granted -- existing robo-advisors use static, rule-based allocation, and institutional-grade systems require account minimums and technology stacks unavailable to individual investors. We present a fully built, integration-tested application that closes this gap: a FastAPI backend and web dashboard that let a user describe an investment goal in plain language (e.g. "I want steady growth but need to sell some shares next month for a down payment"), routes that goal to one of six investment mandates, and produces a live, broker-integrated portfolio recommendation from athree-phase reinforcement learning system -- a self-supervised cross-asset encoder, a Mixture-of-Experts (MoE) allocation policy with a learned intent router, and a lightweight LoRA adapter that personalizes recommendations from an individual's revealed brokerage behavior without retraining the shared model. The system is functionally complete and integration-tested end-to-end against a live brokerage API (Alpaca, paper-trading mode), including multi-user authentication, a trust first preview-before-apply confirmation flow, daily email digests, and an auditable action-integrity chain, but has not yet been opened to real end-users; we report this honestly as an emerging, pre-deployment application with a concrete path to full deployment, alongside 14-day walk-forward backtests (bootstrapped confidence intervals included) as preliminary, pre-deployment validation rather than production performance. We also report several practical engineering lessons -- silently-inactive integration paths, hanging third-party API calls, and the value of end-to-end empirical verification over trusting checkpoint metadata -- that we believe generalize to other applied RL systems built on external, live data sources.

AI 总结：该研究将AFlowNets扩展为适用于不完美信息博弈的IFlowNets，解决了原有约束无法得到有效密度与训练目标的问题，在标准博弈环境中性能与速度优于或相当于OSMCCFR等方法。

链接：https://arxiv.org/abs/2608.05422

作者：Conor M. Artman, Nicholas Di, Scott Perkins

英文摘要：While many algorithms blend reinforcement learning (RL) with counterfactual regret (CFR) methods to leverage tradeoffs in computational speed and performance, there are fewer investigations into generative sampling frameworks in game theoretic applications in incomplete information games. We extend a generative flow network framework, Adversarial Flow Networks (AFlowNets), to incomplete information games, called Information Flow Networks (IFNs). We prove that previously established constraints for generative flow networks in complete information games are inadmissible for obtaining valid densities (corresponding to player strategies) and a valid training objective. We show that our proposed generalization, IFlowNets, alleviates this issue and strictly generalizes AFlowNets. In preliminary results for three standard game environments, IFlowNets perform comparably to or better than Outcome Sampling Monte Carlo Counterfactual Regret (OSMCCFR) and standard RL-based methods in performance and speed.

AI 总结：本研究提出 EvoHarness-RL 方法，通过学习管控器策略解决长视野 LLM 智能体的外部状态管理问题，在 ALFWorld 上达到 96.9% 的任务成功率，验证了可训练管控器策略的有效性。

链接：https://arxiv.org/abs/2608.05446

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

作者：Xuying Ning, Dongqi Fu, Tianxin Wei, Hanqing Zeng, Yuanchen Bei, Bingxuan Li, Zihao Li, Qifan Wang, Xiang Shen, Yifan Wu, Jiayi Liu, Hong Li, Yinglong Xia, Xiangjun Fan, Hanghang Tong, Jingrui He

英文摘要：Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, invoke tools, verify outcomes, and reuse experience across interactions. However, effective harness use raises two coupled challenges: state formation from noisy interaction traces and runtime control over external-state access. Existing agents usually handle both through prompts, heuristics, or domain-specific conventions, leaving the external workspace and its usage policy manually engineered. To address this, we study the problem of harness policy learning, where agents learn harness policies offline and deploy them to construct and update external harness state online during runtime task execution. We introduce EvoHarness-RL, which exposes Belief, Progress, and Experience (BPE) as policy-facing harness state. Supervised harness fine-tuning teaches the base agent the harness action space and how to construct useful external state, while cost-aware GRPO explores coordination policies to selectively read, update, and consolidate that state during long-horizon interaction. Instantiated on ALFWorld with a Qwen3-8B LLM, EvoHarness-RL reaches 96.9% success and reveals two key dynamics: harness annealing, where training internalizes recurring harness-use patterns into the model policy and shifts the agent from frequent harness calls toward selective external-state access, and harness evolution, where progress updates and experience consolidation refine the harness into a compact, task-adaptive state substrate. These results suggest that long-horizon agents benefit from trainable policies for constructing and coordinating with external harness workspaces, beyond simply adding stronger tools or larger memories.

AI 总结：LC-GRPO 是带朗之万校正的基于流的 GRPO 框架，通过对齐推理的 ODE 欧拉步加朗之万校正，缩小流模型训练与推理的样本差距，在多任务上提升奖励优化并保留生成质量。

链接：https://arxiv.org/abs/2608.05600

作者：Yingqing Guo, Hui Yuan, Zijian He, Mengdi Wang, Zheng Ding

英文摘要：Flow-based generative models are typically sampled by solving a deterministic ordinary differential equation (ODE), whereas online reinforcement learning requires stochastic rollouts for policy exploration and optimization. Existing GRPO methods for flow models therefore replace the inference-time ODE with a stochastic differential equation (SDE) during training. Although the ODE and SDE share the same marginal distributions in continuous time, their finite-step discretizations can differ substantially. In particular, SDE rollouts often become blurry as the exploration noise increases, creating a mismatch between the samples used for reinforcement learning and those generated by the test-time ODE sampler. We introduce LC-GRPO, a flow-based GRPO framework with Langevin correction. Each rollout transition first takes an inference-aligned ODE Euler step and then applies a stochastic Langevin correction targeting the marginal distribution at the resulting timestep. The required score is recovered directly from the flow velocity, requiring no additional score model, while the resulting transition remains an isotropic Gaussian with a tractable likelihood for policy optimization. We theoretically show that, under suitable conditions, one Langevin correction step reduces the Wasserstein error of an imperfect ODE Euler step. At a matched randomness level, we further show that the proposed transition can be more accurate than the standard Euler--Maruyama discretization of the reverse SDE. Experiments on SD3.5-Medium, FLUX.1-Dev, and HunyuanVideo demonstrate that LC-GRPO consistently improves reward optimization across text-to-image and text-to-video tasks, preserves generation quality, and substantially narrows the gap between stochastic training rollouts and deterministic test-time ODE inference.

AI 总结：针对视觉连续控制的样本高效策略学习难题，本文提出OG-SPR算法，结合多步隐自预测与下一观测预测，通过轻量适配器优化表示，在DeepMind Control Suite的28项任务中优于现有最优方法。

链接：https://arxiv.org/abs/2608.05989

作者：Xinwei Liu, Junyuan Liang, Jianting Zhang, Wuhui Chen

英文摘要：Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL). Recent dynamics-based representation learning methods have significantly improved the sample efficiency of model-free visual RL by learning dynamics-aware representations through auxiliary prediction performed either in latent space (self-prediction) or observation space (observation prediction). However, state-of-the-art methods from both categories still struggle on challenging visual control tasks when training data is limited. We posit that relying on either predictive objective alone may be insufficient. In contrast, observation prediction grounds learned representations in observation-level dynamics, but does not directly regularize the temporal predictability of latent representations over extended horizons. In this paper, we propose Observation-Grounded Self-Predictive Representations (OG-SPR), a model-free visual RL algorithm for continuous control that learns representations that are both temporally predictive in latent space and grounded in observation-level dynamics. OG-SPR incorporates two core auxiliary objectives: multi-step latent self-prediction and next-observation prediction. We empirically show that directly imposing latent self-prediction on the shared representation may over-constrain it and does not necessarily improve performance. To address this issue, OG-SPR introduces two lightweight adapters for latent self-prediction, allowing the shared representation to benefit from temporally predictive signals without being forced to directly satisfy the self-prediction objective. Experiments on 28 visual control tasks from the DeepMind Control Suite show that OG-SPR improves aggregate performance over state-of-the-art self-predictive and observation-predictive RL methods, with particularly pronounced gains in challenging domains such as dog and humanoid.

AI 总结：ProDVI是利用大型语言模型生成的Python函数初始化RL智能体的框架，通过预训练价值网络编码器，提升无模型RL算法的样本效率，无需依赖数据集或模拟器。

链接：https://arxiv.org/abs/2608.06015

作者：Xinwei Liu, Junyuan Liang, Jianting Zhang, Wuhui Chen

英文摘要：Deep Reinforcement Learning (RL) is notoriously sample inefficient. One contributing factor is that RL agents are typically initialized from scratch, forcing them to acquire task-relevant knowledge through online interaction. Existing approaches obtain informative initializations through pre-collected datasets, high-fidelity simulators, or meta-learning over related tasks, but these prerequisites may be difficult to access or even unavailable. In this paper, we propose Programmatic Dynamics Priors for Value Network Initialization (ProDVI), a framework that leverages the commonsense and domain knowledge encoded in large language models to initialize RL agents without relying on these resources. Specifically, ProDVI prompts a code-generating language model to produce executable Python functions that encode coarse hypotheses about environment dynamics. These functions are then used to generate synthetic transitions. Based on these transitions, we construct an auxiliary dynamics prediction objective to pretrain the state-action encoder of the value network in an actor-critic framework. The learned representation provides dynamics-aware inductive biases before online RL begins. Importantly, the generated programs are used only for representation pretraining and are not required to faithfully simulate the target environment. While the generated programs may be inaccurate, their induced initialization can be corrected through online learning from real transitions and rewards. Experiments on OpenAI Gym and DeepMind Control Suite tasks show that ProDVI can effectively improve the sample efficiency of model-free RL algorithms.

AI 总结：该研究针对仿真闭环RL推理的线程资源匹配问题，提出AutoThread方法，结合PINO与M/M/1排队模型并辅以在线微调，显著提升了推理的加速比与吞吐量。

链接：https://arxiv.org/abs/2608.06025

机构：College of Systems Engineering, National University of Defense Technology（国防科技大学系统工程学院）； College of Computer Science and Technology, National University of Defense Technology（国防科技大学计算机科学与技术学院）

作者：Jiming Su, Hantao Hua, Lujia Yin, Yiping Yao, Feng Zhu

英文摘要：In simulation-in-the-loop decision-making systems, reinforcement learning (RL) inference is often constrained by simulator-side execution overhead, where workloads are highly dynamic and sensitive to runtime thread configurations. Existing multithreaded strategies struggle to match thread resources before or during execution, causing resource contention, scheduling overhead, and reduced throughput. Through empirical analysis, we identify the ratio of task execution time to scheduling time as the key factor determining the optimal thread count. Building on this insight, we propose AutoThread, a hybrid adaptive thread-tuning method for mitigating simulation bottlenecks in RL inference. AutoThread employs a Physics-Informed Neural Operator (PINO) as a thread-count predictor and incorporates a finite-source M/M/1 queueing model to constrain and guide prediction, enabling fast and accurate estimation under dynamic workloads. It further performs load-aware online fine-tuning to compensate for prediction errors and refine resource allocation. Experiments show that AutoThread improves average speedup by 18.4\% over static strategies, achieves average throughput of 1.7x and 1.8x that of XGBoost and Reinforcer, respectively, and reduces execution time by up to 83.8\% compared with state-of-the-art methods. Our code and dataset are publicly available at this https URL.

AI 总结：本研究通过对北极航运航次的受控评估，发现非线性共享奖励模型优于线性基线，添加船舶特定潜在上下文反而降低性能，表明可观测特征已能解释行为差异，为安全关键领域的AI部署提供支持。

链接：https://arxiv.org/abs/2608.06105

作者： Vaishnav Vaidheeswaran, Dilith Jayakody, Biruk Ambaw, Jaswanth Kumar, Md Mahbub Alam, Gabriel Spadon

英文摘要：Artificial Intelligence (AI)-assisted navigation can help Arctic shipping adapt to rapidly changing sea-ice conditions, but reliable deployment requires reward models that are interpretable and robust to changing environments. Inverse reinforcement learning (IRL) provides a framework for recovering such rewards from vessel trajectories, while recent meta-IRL methods introduce latent context variables to capture behavioral heterogeneity. However, it remains unclear whether these latent representations recover genuinely hidden preferences or simply re-encode information already available in the observed state. We conduct a controlled evaluation on 3,186 AIS-derived voyages from 202 vessels across nine Arctic shipping seasons, comparing a linear shared reward, a nonlinear shared reward, and a latent-context model built on the same nonlinear architecture. The nonlinear reward improves held-out likelihood by 50.9% over the linear baseline, whereas adding vessel-specific latent context reduces performance by 16.5%. Behavioral analysis, context probes, and a pre-registered feature-hiding ablation show that apparent vessel-level variation is largely explained by observable route and environmental conditions rather than hidden vessel-specific factors. Moreover, predictive accuracy, route fidelity, and reward transfer yield different model rankings, demonstrating that no single metric is sufficient to evaluate learned rewards. These findings motivate testing whether the observed route, environmental, and vessel features already explain behavioral variation before adding per-vessel latent context. This supports more trustworthy AI deployment in safety-critical domains.

