机器学习学术速递[8.31]

AI 总结：本研究探究基于线性探针的工具调用错误检测方法，在18个工具调用LLM上验证其效能，发现探针可捕捉多种工具调用错误，还能泛化到新型错误，为LLM工具调用错误检测提供有效手段。

链接：https://arxiv.org/abs/2608.27750

机构：Pacific Northwest National Laboratory（太平洋西北国家实验室）； National Security Agency（美国国家安全局）

作者：Eric Yeats, Brendan Kennedy, Loc Truong, John Buckheit, Jung Lee, Jesse Friedbaum, John Emanuello, Henry Kvinge

英文摘要：The hidden states of large language models (LLMs) are known to capture rich information relating to model knowledge and behavior that can be hard to extract from examination of input and output alone. As LLM-based systems increasingly interface with the external world, one area of concern is detecting incorrect or improper use of tools. Motivated by this, we study the effectiveness of using linear probes to detect incorrect tool-calls, measuring probe efficacy across 18 tool-calling LLMs evaluated on the Berkeley Function Calling Leaderboard. Overall, we find that probing is an effective means to catch a range of different tool-calling errors, including errors arising from using an argument that has the wrong value but the correct type, which might not be recorded by standard logging frameworks. Important factors in success include model size, probing layer, and model post-training type. We also show that probes are capable of generalizing to novel types of errors, which is critical in real world deployments.

AI 总结：针对现有神经性能预测器忽略节点级计算成本的问题，提出FeatureFormer模型并构建NNEQ数据集，实现了延迟与能耗预测的最优性能，且可提升现有预测器的效果。

链接：https://arxiv.org/abs/2608.27794

机构：University of South Carolina（南卡罗来纳大学）

作者：Matthew Grenier, William Hammer, Andrew Heuer, Nikhil Krishna, Yi Wang, Ramtin Zand

英文摘要：As neural networks are increasingly deployed on resource constrained edge devices, accurate prediction of latency and energy is critical for efficient neural architecture search. Existing GNN and transformer based predictors achieve strong results but largely ignore node-level computational cost, limiting their ability to model performance critical operations. To address this, we introduce FeatureFormer, a neural performance predictor that incorporates explicit node-wise encodings of FLOPs, parameter counts, and memory proxies within a gated graph attention architecture. We also present NNEQ, a new large-scale energy consumption dataset that enables unified evaluation of latency and energy prediction. Extensive experiments demonstrate that FeatureFormer achieves state-of-the-art performance across both metrics, including challenging out-of-domain settings. Finally, we show that the proposed encoding is broadly applicable and consistently improves existing predictors with negligible overhead.

AI 总结：该研究探究生物启发机制能否促进多层感知机的Grokking转变，经在稀疏奇偶校验和带噪异或分类基准上实验，发现稳态调节增益最强，为相关机制应用于大语言模型提供支撑。

链接：https://arxiv.org/abs/2608.28184

机构：Faculty of Automatic Control and Computer Engineering（自动控制与计算机工程学院）； “Gheorghe Asachi” Technical University of Iași（雅西“格奥尔基·阿萨奇”技术大学）

作者：Florin Leon

英文摘要：Grokking is a delayed transition from memorization to generalization that is often accompanied by substantial reorganization of internal representations. This paper studies whether biologically inspired mechanisms, many of which are not commonly incorporated into artificial neural networks, can actively promote this transition by regulating hidden-layer computation at the levels of neuronal activity, response, and effective connectivity. We augment a multilayer perceptron with input gating, structural plasticity, gain modulation, threshold modulation, homeostasis, lateral inhibition, and activation decorrelation, and evaluate these mechanisms through systematic ablations on two established grokking benchmarks: sparse parity and noisy XOR classification. The results show that the mechanisms contribute unequally to generalization. Homeostasis provides the strongest and most consistent benefit, while structural sparsification emerges as the second major mechanism. The remaining biologically inspired mechanisms have smaller or less consistent effects in the present experiments. For both problems, the results support the common principle that explicit regulation of neuron utilization and effective connectivity can improve the emergence of generalizable internal computation. These findings motivate broader investigation of biologically inspired activity regulation and adaptive sparsification, including in large language models, where they may accelerate the development of generalizable representations and reduce the optimization time required for robust generalization.

AI 总结：针对LLM预训练中梯度噪声与病态损失景观问题，提出带球面约束的曲率条件多尺度动量方法，可加速Muon在不同架构和规模模型上的训练，兼具理论验证与实验支撑。

链接：https://arxiv.org/abs/2608.28442

作者：Shuchen Zhu, Yuxin Fang, Mingze Wang, Kun Yuan

英文摘要：Pretraining accounts for a large fraction of the total computational cost in LLM training. However, noise-dominant gradients and the highly ill-conditioned loss landscape bring severe challenges. Although modern adaptive optimizers such as AdamW and Muon have achieved great success in large-scale pretraining, their reliance on gradient normalization offers limited mitigation of the ill-conditioned curvature. The progress along flat directions (eigen-directions of small eigenvalues), which dominates the final loss reduction, remains relatively slow. To enhance training dynamics along flat directions, we propose a curvature-conditioned multiscale momentum method with sphere constraints, delivering steady acceleration in LLM pretraining. This multiscale momentum, applied only along flat directions, pairs a slow-decay component for noise reduction with a fast-decay component for rapid curvature adaptation, harnessing their complementary strengths. Crucially, we employ a sphere constraint technique to prevent parameter inflation and excessively rapid effective learning rate decay that would otherwise arise from a naive combination. Extensive experiments show that the proposed method significantly accelerates Muon across diverse architectures (dense, MoE) and model sizes (0.12B--2.3B parameters). Theoretically, we verify the acceleration effect and provide insight into the design principles underlying the flat-direction multiscale momentum.

AI 总结：提出曲率感知半径收缩（CARSANN）框架，利用局部流形曲率调整邻域空间范围，在70余个OpenML数据集上较标准k-NN实现显著且具统计意义的分类性能提升。

链接：https://arxiv.org/abs/2608.27634

机构：Computing Department（计算机系）； Federal University of São Carlos（圣卡洛斯联邦大学）

作者：Alexandre L. M. Levada

英文摘要：Nearest neighbor classification relies fundamentally on how locality is defined, yet conventional $k$-NN imposes the same neighborhood cardinality throughout the feature space. This assumption can be inadequate for data whose local geometry varies substantially across the underlying manifold. We introduce Curvature-Aware Radius Shrinkage for Adaptive Nearest Neighbor Classification (CARSANN), a geometry-driven framework that adapts the spatial support of each neighborhood according to local geometric complexity. CARSANN first estimates intrinsic dimensionality using TwoNN and constructs an intrinsic representation through principal component analysis. Local mean curvature is then estimated using a shape-operator-based formulation and controls neighborhood scale: highly curved regions receive stronger radius shrinkage, whereas approximately flat regions retain broader spatial support. Unlike methods that modify only the number of neighbors or the local metric, CARSANN explicitly adapts the spatial extent of local evidence. Experiments on more than 70 real-world OpenML datasets show that CARSANN consistently improves upon standard $k$-NN and is competitive with adaptive nearest-neighbor methods. In a controlled comparison using the same base neighborhood size, CARSANN achieves higher balanced accuracy on 40 of 45 datasets, increasing mean balanced accuracy from 0.6506 to 0.7528. The advantage also persists against $k$-NN with fixed $k=5$. Friedman and Nemenyi tests confirm that the improvements are statistically significant. These results indicate that local manifold curvature can serve as an effective geometric control variable for adapting neighborhood support, providing a complementary paradigm to cardinality-based nearest-neighbor adaptation.

AI 总结：该研究针对并行状态熵优化中的冗余探索问题，提出MCC-PGPSE方法，通过分配边际覆盖率信用重新分配辅助奖励，在多类基准上提升了并行策略的互补覆盖效果。

链接：https://arxiv.org/abs/2608.27507

机构：College of Information Engineering, Hunan Applied Technology University（湖南应用技术学院信息工程学院）

作者：Junhao Cao, Hongyi Xia, Jianian Wu, Xiaopeng Yi, Lixia Huang, Ping Guo

英文摘要：Policy Gradient for Parallel State Entropy maximization (PGPSE) expands state-space coverage by training independently parameterized policies in replicated copies of the same environment. However, its pooled team-entropy score measures only collective exploration and cannot identify policies that contribute non-redundant coverage. We introduce Marginal Coverage Credit for PGPSE (MCC-PGPSE), which combines leave-one-policy-out coverage with state-owner specialization to estimate policy-specific credit. MCC-PGPSE preserves PGPSE's pooled objective and redistributes non-negative auxiliary intrinsic rewards according to these credits without changing their total mass. This redistribution is designed to discourage redundant visitation and promote complementary coverage. We evaluated MCC-PGPSE in controlled environments, seven public discrete-state benchmarks, and representative Room and Maze settings from the original PGPSE protocol. Across all tested settings, MCC-PGPSE produced positive final window gains in normalized team state entropy and state support over the Entropy baseline. Controlled-task comparisons and the fixed-suite public aggregate were significant, whereas five-seed original-protocol comparisons were directionally consistent. Ablations and credit alignment controls indicate that most gains arise from leave-one-policy-out coverage rather than non-uniform weighting, mismatched credit, or neural novelty alone. These results support contribution-conditioned auxiliary reward allocation as an interpretable approach to improving complementary coverage among parallel policies in discrete state spaces.

AI 总结：本文提出SegBench-GC基准，通过受控测试发现离线目标条件强化学习中，管理性分割会显著改变多步任务性能，且CVT处理方式可缓解该问题。

链接：https://arxiv.org/abs/2608.27678

作者：Musa Shams

英文摘要：Offline goal-conditioned reinforcement learning (GCRL) often uses trajectory structure for future-goal sampling and multi-step targets, yet logged trajectories may be partitioned for administrative reasons that do not correspond to termination. We introduce SegBench-GC, a controlled stress test of segmentation invariance that holds transitions, source trajectories, goal sampling, optimization settings, and evaluation fixed while varying only artificial backup boundaries and whether those boundaries retain continuation value. Continuation-valid targets (CVT) provide the segmentation-consistent control: reward accumulation stops at an artificial cut, but the target bootstraps from its stored successor. In a matched-count PointMaze study with 35,000 artificial cuts, three segmentation realizations, and three optimization seeds, final 50-episode-per-task success is 50.5% uncut, 39.1% with CVT, and 19.1% when the same cuts are treated as absorbing; across segmentation realizations, naive mean success ranges from 4.8% to 31.9%. An independent published n-step baseline (n=25) from the Decoupled Q-Chunking codebase shows the same failure on Puzzle-4x5: 47.2% uncut, 58.5% CVT, and 0.27% naive across three optimization seeds. A target-level diagnostic verifies the analytic target difference to numerical precision, and learned-critic diagnostics show a large optimistic shift under naive handling while CVT remains approximately aligned with the uncut critic. CVT applies standard continuation bootstrapping rather than a new Bellman rule; the contribution is the controlled benchmark, failure isolation, and cross-learner evidence that administrative segmentation can materially change multi-step offline GCRL.