AI 总结：本研究针对生成式奖励模型在LLM强化学习中潜力未充分发挥的问题，提出RRC方法，通过两种互补策略提升RL训练效果，在多基准上取得一致增益。

链接：https://arxiv.org/abs/2608.06310

机构：School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）； NiuTrans Research（NiuTrans研究院）； Institute of Psychology, CAS（中国科学院心理研究所）； Kunming University of Science and Technology（昆明理工大学）

作者：Chenglong Wang, Ziming Zhu, Yifu Huo, Bei Li, Qiaozhi He, Yan Ding, Xiaoyang Hao, Yuxin Gao, Tianhua Zhou, Xiaojia Chang, Tongran Liu, Jingbo Zhu

英文摘要：Recent advances in reward modeling show a paradigm shift from discriminative reward models to generative reward models. However, despite their strong capabilities in response ranking, generative reward models have not realized their potential in reinforcement learning (RL). Our analysis reveals that this limitation arises from a mismatch between the comparative nature of generative reward modeling and the scalar scoring paradigm adopted by existing RL algorithms. To bridge this gap, we propose a Ranking-based Reward Construction (RRC) approach, which enables generative reward models to provide more effective RL learning signals by deriving rewards from relative preference rankings. RRC introduces two complementary strategies: self-competitive ranking, which exploits comparisons among sampled responses, and anchor-guided ranking, which enables scalable ranking-based reward construction with a small set of reference responses. Experiments across open-ended chat and reasoning benchmarks demonstrate that RRC substantially improves RL training with generative reward models, achieving consistent gains over existing reward construction approaches. Our code can be found at this https URL.

AI 总结：本研究提出PMOT势匹配最优传输框架，结合CNF与广义Benamou-Brenier形式，实现$p$-最优传输的精确动力学建模，在合成基准、高维表格数据及颜色变换任务中表现出良好性能。

链接：https://arxiv.org/abs/2608.05666

机构：School of Mathematical Sciences, Shanghai Jiao Tong University（上海交通大学数学科学学院）

作者：Lishuo Zhang (1), Ruizhi Huang (1), Yang Yu (1), Lei Li (1 and 2) ((1) School of Mathematical Sciences, Shanghai Jiao Tong University, (2) Institute of Natural Sciences, MOE-LSC, Shanghai Jiao Tong University)

英文摘要：We introduce Potential Matching Optimal Transport (PMOT), a potential-flow framework for general $p$-cost optimal transport with $c_p(x,y)=\|x-y\|^p$. PMOT parameterizes the CNF velocity field with a scalar potential in the generalized Benamou--Brenier form for the chosen exponent $p$. It trains the potential gradient with a self-induced matching loss along straight bridges determined by the model's own endpoints, while allowing flexible terminal distribution matching. Our main result establishes zero-loss exactness: under the stated regularity, exact terminal matching, and uniqueness assumptions, any zero-loss solution satisfies the generalized Benamou--Brenier optimality system and recovers the corresponding $p$-optimal transport map and dynamics. On synthetic benchmarks, PMOT learns $p$-specific maps that agree with the corresponding $p$-matched OT references. It also remains competitive as a likelihood-based density model on high-dimensional tabular data, and an MMD-based color transformation experiment demonstrates flexible sample-based terminal matching.

AI 总结：该研究提出结合循环本体的神经符号闭环架构，用于激光粉末床熔融，可消除焊瘤、保持焊瘤为零且适配新合金，确立了架构可行性，下一步需实验校准深宽比。

链接：https://arxiv.org/abs/2608.05773

作者：Gisuk Hong, Jaebong Cho, Hyunbo Cho

英文摘要： A geometry-conditioned, neuro-symbolic closed-loop architecture is proposed for laser powder bed fusion, in which a standards-aligned ontology operates inside the control loop and couples symbolic reasoning with statistical learning to set the targets of a constraint-aware predictive controller. The ontology links the process objectives and constraints to the signals a controller can observe, and a description-logic reasoner converts them into the references and bounds enforced on each scan. The demonstrated case is overhang dross, a quality limit on the melt pool depth, which governs quality yet cannot be measured during the build, is mapped through a geometry- and power-dependent depth-to-width ratio onto a bound on the observable width, with the ratio and its calibrated uncertainty supplied by a Gaussian process. The reasoner classifies each upcoming feature and selects the active constraints-adding a lack-of-fusion floor at overhangs, a monotone guard beyond the calibrated range, and an energy-density cap where a process window is declared while running only on changes of geometric context and otherwise leaving a single small quadratic program on the per-scan path. In an Eagar-Tsai surrogate calibrated to the NIST AM-Bench benchmark for IN625, the architecture eliminates the dross produced by a geometry-blind controller, holds dross at zero with only a small residual lack-of-fusion under dual scoring, degrades gracefully under deliberate plant mismatch, and retargets to new alloys and constraints by editing ontology data rather than code. The results establish architectural feasibility, experimental calibration of the ratio is the principal next step.

AI 总结：该研究针对有限VC维的二元分类函数类，构造出达到统计最优风险界的不可知PAC学习算法，确定了其样本复杂度（仅差通用常数），匹配了已有下界。

链接：https://arxiv.org/abs/2608.06363

机构：Aarhus University（奥胡斯大学）； The University of Hong Kong（香港大学）； University of California, Berkeley（加州大学伯克利分校）

作者：Markus Engelund Mathiasen, Jian Qian, Nikita Zhivotovskiy

英文摘要：Let $H\subseteq\{-1,+1\}^X$ be a class of finite VC dimension $d\ge1$. Writing $L$ for the binary risk and $L^*=\min_{h\in H}L(h)$, we construct a learner achieving the statistically optimal risk bound: from an i.i.d.\ sample of size $n$, for every $0

AI 总结：本文提出BioKD框架，以生理信号为训练特权信息指导视频学生模型，通过可靠性门控抑制负迁移，在DEAP、AMIGOS数据集上的情感识别任务中优于基线，且推理无额外开销。

链接：https://arxiv.org/abs/2608.06023

机构：The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； New York University（纽约大学）

作者：Bojing Hou, Ruohao Li, Yitong Zhu, Hongjun Liu, Luwen Yu, Yuyang Wang

英文摘要：To address the limitations of video-based emotion recognition under ambiguous or socially masked behavioral cues, as well as the poor deployability of physiological signals, this paper proposes a reliability-aware physiology-to-video knowledge distillation framework, termed BioKD. The proposed framework leverages physiological signals as privileged information during training to guide a video-based student model in learning deep affective representations, while relying solely on non-intrusive video inputs at inference time. To cope with the high noise and instability of physiological teacher supervision caused by inter-subject variability, signal artifacts, and temporal inconsistency, BioKD incorporates a sample-wise reliability-aware gating mechanism together with a progressive distillation strategy. By adaptively regulating the strength of knowledge transfer, the framework suppresses negative transfer induced by unreliable physiological supervision and enables more stable cross-modal distillation. Experiments on DEAP and AMIGOS show that BioKD consistently outperforms representative baselines under both trial-wise and subject-wise evaluation protocols for valence and arousal recognition. For example, BioKD achieves 68.01\% on DEAP (trial-wise arousal) and 65.29\% under the more challenging subject-wise setting, demonstrating improved performance under a subject-independent evaluation setting. Further analyses show that BioKD effectively mitigates overconfident teacher errors and outperforms an entropy-only weighting strategy, confirming the importance of explicitly modeling supervision reliability. In addition, BioKD introduces no additional inference-time overhead relative to the same video student architecture and removes the need for physiological sensing and multimodal synchronization.

AI 总结：本研究提出DG-FedReuse机制，通过代理梯度门控缓存更新复用结合匹配稀疏上行链路核算，在联邦学习中实现更高上行链路节省，但需注意其未确立无偏泛化等优势。

链接：https://arxiv.org/abs/2608.05358

机构：Jamia Hamdard（贾米亚·哈姆达德大学）； Homi Bhabha National Institute（霍米·巴伯国家研究所）； Variable Energy Cyclotron Centre（可变能量回旋加速器中心）； Gargi Memorial Institute of Technology（加尔吉纪念技术学院）； Maulana Abul Kalam Azad University of Technology（毛拉纳·阿布尔·卡拉姆·阿扎德技术大学）

作者：Rahil Aftab, Vineet Kumar Rakesh, Soumya Mazumdar, Tapas Samanta

英文摘要：Federated learning repeatedly incurs local optimization and model-update transmission. We study DG-FedReuse, a simulator-level mechanism that allows selected clients to contribute age-decayed cached updates when a stochastic head-gradient discrepancy proxy remains below a round-dependent threshold. A hard cache-age limit and minimum fresh-client quota constrain reuse, while fresh updates use an adaptive per-tensor Top-K numerical-field representation. Experiments cover six image-classification datasets, 50 virtual clients, Dirichlet label heterogeneity ({\alpha}=0.5), and three seeds. At a common 90-round budget, DG-FedReuse yields 83.36-85.42% modeled update-data-field uplink saving, compared with 76.88% for matched Top-K FedAvg; the seed-aligned accuracy differences range from -5.29 to -0.14 percentage points. Best-observed test accuracies obtained under test-controlled checkpointing are retained only as exploratory archival evidence and range from -2.38 to +0.45 percentage points relative to matched FedAvg. A symmetric dense-model-downlink sensitivity reduces the headline saving to 41.68-F42.71% and the incremental gain over Top-K FedAvg to 3.24-4.27 percentage points, demonstrating the dependence of communication conclusions on the accounting boundary. The study characterizes the proposed reuse rule in the implemented simulator; it does not establish unbiased generalization, end-to-end bandwidth reduction, runtime or energy savings, faster convergence, or superiority over existing stale-update and lazy-aggregation methods.

AI 总结：GROM是一种无梯度快速一次性机器遗忘方法，通过闭式加性更新实现高效知识移除，在多数据集上取得最优遗忘-效用权衡，且能抵御低比特量化攻击。

链接：https://arxiv.org/abs/2608.05783

作者：Paweł Batorski, Przemysław Spurek, Paul Swoboda

英文摘要：Machine unlearning has become a critical capability for safely removing specific, sensitive knowledge from large language models (LLMs). Current state-of-the-art approaches primarily rely on iterative, training-time unlearning via fine-tuning. However, even when utilizing parameter-efficient dimensionality reduction techniques like LoRA, gradient-based optimization remains computationally expensive and lacks explicit analytical formulations. It can also leave the targeted knowledge merely hidden rather than removed, to the point that simply quantizing the unlearned model restores much of what it was supposed to have erased. To resolve this, we propose a novel one-shot unlearning approach, abandoning iterative optimization in favor of a direct, exact analytical solution. We frame the unlearning process as a ridge-regularized least-squares optimization problem, deriving a closed-form additive update for targeted weight matrices. This update forces the selected layer to suppress unwanted content while strictly preserving its behavior on retained data. Computed from gradient-free forward passes alone, with no backpropagation and no iteration to convergence, GROM applies the weight edit in mere seconds, which makes it orders of magnitude faster than traditional fine-tuning. Extensive evaluations demonstrate that GROM achieves state-of-the-art forgetting-utility trade-offs on TOFU-5%, TOFU-10%, MUSE-Books, MUSE-News and WMDP, significantly reducing computational overhead without sacrificing overall model performance. Because the update removes the targeted content from the weights instead of masking it, GROM also withstands the low-bit quantization attack that recovers much of the content a gradient-based baseline had appeared to forget. Our code is publicly available at this https URL.

AI 总结：本研究指出生成式训练中XM的第三轴实际是自由，通过理论与实验证明自由选择优于MDL，且在分布偏移下针对自由度的选择可提升XM表现。

链接：https://arxiv.org/abs/2608.05423

机构：The Australian National University（澳大利亚国立大学）

作者：Michael Timothy Bennett

英文摘要：In generative training, a model produces an output and is penalised for its difference from an example. With one output per comparison, a model that produces one common answer can outperform a model retaining a broader repertoire. Explorative Modeling (XM) produces $K$ outputs per comparison and updates on the closest, claiming exploration as a "third pretraining axis" associated with generative expressivity. Here I show the third axis is actually freedom, meaning the weakness of the constraint implied by a model's behaviour. Previous work showed freedom is a property of function rather than form. Parameters, architecture, minimum-description-length (MDL), and data can vary while the behavioural constraint remains unchanged. It was formally proved that weakest models are likeliest to generalise, and freedom selection beat MDL by 110-500\% in induction experiments. I prove average XM loss depends on the chance a candidate misses an acceptable region, with exploration raising miss probability to power $K$. For $K>1$, match probability rises with freedom. I then demonstrate empirically that XM optimises for freedom. In a Forward XM experiment, larger $K$ increased or saturated measured freedom, and increased freedom at every tested value under context-dependent targets. I trained XM candidate pools and compared validation selection with a freedom selector that read unlabelled parent contexts. Freedom won in 29 of 30 cases. Generative expressivity is a mode-count proxy for freedom, that discards the extension structure that gives freedom its generalisation significance. XM is a means, freedom an end, and selecting for freedom improved XM under distribution shift.