AI 总结：本研究针对无搜索国际象棋网络，用先验引导探索替换原熵奖励，经约2000步微调后提升了谜题与四步将死准确率，且发现战术准确率与博弈强度存在分离。

链接：https://arxiv.org/abs/2608.27757

机构：Institute of Applied Computer Science, Lodz University of Technology（罗兹理工大学应用计算机科学研究所）

作者：Szymon Miłosz, Piotr Duch, Szymon Grabowski

英文摘要：Searchless chess networks reach human master strength from a single forward pass by imitating a stronger teacher: the strongest, Leela Chess Zero's (Lc0) released Chessformer, distills the visit counts of an AlphaZero-style Monte Carlo Tree Search (MCTS). Imitating a search is a poor proxy for playing without one, so we fine-tune for single-pass strength with self-play reinforcement learning (RL). Its exploration is usually supplied by an entropy bonus, the reverse Kullback-Leibler (KL) divergence to uniform. We replace it with a forward, mass-covering KL toward the network's own MCTS prior (prior-directed exploration), so exploration covers the moves the prior judges promising, and pair it with an entropy-adaptive sampling temperature, set by the value head's outcome uncertainty, that sharpens once a position is decided. In about two thousand steps it raises puzzle accuracy from 93.9% to 94.9% on a 100,000-puzzle suite and mate-in-four accuracy from 77% to 81% while holding searchless strength at or slightly above the base. Measuring tactical accuracy and playing strength together across a matched-compute sweep, we find the two dissociate: accuracy gains fall in a one-point band while ratings straddle the base, and a control fine-tuned on puzzles alone posts the study's largest tactical gains while shedding roughly 260 Elo; a better puzzle-solver is not thereby a stronger player. Distribution-level measurements show what anchoring buys: without a regularizer self-play collapses onto a single line of play, and the puzzles newly solved are the near misses whose winning move the prior kept alive. The forward-KL prior tops the rating ladder, statistically tied with a reverse-KL anchor that concentrates twice as hard and drops the hardest solutions the mass-covering prior keeps in support.

AI 总结：本文论证蒙特卡洛树搜索（MCTS）与全访问蒙特卡洛控制本质等价，仅表述术语不同，MCTS可简化为轨迹采样与全访问蒙特卡洛更新两个操作，旨在明确二者的等价关系。

链接：https://arxiv.org/abs/2608.27985

机构：ECNU（华东师范大学）

作者：Xianyi Wu

英文摘要：Monte Carlo Tree Search (MCTS) and every-visit Monte Carlo (MC) control are usually presented as different methods. MCTS is described in the language of search (selection, expansion, simulation, and backup), whereas MC control is described in the language of reinforcement learning (trajectory sampling, return estimation, action-value updating, and policy improvement). This note argues that, at the level of trajectory generation and action-value updating, the distinction is largely terminological. The tree policy and rollout policy can be viewed as the learned and not-yet-learned parts of a single evolving policy; expansion corresponds to first visit and initialization; and backup is the ordinary every-visit Monte Carlo update. Under this interpretation, the four stages of MCTS reduce to two basic operations: trajectory sampling under the current policy and every-visit Monte Carlo updating. In this sense, MCTS is simply every-visit Monte Carlo control expressed in the language and data structure of search. The purpose of this note is expository: to make this equivalence explicit and easier to recognize.

AI 总结：本文提出广义吉布斯集成加权（GGEW）框架，结合在线Local-UCB机制，在多基准数据集上验证其作为预测组合工具的竞争力，为自适应吉布斯型预测组合的应用提供实证依据。

链接：https://arxiv.org/abs/2608.28116

机构：Utrecht University（乌得勒支大学）

作者：Prasen R. Nuthanakaluva, Nava K. Gaddam

英文摘要： Forecast combination is a reliable way to improve predictive performance when several forecasting models are available. Simple aggregation rules such as the mean, median, trimmed mean, inverse-loss weighting, and exponential weighting are often strong baselines, but their relative performance can vary across datasets, forecast horizons, deployment settings, and levels of disagreement among base forecasters. We develop Generalized Gibbs Ensemble Weighting (GGEW), a probabilistic framework that treats forecasting models as experts and assigns ensemble weights using a Gibbs-style exponential transformation of normalized predictive loss. The framework extends this basic weighting rule through numerical stabilization, diversity-aware score corrections, and online hyperparameter adaptation. GGEW produces a family of related methods, including Stable Gibbs weighting, Directional Gibbs-NCL, and Symmetric Gibbs-NCL. These variants share one core algorithm and differ only in the score used inside the exponential weighting rule. For sequential deployment, we adopt a UCB-style bandit mechanism, called online Local-UCB, to adapt the learning rate, diversity strength, and Gibbs variant without evaluating the full hyperparameter grid at every prediction step. We evaluate GGEW on official M4 competition forecast submissions and external rolling-origin deployment experiments using Monash Traffic Hourly, Electricity Hourly, and Solar Weekly datasets. Results suggest that Gibbs-style adaptive weighting is a useful and competitive tool across several benchmark settings, although its relative performance varies across datasets, forecast horizons, deployment protocols, and forecast disagreement groups. The contribution is not a universal dominance claim, but a framework and empirical study motivating further investigation of when adaptive Gibbs-style forecast combination is useful.

AI 总结：针对长 horizon LLM 智能体强化学习的细粒度信用分配挑战，提出 VICT 方法，通过验证器侧的证明边追踪分配信用，在 ALFWorld 和 WebShop 上性能显著优于仅结果训练。

链接：https://arxiv.org/abs/2608.28128

机构：Tsinghua University（清华大学）； Xi’an Jiaotong University（西安交通大学）； Jiaxing Nanhu University（嘉兴南湖学院）

作者：Pengcheng Li, Zhengyang Zhang, Dongxu Zhang, Sui Huang, Shaohua Ma

英文摘要：Fine-grained credit assignment is a central challenge in reinforcement learning for long horizon LLM agents. Standard objectives often train from programmatically verifiable terminal rewards by broadcasting each sparse outcome to every action in a trajectory. Existing methods typically seek finer credit from the rollout side, constructing auxiliary trajectory signals or additional comparisons to estimate action importance. Although useful, these approaches still treat the verifier that judged success as a scalar reward, discarding its internal task structure. Our key insight is that many verifiable tasks already encode the relevant checks inside their terminal verifier. We propose VICT (VerifierInstrumented Credit Tracing), a training-time interface that exposes executable or evidence backed atoms and traces them back to actions through dependency-valid proof edges. VICT redistributes group-relative advantage only along those edges, shifting credit assignment from rollout-side inference to verifierside tracing. It preserves the original terminal reward, abstains when evidence is incomplete or ambiguous, and changes only the training-time advantage tensor, requiring no learned critic, process labels, branch rollouts, or inference-time verifier access. On ALFWorld and WebShop, VICT improves substantially over outcome-only training and achieves strong performance alongside recent fine-grained credit methods; ablations rule out dense atom rewards, final-commit credit, temporal proximity, and sparsity as sufficient explanations.

AI 总结：HARTS是首个针对任意展开树前缀共享的混合注意力模型智能体RL系统，通过分块线性注意力算法等技术实现了4.81-4.87倍的训练加速，数值与奖励表现与基线相当。

链接：https://arxiv.org/abs/2608.28158

机构：Ant Group（蚂蚁集团）

作者：Boyuan Meng (1), Peihua Bao (1), Hong Liu (1), Xiaowei Zhu (1), Chao Wang (1), Gen Li (1), Zhenxuan Pan (1) ((1) Ant Group, China)

英文摘要：Agentic reinforcement learning (RL) often produces irregular rollout trees with shared histories. Training root-to-leaf trajectories independently recomputes these shared prefixes. Existing systems primarily target full-attention models and lack dense, differentiable hybrid-attention execution compatible with activation recomputation. We present HARTS (Hybrid-Attention RL over Tree Structures). HARTS jointly plans microbatches, data-parallel (DP) replica assignments, and microbatch-slot schedules using non-replay compact-token work after prefix compression. For chunkwise linear attention, a linear-time algorithm coordinates chunk-boundary state recovery and replay and produces the minimum number of sequential linear-attention calls under our packed execution model. HARTS preserves the chunkwise state partitioning of trajectory-wise training: it does not repeat projections, MLP/MoE computation, or final outputs, and performs only bounded state replay for numerical alignment. Per round, HARTS batches all branches into one packed call, propagates gradients through differentiable state handoffs, supports activation recomputation, and restores per-token log-probabilities. For deterministic, no-token-drop top-$k$ MoE routing, semantic multiplicities restore MoE-objective token weights and load statistics. Existing RL objectives retain their interface. To our knowledge, HARTS is the first system to demonstrate arbitrary-rollout-tree prefix-sharing speedups on a real hybrid-attention model. On an Agentic RL workload generated from SWE-bench tasks, HARTS achieves $4.81$--$4.87\times$ forward/backward/gradient speedup with activation recomputation across multiple parallel configurations. Its numerical differences are comparable to baseline self-rerun variation, and its reward trend is similar to the baseline over the first 120 steps of $\tau^3$-Bench training.

AI 总结：Replicant是深度强化学习框架，在仅标签黑盒威胁模型下学习恶意软件规避策略，在7种Android恶意软件检测器上攻击成功率达78.8%，还可用于提升检测器鲁棒性。

链接：https://arxiv.org/abs/2608.28499

机构：University College London（伦敦大学学院）； KU Leuven（鲁汶大学）； The Alan Turing Institute（阿兰·图灵研究所）； King’s College London（伦敦国王学院）； Core64； Devotion AI Labs（Devotion AI实验室）

作者：Shae McFadden, Ilias Tsingenopoulos, Mario D'Onghia, Alexander Herzog, Myles Foley, Chris Hicks, Lorenzo Cavallaro, Fabio Pierazzi

英文摘要： To determine the real-world effectiveness of machine learning based malware detection, it is vital to evaluate its robustness against highly capable adversaries. However, state-of-the-art attacks do not effectively model realistic adversaries, as they often assume access to privileged information such as the training data, feature space, or confidence scores of the target. In this work, we present Replicant, a deep reinforcement learning framework that learns the realistic task of evasion under a strict label-only black-box threat model. Replicant learns a reusable policy on how to modify a malware sample and when to query the target, which transfers across samples, detectors, and feature spaces. Across seven Android malware detectors and three feature spaces, Replicant is the strongest and most query-efficient approach achieving a mean attack success rate of 78.8%, a relative improvement of 20.9%-39.2% over the state-of-the-art. Furthermore, when used for adversarial training, Replicant also outperforms the state-of-the art by producing detectors with more generalizable robustness. With Replicant we demonstrate that learning the task of evasion not only results in stronger attack performance but, crucially, provides a better signal for hardening malware detectors.

AI 总结：该研究针对扩散模型生成天气集合时迭代采样成本高的问题，提出有监督能量距离蒸馏方法，将多步扩散教师模型压缩为单步学生模型，在全球预报和台风路径预测中表现优于现有方法。

链接：https://arxiv.org/abs/2608.27728

机构：University College London（伦敦大学学院）； University of Oxford（牛津大学）

作者：Yiming Yang, Valentin Brekke, James Briant, Serge Guillas

英文摘要：Diffusion models generate skillful weather ensembles but require costly iterative sampling. We introduce a supervised energy-distance distillation method that compresses a multi-step diffusion teacher into a single-step student by aligning student forecasts with teacher samples and ground-truth observations. Experiments on global forecasting and typhoon-track prediction show that our student outperforms existing distillation methods and preserves skill for extreme events. It matches or surpasses the teacher across key metrics using only one neural function evaluation per autoregressive step.

AI 总结：该研究提出A-CBFI框架，结合结构分解与因果反事实追索，在金融、医疗领域可降低76.9%主动干预负担，保持因果有效性与追索成本，实现针对性可操作的反事实追索。

链接：https://arxiv.org/abs/2608.27821

作者：Sejong Oh

英文摘要：Explainable artificial intelligence (XAI) increasingly calls for actionable counterfactual recourse, yet current methodologies face challenges related to causal invalidity, excessive cognitive burden, and predictive failure. Exhaustive causal search algorithms often require modifications to multiple attributes, whereas additive attribution-guided methods, such as SHAP, ignore higher-order feature synergies, leading to suboptimal predictive momentum and diffuse intervention effort in complex nonlinear models, such as XGBoost. To bridge this gap, we introduce actionable case-based feature importance (A-CBFI), a diagnosis-prescription integrated framework for tabular machine learning. Grounded in structural causal models (SCMs), A-CBFI isolates synergistic interaction bottlenecks and releases suppressive structural locks, translating them into targeted interventions. By mathematically separating the active user intervention space (L_{\mathrm{active}}) from downstream effects and concentrating over 98.3% of the intervention effort on diagnosed root causes, A-CBFI enables highly targeted interventions. Empirical evaluations across the financial and healthcare domains demonstrate that A-CBFI reduces the active human intervention burden by 76.9% while maintaining comparable global recourse cost to exhaustive causal baselines. By prioritizing the diagnosed causal bottlenecks, A-CBFI provides targeted and actionable recourse while maintaining causal validity and achieving full relative convergence across all causally feasible instances.

AI 总结：本文通过理论分解刻画了条件流匹配（CFM）可替代逐点负对数似然（NLL）的条件，指出其在离策略总体最优处的局限性，相关结论及分解为适配LLM方法至流匹配提供了理论基础。

链接：https://arxiv.org/abs/2608.28010

机构：Zhejiang University（浙江大学）； Westlake University（西湖大学）； Fudan University（复旦大学）

作者：Yansen Han, Hongxin Sun, Tao Lin

英文摘要：Flow matching enables likelihood-free training, yet alignment methods increasingly reuse conditional flow matching (CFM) losses as endpoint negative log-likelihoods (NLLs) and their old/new differences as log-likelihood ratios. We characterize when these substitutions are valid. For linear Gaussian paths, we exactly decompose endpoint NLL into entropy, a weighted CFM objective, an interior velocity--score residual, and a boundary residual. Thus CFM-only estimates and differences are exact only when the corresponding residuals cancel. At the off-policy population optimum, ordinary CFM is not generally a pointwise NLL estimator, whereas \(w_{\mathrm{sc}}(t)=(1-t)/t\) removes the interior residual; this positive result does not extend generally to training or on-policy alignment. On-policy log-ratios can remain biased even for identical endpoint laws or after surrogate optimization. Experiments across dimensions, distributions, and geometries support these conclusions and the mechanisms that make inexact ratios useful. **More broadly, the decomposition provides a theoretical basis for adapting likelihood-based LLM methods to flow matching, while distinguishing exact substitutions from controlled surrogates.**

AI 总结：该研究提出潜在条件扩散模型，基于1.2万次商用EV行程遥测数据生成电流轨迹，其性能优于直接条件注入，为不确定性感知的大规模车队规划奠定基础。

链接：https://arxiv.org/abs/2608.28142

机构：University of Washington（华盛顿大学）； Amazon Science（亚马逊科学）； University of Cambridge（剑桥大学）

作者：Hemanth Neelgund Ramesh, André Snoeck, Chyi-Fu Hong, Shijing Sun

英文摘要： Electrification of commercial delivery fleets is shifting fleet routing from distance- and time-based optimization toward energy-aware decision-making. Existing sequence models primarily provide deterministic point estimates or limited uncertainty summaries, which do not capture the range of plausible energy-consumption trajectories required for operational decision-making. In this work, we introduce a conditional diffusion framework that generates EV battery-current profiles conditioned on route features such as vehicle velocity and ambient temperature. The model combines a latent conditioning encoder with a temporal 1D U-Net denoising backbone that enables trip-related conditions to be mapped into a shared representation and guides the reverse diffusion process. We evaluate the framework on an open-access commercial EV telemetry dataset containing 12k trips from 9 vehicles. The proposed latent-conditioned diffusion model generates realistic cur- rent trajectories that capture both the dominant temporal envelope and sharp transient events. The model achieves a Wasserstein distance of 0.0029 between generated and measured current distributions below the real vs real reference distance of 0.0085 indicating that generated samples lie within the empirical variability of the test set. We further demonstrate that learned latent conditioning substantially improves performance over direct condition injection, reducing the Wasserstein distance by 89.1% and MAE by 52.8%. This work demonstrates a generative modeling framework for characterizing EV energy consumption under real-world operating conditions, providing an essential foundation for uncertainty-aware fleet planning in large-scale operational settings.

AI 总结：该研究对比10组BCG特征，发现频域特征主导呼吸事件检测，采用随机森林等模型获高AUC，为BCG监测系统特征选择提供实证依据。

链接：https://arxiv.org/abs/2608.28242

机构：University of Groningen（格罗宁根大学）； University Hospital Zürich（苏黎世大学医院）； ETH Zürich（苏黎世联邦理工学院）

作者：Israel Campero Jurado, Zoe Bousraou, Lara Benning, Sara Padilla Neira, Alexander Breuss, Robert Riener, Esther Irene Schwarz, Elisabeth Wilhelm

英文摘要：Unobtrusive ballistocardiographic (BCG) sensing is a promising modality for long-term sleep-apnea monitoring, yet it remains unclear which signal features are most discriminative for respiratory-event detection. We present a literature-guided, patient-independent comparison of ten BCG feature groups using a 512-sensor capacitive pressure mat recorded simultaneously with respiratory polygraphy in 155 patients (52 female, 103 male) undergoing in-hospital evaluation for obstructive sleep apnea. Features were extracted from six spatially distinct signal channels, yielding a 191-dimensional feature vector spanning general statistical, time-domain, frequency-domain, wavelet, frame-energy, and nonlinear complexity descriptors. Under strict leave-one-patient-out cross-validation for binary classification of respiratory-event windows versus event-free reference windows, Random Forest and Histogram Gradient Boosting achieved AUC-ROC of 0.967 and 0.969 and AUC-PR of 0.977 and 0.979, respectively. Feature-importance analysis revealed that frequency-domain features dominate discrimination: breathing-band power in the 0.1-0.4 Hz range accounted for 30.3% of total discriminative information across all spatial channels, and Fast Fourier Transform spectral-shape descriptors of the adaptively preprocessed channel contributed a further 15.1%. AUC and curve-length features provided the main complementary time-domain evidence (21.5%), whereas wavelet-derived and nonlinear features contributed smaller secondary effects (10.4% combined across 59 features). Frequency-domain and time-domain features together accounted for 67% of total discriminative information, demonstrating that a compact, interpretable subset of the full feature library achieves clinically relevant performance under patient-independent validation and providing an empirical basis for feature selection in future BCG systems.

AI 总结：本文提出SinkSLOT算法，通过引入非独立先验耦合的期望切片提升传输计划稀疏化Gibbs核，解决标准Sinkhorn-Knopp算法的局限，实验显示其在合成基准上加速效果显著，且所得散度可应用于梯度流实验。

链接：https://arxiv.org/abs/2608.28262

机构：Sorbonne Université（索邦大学）； King’s College London（伦敦国王学院）

作者：Ian Hsieh, Soumya Snigdha Kundu, Tom Vercauteren, Reuben Dorent

英文摘要：Entropic optimal transport (EOT) has been shown to offer a computationally tractable approximation to exact optimal transport. However, the standard Sinkhorn-Knopp algorithm has two main limitations. First, given discrete measures with $N$ points, each iteration requires $O(N^2)$ operations, which restricts its use on large-scale datasets (e.g. $N\geq10^4$). Second, it uses the independent coupling as a reference measure for regularisation. This assigns mass to high-cost transport edges at moderate regularisation strengths. We propose SinkSLOT, which addresses both limitations by putting forth the expected sliced lifted transport plan as a natural way to sparsify the Gibbs kernel with a non-independent prior coupling. We prove that: 1) SinkSLOT converges; 2) with $L$ slices, each resulting sparse Sinkhorn iteration costs $O(LN)$; and 3) the resulting objective is a divergence requiring no debiasing. Experiments on synthetic benchmarks show that SinkSLOT delivers substantial speedups over state-of-the-art dense and sparse EOT methods. We also demonstrate the applicability of the proposed divergence in a gradient flow experiment. The code is publicly available at this https URL.