AI 总结：该研究提出混合概率 zonotope（HProbZ）作为神经网络预测头，分离三种不确定性来源，可细化多步预测分布，具备独特结构特性，在基准测试中优于同编码器混合基线。

链接：https://arxiv.org/abs/2608.05454

作者：Zhen Zhang, Amr Alanwar

英文摘要：Probabilistic prediction heads in neural networks typically output either a Gaussian mixture or a single conformal region. Neither separates the distinct sources of uncertainty often present in real prediction tasks: a discrete choice among modes, bounded systematic drift within the chosen mode, and irreducible stochastic noise. We introduce the Hybrid Probabilistic Zonotope (HProbZ), an output head that represents these three sources as binary, bounded, and stochastic generators of a zonotope, and admits a closed-form likelihood by convolution. Sharing the bounded generator across prediction steps couples future predictions algebraically, so observing one step refines the predictive distribution at every remaining step in a single forward pass. We establish that the three generators are identifiable from the likelihood up to permutation, and that an HProbZ density is representationally distinct from any finite Gaussian mixture. The same shared structure provides analytic per-mode risk and distribution-free multi-modal conformal sets at inference time. Empirical analysis on representative prediction benchmarks supports the effectiveness of the design relative to same-encoder mixture baselines, while offering structural properties that mixture or convex-conformal predictors do not jointly provide.

AI 总结：提出FERL方法，学习可解释的模糊规则模型，在30个表格数据集基准中准确率显著更高，在OOD检测等任务中表现优异，兼具可解释性与良好性能。

链接：https://arxiv.org/abs/2608.05859

机构：School of Computer Science and Electronic Engineering（计算机科学与电子工程学院）； University of Essex（埃塞克斯大学）

作者：Javier Fumanal-Idocin, Javier Andreu-Perez

英文摘要： Interpretable classification often requires more than accurate predictions for real-life deployment: models should be transparent about the evidence behind their decisions and abstain when they cannot decide reliably. We introduce Fast Evidential Rule Learning (FERL), a method that learns interpretable, accurate fuzzy rule models whose outputs are evidential. Unlike post-hoc calibration, FERL's belief, plausibility, and abstention capabilities arise directly from the fuzzy memberships in a single deterministic pass, with no auxiliary head, held-out set, or repeated inference. Our theoretical analysis further shows that FERL is Lipschitz stable, which means that its evidential outputs vary smoothly with the input. Against state-of-the-art rule learners, FERL is statistically significantly more accurate across a 30 tabular-dataset benchmark ($+2.6\%$ average accuracy over the second best). Its native set predictions attain the best utility-discounted accuracy among credal classifiers ($u_{65}/u_{80}=0.80/0.83$ vs.\ $0.79/0.80$ for the naive credal classifier), at higher set coverage ($0.92$ vs.\ $\le0.82$). FERL also matches dedicated out-of-distribution detectors on tabular near-OOD detection ($77.7$ vs.\ $77.4$ AUROC for the strongest baseline). Under detector-class-disjoint concept-bottleneck evaluation, its it is within $2.3$ AUROC points of the strongest dedicated detector on both CUB and AwA2, while attaining the best AwA2 AUPR-Out ($68.3$) and novel-class rejection ($57.2$), while being able to name which attributes are anomalous.

AI 总结：本文提出将不确定性统一定义为逐点后验风险，构建了可直接计算神谕不确定性的理论基准，发现准确预测不保证可靠的不确定性解耦，该基准可分析不同方法的不确定性估计性能。

链接：https://arxiv.org/abs/2608.05995

机构：University of Tübingen（蒂宾根大学）； Hertie Institute for AI in Brain Health（赫蒂脑健康人工智能研究所）； Tübingen AI Center（蒂宾根人工智能中心）； Charité–Universitätsmedizin Berlin（柏林夏里特医学院）； Bernstein Center for Computational Neuroscience Berlin（柏林伯恩斯坦计算神经科学中心）

作者：Frieder Wizgall, Georg Tirpitz, Moritz Seiler, Kerstin Ritter, Bálint Mucsányi

英文摘要：Reliable uncertainty estimates are critical in safety-sensitive applications, where understanding the sources of predictive uncertainty is essential. This often requires disentangling epistemic uncertainty from aleatoric uncertainty, yet these uncertainty types are not defined consistently across the literature, making it difficult to assess whether a method produces accurate uncertainty estimates. Evaluation is further complicated by the fact that ground-truth epistemic uncertainty is typically unavailable. Existing benchmarks therefore mostly rely on proxy tasks such as out-of-distribution detection, which do not provide complete ground-truth uncertainty targets and offer limited insight into the structure and quality of uncertainty estimates. We propose a unified definition of uncertainty as pointwise posterior risk, the expected loss of a predictor under the distribution of plausible ground-truth functions given the data. This view combines Bayesian uncertainty over functions with estimator-dependent deviations from the posterior mean, capturing effects such as misspecification and optimization error. This formulation constitutes the foundation of a theory-backed benchmark that enables direct computation of oracle epistemic and aleatoric uncertainty using semi-synthetic datasets with real covariates and known generative processes. By avoiding proxy evaluations, the benchmark enables fine-grained analysis of uncertainty estimates. Empirically, we find that accurate prediction does not guarantee reliable uncertainty disentanglement. The benchmark reveals practically useful differences between methods, identifying approaches with meaningful alignment to oracle uncertainty targets while exposing sensitivity to datasets and modeling choices.

AI 总结：SkillTFM是一种无训练系统，通过可验证可扩展的技能库将表格基础模型的适应转向技能门控演化，在电价预测等任务中提升了AUC，且在不同骨干网络上均有效。

链接：https://arxiv.org/abs/2608.06137

作者：Yi He, Zhengkang Guan, Anpeng Wu, Peng Cui, Fei Wu, Kun Kuang

英文摘要：Tabular data are ubiquitous in real-world applications and are crucial for data-driven prediction and decision-making across science, industry, finance, healthcare, and public services. Tabular foundation models (TFMs) have emerged as a promising paradigm for general-purpose tabular learning, offering reusable predictors across diverse datasets and substantially reducing the need for task-specific training, tuning, and model development. However, their practical deployment remains constrained by distribution shifts, heterogeneous feature semantics, and task-specific patterns that are difficult to capture without costly fine-tuning or additional labeled data. To this end, we propose SkillTFM, a training-free system that shifts TFM adaptation from parameter updates to the gated evolution of agentic skills. The core of SkillTFM is a verifiable and extensible skill bank that couples boundary evidence identification with gated skill evolution: the former characterizes task structure and base-model failure patterns, whereas the latter retrieves and extends reusable skills subject to explicit validation. Across simulated boundary settings and real-world electricity-price forecasting, SkillTFM improves AUC by 0.128--0.142, raises nonlinear-boundary AUC from 0.699 to 0.898. Furthermore, experiments across TFM backbones demonstrate the effectiveness and generality of SkillTFM.

AI 总结：该研究提出解耦空间推理器（DiSR）框架，将3D感知与LLM推理解耦，在空间推理基准上取得竞争力性能，兼具可解释性、模块化性与计算效率，为空间智能提供替代范式。

链接：https://arxiv.org/abs/2608.05242

作者：Haoze Sun, Jiequan Cui, Qingshan Xu, Richang Hong

英文摘要：In this work, we explore an alternative paradigm for spatial reasoning by explicitly disentangling 3D perception from reasoning, rather than jointly acquiring implicit 3D perception and reasoning through large-scale training. Our key observation is that modern perception models excel at estimating continuous 3D geometry, whereas large language models (LLMs) are particularly effective at compositional and symbolic reasoning. Motivated by these complementary strengths, we propose the Disentangled Spatial Reasoner (DiSR), a simple yet effective framework that reconstructs the physical world into structured 3D evidence using off-the-shelf expert perception models and fine-tunes an LLM with LoRA to perform reasoning solely over this explicit geometric evidence. Without large-scale 3D VQA training or complex tool-use policies, DiSR achieves competitive performance on popular spatial reasoning benchmarks. Beyond its strong performance, DiSR offers improved interpretability, modularity, and computational efficiency, demonstrating that explicit separation of perception and reasoning is a scalable and effective alternative paradigm to end-to-end modeling for spatial intelligence.

AI 总结：针对类别不平衡脑电图的在线源适配问题，提出OSPDIM框架，通过流形约束偏置参数的实时优化校正几何错位，在运动想象数据集上显著优于标准黎曼基线。

链接：https://arxiv.org/abs/2608.05315

作者：Shiwen Chu, Shanglin Li, Motoaki Kawanabe, Reinmar Kobler

英文摘要：Electroencephalography (EEG) based Brain-Computer Interfaces (BCIs) often require unsupervised domain adaptation (UDA) to generalize across subjects and sessions. While Riemannian alignment methods like the Riemannian Centering Transformation (RCT) are effective for handling covariate shifts, they implicitly assume balanced class priors. However, in realistic online BCI scenarios, the label distributions vary dynamically (label shift), causing standard alignment techniques to geometrically misalign the target data distributions. In this work, we propose OSPDIM (Online SPD manifold information maximization), a source-free online UDA framework designed to address label shifts on the Riemannian manifold. OSPDIM introduces a manifold-constrained bias parameter into the tangent space mapping, which is optimized via information maximization to correct the geometric skew caused by imbalanced data streams. Unlike offline methods relying on global batch statistics, OSPDIM estimates and corrects geometric bias on-the-fly. Simulations on 2D SPD matrices visually demonstrate that OSPDIM successfully rectifies the misalignment where standard centering fails. Extensive experiments on multiple motor imagery datasets show that OSPDIM significantly outperforms standard Riemannian baselines, particularly in challenging online adaptation scenarios with severe class imbalance, offering a robust solution for practical, plug-and-play BCI systems.

AI 总结：该研究提出KV-Skill，通过外部因子化算子存储任务知识，在多基准测试中提升了模型在LiveMath等任务上的准确率，且可独立加载多个技能无明显遗忘。

链接：https://arxiv.org/abs/2608.05475

机构：University of Michigan（密歇根大学）

作者：Zhaowei Han, Xiang Zhang, Bing Han, Kai Liu, Danqi Hu, Jie Liu

英文摘要：Task knowledge is commonly stored either as text in the prompt or as an update to model weights. Text is modular but must be interpreted on every use, while weight adaptation makes the resulting capability difficult to load, remove, or share independently. We introduce KV-Skill, a design space of external factorized operators that a frozen language model reads through a lightweight interface. KV-Skill supports two complementary paths. Registration converts an authored text skill into a text-derived operator and trains a shared per-backbone interface. Reward learning develops a compact latent operator directly from task outcomes, with or without an authored skill. Neither path adds positions to the prompt. Across ten benchmarks and four backbones from three model families, converting text to a KV-Skill consistently makes the same procedural knowledge more effective. On Qwen3.5-4B LiveMath, registration reaches 77.2 accuracy, compared with 23.4 for the source text skill, 52.0 for SkillOpt, and 64.5 for SoftSkill. Under matched reward training and parameter budgets, KV-Skill gives the best result in seven of eight matched settings against soft prefixes, prefix tuning, and LoRA. A post-hoc rank analysis further shows that text-derived operators retain nearly all of their benefit with one task-aligned direction per injection layer, while matched random directions fail. Finally, one shared interface retains three independently loadable KV-Skills without measurable forgetting. These results show that task knowledge can be acquired from text or experience, compressed into an external operator, and deployed separately from the backbone. Code is available at: this https URL

AI 总结：本文系统综述持续学习从以参数为中心向系统级适配的转变，通过时机、方式、位置三轴框架分析其演化，讨论相关挑战与未来方向。

链接：https://arxiv.org/abs/2608.06216

机构：Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； National University of Singapore（新加坡国立大学）

作者：Zhiyan Hou, Dan Zhang, Tao Feng, Liyuan Wang, Wei Li, Xiangzhao Hao, Hongyan An, Junfeng Fang, Haokai Ma, Zhaohui Xu, Haiyun Guo, Jinqiao Wang, Tat-Seng Chua

英文摘要：Classical continual learning (CL) has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms, e.g., training strategies, architectural designs, and weight adaptation. However, emerging paradigms are reshaping the scope of CL beyond this traditional model adaptation view. For instance, on-policy learning broadens the space of update mechanisms; test-time training extends CL from the training phase to inference; and external harness components such as memory, skill libraries, and interaction protocols extend the evolutionary boundaries of model capabilities far beyond the static parameter space. Collectively, these developments indicate a transition from parameter-centric learning toward system-level adaptation. To characterize this transition, we examine the evolution of continual learning through three dimensions: When, How, and Where learning occurs. The How dimension encompasses off-policy, on-policy, and beyond-gradient optimization mechanics. The When dimension captures evolution across pre-training, post-training, and inference-time stages. The Where dimension delineates updates occurring within internal parameters versus external structural constraints. Anchored by this tri-axial framework, we systematically survey representative methods, trace the ongoing transition of continual learning, and discuss the key challenges, broader implications, and future directions arising from this paradigm shift.

AI 总结：该研究提出首个开源MS分类基准MS-MLB，基于GSE17048全血RNA数据，用控制数据泄露的流程评估算法，梯度提升在留存集表现最优，内置外部模型提交路径，仅用于研究比较。

链接：https://arxiv.org/abs/2608.05196

作者：Adam Simson, Ankush Dutta, Quang Bui

英文摘要：Multiple sclerosis (MS) is diagnosed through clinical assessment, magnetic resonance imaging, laboratory evidence when appropriate, and exclusion of better explanations. Blood RNA expression data may contain disease associated immune signal, but a blood RNA classifier cannot be treated as a replacement for clinical diagnosis. This paper presents MS-MLB (Multiple Sclerosis Machine Learning Benchmark), a reproducible open benchmark for machine learning based MS research classification from whole blood RNA expression data. MS-MLB uses the public GSE17048 cohort, converts it into an MS versus healthy control task, and evaluates multiple algorithms under a shared, leakage controlled pipeline that a researcher can rerun without reconfiguring the evaluation. The evaluation includes nested cross-validation, an untouched stratified holdout set, bootstrap confidence intervals, ROC and precision recall analysis, calibration measurement, and an exploratory MS Research Score. In the final benchmark summary, Gradient Boosting ranked first by MS Research Score on the holdout set, with an MS Research Score of 93.83, AUC-ROC of 0.989, sensitivity of 0.950, specificity of 0.778, $F_{1}$ score of 0.927, and Brier score of 0.050. Prior studies have applied machine learning to MS blood transcriptomic data, including PBMC stage classification and whole blood diagnostic signature modeling. The contribution here is different and narrower. To our knowledge, MS-MLB is the first open benchmark focused on MS versus healthy control classification from GSE17048 whole blood RNA expression data with a documented external model submission pathway built into the framework. The score is intended for research comparison only and has not been clinically validated. The benchmark is accessible here: this https URL.

AI 总结：BaKron是一种高效神经网络量化算法，通过结合反对角并行与递归分治结构，将计算量从O(m²n²)降至O(mn(m+n))，兼具GPTQ的缩放效率与更丰富的曲率信息，且对基础量化器和海森估计器模块化。

链接：https://arxiv.org/abs/2608.06291

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

作者：Johann Birnick, Rayan Saab

英文摘要：We accelerate a family of algorithms for neural network quantization whose geometry is informed by any Kronecker-factored approximation of the Hessian. GPTQ-style adaptive rounding typically uses one-sided information derived from input activations. Two-sided Kronecker-factored Hessian approximations can additionally capture correlations across output coordinates, but applying GPTQ directly in the vectorized weight domain is computationally expensive. Building on the two-sided adaptive-rounding formulation used by BoA and YAQA, we introduce BaKron, an efficient solver that combines anti-diagonal parallelism with a recursive divide-and-conquer construction. For an $m\times n$ weight matrix, BaKron uses $O(m+n)$ sequential steps while reducing the total work from $O(m^2n^2)$ to $O(mn(m+n))$. Thus, it matches the cubic scaling of GPTQ while exploiting richer curvature information. Moreover, BaKron is modular with respect to both the base quantizer and the Hessian estimator. We also provide practical benchmarks, consider a range of Hessians that BaKron can be called with, find an efficient technique to compute these Hessians, and evaluate the algorithm experimentally.

AI 总结：SEAM是一种与生成器无关的科学机器学习框架，可跨多维度计算局部到全局的一致性，能在局部预测准确时检测不兼容解释并归因故障，为模型提供全局解释一致性审计。

链接：https://arxiv.org/abs/2608.05702

机构：Axiom Research Group（阿克西姆研究集团）； The Nelson Mandela African Institution of Science and Technology（纳尔逊·曼德拉非洲科学技术研究院）； African Institute for Mathematical Sciences（非洲数学科学研究所）； The University of Tokyo（东京大学）

作者：Gnankan Landry Regis N'guessan, Bum Jun Kim

英文摘要：Scientific machine learning commonly validates models at the level of a subdomain, a benchmark split, or an explanation for one prediction. Yet such local checks cannot establish whether the resulting explanations can be assembled into one globally admissible explanation. We introduce Scientific Explanation-Admissibility Machines (SEAM), a generator-agnostic framework that makes this local-to-global consistency question computable across regions, sensors, regimes, and model components. The finite explanation-sheaf instantiation SEAM-$\Omega$ represents each region by a structured explanation with state, closure, and observation channels together with optional contract metadata; compares neighboring explanations on their overlaps; and converts disagreement into a channel-resolved obstruction. This obstruction locates inconsistency and tests competing declared accounts by restricting each repair to the revisions that one account permits. Exact feasibility refutes or retains an account; when exact repair is unavailable, residual-aware regularized records provide a separately labeled empirical attribution. The framework also separates inconsistency from non-identifiability and monitors learned generators under distribution shift. We establish theorems for minimum-cost intervention and conservation-contract detectability, together with companion results for identifiability and closure recoverability. Across nineteen experiments involving synthetic partial differential equation systems and out-of-distribution Fourier neural operator (FNO) monitoring, SEAM detects incompatible explanations even when local predictions are accurate, and attributes failures to specific channels and overlaps. SEAM adds a global explanation-consistency audit to existing solvers and learning models, testing whether their local explanations form a coherent scientific account.

AI 总结：针对直接预测范式未显式约束跨变量结构的问题，提出跨变量损失CvLoss作为结构正则化项，可提升多变量时间序列预测模型性能，适配多种骨干网络。

链接：https://arxiv.org/abs/2608.05742

机构：University of Technology Sydney（悉尼科技大学）； Tsinghua University（清华大学）； The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））

作者：Kuiye Ding, Yifan Hu, Hanchen Wang, Hao Xue

英文摘要： Multivariate time series forecasting presents unique challenges because future variables often co-evolve under shared system dynamics. While existing studies mainly focus on cross-variable dependencies in historical observations, dependencies among future values are much less explored. Specifically, modern forecasting models largely follow the Direct Forecasting (DF) paradigm, generating multi-step forecasts with point-wise objectives that do not explicitly constrain cross-variable structure. In this work, we show that the DF objective is mismatched in the presence of cross-variable and lagged dependencies, revealing an objective gap. To address this issue, we propose \textbf{C}ross-\textbf{V}ariable \textbf{Loss} (CvLoss), a plug-in structural regularizer that constrains forecast residuals on a cross-variable graph. CvLoss penalizes inconsistent edge-wise residual differences over forecast patches, encouraging consistency across both synchronous and asynchronous interactions. Our experiments show that CvLoss consistently improves competitive forecasting models, outperforms representative learning objectives, and is compatible with a variety of forecasting backbones.

AI 总结：本研究提出FALM-PINN框架，解耦PINN的表示学习与系数拟合，可高效求解高频、非线性PDE，数值实验显示其相对L²误差较基准低两个数量级。

链接：https://arxiv.org/abs/2608.05892

机构：KTH Royal Institute of Technology（瑞典皇家理工学院）

作者：Yulun Wu, Matthieu Barreau, Miguel Aguiar, Karl H. Johansson

英文摘要：Physics-informed neural networks (PINNs) often fail to accurately resolve partial differential equations (PDEs) with high-frequency or multi-scale solutions, as well as strongly nonlinear problems. Two factors underlie this difficulty: spectral bias, the tendency of neural networks to underfit high-frequency features; and representation-coefficient coupling, the entanglement of representation learning and coefficient fitting within a single nonconvex optimization objective. In this work, we propose the Fourier-enhanced alternating Levenberg--Marquardt PINN (FALM-PINN), an optimization framework that decouples representation learning from coefficient fitting. The upper-level problem learns a Fourier-enhanced basis that enriches the latent space with high-frequency components, while the lower-level problem resolves the coupling by fitting the projection coefficients on this basis, solving a nonlinear least-squares problem with the Levenberg--Marquardt algorithm. The framework applies to general nonlinear and coupled PDE systems, and reduces to a single-step convex optimization problem for linear PDEs. We prove global convergence of the alternating training scheme in both cases. Numerical examples on multiple challenging high-frequency and nonlinear PDEs show that FALM-PINN achieves relative $L^2$ errors up to two orders of magnitude lower than state-of-the-art baselines.

AI 总结：该研究提出名为GEM-3的轻量级邻域注意力Transformer，通过显式多时间步推理解决天气预报时间步长的权衡问题，实现平衡可预测性与可用性的全球天气预报系统。

链接：https://arxiv.org/abs/2608.06241

作者：Sam Levang, Fran Bartolic, Ty Dickinson, Chase Dwelle, Paulius Rauba, Viktor Cikojevic

英文摘要：Existing machine-learning weather forecasting models rely on predetermined and fixed autoregressive timesteps. The choice of model timestep involves a fundamental trade-off: shorter timesteps (e.g. 1 to 6 hours) finely resolve atmospheric dynamics within the diurnal cycle but increase error accumulation for a given forecast horizon, while longer timesteps (e.g. 24 hours) reduce error accumulation but limit the usability of short-range forecasts where sub-daily predictability is high. In this work, we present GEM-3, a probabilistic global weather model that addresses this trade-off through explicit multi-timestep inference. With a single set of trained weights, the model timestep can be configured at inference time to balance predictability and usability across a broad forecast horizon. Additionally, we find that mixed-timestep training consistently improves rollout stability relative to timestep-specialist models. Under the hood, GEM-3 is a lightweight neighborhood-attention transformer with ~134M parameters on an equirectangular grid with a number of architectural advancements beyond its predecessor GEM-2. The result is a practical forecasting system that couples near-SOTA medium-range probabilistic skill, stable extended-range rollouts, efficient training and inference, and decision-relevant diagnostics.

AI 总结：本文提出CRAFTER智能体，挖掘黑盒冻结预测器的残差以生成纠正特征，在6个数据集和6个主干上优于现有系统，使改进翻倍、误差降27%，可归因特征来源。

链接：https://arxiv.org/abs/2608.05207

机构：University of Illinois Chicago（伊利诺伊大学芝加哥分校）； Texas A&M University（德克萨斯农工大学）； Massachusetts Institute of Technology（麻省理工学院）； Tsinghua University（清华大学）

作者：Fangxin Wang, Ziyi Zhang, Diyi Zhuang, Langzhou He, Shiyu Wang, Baichuan Mo, Philip S. Yu

英文摘要：Frozen pretrained forecasters often fail in structured, recurring ways that are costly to repair through fine-tuning. We study corrective feature discovery: mining interpretable features of a frozen forecaster's residual to drive a lightweight post-hoc corrector. Prior automated feature engineering models the data-generating process; corrective features instead model the model-failure process. We present CRAFTER (Corrective Residual Agent with Feature-based Temporal Exploration and Reasoning), which keeps the backbone frozen and mines its residual with two complementary generators: a compositional search over the raw input channels, and a large language model (LLM) that proposes named feature combinations, binary flags, and short executable code. A single validation-grounded gate accepts or rejects every candidate regardless of its origin, and a validation-selected corrector applies the accepted features or leaves the forecast unchanged. This source-agnostic pipeline also allows prior feature-engineering systems to be evaluated under identical conditions, making CRAFTER an instrument for attributing forecast improvements to the feature source alone. Across six public datasets and six frozen backbones, CRAFTER surpasses every dedicated feature-engineering system at every feature budget, roughly doubling the improvement achieved by the corrector alone and reducing the error of the weakest backbones by up to 27%. These gains are robust across different LLM backends and persist even when applied on top of fine-tuned backbones.