AI 总结：本研究重构优化扩展scikit-rebate包，对比新型Relief类算法在基因组模拟数据中的表现，发现MultiSWRFDB等算法可有效保留主效应与交互作用，运行时间显著缩短。

链接：https://arxiv.org/abs/2608.28552

机构：Cedars-Sinai Health Sciences University（西达赛奈健康科学大学）

作者：Kia Kazemi-Nia, Harsh Bandhey, Philip J. Freda, Ryan J. Urbanowicz

英文摘要： As a precursor to high-dimensional biomedical data modeling, reliable feature selection can reduce computational expense, improve modeling performance, and yield simpler, more interpretable models. However, most filter-based feature selection methods struggle to detect feature interactions, while wrapper or embedded feature selection methods are computationally expensive. Relief-based algorithms (RBAs) are filter methods that are sensitive to feature interactions while mitigating these other limitations. This study (1) refactors, optimizes, and expands the scikit-rebate Python package with existing and newly proposed RBA variants and (2) conducts rigorous RBA benchmark comparisons across diverse genomic simulations. We expand scikit-rebate to include SWRF*, mu-Relief, and 5 novel RBA variants implementing alternative strategies for neighbor selection and feature scoring. All RBAs were evaluated to compare predictive feature ranking and runtime across simulated genomic datasets varying in sample size, number of features, heritability, and underlying association type (e.g. main effects and interactions). All RBAs, except mu-Relief, were proficient in detecting 2-way interactions in noisy data. RBAs utilizing 'far' scoring were best at detecting 2-way interactions - with MultiSWRFDB* top-performing - but were far less sensitive to main effects. SWRF, MultiSWRF, MultiSURF, and MultiSWRFDB yielded top performance across main effect and 2-way interaction datasets with MultiSWRFDB performing best when also considering 3-way interactions. Refactoring of scikit-rebate resulted in 10 to 35-fold reductions in RBA runtimes. The newly introduced RBAs were among the strongest performing, and by robustly retaining both main effects and 2-way epistatic interactions, these algorithms preserve predictive signals for downstream modeling.

AI 总结：该研究发现仅源精度审计无法排除语言模型的量化触发后门，提出量化行为等价类理论，在多语言模型中实现量化后激活的后门攻击，证明攻击持久性与量化方案及模型架构相关。

链接：https://arxiv.org/abs/2608.27512

机构：University of Bologna（博洛尼亚大学）； Luiss Guido Carli University（路易斯 Guido Carli 大学）； Live Tech； University of Salerno（萨勒诺大学）

作者：Jacopo Dardini, Claudio Stanzione, Giordano Colò, Giuseppe Fenza

英文摘要：Post-training quantization is often treated as a semantically neutral optimization for edge deployment of Large Language Models. When a full-precision source checkpoint is evaluated and quantization is applied downstream without equivalent re-evaluation, this workflow creates a structural validation--deployment gap: because quantization is a many-to-one mapping over parameter space, source-precision certification does not guarantee behavioral equivalence in the deployed configuration. We formalize this gap through Quantization Behavioral Equivalence Classes (QBECs) and prove that QBEC membership does not imply behavioral equivalence, providing a theoretical basis for quantization-triggered backdoor attacks. Building on a three-stage adversarial fine-tuning framework, we embed latent malicious payloads into models that satisfy the source-precision checks used in our evaluation, yet activate targeted adversarial behavior upon INT8 or 4-bit compression. We evaluate this threat in two operationally motivated scenarios, tactical machine translation and political content analysis, extending prior work from decoder-only causal LMs to multilingual encoder-decoder sequence-to-sequence models. Results show that backdoored translation models move from zero measured friend--foe corruption at repaired FP16 to up to 85.02% inversion after quantization, and that a paired stance classifier measures an ideological shift of up to $\Delta\mathrm{Bias}=0.33$ upon compression. A cross-quantizer transferability analysis further shows that attack persistence varies across quantization schemes and model architectures, rather than being determined by nominal bit-width alone. These findings demonstrate that source-precision auditing alone does not rule out quantization-triggered behavior and that the final deployed configuration must be included in behavioral certification for trustworthy edge AI.

AI 总结：DART-FL是一种感知SLO的多任务联邦学习框架，可动态分配边缘设备的推理与训练资源，在高需求任务突发时段提升其准确率，同时维持长期多任务性能。

链接：https://arxiv.org/abs/2608.27713

机构：Northeastern University（东北大学）； University of Georgia（佐治亚大学）

作者：Yiming Xie, Pinrui Yu, Geng Yuan, Xue Lin, Ningfang Mi

英文摘要：Edge intelligence systems increasingly require model training and online inference to coexist on resource-constrained devices, while inference demand can vary substantially across tasks over time. This creates two coupled challenges: sufficient computation must be reserved for inference to maintain service-level objectives (SLOs), while the remaining training capacity should adapt to task-specific demand so that frequently requested tasks can improve earlier during training. We propose an SLO-aware, demand-driven multitask federated learning framework (DART-FL) that jointly adapts the inference-training resource split and task-level training emphasis. At each scheduling interval, DART-FL uses the inference backlog and profiled service capacity to determine the minimum resource allocation required for inference. The remaining training capacity is then distributed across tasks using a queue-aware DPP-inspired scheduler, and the resulting task allocations are mapped to dynamic loss weights. This allows tasks experiencing higher inference demand to receive greater training emphasis in earlier communication rounds. Clients train a shared backbone with task-specific heads, and the complete multitask model is aggregated through FedAvg. We evaluate DART-FL using Stanford Cars and Oxford Flowers 102 under both synthetic and real Alibaba trace-derived workloads. Results show that DART-FL dynamically adapts the inference-training resource split to time-varying inference demand and shifts the learning progress of high-demand tasks toward their burst periods, improving model accuracy when those tasks are frequently requested while maintaining comparable long-term multitask performance.

AI 总结：本文针对联邦学习中学习者与客户端的分布不匹配问题，提出动态感知影响力的客户端选择框架，在CIFAR-10数据集上验证其性能优于基线，可加快收敛并提升准确率。

链接：https://arxiv.org/abs/2608.27715

机构：Northeastern University（东北大学）

作者：Yiming Xie, Lili Su, Ningfang Mi

英文摘要： Federated learning systems are increasingly deployed to facilitate collaborative model training across a heterogeneous client population. Existing practice mostly implicitly assumes that the aggregated client data distribution is representative of the learner's target distribution or that learning from all available clients is uniformly beneficial for the learner distribution. However, such an assumption often does not hold in reality. Traditional client selection strategies in FL literature largely overlook such misalignment, while most existing work on multi-source transfer learning either requires direct access to local data or uses one-shot model/feature aggregation. In this paper, we take the initiative to understand and mitigate the impacts of such learner-client population misalignment. In particular, we consider the practical setting where the learner keeps a small proxy dataset. We observe that client contributions vary significantly across training rounds, and traditional technology is insufficient to identify beneficial sources under multi-source transfer diversity. Then, we propose a dynamic, influence-aware client selection framework that estimates each client's potential utility to the learner's optimization objective using proxy influence signals on a learner-specific proxy set. Via using leave-one-out evaluations, we prioritize the most informative sources of knowledge while controlling the negative impacts of statistical noise and data heterogeneity. Experiments on CIFAR-10 under heterogeneous data partitions demonstrate that our approach consistently outperforms static and dynamic baselines, achieving faster convergence and higher accuracy.

AI 总结：针对联邦短期负荷预测中客户端负载数据的结构化异质性问题，该研究提出全局预训练初始化与局部SLIAvg策略，有效减少客户端漂移并提升预测性能，且兼容性强。

链接：https://arxiv.org/abs/2608.27791

机构：School of Electrical Engineering and Computer Science, The Pennsylvania State University（宾夕法尼亚州立大学电气工程与计算机科学学院）； Department of Electrical and Computer Engineering, Bucknell University（巴克内尔大学电气与计算机工程系）

作者：Jianing Chen, Vajiheh Farhadi, Yan Li, Thomas La Porta

英文摘要：Short-term load forecasting (STLF) provides essential information for numerous applications in modern power systems. However, accurate STLF often relies on fine-grained smart-meter data from distributed users, raising increasing concerns about data privacy. Federated learning (FL) has therefore emerged as a promising privacy-preserving paradigm for STLF. Nevertheless, this paper reveals structured heterogeneity in clients' load data. Specifically, clients exhibit different responses to exogenous factors and distinct temporal load profiles, which can degrade forecasting performance in FL. To mitigate these issues, this paper studies the role of model initialization in federated STLF, and proposes two initialization strategies from global and local perspectives. For global model initialization, when auxiliary public load data are available, a pretrained initialization strategy is developed to initialize the global model before federated training, thereby reducing client drift during the training process. For local model initialization, we propose SLIAvg, a sequential local initialization strategy that promotes a more consistent training process by allowing participating clients to start from progressively adapted models within each communication round. Since the proposed strategies only modify the initialization process, they are compatible with most existing FL frameworks and privacy-enhancing techniques. Experiments on real smart-meter data with two representative forecasting architectures demonstrate that the proposed strategies effectively improve forecasting performance, as evidenced by reduced client drift, improved convergence behavior, and lower forecasting errors.