AI 总结：本文提出用于编程基于LLM的流的概率语言PPDL，可量化传播流中不确定性，无需额外代码即可尝试推理缩放技术，还通过实验及面向Rocq的定理证明智能体案例验证了其能力。

链接：https://arxiv.org/abs/2608.05234

作者：Louis Mandel, Guillaume Baudart, Mandana Vaziri, Martin Hirzel

英文摘要：Building reliable applications that leverage large language models (LLMs) remains a significant challenge. While LLMs offer impressive capabilities across diverse tasks, their outputs often lack accuracy and provide no clear measure of confidence. This uncertainty compounds in flows of multiple calls to LLMs and other tools, making it difficult for developers and end-users to trust the results. This paper introduces a probabilistic language for programming LLM-based flows. It enables developers to quantify and propagate uncertainty throughout the application's flow, and experiment with different inference scaling techniques without adding a single line of code beyond the flow's logic. We present an experimental study to demonstrate this capability, and a case study building a theorem proving agent for the Rocq theorem prover.

AI 总结：该研究针对多模态时间序列语言对齐的三难困境，提出CGTime模型，通过计算处理感知、LLM处理描述，在多变量理解任务上优于更大的通用模型。

链接：https://arxiv.org/abs/2608.05238

作者：Xinran Feng, Yi Xie, Chao Zhang, Ruikun Li, Wanyun Ling, Ziyue Li, Chenxi Liu

英文摘要：Training multimodal models to align time series with language runs into a self-supervision trap. The usual recipe asks an LLM to read a series and write a description, so label quality is capped by the perceptual skill the model is supposed to learn. The data can never teach more than the labeler already knows. A second gap makes this worse: most datasets use a single variable, but the patterns that matter (cross-channel correlation, lead-lag structure, co-occurring anomalies) appear only with several variables, right where the labeling LLM's limits are most exposed. These two problems create a trilemma: existing methods are reliable, realistic, or scalable, but none achieves all three. We resolve this by decoupling perception from description. Deterministic code computes a set of statistics from real, open-source multivariate series; the LLM verbalizes those precomputed facts. Perception, which LLMs do poorly, is handled by computation, while the LLM handles expression. This produces CGTime, our 4B-parameter computation-grounded time-series-language model. CGTime outperforms far larger general-purpose models on multivariate understanding tasks: it attains the best multivariate fact score on our held-out benchmark (0.283 vs. 0.173 for GPT-4o-mini and 0.203 for GPT-5.4-nano), a gap that survives Holm-corrected paired significance tests against every baseline. It also states verifiable numerical facts in generated captions more accurately and covers a broader range of statistical properties.

AI 总结：该研究指出因子化生成模型中仅匹配潜在风格的边际分布无法保证其与类别信息独立，通过实验证实存在风格泄漏，并提出相关缓解策略及验证方法。

链接：https://arxiv.org/abs/2608.05243

作者：Duong Bach, Hai Nguyen Hong, Cuong Do

英文摘要：Factorized generative models commonly regularize a latent style variable z_s by matching its marginal distribution to a fixed Gaussian prior and interpret this as evidence that the style representation is independent of class information. We show that this interpretation is incorrect. Matching only the marginal distribution places no constraint on the class-conditional distributions, allowing the latent style to remain highly predictive of the label despite appearing perfectly Gaussian in aggregate. We derive an exact decomposition showing that this mismatch is one of four conditions required for factorized sampling, and demonstrate that eliminating it is necessary but not sufficient to obtain the intended factorization. Empirically, our case-study model and four representative latent baselines achieve near-zero global MMD while still allowing a linear probe to recover class labels with 74%--100% accuracy (10% chance level). Our model reaches 99.15% clustering accuracy, whereas externally evaluated class-conditional generation succeeds only 16% of the time. This leakage remains under six independent perturbations involving model capacity, curriculum, prior geometry, and supervision across two datasets. Four mitigation strategies reduce probe accuracy to 21%--46%, although they leave within-class dependence largely unchanged. A post-hoc conditional prior improves externally evaluated class generation to 0.97 on MNIST without retraining but reaches only 0.41 on CIFAR-10, while an empirical style bank achieves 0.88 on CIFAR-10. These results demonstrate that no divergence computed solely on the marginal distribution of the style latent can certify independence from class labels, and that reporting marginal statistics alone does not verify the property commonly claimed in factorized generative models.

AI 总结：针对多任务SFT的全模型回滚成本高的问题，提出参数高效框架AuroSFT，将状态转为可合并的适配器状态，在保留骨干网络的比较中平均准确率达61.36%，优于msft的59.85%。

链接：https://arxiv.org/abs/2608.05250

作者：Yue Han, Ziniu Liu

英文摘要： Multi-task supervised fine-tuning (SFT) often casts a heterogeneous data mixture as a single optimization problem, even though different tasks may reach their best generalization at different times. msft exposes this mismatch through task-wise roll-out, exclusion, and rollback, but its original formulation materializes the scheduler state as full-model checkpoints, making stage transitions costly to store, restore, and deploy. This paper introduces AuroSFT, a parameter-efficient framework that recasts the carried state of overfitting-aware multi-task SFT as a compact, mergeable adapter state. AuroSFT freezes the pretrained backbone, trains only injected adapters, rolls back adapter checkpoints at task-wise peaks, and continues on the remaining active mixture. At the layer level, each adapter applies an AuroRA-inspired adaptive nonlinear layer to a low-rank weight factor rather than to the sample representation. The resulting update remains linear in the input, rank-bounded, and exactly mergeable into the frozen projection. Under the retained-backbone comparison protocol, AuroSFT achieves 61.36% average accuracy, compared with 59.85% for the corresponding msft reference row, and obtains higher accuracy on all five backbones. Our code is available at the anonymous repository: this https URL.

AI 总结：该研究针对量化正交微调（qoft）的线性正交变换局限，提出AuroOFT方法，在保留qoft稳定分支的基础上附加零起点门控低秩非线性残差，在Qwen2.5设置上提升性能并减少可训练参数。

链接：https://arxiv.org/abs/2608.05253

作者：Yue Han, Dianlin Wang

英文摘要：Quantized orthogonal fine-tuning (qoft) enables parameter-efficient adaptation of low-bit language models by learning structured activation rotations before frozen quantized weights. However, its task-specific updates remain constrained to linear orthogonal transformations, limiting input-dependent nonlinear corrections. We introduce AuroOFT, which keeps qoft as a stable quantization-compatible branch while attaching a zero-start gated low-rank nonlinear residual to each adapted linear layer. AuroOFT maps activations into an RMS-normalized compact latent space and uses adaptive nonlinear bases with bounded or token-dependent gating. The zero-initialized up projection makes AuroOFT functionally identical to qoft at initialization, while orthogonality remains a branch-level stability property rather than a property of the combined nonlinear layer. Under matched data, optimization, decoding, and parser protocols, AuroOFT improves Macro-6 over matched qoft by 1.30-2.70% on the 1.5B/3B Qwen2.5 settings, exceeds QLoRA by 6.52-10.62%, and saves 32.3-44.7% trainable parameters relative to QLoRA in representative scales. The small exam-style multiple-choice math set is treated only as a protocol-sensitivity diagnostic. Our code is available at the anonymous repository: this https URL.

AI 总结：本研究系统评估15种机器学习模型，发现TabPFN在野火后泥石流预测中表现最优，合成数据增强可提升多数模型性能，结合可解释分析为该预测提供了全面框架。

链接：https://arxiv.org/abs/2608.05265

机构：University of Calgary（卡尔加里大学）

作者：Quinn Ledingham, Zhengsen Xu, Yimin Zhu, Zack Dewis, Mabel Heffring, Saeid Taleghanidoozdoozan, Motasem Alkayid, Megan Greenwood, Lincoln Linlin Xu

英文摘要：Prediction of post-wildfire debris flows is critical for mitigating hazards to communities, infrastructure, and resources during intense rainfall in recently burned areas. However, identifying reliable machine learning models is complicated by overlapping debris-flow and non-debris-flow events in feature space, the need for model interpretability, and limited training data. This paper addresses these challenges through a systematic evaluation of machine learning models in terms of predictive performance, feature importance, and synthetic data augmentation. Using basin-scale observations of post-wildfire debris-flow events across the western United States, we compare 15 models, including the Tabular Prior-Data Fitted Network (TabPFN). Repeated stratified cross-validation shows that TabPFN achieves the highest unaugmented performance with a threat score of 0.637, closely followed by the best tree-based models. SHapley Additive exPlanations (SHAP) are used to identify the features driving predictions, revealing that short-duration rainfall intensity and storm accumulation consistently rank highest, while burn severity and terrain features contribute less. We further evaluate synthetic data augmentation using TabPFN-generated samples to address the scarcity of debris-flow observations. Synthetic augmentation improves the performance of all models except CNN, with the largest mean threat score increase of +0.041 among the deep learning models. By combining rigorous model benchmarking, interpretable feature analysis, and synthetic data augmentation, this work provides a comprehensive framework for improving post-wildfire debris-flow prediction.

AI 总结：QEvict是一种三层KV缓存管理方案，通过可恢复量化驱逐解决长上下文解码中的注意力漂移问题，在固定内存预算下提升了长上下文任务的信息保留效果。

链接：https://arxiv.org/abs/2608.05326

作者：Ayushman Garg, Akshita Gupta, Shaswata Bhattacharya, Abhishek Gupta, Sandeep Kumar, Manoj Kumar

英文摘要：Autoregressive large language model inference is increasingly constrained by the memory footprint of the Key-Value (KV) cache. A dominant line of work reduces this footprint by evicting tokens that appear unimportant under attention-derived scores. However, such policies make an implicit irreversible decision: once a token is evicted, it cannot become useful again. We show that this assumption is brittle during decoding. Token and window importance drift as generated queries evolve, causing standard eviction policies to permanently discard states that later receive substantial attention under the full-cache model. To characterize this behaviour, we introduce Future Missed Mass and Global LIR, two diagnostics that measure future attention assigned to discarded states and the reactivation of historically inactive regions. We propose QEvict, a three-tier KV-cache management scheme that replaces binary retain-or-delete eviction with recoverable eviction. QEvict maintains high-confidence windows in full precision, stores intermediate windows in a quantized recoverable tier, and deletes only the lowest-confidence windows. During decoding, cumulative attention scores update window importance and when a quantized window becomes important again, it is dequantized and promoted to the full-precision. Under a fixed memory budget, this design preserves broader historical context while retaining exact full precision for the most important regions. Across long-context understanding, retrieval, and reasoning benchmarks, QEvict consistently improves over representative eviction and quantization baselines, reducing missed attention and improving information retention

AI 总结：本文提出量子结构化世界模型（QSWMs），研究量子启发结构对世界建模的作用，在基本元胞自动机上评估其变体，发现复值QSWM局部预测潜力良好但类密度矩阵变体存在长时序预测局限。

链接：https://arxiv.org/abs/2608.05371

机构：Youngstown State University（扬斯敦州立大学）； Kent State University（肯特州立大学）； George Washington University（乔治·华盛顿大学）

作者： Hailong Jiang, Emran Hossain, Feng Yu, Jianfeng Zhu, Guilin Zhang, Wulan Guo

英文摘要：World models learn latent states that summarize interaction histories, evolve over time, and support prediction, simulation, or planning. Most existing world models represent these states using classical vectors, probability distributions, recurrent hidden states, or transformer activations. In this paper, we introduce Quantum-Structured World Models (QSWMs), a quantum-inspired framework for predictive world modeling with structured latent states, latent transition operators, and measurement-inspired decoding maps. We study whether mathematical structures inspired by quantum theory, such as complex-valued representations and density-matrix-like latents, provide useful inductive biases for world modeling. We establish three foundational properties: classical inclusion, predictive sufficiency, and structured compactness. We then instantiate complex-valued and density-matrix-like QSWM variants and evaluate them on elementary cellular automata against strong classical baselines. Results show promising local predictive potential for complex-valued QSWMs, while also revealing limitations in long-horizon rollout, density-matrix variants

AI 总结：本文提出收敛时的扰动敏感性信号，无需群体标注与早停轮次即可识别虚假相关样本，用其重新平衡训练可将Waterbirds数据集最差群体准确率从57.3%提至80.8%。

链接：https://arxiv.org/abs/2608.05419

作者：Nilesh Kumar

英文摘要：Models trained by empirical risk minimization on data containing spurious correlations achieve high average accuracy while failing on subpopulations where the correlation does not hold. Existing methods for identifying the affected samples without group annotations rely on signals from early training, which requires locating the epoch at which to intervene, a hyperparameter typically selected using group-labeled validation data. We show that a usable signal is available after convergence, when loss no longer distinguishes the two populations. Samples consistent with the spurious correlation are classified by a shared rule, while the remaining samples are fit through configurations specific to individual inputs and are correspondingly more fragile. Applying a fixed perturbation to a converged model's inputs flips the predictions of the latter far more often than the former. The resulting procedure requires two forward passes per training sample, no group annotations at any stage, and no early-stopping epoch. Using the detected samples to rebalance training raises worst-group accuracy on Waterbirds from 57.3% to 80.8%, against 85.8% with ground-truth group labels.