AI 总结：针对医院EHR数据隐私与协作局限，提出以经验为中心的FedEHR-Agents框架，通过联邦智能体聚合建模经验，在多医院EHR基准上的临床预测任务中表现优于基线方法。

链接：https://arxiv.org/abs/2608.27856

机构：School of Computer Science, McGill University（麦吉尔大学计算机科学学院）； Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）

作者：Jun Bai, Ruilin Wang, Yue Li

英文摘要：Recent advances in large language models are enabling autonomous clinical agents to perform increasingly complex electronic health record (EHR) modeling workflows. However, agents deployed at individual hospitals remain constrained by institution-specific data and modeling environments, while direct cross-hospital collaboration is restricted by the sensitivity of patient-level EHR data. Although federated learning (FL) provides a natural foundation for privacy-preserving collaboration, existing approaches remain predominantly model-centric, limiting federation to prediction models or their updates while overlooking the richer modeling experience accumulated by autonomous agents. To address this limitation, we propose FedEHR-Agents, an experience-centric federated agentic optimization framework for automated EHR modeling. Each hospital deploys an autonomous clinical EHR agent that performs data preprocessing and model development while refining local clinical modeling experience through historical memory, task-specific evaluation, and TextGrad-based prompt refinement. The federated server performs evidence-guided experience aggregation to integrate reliable and complementary modeling experience across heterogeneous hospitals and distills the aggregated experience into global meta-prompts for subsequent local refinement. Extensive experiments on real-world multi-hospital EHR benchmarks demonstrate that FedEHR-Agents consistently outperforms local and federated baselines across diverse clinical prediction tasks and remains robust across different federation scales and LLM backbones. These results establish clinical modeling experience as a promising collaborative object beyond conventional parameter-centric FL and point toward federated autonomous clinical intelligence.

AI 总结：该研究结合表演式学习与隐私保护，提出表演式隐私概念，通过理论与实验证明，当数据泄露与用户参与的反馈回路足够强时，有限隐私预算的差分隐私机制在长期效用上优于非隐私估计。

链接：https://arxiv.org/abs/2608.28198

机构：Dauphine PSL（巴黎第九大学PSL校区）； CNRS（法国国家科学研究中心）

作者：Uddalak Mukherjee, Edwige Cyffers, Yann Chevaleyre

英文摘要：Privacy-preserving learning is often motivated by the idea that protecting users' data can preserve trust and thus participation, improving utility in the long term. However, this claim has not been formalized so far. In parallel, performative learning provides a framework for studying learning systems whose deployment affects the data they later observe. In this work, we bring these two perspectives together and introduce \emph{performative privacy}, where data leakage reduces future participation. We study a simple model where agents repeatedly contribute data for mean estimation but may leave the system when their data is leaked. Privacy is implemented through differentially private mechanisms, creating a trade-off between estimation noise and future participation. We show, through a theoretical study of the dynamics and numerical experiments, that a finite privacy budget can outperform non-private estimation in the long term when the feedback loop between leakage and participation is sufficiently strong. This provides first evidence that differential privacy can be optimal not only as a protection mechanism, but also from the perspective of long-term utility.

AI 总结：本文研究了5种恰当评分规则作为训练目标对LLM预测的影响，发现不同规则训练的模型在校准、概率使用等方面有差异，Brier训练模型表现最优。

链接：https://arxiv.org/abs/2608.28482

机构：Lightning Rod Labs（闪电杆实验室）； INSEAD（欧洲工商管理学院）； School of Arts & Sciences, University of Pennsylvania（宾夕法尼亚大学文理学院）

作者：Benjamin Turtel, Paul Wilczewski, Kris Skotheim, Ville A. Satopää, Philip E. Tetlock

英文摘要：This paper evaluates how reward function choice shapes the performance and behavior of LLM forecasters. We compare five proper scoring rules as training objectives for binary forecasts of resolved real-world events. Although the rules share the same theoretical incentive for truthful probability reporting, the resulting models differ in calibration, probability use, and estimated profiles of bias, information, and noise, with smaller differences in aggregate accuracy and discrimination. The Brier-trained model has the lowest observed Brier score and highest AUC-ROC, while the log-trained model has the highest observed log score and lowest calibration error. Models with similar aggregate performance also reach that performance through different combinations of bias, information, and noise. Proper scoring rules therefore need not behave interchangeably as training objectives. Reward choice may shape not only how well an LLM forecasts, but how its forecasting errors are structured. Each condition uses a single seed, so some differences may reflect training stochasticity.

AI 总结：本文提出SEMGNN，一种端到端自解释多标签图神经网络，联合学习预测器与边掩码解释器，利用标签相关性提升多标签分类性能及解释忠实度，在多类网络上表现优于或相当事后方法。

链接：https://arxiv.org/abs/2608.27574

机构：Florida Atlantic University（佛罗里达大西洋大学）； University of Louisiana at Lafayette（拉斐特路易斯安那大学）

作者：Yingqi Feng, Yufei Tang, Min Shi, Xingquan Zhu

英文摘要：Multi-label graph learning intends to capture the intrinsic complexity of real-world applications, where one sample is often related to multiple groups or consists of multiple objects. To date, a handful of multi-label graph learning methods exist, but none of them integrate training-time interpretation capability. While post-hoc graph explainers have been developed, they do not explicitly model label-dependent evidence sharing in multi-label graph learners, especially when label pairs are weakly or negatively associated. As a result, post-hoc approaches may miss how evidence should be shared or separated across different labels. This paper advances a new end-to-end self-explainable multi-label graph neural network (SEMGNN), which aims to simultaneously classify multi-labeled nodes and identify edges significantly contributing to each target node w.r.t. predicted labels. Different from post-hoc methods, SEMGNN jointly learns a predictor and a sparse edge-mask explainer within a unified framework and training objective. Label-label correlations are used to improve multi-label node classification and enhance individual label explanations, so that different labels of a node can be supported by distinct yet coherent structural and/or correlated evidence. Experiments and comparisons on synthetic and real-world multi-label networks, in social networking, entertainment, and life sciences, show that SEMGNN achieves competitive or improved predictive performance while providing more faithful and compact label-conditioned explanations.

AI 总结：针对电路表示学习受工业网表规模与时序动态建模缺陷制约的问题，提出DeepSeq3分层框架，结合双GNN架构与状态中心预训练，在大规模基准上实现BMC求解时间降18%且保证正确性。

链接：https://arxiv.org/abs/2608.28188

机构：The Chinese University of Hong Kong（香港中文大学）； Tsinghua University（清华大学）

作者：Jingyi Zhou, Zhengyuan Shi, Jiaying Zhu, Ziyang Zheng, Qiang Xu

英文摘要：Circuit Representation Learning (CRL) offers a powerful paradigm to guide and optimize core Electronic Design Automation (EDA) tasks, but its practical adoption is hindered by the immense scale of industrial netlists and a failure to explicitly model register-level temporal dynamics. To overcome these barriers, we introduce DeepSeq3, a novel hierarchical framework that abstracts circuits into a two-level representation: fine-grained combinational subgraphs partitioned by flip-flops (FFs), and a high-level Super-Node Graph (SNG) that models the register-transfer structure. A dual Graph Neural Network (GNN) architecture learns representations at both levels, capturing local Boolean logic and global state transitions. Crucially, we introduce a state-centric pre-training scheme that predicts the reachability between FF states, endowing the model with a deep understanding of temporal behavior. Demonstrated on large-scale benchmarks, DeepSeq3's approach yields superior scalability and richer representations, reducing bounded model checking (BMC) solving time by 18% while guaranteeing correctness.

AI 总结：本研究将持续学习与模型融合的共同挑战归为任务干扰，发现Muon优化器可通过调控谱范数收紧干扰界，在多任务基准上替换AdamW能显著提升性能。

链接：https://arxiv.org/abs/2608.27518

机构： State Key Laboratory for Novel Software Technology, Nanjing University（南京大学现代国家重点实验室（注：此处按原文直译，实际常见译名为“南京大学计算机软件新技术国家重点实验室”））； University of Wollongong（卧龙岗大学）

作者：Shangge Liu, Yuehan Yin, Yinghuan Shi, Lei Wang, Wenbin Li

英文摘要：Continual learning (CL) and model merging (MM) both aim to obtain a single model that performs well across multiple tasks, challenged respectively by catastrophic forgetting and weight-disentanglement error. In the literature, these difficulties are merely treated separately and mitigated through a variety of solutions, while the geometry induced by the base optimizer is treated as an implementation detail. In this work, we show that the two difficulties are in fact two instances of the same phenomenon: a parameter update useful for one task shifts the model's outputs on another. We formalize this shared phenomenon as \textit{task interference} and reduce it to a common layer-wise Frobenius inner product $\langle \Delta W_\ell, J_\ell(x)\rangle_F$. This quantity, in turn, is utilized to expose the role of the optimizer. We theoretically derive an upper bound that isolates the spectral norm $\|\Delta W_\ell\|_2$ as an optimizer-controllable factor of task interference, and a per-mode analysis shows that this bound tracks the dominant part of the empirical interference. Specifically, we then identify the recent Muon optimizer as a mechanism that regulates this factor by construction. Our work reveals that its elegant control on spectral norm tightens the interference bound for both CL and MM, positioning Muon as a principled optimizer-centric approach complementary to existing solutions. Our theoretcal analysis is well validated by experimental results. Replacing the AdamW optimizer with Muon improves accuracy by up to +5.02 points on the eight-task model-merging benchmark across three CLIP backbones. For continual learning, Muon also delivers uniformly positive gains across ten class-incremental protocols, three task-incremental protocols, and the 11-task MTIL benchmark.

AI 总结：本研究提出基于生长自组织映射与合成重放的无监督持续学习框架，无需原始数据与监督信息，在多基准测试中性能优于无内存方法，在单类增量场景表现突出，为相关研究提供参考。

链接：https://arxiv.org/abs/2608.27662

机构：Rochester Institute of Technology（罗切斯特理工学院）

作者：Pujan Thapa, Alexander Ororbia, Travis Desell

英文摘要：This work presents a generative continual learning framework based on growing self-organizing maps (GSOMs) that are augmented with learned distributional statistics as well as encoder-decoder models for class-incremental learning. The proposed approach enables exemplar-free replay using distributional statistical memory, which eliminates the need to store raw data. Each GSOM unit maintains its own mean, variance, and covariance estimates, which are subsequently used to generate synthetic samples for replay; in encoder-decoder configurations, these samples are then decoded back into the input space (via ancestral sampling) for subsequent training. Our method is fully unsupervised, as it does not rely on explicit task boundaries or class labels during training. Results across multiple benchmarks show that the proposed approach achieves performance competitive even with supervised state-of-the-art memory-based methods while consistently outperforming memory-free approaches. In several settings, our framework matches or exceeds existing baselines, particularly in challenging single-class incremental scenarios. We also provide baseline results for single-class incremental TinyImageNet and MiniImageNet, offering a useful reference for future work. This work highlights the effectiveness of an unsupervised, adaptive, topology-driven neural form of statistical replay as a scalable, flexible approach to continual learning.

AI 总结：该研究针对持续学习，推导了Falcon系列快速权重更新规则，结合多种计算形式，在语言建模等任务中保持竞争力并提升可变数字加法的长度外推能力，分离了序列模型的时间对齐等关键机制。

链接：https://arxiv.org/abs/2608.27763

作者：Yifan Zhang, Steve Ta, Jasper Zhang, Jichen Feng, Shuzhen Li, Yongxin Zhang, Yifeng Liu, Huizhuo Yuan, Mengdi Wang, Quanquan Gu, Andrew Chi-Chih Yao

英文摘要：Recurrent fast-weight memories and selective state-space models compress an expanding context into a fixed-size recurrent state, making the state transition an online learning rule. We study this rule under read-after-write autoregressive semantics. For the prefix-prediction objective considered here, the local fast-memory example revealed at step $t$ is the prefix-aligned pair $(\mathbf{x}_t,\mathbf{y}_t)=(\phi(\mathbf{k}_{t-1}),\mathbf{v}_t)$. The common same-step association $(\phi(\mathbf{k}_t),\mathbf{v}_t)$ remains causal, but optimizes a different internal objective. We derive normalized first-order updates for squared-error regression and negative inner-product objectives. The regression family comprises Falcon-1 (a scalar NLMS update), Falcon-2 (its per-column extension), and Falcon-3 (a sliding-window mini-batch update); Falcon-1A/Falcon-2A/Falcon-3A are the corresponding inner-product variants. We provide recurrent, masked-parallel, and chunk-parallel forms, together with numerically stable positive-decay renormalization. Representative variants remain competitive in language modeling and improve length extrapolation on variable-digit addition. This framework separates temporal alignment, plasticity, forgetting, and bounded rehearsal in recurrent sequence models.

AI 总结：本文针对动态图测试时自适应的研究空白，提出DGOTTA框架，通过三个模块提升DGNN在分布偏移下的泛化性能，经多数据集实验验证有效。

链接：https://arxiv.org/abs/2608.27948

机构：Griffith University（格里菲斯大学）； RMIT University（皇家墨尔本理工大学）

作者：Bo Li, Xin Zheng, Ming Jin, Can Wang, Shirui Pan

英文摘要： Test-time adaptation (TTA) on graphs aims to adapt a graph neural network (GNN) that is well-trained on the training graph to the test graph, which involves potential distribution shifts that may harm model generalization and test-time inference. While recent efforts have investigated TTA on static graphs, there is still a research gap on dynamic graphs learned with dynamic GNN (DGNN) models, where both structural connectivity and node semantics evolve continuously over time. This makes adapting a DGNN model for reliable test-time performance substantially challenging. To fill this gap, in this work, we propose a novel framework of temporal memory-aware Online Test-Time Adaptation on Dynamic Graphs, named DGOTTA, to effectively adapt well-trained DGNNs during test time. Specifically, the proposed DGOTTA contains three modules: (1) temporal-aware augmentation, to extend the diversity of test dynamic graphs for addressing complex temporal and spatial shifts; (2) memory-aware model prediction, to alleviate catastrophic forgetting; (3) consistency-guided online adaptation, to enforce temporal alignment and memory smoothness. Extensive experiments on three real-world datasets and four DGNN backbones demonstrate that DGOTTA significantly improves generalization under diverse distribution shifts and multiple model architectures.

AI 总结：本文针对不相交表格数据迁移学习的共享特征假设不切实际的问题，提出CATTLE方法，通过Transformer投影权重捕获广义上下文实现跨域注意力迁移学习，在十组数据集上优于九种基线方法，取得平均排名2.9、平均AUROC提升3.7%的效果。

链接：https://arxiv.org/abs/2608.28209

机构：Tennessee State University（田纳西州立大学）； North Carolina Agricultural and Technical State University（北卡罗来纳农工州立大学）

作者：Kazi F. Akhter, Ibna Kowsar, Manar D. Samad

英文摘要：Unlike images and text, applying transfer learning to tabular data is challenging due to heterogeneity in feature types, structures, and semantics across disparate domains. Existing methods assume shared features across data tables to enable knowledge transfer between domains, which is unrealistic in practice. \mds{This paper introduces generalized context learning to remove the requirement of shared features across domains. The generalized context captured by transformer projection weights for $key$, $value$, and $query$ provides rule-based generalization rather than the domain-specific context conventionally learned from transformer activations. Projection weights for $key$ from the source domain interact with the weight for $query$ in the target domain to achieve Cross-domain Attention Transfer Learning (CATTLE) in a data-agnostic manner. Our experiments on ten pairs of disjoint source-target data sets show that CATTLE can learn generalized context from a single source data set and is rank-wise and statistically superior to nine state-of-the-art baselines, including machine learning, deep learning, and transfer learning methods using large-scale pre-trained models. CATTLE achieves the best average rank (2.9) and delivers a 3.7% average AUROC gain over the baseline methods.} The CATTLE source code is available at this https URL.

AI 总结：本文提出D-TAIA框架，通过参数高效微调FM骨干网，结合DATL预训练与FAISS检索等技术，在四个真实事件日志上实现多任务PPM的SOTA或竞争力性能。

链接：https://arxiv.org/abs/2608.28236

机构：Eindhoven University of Technology（埃因霍温理工大学）； University of Wuppertal（伍珀塔尔大学）

作者：Sjoerd van Straten, Christine Jacob, Marwan Hassani

英文摘要：Predictive Process Monitoring (PPM) enables organizations to forecast future process behavior, such as the next activity and remaining time of ongoing cases. In practice, three conditions cause existing methods to degrade, namely data scarcity, high process entropy and distributional shift. While Foundation Models (FMs), especially Large Language Models (LLMs), offer a new paradigm through broad sequential reasoning, adapting them to multi-task PPM under these conditions remains an open challenge. Existing FM-based approaches either lack mechanisms for handling distributional shift or rely on direct regression heads that can be structurally misaligned with continuous time prediction tasks. This paper introduces D-TAIA (Domain-aware Training and Attention-based Inference Architecture), a framework for a joint next activity and remaining time prediction task via parameter-efficient fine-tuning of an FM backbone. Our approach combines domain-aware triplet loss (DATL) pre-training with FAISS-based nearest neighbor retrieval for remaining time prediction, and adopts the TAIA inference strategy to preserve pre-trained sequential reasoning during fine-tuning. Evaluated across four real-world event logs, D-TAIA consistently shows SOTA or competitive performance compared to a fine-tuned LLM and a recurrent neural network baseline. Ablation studies confirm that techniques from NLP and computer vision can be transferred effectively to PPM with only a 10M-parameter backbone, though component contributions vary by dataset entropy.

AI 总结：针对PPM领域基础模型在线持续微调的冷启动问题，提出COMPASS框架，通过自适应子空间与漂移检测技术实现更优性能，且计算开销可接受。

链接：https://arxiv.org/abs/2608.28237

机构：Eindhoven University of Technology（埃因霍温理工大学）； University of Wuppertal（伍珀塔尔大学）

作者：Sjoerd van Straten, Marwan Hassani

英文摘要：Predictive Process Monitoring (PPM) models are increasingly deployed in dynamic environments where concept drift causes the underlying process distribution to shift over time. While recent work has moved toward online continual learning, existing methods train compact, task-specific networks entirely from scratch, leaving a persistent cold-start problem. Foundation Models (FMs) offer a compelling solution to this problem, but their continual fine-tuning in the process mining domain remains unexplored. We propose COMPASS (Continual Online foundation Model-based PPM with Adaptive SubSpaces), the first framework for online continual fine-tuning of FMs for PPM. COMPASS adapts loss-plateau drift detection to autonomously identify task boundaries in event streams and maintains a unified knowledge subspace including both pre-trained and task-specific directions. We evaluate our approach on nine event streams covering synthetic and real-world concept drift scenarios, across task-free and task-aware settings with multiple backbones and with consistent hyperparameter tuning across all methods. Our approach outperforms three SOTA non-FM competitors and two update strategy baselines, with particularly strong gains on streams exhibiting recurrent drift and complex, long-running cases, while incurring acceptable computational overhead compared to the non-FM competitors.

AI 总结：本研究对比经典与量子机器学习模型在高能物理对撞数据回归任务中的表现，发现量子模型参数效率更高，经典模型当前硬件下性能略优，为相关研究提供基准。

链接：https://arxiv.org/abs/2608.28084

机构： University of the Punjab（旁遮普大学）； Universidad Michoacana de San Nicolás de Hidalgo（米却肯州圣尼古拉斯德伊达尔戈大学）； Universidad del Bío-Bío（比奥比奥大学）

作者：Tariq Mahmood, Zain ul Abidin, Itzel Luviano Soto, Alfredo Raya

英文摘要：The classification and regression of particle collision events constitute a persistent computational challenge in experimental high energy physics, where large volumes of simulated data must be processed with both speed and precision. This work carries out a systematic comparison of four classical machine learning architectures, support vector machines (SVM), artificial neural networks (ANN), convolutional neural networks (CNN), and long short-term memory (LSTM) networks against their quantum counterparts: quantum SVM (QSVM), quantum neural networks (QNN), quantum CNN (QCNN), and quantum LSTM (QLSTM). All models are trained on simulated proton-proton collision events with electron-positron and muon-antimuon final states from the CERN Open Data portal, using transverse-momentum components as input features and transverse-momentum magnitude as the regression target. Classical architectures, and in particular the CNN and LSTM, achieve marginally better quantitative performance under current hardware and dataset constraints. Quantum models, however, reach competitive accuracy with substantially fewer trainable parameters: the QCNN reproduces the performance of the deep classical CNN using only four qubits and a circuit of depth three, pointing to a genuine parameter-efficiency advantage on near-term quantum devices. A baseline analysis confirms that the regression problem is non-trivial for shallow polynomial fits, supporting the relevance of the architectural comparison. These results characterize the trade-offs between classical and quantum approaches under realistic, resource-constrained conditions and provide a benchmark for future studies on actual quantum hardware.