AI 总结：该研究针对集合 Transformer 提出矩阵 zonotopic 注意力（MZAttn），通过上下文自适应值投影解决多头注意力的不对称性问题，在高秩稀疏组合的集合预测任务上表现出架构优势。

链接：https://arxiv.org/abs/2608.05472

作者：Zhen Zhang, Amr Alanwar

英文摘要：Multi-head attention combines an input-dependent softmax routing with an input-independent linear value projection, so the per-sample operator mapping aggregated values to outputs is the same for every input set. We study the consequences of this asymmetry for permutation-invariant set targets. We introduce the Transformation Degrees of Freedom (TDOF) of a target operator, a complexity measure counting the input-dependent directions an exact representation requires, and present a depth-separation analysis showing that context-rigid attention needs depth proportional to the target's TDOF, whereas a single layer with a context-adaptive value family can represent the same target. Building on this analysis, we propose Matrix Zonotopic Attention (MZAttn), which replaces the fixed value projection with a context-adaptive matrix-zonotope family: a centre matrix plus a sum of generator matrices weighted by input-dependent gates. The construction reduces to standard multi-head attention at initialisation, preserves permutation equivariance, and admits a data-driven reachability interpretation. Experiments on a range of set-prediction tasks are consistent with the TDOF prediction that the architectural advantage is selective: it appears on targets that depend on the input set in a high-rank, sparsely combinatorial way, and is small on aggregate-statistic targets where parameter-matched standard attention is already competitive.

AI 总结：提出无需训练的Align-RAG方法，通过闭式对齐检索窗口，在冻结TSFM上提升检索增强预测性能，证明冻结TSFM可动态整合检索结果，闭式对齐可作为默认基线。

链接：https://arxiv.org/abs/2608.05571

机构：Stanford University（斯坦福大学）； Amazon（亚马逊公司）

作者：Mohammad Asadi, Soheil Hor, Bardiya Akhbari, Jack W. O'Sullivan, Tahoura Nedaee, Layne C. Price, Raviteja Anantha, Euan Ashley, Ehsan Adeli

英文摘要：Retrieval-augmented forecasting promises to adapt frozen Time Series Foundation Models (TSFMs) to new domains without fine-tuning, but recent methods typically rely on learned fusion modules, i.e., trained adapters that merge retrieved examples into the backbone's forecast, based on the assumption that frozen backbones cannot dynamically incorporate retrieved context on their own. We show this assumption is unnecessary. We introduce Align-RAG, a training-free method that applies a closed-form per-pair amplitude rescaling and integer-lag phase shift to retrieved past-future windows before they enter a frozen backbone's context. With no learned parameters, Align-RAG outperforms the state-of-the-art trained retrieval adapter on a frozen Chronos-Bolt on all seven datasets of the standard benchmark (avg -3.75% MSE), showing that the gains previously attributed to learned fusion are recoverable without any training. Align-RAG further improves zero-shot MSE on four additional frozen TSFMs with various architectures by 2.5% to 13.7% per backbone with no per-backbone tuning. To probe why alignment helps, we compare the frozen backbone's prediction shift under aligned demonstrations to the closed-form ridge prediction shift on the same pairs. We find that aligned demonstrations induce prediction shifts that track a closed-form ridge predictor on the same pairs, with a future-shuffle control ruling out a futures-averaging account. Together, these results indicate that frozen TSFMs already support dynamic in-context use of retrievals, and that closed-form alignment should be the default baseline for retrieval-augmented forecasting before any fusion module is trained. Code available at: this https URL

AI 总结：针对不完整多模态分类问题，提出轻量型GAUGE框架，通过细粒度反事实证据门控实现更优性能，为模态不完整下的证据控制提供了可扩展方案。

链接：https://arxiv.org/abs/2608.05608

作者：Yunping Shi, En Yu, Kairui Guo, Jie Lu

英文摘要：Multimodal classification typically assumes all modalities are available, yet real-world inputs are often incomplete. Imputation and dynamic fusion can mitigate such incompleteness, but existing methods operate at a coarse modality level and thus cannot retain reliable components while suppressing misleading ones within the same recovered modality, compromising prediction reliability. To address this issue, we propose GAUGE, a lightweight counterfactual gating framework for incomplete multimodal classification. GAUGE first imputes missing modalities with a frozen imputer and encodes observed and recovered inputs uniformly as fine-grained evidence units. Rather than intervening on each unit explicitly, GAUGE scores the counterfactual effect of replacing every unit with a reference representation through prediction-aware Taylor evidence scores, all obtained in a single forward-backward pass. These scores are mapped to continuous gates, which are converted into additive attention-logit biases for unit-wise evidence modulation without altering the backbone architecture. Experiments across six benchmarks demonstrate that GAUGE outperforms strong baselines across diverse incomplete-input settings. Furthermore, a Taylor remainder theoretical analysis characterizes the error of the first-order approximation relative to the exact counterfactual effect, establishing GAUGE as a principled and scalable framework for fine-grained evidence control under modality incompleteness.

AI 总结：该研究针对大语言模型推理错误检测的权衡问题，提出三流检测器，在推理基准上提升选择准确率，还适用于事实类任务，验证了运动、区域、方向信号的互补性。

链接：https://arxiv.org/abs/2608.05660

机构：Australian Institute for Machine Learning（澳大利亚机器学习研究所）； Adelaide University（阿德莱德大学）； Naval Group Pacific（太平洋海军集团）； Responsible AI Research Centre（负责任人工智能研究中心）

作者：Hamed Damirchi, Ignacio Meza De la Jara, Damith Ranasinghe, Yuhang Liu, Javen Shi

英文摘要：As language models are increasingly used for tasks that require verifiable reasoning, reliably distinguishing sound reasoning from flawed reasoning has become an important practical problem. Recent trajectory-based methods seek this signal in layerwise residual-stream displacements, which capture how representations change while attenuating some stable, token-specific information. However, displacement omits the state from which an update originates, whereas restoring the full state risks reintroducing shortcut-prone information. We identify this trade-off and propose a three-stream detector that combines motion with two restricted views of location. A coarse region reader based on vector quantization and a fine direction reader over normalized multi-layer states. This design restores enough state context to interpret the motion without returning to full-state probing. On reasoning benchmarks unseen during training, our method improves selection accuracy by up to 12% over the displacement-only state of the art and 21% over single-layer probing baselines. Although trained only on reasoning benchmarks, it also reads factual completion and fact verification, ahead of every detector we compare against, which places the signal on correctness rather than on a kind of reasoning. Ablations further show that motion, region, and direction provide complementary signals. These results suggest that reasoning validity is better read from state-conditioned motion than from either static states or decontextualized trajectories alone.

AI 总结：该研究构建了RENDEQ生成科学图形渲染等价集，测量VLMs的共识-准确性耦合，发现重渲染优于重采样，共识在多数模型上优于基线，微调共识会降低准确性，共识仅在错误扩散阈值以上才证明正确性。

链接：https://arxiv.org/abs/2608.05670

作者：Rasul Khanbayov, Hasan Kurban

英文摘要：A model's agreement across perturbed inputs is used both as a label-free reliability signal and as a self-training target, on the premise that agreement tracks correctness. That coupling is rarely measured directly: natural-image perturbations preserve meaning only by assumption, and no exact answer key localizes errors. Scientific figures remove both obstacles, a figure is drawn from data by a program, so redrawing it yields images that are semantically equivalent by construction and share a programmatically exact answer. We build RENDEQ, a generator of such render-equivalence sets, and measure the coupling on three open-weight VLMs, checking every finding across three independent instantiations. Re-rendering beats resampling on both accuracy and reliability. Agreement beats an evidence-carrying baseline, mean token log-probability, on two of three models and ties on the third, reversing an intermediate, buggy replication traced to a rendering-pipeline failure. The dispersion behind this is concentrated in one style factor, the plotting library, more than double the next-largest factor and an order of magnitude above the noise floor. Fine-tuning on the model's own cross-render consensus inverts: accuracy falls in every one of five replication runs, the opposite sign to published results on natural images. Agreement certifies correctness only above a threshold set by how diffuse a model's errors are, and an objective that rewards agreement destroys exactly that diffuseness.

AI 总结：该研究提出视觉-语言图表阅读的无标签可靠性交换理论，构建无标签、无需训练的检测器，发布REND-EQUIV数据集，揭示一致性盲区可计算，循环重标记可提升性能，解释排序反转现象。

链接：https://arxiv.org/abs/2608.05675

作者：Rasul Khanbayov, Hasan Kurban

英文摘要： Label-free reliability for vision-language models rests on invariance: perturb the input and a faithful reader's answer should not change. This has a known blind spot, a systematic misreading survives the perturbation and gets certified wrong, which we show is computable, not just real: an error is invisible to an edit exactly when the two commute, so the errors a suite cannot reach form its joint centralizer, a set that shrinks as edits are added and can be written down rather than guessed at. We act on the complementary relation, equivariance: edit a figure's data and the correct answer must change by a computable amount. Two matched edits are provably complete for affine reading errors; no suite of swap edits is complete for label permutations, and cyclic relabeling closes most of that gap. We instantiate the theory as the Equivariance-Consistency Score, a label-free, training-free detector, and release REND-EQUIV, pairing matched invariance and equivariance sets over identical data. The predicted ordering holds across three models and a hand-labeled population immune to the one circularity in how it is selected; a second invariance-family method confirms the blind spot belongs to the relation, not to any implementation; and cyclic relabeling delivers its predicted gain on a matched real sample. The same characterization explains a reported inversion of this ordering in the classifier metamorphic-testing literature: detectability is a joint property of the relation and the fault class, never of the relation alone.

AI 总结：CircuitSteer是利用SAEs识别多层语义回路的新型框架，通过几何对齐合成引导向量实现多点干预，在多任务多模型上，其引导效果优于牺牲流畅性或覆盖不足的对比方法。

链接：https://arxiv.org/abs/2608.05732

机构：University of Southern California（南加利福尼亚大学）

作者：Mehrshad Saadatinia, Parsa Razmara, Ardalan Aryashad, Ali Abbasi, Seyedarmin Azizi

英文摘要：Controlling the behavior of large language models (LLMs) remains a critical challenge for AI alignment. Existing steering methods, such as Contrastive Activation Addition (CAA), typically rely on fixed single-layer interventions derived from aggregate activation differences. These methods impose a single intervention across semantically diverse inputs and often fail to sustain consistent behavioral changes across layers, limiting the effectiveness of the steering. In this work, we introduce CircuitSteer, a novel framework that leverages Sparse Autoencoders (SAEs) to identify and manipulate coherent semantic circuits distributed across multiple layers. By constructing a feature flow circuit based on feature co-activation and the geometric alignment of decoder directions, we isolate the specific multi-layer subcircuits responsible for a target behavior. We then synthesize dense steering vectors from these sparse features and apply multi-point interventions to guide the model's internal semantic trajectory. We evaluate CircuitSteer using contrastive examples across a diverse set of tasks, including toxicity, emotion-intensity, sycophancy, and refusal, spanning two model families. Across all models and datasets, CircuitSteer is the only method to consistently produce fluency-preserving interventions; competing methods either sacrifice text quality or lack coverage, failing entirely on complex behaviors like sycophancy and refusal. These results demonstrate that multi-layer circuit steering, enabled by enforcing geometric alignment among selected features, yields strictly more robust and effective behavioral control than static single-point interventions. Code is available at this https URL.

AI 总结：本研究提出并验证基于形状约束的预测建模方法，结合少量实验数据可准确预测纳米药物开发中的颗粒特性，减少实验流程，加速连续流系统中纳米药物的开发。

链接：https://arxiv.org/abs/2608.05761

作者：Kai Dahms, Eilien Heinrich, Jochen Schmid, Michael Bortz, Iryna Savych, Regina Bleul

英文摘要：The development of nanotherapeutics often involves extensive empirical optimization due to the sensitivity of nanoparticle properties, such as size and polydispersity index (PDI), to minor changes in process parameters. Factors like formulation concentration, flow rates, and mixing ratios can significantly influence clinical efficacy and therapeutic outcomes. The absence of predictive mathematical frameworks has made iterative experimental screening necessary, increasing both costs and development time. This study introduces and validates a predictive modeling approach based on shape constraints, aiming to enhance the estimation of nanoparticle characteristics across various process conditions. Using controlled microfluidic methods, liposomes and lipid nanoparticles were systematically prepared under varying lipid concentrations, flow rates, and aqueous-to-organic mixing ratios. The shape-constrained model, informed by both experimental data and expert knowledge, was subsequently validated for a pharmaceutical application using minimal empirical data. Results reveal that shape-constrained modeling facilitates accurate prediction of nanoparticle size and dispersity, reducing the need for extensive experimental workflows. This framework supports rational and efficient process development for manufacturing nanomedicine systems.