AI 总结：该研究针对OpenEuroLLM模型，探究预训练时学习率与批量大小的缩放规律，开发相关模型并评估损失的缩放形式，建立基线与缩放程序并开源预训练运行集合。

链接：https://arxiv.org/abs/2608.28308

作者：Niccolò Ajroldi, Diana Alexandra Onutu, Haider Al-Tahan, Jörg Franke, Sampo Pyysalo, Jenia Jitsev, Aaron Klein

英文摘要：We study the scaling behavior of learning rate and batch size in pretraining dense large language models on English-prevalent corpora. Beyond scaling \textit{jointly optimal} learning rates and batch sizes, we investigate their \textit{marginal} evolution with model capacity and data scale and develop a model that captures these relationships. As we employ a Warmup-Stable-Decay learning rate schedule, we further investigate the gains from learning rate annealing over a broad range of hyperparameters settings, models and data budgets, and whether the optimal learning rate and batch size \textit{transfer} between the stable and decay phases. Finally, we characterize the dependence of loss on model capacity and dataset size, evaluating recently proposed scaling forms that explicitly model their interaction. We find these approaches particularly effective at capturing both undertraining and overtraining regimes across our experiments. This study establishes a first baseline and scaling procedure for the development of future OpenEuroLLM models. We open-source the complete collection of pretraining runs used in this study.

AI 总结：本文提出球形神经PDE求解器Dandelion，发布含6类数据集的球形PDE基准，其在所有数据集上表现最优或次优，分辨率提升时优势更显著。

链接：https://arxiv.org/abs/2608.27521

机构：University of Basel（巴塞尔大学）

作者：Till Muser, Giovanni Abati, Ivan Dokmanić

英文摘要：Many dynamical processes unfold on the sphere but the default scientific machine learning architectures are Euclidean. Applying these architectures on a regular lat-lon grid causes problems: Cartesian convolutions become distorted at high latitude; 2D FFTs in Fourier neural operators incorrectly assume double periodicity; Cartesian positional encodings in ViTs distort spherical geodesic distances. Recent work moves towards natively spherical primitives, including spherical convolutions (e.g., DeepSphere or DISCO), Spherical Fourier Neural Operators (SFNOs), and geodesic attention. Here we propose Dandelion, a spherical version of Flower, a warp-based neural PDE solver. Layers of Dandelion predict a tangent-plane displacement and transport features along great circles. We obtain a U-Net-like structure by implementing hierarchical pooling entirely in the spherical-harmonic domain. There are thus no convolutions: spatial mixing is achieved only through spherical coordinate changes, or warps. To compare Dandelion with existing spherical architectures, we release an evolving benchmark suite of challenging, natively-spherical PDE datasets including a modified Galewsky jet, anomalous chained turbulence, Cahn-Hilliard decomposition, spherical Riemann shocks, Held-Suarez dry atmospheric transport and global ocean dynamics. This new benchmark fills the gap in existing spherical datasets which are either too small and stylized, or much too large (ERA5) for model iteration. Dandelion is best or second-best on every dataset, and the gap to non-warp baselines widens with resolution: at $256\times 512$, Dandelion and Flower2D occupy the top two slots in both single-step prediction and rollout.

AI 总结：该研究针对参数化偏微分方程，提出超图自适应小波算子HALO，在多类基准测试中精度优异且滚动稳定，可扩展至工业空气动力学几何，性能优于或媲美相关基线模型。

链接：https://arxiv.org/abs/2608.27883

机构：Indian Institute of Technology Delhi（印度德里理工学院）； Yardi School of Artificial Intelligence (ScAI)（亚迪人工智能学院）； Department of Applied Mechanics（应用力学系）

作者：Rajat Sarkar, Venkataramana Runkana, Souvik Chakraborty

英文摘要： Physical systems are often modeled by solution operators that map input fields, parameters, geometries, or past states to steady or future physical states. Learning these maps is difficult, especially for time-dependent systems that must assimilate history and remain stable under autoregressive rollout. Many neural operators work best on regular, structured grids, while realistic simulations often require unstructured meshes or point clouds to resolve complex geometries; in such settings, grid-centric representations can lose accuracy. Graph neural operators handle these domains through message passing or spectral graph filtering, but pairwise edges do not directly capture group-wise couplings among mesh cells, local neighborhoods, or conservation volumes. We introduce the Hypergraph Adaptive waveLet Operator (HALO), which lifts the domain to a hypergraph and learns in its spectral wavelet domain. HALO avoids explicit hypergraph-Laplacian eigendecomposition through Chebyshev polynomial wavelet filters, giving localized spectral kernels at linear sparse-matrix cost. Its trainable dyadic wavelet scales are regularized toward tight-frame coverage, allowing the frequency response to adapt to each PDE while encouraging stable multi-scale spectral coverage. Across 2D and 3D benchmarks on structured and unstructured discretizations, HALO achieves best or near-best accuracy among frequency-, transformer-, DeepONet-, state-space-, and graph-based baselines and sustains stable multi-step rollouts. The same model scales to industrial aerodynamic geometries: on meshes of a few hundred thousand points it is on par with, or better than, the strongest fixed-discretization transformers, while remaining resolution-equivariant.

AI 总结：该研究提出自适应可逆差分（AdaRDiff）即插即用模块，通过可学习权重的加权差分稳定残差，实现长程时间序列预测精度提升，可改进多种骨干网络且加速明显。

链接：https://arxiv.org/abs/2608.28134

机构：Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）； CNRS（法国国家科学研究中心）； Grenoble INP（格勒诺布尔理工学院）； LIG（信息与信号处理实验室）； Savoye（萨沃伊公司）

作者：Morad Laglil, Younes Hlal, Marouane El Hadari, Emilie Devijver, Eric Gaussier

英文摘要：Reliable long-horizon time series forecasting is an important yet difficult problem. Trends and seasonality introduce complex temporal structure that challenges learning-based forecasting models. Differencing, which subtracts nearby past values to remove such structure, is the classical remedy, but its reliance on hand-picked orders and periods has kept it largely absent from recent deep architectures. We propose \textbf{\underline{Ada}}ptive \textbf{\underline{R}}eversible \textbf{\underline{Diff}}erencing \textbf{(AdaRDiff)}, a generalized differencing approach that uses learnable weights to simplify the series through weighted differencing with previous time instants. This yields stabilized residuals on which forecasting is performed, after which the removed components are restored autoregressively to reconstruct the forecast, capturing trend and seasonality jointly through a single operator. This reconstruction admits a closed-form convolutional expression, which parallelizes on GPU and yields up to $33.7\times$ speedup over the naive recurrence. We furthermore rely on a two-phase training schedule that separates temporal structure discovery from reconstruction learning, as suggested by a theoretical analysis of the gradient when using a linear forecasting model. AdaRDiff attains state-of-the-art forecast accuracy across eight benchmarks spanning electricity, weather, traffic, and energy, at negligible parameter cost. Furthermore, it is designed as a plug-and-play module: integrating AdaRDiff improves eight diverse backbones, from linear models to Transformers, in the large majority of cases, by up to $25.9\%$ with a linear backbone and $18.3\%$ with iTransformer.

AI 总结：针对城市多模式交通需求联合预测的挑战，提出统一框架TransMod，通过共享空间表示对齐不同粒度交通系统，实现跨模式知识迁移，在真实数据集上表现优于现有方法。

链接：https://arxiv.org/abs/2608.28273

机构：University of Exeter（埃克塞特大学）

作者：Yixuan Zhao, Man Luo

英文摘要：Urban transportation systems consist of multiple mobility modes that coexist within the same city and exhibit complex interdependencies, leading to correlated demand dynamics across modes. However, forecasting demand jointly across different modes remains challenging due to substantial heterogeneity in space and the limited availability of historical data for emerging modes. Existing forecasting methods are largely developed for individual mobility modes and implicitly assume compatible spatial structures between source and target systems, which severely restricts their applicability in multi-modal settings. To address these challenges, we propose \textbf{TransMod}, a unified framework for urban mobility demand forecasting that enables effective knowledge transfer across heterogeneous mobility modes. TransMod constructs a shared zone-level spatial representation that aligns mobility systems with different spatial granularities into a common space, thereby reducing structural mismatch and distributional shift. Built on this unified representation, TransMod further learns transferable spatio-temporal patterns from data-rich source modes and adapts them to data-scarce target modes, alleviating the dependence on extensive target-domain histories. Extensive experiments on real-world datasets demonstrate that TransMod consistently outperforms existing approaches and provides robust forecasting performance under limited target data.

AI 总结：该研究针对傅里叶神经算子跨域迁移能力差的问题，提出域无关的欧几里得傅里叶神经算子，经热方程和材料科学任务验证，可泛化到未见过的网格尺寸与域。

链接：https://arxiv.org/abs/2608.28425

机构：Institute of Mathematics（数学研究所）； Institute of Materials（材料研究所）； École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）

作者：Nathanael Bosch, Niklas Frederik Schmitz, Michael F. Herbst

英文摘要：Fourier neural operators (FNOs) provide an efficient framework for learning mappings between function spaces as they are, by construction, independent of the grid resolution at which they are trained and evaluated. However, FNOs are not independent of the periodic domain they are applied to: their discrete spectral weights are indexed by integer Fourier mode numbers, which correspond to physical wavevectors. When applied to a different domain, the same trained weights act at different wavevectors, and the FNO silently represents a different operator. This makes FNOs unsuitable for tasks where transfer across domains is crucial. We propose Euclidean Fourier neural operators~(EFNOs) as a domain-independent alternative to FNOs. By parameterizing the spectral kernel as a continuous function of the physical wavevector, the EFNO can learn operators that act consistently across periodic domains of varying shape and size. We evaluate the EFNO on a simple heat equation and on a practically relevant materials science task of learning exchange-correlation potentials across different crystal structures, and demonstrate that the EFNO is able to generalize to unseen grid sizes and domains.