AI 总结：该研究针对17个跨多领域的智能体基准，提出无需展开的任务难度预测方法，发现token级熵是有效预测信号，可通过难度残差暴露环境缺陷，助力校准基准与构建训练课程。

链接：https://arxiv.org/abs/2608.05797

机构：Andromede AI（安卓迈德人工智能）

作者：Stefan Krsteski, Charlotte Meyer

英文摘要：Task difficulty dictates an agent's likelihood of success, and estimating it without rollouts means forecasting this directly from a task description before executing costly simulations in stateful environments. Reliable estimates would therefore allow environment designers to calibrate evaluation benchmarks and construct progressive training curricula. This becomes increasingly important as agents move into long-horizon domains, where empirical trial-and-error is a severe computational bottleneck. Prior work on early prediction is limited to static tasks or isolated coding environments, often relying on narrow features and inaccurate evaluation metrics. We study \textit{ex ante} difficulty prediction across 17 agentic benchmarks spanning coding, mathematics, machine learning, web navigation, function calling, and other domains. We show that AUC can mask poor difficulty estimates, identify token-level entropy as a useful predictive signal, and show how residuals between expected and observed difficulty can expose hidden environment flaws such as contamination and infeasibility.

AI 总结：该研究提出学习排序框架，基于GPU测量训练梯度提升排序器，用于选高效张量网络收缩计划以加速量子电路模拟，其排序在不同GPU间具稳定性，可减少计划搜索成本。

链接：https://arxiv.org/abs/2608.05819

机构：Universitat de València（瓦伦西亚大学）； Universitat Jaume I（哈梅一世大学）

作者：Alfred M. Pastor, Maribel Castillo, Jose M. Badia

英文摘要：Classical simulation remains essential for developing and validating quantum algorithms, but its cost grows rapidly with circuit size. Tensor-network contraction can reduce this cost by exploiting circuit structure, although its efficiency depends strongly on the chosen contraction plan. On GPUs, plans with similar theoretical complexity may perform very differently because execution also depends on parallelism, reduction structure, memory traffic, and contraction geometry. We present a learning-to-rank framework for selecting efficient contraction plans before executing them. Each plan is represented by structural features derived directly from its sequence of pairwise contractions, and gradient-boosted rankers are trained from GPU measurements using listwise and pairwise objectives. We evaluate the resulting models on diverse circuit families, using separate in-distribution and circuit-family-shift test sets, and compare them with random and MinFill-based baselines. The learned rankers generally identify better plans, with the listwise model providing the strongest overall decision quality. We also study backend shift by comparing empirical plan orderings on two GPU architectures and evaluating the source-trained models on the second device without retraining. The rankings remain substantially, though not perfectly, stable across GPUs, and the models retain useful decision quality. These results support Learning to Rank as a practical way to reduce contraction-plan search, while showing that performance remains partly backend dependent.

AI 总结：本研究提出CohortHijack鲁棒性审计方法，证实通过移除少量伴随细胞可操纵单细胞注释的修正标签，揭示查询队列组成是单细胞注释的攻击面。

链接：https://arxiv.org/abs/2608.05900

机构：Faculty of Computer Science, University of New Brunswick（新不伦瑞克大学计算机科学学院）； Farzanegan Amin 2 High School（法尔扎内甘阿明第二高中）

作者：Arash Vashagh, Yasmin Vashagh

英文摘要：Many single-cell annotation tools refine an initial cell label using nearby cells or cluster-level voting. We study whether this refinement can be manipulated without changing the target cell. We introduce CohortHijack, a robustness audit that removes selected non-target cells from the query cohort while preserving the target expression profile, base prediction, and trained model. We evaluate random and structured removal methods, together with greedy, multi-start, and beam search, on PBMC3K and Paul15 using logistic regression and calibrated linear SVM classifiers. Structured removal was consistently stronger than random removal on Paul15. Multi-start search changed 24.33% of linear-SVM targets and 19.67% of logistic-regression targets while removing a small fraction of the cohort and keeping mean collateral changes below 0.4%. Ablations confirmed that the effect disappeared when neighborhood refinement was disabled. We also evaluated CellTypist majority voting, where independent predictions remained unchanged across all evaluations, but refined labels changed after small companion-cell removals. These findings identify query cohort composition as a target-preserving attack surface in single-cell annotation.

AI 总结：该研究探究简单变换在异构文本嵌入模型间的迁移性，通过9种不同模型的多维度评估发现，异构嵌入空间并非普遍可通过简单映射关联。

链接：https://arxiv.org/abs/2608.05980

作者：Sid Ali Hamideche, Louis Adrien Dufrene, Quentin Lampin, Guillaume Larue (Orange Research)

英文摘要：We investigate whether simple transformations can translate representations across heterogeneous text embedding models. Understanding how independently trained models organize semantic information is an enabler for AI-to-AI latent communication without decoding into human-readable text. Focusing on lightweight translators such as linear mappings, we test the literature hypothesis of latent universality in a realistic text setting beyond simplified benchmarks. Across nine embedding models differing in architecture, pooling strategy, and training objective, we evaluate compatibility using CKA, downstream transfer, fidelity, and retrieval. Simple translators recover meaningful shared structure and support transfer for some compatible pairs, but fail sharply for others. Compatibility depends jointly on architecture, training objective, pooling, and data distribution. Overall, the results show that heterogeneous embedding spaces are not universally related by simple mappings as often suggested in some literature.

AI 总结：该研究提出THBKG时间生物医学知识图谱，通过图传播方法预测靶点-疾病对的临床进展，在无直接证据的对中表现优异，还提供可解释预测的路径解释器。

链接：https://arxiv.org/abs/2608.05982

机构：Queen Mary University of London（伦敦玛丽女王大学）； Recursion Pharmaceuticals Inc.（Recursion制药公司）

作者：Pui Chung Siu, Claudia Cabrera, Mani Mudaliar, Arkaitz Zubiaga

英文摘要： Inadequate target--disease linkage accounts for 40--50\% of Phase~II efficacy failures, so anticipating which programmes will advance would let sponsors back the hypotheses most likely to reach patients. What a programme can be judged on is the evidence that supported its linkage \emph{when it entered the clinic}. No existing biomedical knowledge graph allows that evidence profile to be assembled as of a past date. We present the Temporal Heterogeneous Biomedical Knowledge Graph (THBKG), which describes and predicts therapeutic target--disease links through time: 110,396 entities and 11.1M edges across nineteen relation types, each edge carrying the year its evidence changed, so a pair's profile can be recovered as it stood when its own decision fell due. On this graph we define a decision-aligned benchmark that predicts, for a target--disease pair entering Phase~II, whether it advances to Phase~III on evidence datable before that decision. Graph propagation over the THBKG outranks every direct-evidence reference scored under the same decision-aligned protocol, reaching a relative success of 4.3--4.5 at the top ten pairs per therapeutic area. The gain concentrates on the 72.8\% of pairs with no direct target--disease evidence at their decision point, where a direct-edge model has nothing to read: the encoders still rank five- to sixfold above chance, recovering the signal by propagating over the intervening biology. Adapting a path-based explainer to the decision-time subgraph decomposes each prediction into the evidence landscape behind the hypothesis for explainable prediction. We release the THBKG as a continually updated substrate for studying therapeutic target hypotheses by retrospective validation.

AI 总结：本文针对表格基础模型（TFMs），提出其预测是否可由任意联合分布生成的问题，设定边际一致性与分解一致性要求，发现所有评估的TFMs均违反这两项要求。

链接：https://arxiv.org/abs/2608.06004

作者：Christian Klötergens, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme, Tom Hanika

英文摘要：Tabular Foundation Models (TFMs) are currently the best approach to tabular prediction problems. They are constructed as transformers that approximate the Bayesian posterior predictive distribution based on a pre-training prior. These univariate predictors can be converted into multivariate ones autoregressively by sampling one target and adding it to the features. However, the faithfulness of the resulting joint has not been investigated. Furthermore, TFMs cannot be evaluated against the posterior itself, at least not on real-world datasets, because the ground-truth distribution is unknown. We therefore propose asking a different question: could a model's predictions result from any joint distribution? To answer this question, we pose two requirements that any such model must satisfy. The first is marginalization consistency, which demands that marginalized conditionals are equal to directly predicted marginals. The second is factorization consistency, which demands that different factorization orders result in equal joint distributions. Every TFM that we evaluate violates both of these requirements for both classification and regression across all datasets.

AI 总结：本研究针对动态图提示的几何适配不足问题，提出CurvPrompt框架，通过拓扑路由混合曲率专家实现自适应表示，在少样本链接预测和节点分类任务上表现优异，验证了几何自适应提示的必要性。

链接：https://arxiv.org/abs/2608.06031

作者：Quanxin Wang, Xuanting Xie, Bingheng Li, Xingtong Yu, Shuo Wang, Ruiyi Fang, Zhao Kang

英文摘要：Dynamic graph prompting freezes a pre-trained temporal backbone and adapts it to label-scarce downstream tasks using lightweight prompts. However, existing methods operate within a single, fixed embedding space. In this work, we reveal that temporal shifts in local clustering and degree heterogeneity actively reorganize the edge curvature spectrum---indicating that the optimal representation geometry dynamically evolves with local topology over time. We formalize this unaddressed mismatch as geometry under-adaptation. To overcome this limitation, we propose CurvPrompt, a topology-routed geometry prompting framework for dynamic graphs. Instead of relying on a single space, CurvPrompt maintains a bank of curvature-diverse Riemannian experts, each paired with a learnable prompt. A topology-aware gate dynamically routes each node--time instance to a sparse subset of experts, constructing a personalized mixed-curvature representation. To ensure parameter efficiency and training stability under extreme label scarcity, CurvPrompt employs soft routing during pre-training to build a continuous topology--geometry mapping, and transitions to hard Top-K routing with uniform weights during downstream adaptation. Extensive experiments across four benchmark datasets show that CurvPrompt significantly advances few-shot link prediction while delivering strong, consistent performance on node classification tasks, validating the necessity of geometry-adaptive prompting.

AI 总结：本研究提出Kastor微调策略，通过两阶段推理、均值预测正则化等方法改进物理基础模型，在The Well数据集上实现比Walrus更优的PDE仿真性能，降低预测误差并提升效率。

链接：https://arxiv.org/abs/2608.06107

作者：Guillaume Couairon, Alexis Jacq, Yu-Han Wu, Renu Singh, Yana Hasson, Quentin Berthet, Romuald Elie

英文摘要：Machine learning offers a promising avenue to accelerate physical simulations by replacing computationally expensive traditional Partial Differential Equation (PDE) solvers with fast, differentiable surrogate models. However, standard auto-regressive ML emulators often suffer from error accumulation over long horizons and struggle to capture the stochasticity of complex physical systems. In this paper, we propose Kastor, a comprehensive methodology to adapt a deterministic physics foundation model into a highly efficient and accurate generative surrogate. First, we introduce a two-stage inference scheme that combines a large-stride causal auto-regressive model with a non-causal temporal super-resolution network, significantly reducing error accumulation while minimizing computational cost. Second, we present Mean prediction regularization (MPR), a novel training objective that constrains the generative model to predict the deterministic distribution mean under null noise conditioning. This regularization dramatically improves the performance and stability of both Functional Generative Networks (FGN) and diffusion-based emulators. Finally, we demonstrate that incorporating spatial gradient matching improves the accuracy and physical fidelity of the simulations as measured by power spectrum density. Extensive evaluations on diverse simulation datasets of the benchmark The Well show that with these components, our model outperforms competing methods in forecasting accuracy, spectral consistency, and computational efficiency. Our model achieves a 42.9% average reduction in forecasting compared to our reference based on the Walrus finetuning methodology, and outperforms Walrus for 8 out of 10 datasets on variance-normalized RMSE (VRMSE).

AI 总结：该研究针对LLM推理中突发工作负载的问题，改进了WAIT算法，通过在线估计请求强度提升了低到达率变化场景下的吞吐量，且延迟与现有基准相当。

链接：https://arxiv.org/abs/2608.06135

机构：Indian Institute of Technology Dharwad（印度达尔瓦德印度理工学院）； Indian Institute of Technology Kanpur（印度坎普尔印度理工学院）

作者：Anjali Gangadhar Katageria, Shobha Rani, Raghu Nandan Sengupta

英文摘要： Large Language Models (LLMs) such as ChatGPT and Claude are widely used for information retrieval and problem-solving. Recent work has focused on improving scheduling algorithms to boost throughput while maintaining low latency. However, these approaches often assume Poisson request arrivals with constant rates - an assumption that fails to reflect the inherently bursty and dynamic nature of real-world traffic. We propose a lightweight extension to the state-of-the-art WAIT algorithm [1], which adapts to time-varying arrival rates without prior traffic knowledge. The proposed algorithm performs online estimation of request intensity based on observed interarrival times. Using Markov Modulated Poisson Process (MMPP)-based synthetic workloads with diverse request types, we conduct a simulation-based evaluation demonstrating that the proposed method achieves higher throughput than Sarathi-Serve [2], ORCA [3], and vLLM [4] in the evaluated low arrival-rate shift scenarios while maintaining comparable latency.

AI 总结：本文提出一种训练后早停机制，通过预测二值神经网络累积量的最终符号，可减少VGG11在CIFAR-10上的运算量，仅造成小幅准确率下降。

链接：https://arxiv.org/abs/2608.06177

作者：Quentin Luquet de Saint-Germain, Massil Ait Abdeslam, Jean Pierre David

英文摘要：Binary neural networks are very attractive for constrained deployment, enabling small footprint and low-power inference. For binary activations, the dot products become sign-controlled additions or subtractions, but the number of operations is unchanged. Indeed, every neuron or output channel still accumulates all of its input, even though only the sign will be retained, which is often wasteful. As the accumulation progresses, the running partial sum frequently drifts so far from zero that its final sign becomes highly predictable long before the last term is reached; every contribution evaluated after that point changes the value of the sum but not the final output activation. This paper turns this observation into a post-training early-stopping mechanism. We characterize the behavior of the running accumulations on the training dataset and use this information to predict the final sign as soon as possible. No model parameter is retrained. We count the number of operations under an idealized ordering of weights. On VGG11 applied to the CIFAR-10 dataset, the method removes $86.6\%$ of the accumulation terms of the deepest convolution for a $0.37$-point accuracy drop, and $25\%$ of the full-network arithmetic when used on the three deepest convolutions simultaneously, for a $1.36$-point drop.

AI 总结：该研究提出SAGA框架，用依存句法分析器监督取代人类偏好标注，在丹麦语、冰岛语等低资源北欧语言上提升了GPT-SW3-1.3B的语法质量，为相关语言的语法对齐提供了实用替代方案。

链接：https://arxiv.org/abs/2608.06179

机构：Linköping University（林雪平大学）； University of Iceland（冰岛大学）

作者：Hoda Fakharzadehjahromy, Emil Wiman, Andreas Bueff, Hafsteinn Einarsson, Fredrik Heintz

英文摘要：Preference optimisation has proven effective for improving large language models but typically relies on costly human preference annotations. Extending these methods to morphologically rich, low-resource languages remains challenging because such annotations are scarce. We present SAGA (Score-weighted Adaptive Generation Alignment), a parser-guided preference optimisation framework that replaces human labels with dependency-parser supervision. SAGA converts parser judgements into preference pairs for delta-DPO, combines parser quality with lexical diversity in a composite reward, filters low-information pairs using a reward-gap criterion, and monitors reward hacking to maintain reliable supervision. Across Danish, Icelandic, and Norwegian Bokmål using GPT-SW3-1.3B, SAGA consistently improves grammatical quality without requiring human preference labels. Danish parse success increases from 69.0% to 93.8%, Icelandic achieves a +4.5 percentage-point improvement on an independent Stanza evaluation (three-run mean +3.3 percentage points) while native speakers prefer SAGA outputs in 80% of pairwise comparisons, and Norwegian Bokmål improves by +28 percentage points. These results demonstrate that parser-derived supervision is a practical alternative to human preference annotation for grammatical alignment in low-resource languages where high-quality dependency parsers are available.

AI 总结：本综述构建了后训练适应技术的六维分类法，梳理技术间关系，为AI治理提供术语支持，并指出该领域的开放挑战。

链接：https://arxiv.org/abs/2608.06246

作者：Fardin Afdideh, Fernando Seoane, Farhad Abtahi

英文摘要：Post-training adaptation has become central to modern machine learning practice and includes techniques such as retraining, fine-tuning, parameter-efficient adaptation, alignment, retrieval augmentation, model editing, unlearning, calibration, and Multimodal Instruction Tuning. However, the literature remains fragmented across technique families, model classes, and deployment contexts, making it difficult to compare methods or describe how a trained model has been modified. This survey synthesizes the post-training adaptation literature and introduces a six-dimensional taxonomy organized by mechanism, goal, data requirement, persistence, structural scope, and model type. The taxonomy distinguishes commonly conflated terms such as fine-tuning, retrieval augmentation, and prompting, and shows how adaptation strategies evolve from traditional machine learning through deep learning, foundation models, large language models, and multimodal large language models. It also maps relationships among techniques, including inheritance, supersession, hybridization, and layered deployment stacks. The resulting vocabulary can support technical documentation, model-change tracking, and governance analysis. The survey concludes by identifying open challenges in evaluation, reproducibility, persistent inference-time adaptation, unlearning, multimodal adaptation, and governance-aware post-training workflows.

AI 总结：该研究开发了代谢组学专用大语言模型MetaboLLM及配套的MetaboLLM-GIN，经多阶段适配后，在相关任务及两个临床预测场景中均取得优于对照模型的性能，证明领域专用语言模型可构建可预测且可解释的代谢物图表征。

链接：https://arxiv.org/abs/2608.06253

作者：Dohyun Ku, Min Gu Kwak, Francisco J. Pasquel, Jing Li

英文摘要：Metabolomics knowledge is distributed across heterogeneous resources and remains difficult to translate into predictive representations. We developed MetaboLLM, a metabolomics-specialized large language model adapted through continual pretraining, supervised fine-tuning, and structured retrieval, together with MetaboLLM-GIN, which converts generated biochemical descriptions into metabolite graphs for patient-level prediction using a graph isomorphism network. Across four backbone families, MetaboLLM outperformed corresponding base and medically adapted models on metabolomics knowledge, relational, and description tasks, and transferred to an external public benchmark. MetaboLLM-GIN achieved the highest AUC for stress hyperglycemia prediction after coronary artery bypass grafting (0.8616) and postmenopausal hormone-regimen classification (0.8123), outperforming conventional models, alternative graph constructions, and graphs generated from unadapted or non-retrieval LLM configurations. Model interpretation further produced biologically meaningful findings in both applications. These results show that domain-specialized language models can organize heterogeneous biochemical knowledge into predictive and interpretable metabolite graph representations.

AI 总结：

链接：https://arxiv.org/abs/2608.06262

机构：Fudan University（复旦大学）

作者：Zonghuan Xu

英文摘要：Model evaluations may fix all tests before observing any responses or select later tests using earlier responses. We study this choice in a conditional-query model on a finite outcome space $\mathcal{X}$ with $|\mathcal{X}|=N$. We first ask which pairs of distribution classes can be reliably distinguished. We then ask how many additional queries are required to match an adaptive tester when all queried events must be fixed in advance. We show that learnability holds if and only if the two classes have positive separation in their pairwise conditional probabilities. When this separation is zero, the optimal worst-case error is exactly $1/2$ at every finite query budget. For any $T$-query adaptive policy and any $\rho \in (0,1)$, we construct a randomized non-adaptive procedure using $O(N^2(T + \log(1/\rho)))$ pair queries chosen before any response is observed. Its simulated transcript is within $\rho$ in total variation of the adaptive transcript, uniformly over all distributions in the model. We also construct a matching family with constant adaptive query complexity and $\Omega_\varepsilon(N^2)$ non-adaptive query complexity. Consequently, the worst-case fixed-error adaptivity gap is $\Theta_\varepsilon(N^2)$. Thus interaction can reduce the required number of tests by a quadratic factor, but the apparent exponential branching of an interactive evaluation does not yield an exponential query advantage.

AI 总结：本文针对非光滑、超线性梯度增长且非凸的目标分布采样问题，提出SG-TULA算法，推导其非渐近收敛界，验证假设并用于GPT-2系列LLM预训练，效果优于AdamW等。

链接：https://arxiv.org/abs/2608.06283

机构：University of Edinburgh（爱丁堡大学）； National Technical University of Athens（雅典国立技术大学）； Athena/Archimedes Research Centre（雅典娜/阿基米德研究中心）

作者：Iosif Lytras, Nikolaos Makras, Sotirios Sabanis

英文摘要：We study the problem of sampling from target distributions whose potentials are simultaneously non-smooth, subject to superlinear gradient growth, and non-convex. We introduce the Subgradient Tamed Unadjusted Langevin Algorithm (SG-TULA), a discretisation of the Langevin diffusion that operates directly on subgradients, without relying on computationally demanding smoothing procedures. To handle the superlinear regime, taming techniques are employed to produce a stable, explicit scheme. We derive non-asymptotic convergence bounds in Wasserstein-2 distance, with all constants tracked explicitly in terms of dimension and inverse temperature, improving upon the currently known rates for subgradient-based Langevin algorithms. We further provide excess risk estimates for the associated optimisation problem. We verify the assumptions, with explicit constants, for the regularized pretraining potential of a LLM in the GPT-2 lineage and the boosted coordinate-wise variant of SG-TULA pretrains the former competitively against finetuned AdamW and Muon, for which no comparable non-asymptotic guarantees are presently available.

AI 总结：本研究提出无监督在线策略自蒸馏（U-OPSD），仅用模型自身生成结果实现在线策略自蒸馏，在多数学基准上优于基础模型，部分场景超越OPSD、GRPO等监督方法。

链接：https://arxiv.org/abs/2608.06296

机构：UC San Diego（加州大学圣迭戈分校）； Georgia Institute of Technology（佐治亚理工学院）； University of Maryland, College Park（马里兰大学帕克分校）； ByteDance（字节跳动）

作者：Yijiang Li, Bingyang Wang, Yijun Liang, Yunjie Tian, Di Fu, Nuno Vasconcelos

英文摘要：On-policy (Self-)Distillation (OPD / OPSD) has shown strong potential for post-training large language models (LLMs). However, existing methods still rely heavily on external supervision, including ground-truth signals, environmental feedback, or guidance from larger models, and therefore fall short of genuine "self"-distillation. In this study, we show that on-policy self-distillation can be achieved using only a model's own generations via internal consistency. We propose Unsupervised On-Policy Self-Distillation (U-OPSD). U-OPSD first samples multiple rollouts and constructs a pseudo-solution by majority vote under a self-consistency threshold. It then conditions a teacher distribution on the shortest pseudo-solution and distills it into prefixes of the model's longest incorrect completion, allowing the model to correct itself precisely where it is confidently wrong. Across diverse benchmarks, base models, and training settings, U-OPSD consistently improves over the base models and matches or surpasses supervised methods with ground truth (GT), such as OPSD and GRPO. On AIME24, AIME25, HMMT25, MATH500, and AMC23, U-OPSD improves over the base model by 8.5% and 10.7% on Qwen3 non-thinking mode at the 4B and 8B scales, respectively, and outperforms OPSD by an average of 3.2% and 2.3%. In thinking mode, U-OPSD remains on par with OPSD, outperforming it by 0.9% at 4B and matching it at 8B, while surpassing GRPO by 0.7% and 1.1%, respectively.

AI 总结：本文提出CalibForge系统，通过对抗性求解器校准合成5431个终端任务，训练的模型在多个基准测试中取得显著性能提升，验证了求解器相关可学习性的实用价值。

链接：https://arxiv.org/abs/2608.06352

作者：Fanzhe Meng, Guoxin Chen, Jiale Zhao, Shuang Sun, Zhiyu Lin, Wayne Xin Zhao, Ruihua Song, Ji-Rong Wen, Kai Jia

英文摘要：Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning. Executable validation establishes feasibility, yet does not reveal how a task behaves relative to a given solver setting. In this paper, we present CalibForge, an autonomous terminal-task synthesis system that uses verified solver behavior to revise candidate tasks through adversarial solver calibration. Multi-solver calibration targets disagreement within a heterogeneous solver pool, whereas contrastive solver calibration targets a designated strong-pass/weak-fail relation; both operationalize a solver-relative learnable zone anchored in demonstrated solvability. Using CalibForge, we construct 5,431 calibrated terminal tasks. Our ablations show that both strategies yield more effective supervision than authoring and validation alone or ordinary single-solver feedback. Models trained on the full collection achieve 32.58% and 47.57% on Terminal-Bench 2.0. The largest improvements over the corresponding base model reach 24.71 percentage points on Terminal-Bench 2.0, 27.68 points on SWE-bench Pro, and 30.04 points on Doc2Repo. Together, these results support solver-relative learnability as a practical target for constructing effective and transferable agent training data.