AI 总结：研究针对量子图上非局部微分方程的数值求解，提出基于PyTorch的QGPINNs框架，整合图适配学习策略，可求解两类非线性模型，还可扩展至逆问题，经基准与真实网络实验验证有效。

链接：https://arxiv.org/abs/2608.28589

机构：Birla Institute of Technology and Science, Pilani（贝拉理工科学技术大学皮尔尼分校）

作者：Vaibhav Mehandiratta, Saket Ramchandra

英文摘要：We propose QGPINNs, a physics-informed neural network framework developed in PyTorch for the numerical solution of nonlocal differential equations on quantum graphs. The framework is designed as a general computational implementation in which the solution on each edge of the graph is approximated by a neural network, while a unified graph-based loss function enforces the governing equations together with initial, boundary, and vertex transmission conditions. In particular, the formulation incorporates standard continuity and Kirchhoff-Neumann vertex conditions and Dirichlet boundary conditions into the learning process to couple the local edge-wise neural approximations into a global solution on the graph. The framework is developed for two representative classes of nonlinear models: multi-order fractional elliptic problems and time-fractional evolution equations on quantum graphs. To improve accuracy and training stability, QGPINNs integrates several graph-adapted learning strategies, including soft and hard constraint enforcement, dynamic loss balancing, Fourier feature embeddings, and a learnable singularity-capturing feature for weakly singular solutions arising in the considered problems. The framework also extends naturally to inverse problems, including the identification of the orders of fractional operators and physical parameters from noisy observational data. We validate the accuracy, computational efficiency, and physical consistency of the proposed framework through numerical experiments on benchmark graph structures and real-world networks, including the IEEE 14-bus system and an open-channel agricultural drainage network.

AI 总结：DAMP是针对GDN、KDA类语言模型循环状态的混合精度量化方法，通过识别高风险通道差异化精度存储，在接近FP32基线精度的同时大幅降低存储、加速更新并减少推理延迟。

链接：https://arxiv.org/abs/2608.27513

机构：South China University of Technology（华南理工大学）； Meituan（美团）； East China Normal University（华东师范大学）

作者：Tao Zhang, Jianchao Tan, Pingwei Sun, Yanqi Yu, Zixu Jiang, Yuchen Xie, Xunliang Cai, Ziqian Zeng

英文摘要：Softmax attention stores key and value vectors for every preceding token, causing inference memory to grow with sequence length. Recent language models incorporating Gated DeltaNet (GDN) or Kimi Delta Attention (KDA) reduce this cost by replacing the KV cache in most layers with fixed-size recurrent states. However, these recurrent states are commonly stored in FP32 and consume substantial GPU memory; their updates are memory-bandwidth bound and contribute significantly to decoding latency. To our knowledge, we are the first to study post-training quantization of recurrent states in GDN and KDA based language models. We find that uniform quantization provides a poor accuracy--storage trade-off: INT8 and FP8 already degrade accuracy on complex reasoning tasks, while INT4 and NVFP4 reduce it to near zero. We further find that most quantization-error energy is concentrated in a small subset of channels and that the relative decay strength of state channels remains stable across prompts and tasks. Motivated by these findings, DAMP uses both quantization-error energy and decay-based persistence to identify high-risk channels during offline calibration. It stores these channels at higher precision and the remainder in INT8. We evaluate DAMP on Qwen3.6-35B and Kimi-Linear-48B across six benchmarks covering mathematical reasoning, general reasoning, and code generation. At 9.9 bits per state value, DAMP maintains average accuracy close to the FP32 baseline. DAMP reduces recurrent-state storage by 69.1%, accelerates the recurrent-state update kernel by up to 2.01x, and lowers full-model TPOT by up to 10.9%.

AI 总结：本文深入分析块稀疏特征化器（BSF）的优缺点，针对其存在的经典稀疏自编码器失效模式，提出锦标赛Top-K选择规则等架构改进，并将块范式扩展至跨编码器。

链接：https://arxiv.org/abs/2608.27515

机构：Columbia University（哥伦比亚大学）

作者：Alexandru-Iulius Jerpelea, Amith Ananthram

英文摘要：The recently introduced block-sparse featurizer (BSF; Fel et al., 2026) is similar to a sparse autoencoder (SAE), but its atomic unit is a small subspace (a block of directions) rather than a single direction. It is designed for features that live on low-dimensional manifolds, which are especially frequent in vision. This work studies the BSF's strengths and weaknesses, finding how it still somewhat suffers from classic SAE failure modes, like feature splitting and composition. We propose several architectural changes to the BSF, including a Tournament Top-K selection rule that significantly reduces feature splitting, and we also extend the block paradigm to the crosscoder.

AI 总结：该研究针对无监督表征对齐的退化问题，将已知不变性转化为设计时诊断方法，通过选择非对称颜色集，大幅降低了灾难性对齐失败率，且仅需一次函数调用即可完成数据收集前的检查。

链接：https://arxiv.org/abs/2608.27651

机构：University of Rochester（罗切斯特大学）

作者：Jing Xu, Christopher Kanan

英文摘要： Unsupervised representational alignment recovers a stimulus-by-stimulus correspondence from geometry alone, but the automorphism group of the stimulus geometry bounds what any such alignment can identify, before data exist. The obvious diagnostic for this degeneracy, the cheapest non-identity relabelling, ranks two published designs in the wrong order, because dense sampling creates near-duplicates whose transposition is nearly free. We turn this known invariance (Demetci et al., 2024) into a design-time diagnostic and intervention. In colour, where candidate geometries have closed form, we show that the failure is structural: sixty-four times the restart budget leaves a symmetric design unmoved while an asymmetric set at the same N recovers every time. Discriminating representational models and recovering a correspondence are essentially uncorrelated objectives (r = -0.02 over 3,000 subsets). Choosing nine colours by this diagnostic alone, without consulting any learned representation, moves all 93 model representations away from the degenerate point and cuts catastrophic alignment failures from 75% to 2% with the models, the layers, N and the solver all held fixed. The same risk arises wherever a regular design meets its candidate geometry's isometry group, including evenly spaced orientations, tones, or motion directions, and the check costs one function call before data collection.

AI 总结：本文开发了SafeStep这一实时语义通信平台，对比Meta-VIB等收发器，证实Meta-VIB损失降低92.1%，且SafeStep可观测AoI诱导的性能下降，是同类平台首例。

链接：https://arxiv.org/abs/2608.27688

机构：Auburn University（奥本大学）

作者：Christian McDowell, Andrea Panebianco, Jeremiah Yang, Sirin Chakraborty, Samuel Chamoun, Travis Ross, Yin Sun

英文摘要：In this paper, we develop SafeStep, an interactive browser-based semantic communication platform for live pedestrian safety monitoring. SafeStep extracts pedestrian information from four live traffic-camera feeds, transmits it through a semantic communication transceiver over an Additive White Gaussian Noise (AWGN) channel, and renders user-specific positions, trajectories, and risk labels. The platform allows to independently select the transceiver, Signal-to-Noise Ratio (SNR), codelength, and Age of Information (AoI), and demonstrates the transceiver performance of the selected configuration through live pedestrian safety monitoring to each browser. SafeStep compares a recently proposed semantic communication design called Meta-VIB with five baseline transceivers. Meta-VIB uses a compact neural model with only $4.16$ million parameters to generalize across varying SNR, codelength, and AoI values without online retraining. Experimental results show that Meta-VIB achieves mean task-loss reductions of up to $92.1\%$. On one high-end GPU server, the integrated concurrent-access workload maintains the target $5$ frames/s through $20$ users. At $100$ users, each requesting a distinct configuration, SafeStep records no request failures and a mean application response time below $1$ s, but its mean per-browser frame rate falls to approximately $1$ frame/s. To our knowledge, SafeStep is the first real-time semantic communication platform to make AoI-induced downstream degradation directly observable in live monitoring applications.

AI 总结：RiskBlend是一种多信号优先级排序框架，融合四类跨版本风险信号，在1200种实验配置下于所有80种组合中均获最高平均APFD，可高效检测机器学习回归故障。

链接：https://arxiv.org/abs/2608.27704

机构：East Carolina University（东卡罗来纳大学）

作者：Madhusudan Srinivasan, Namith Nishal Raphae

英文摘要：When machine learning classifiers are retrained, inputs correctly classified by the previous model version may be misclassified by the updated version, creating regression faults that are costly to detect because verifying predictions against ground truth may require human annotation, expert review, or expensive simulation rather than inexpensive model inference. Test input prioritization addresses this problem by ranking inputs so that a limited verification budget reveals as many regression faults as possible. Existing approaches rely predominantly on single-model confidence scores and do not exploit how predictions, decision boundaries, and local neighborhoods change between model versions. We propose RiskBlend, a classifier-agnostic prioritization framework that combines four complementary risk signals: historical failure patterns, prediction shift, decision-boundary shift, and neighborhood change. These signals are combined using validation-learned APFD-squared weighting. Across four datasets, five classifiers, four regression-update scenarios, and 15 random seeds, totaling 1,200 experimental configurations, RiskBlend achieves the highest average APFD in all 80 dataset-classifier-scenario combinations, with improvements of up to 0.32 APFD over the strongest baseline. Confidence-based methods remain competitive primarily for linear classifiers on sparse categorical features, which we attribute to feature-space geometry. The results show that cross-version behavioral signals provide important complementary information for prioritizing regression faults in machine learning systems.

AI 总结：本研究针对阿尔茨海默病诊断挑战，采用预训练于2500小时脑电图的大型脑模型LaBraM，结合随机森林分类器，仅用8秒脑电片段即达89.36%的ROC-AUC，优于传统方法，可提取临床相关生物标志物。

链接：https://arxiv.org/abs/2608.27719

机构：University of California, San Diego（加利福尼亚大学圣地亚哥分校）； HippoScreen Neurotech Corp.（HippoScreen神经科技公司）； Swartz Center for Computational Neuroscience（Swartz计算神经科学中心）

作者：Maggie Lin, Chung-Lin Hou, Tzyy-Ping Jung

英文摘要：Biological heterogeneity in Alzheimer's Disease (AD) poses a critical diagnostic challenge, particularly for traditional linear methods that fail to capture non-linear neural dynamics. To address this, we propose a diagnostic framework utilizing the Large Brain Model (LaBraM), pretrained on over 2,500 hours of EEG data. By integrating these high-dimensional latent embeddings with a non-linear Random Forest classifier, our approach effectively isolates robust disease markers. Under a rigorous subject-independent 5-fold cross-validation protocol, the method achieves an ROC-AUC of 89.36% +/- 3.49%, PR AUC of 81.45% +/- 4.43%, and Balanced Accuracy of 82.44% +/- 4.34% in distinguishing dementia patients from healthy controls. Notably, this performance uses only 8-second EEG segments, surpassing traditional spectral baselines, including band-power and parameterized oscillatory features (FOOOF). Post-hoc occlusion analysis confirms the model captures clinically validated biomarkers, specifically occipital-frontal Alpha and Theta rhythm degradation. Additional neurophysiological alignment analysis demonstrated that higher LaBraM-predicted dementia probability significantly correlated with worse cognitive performance, greater clinical severity, increased theta and alpha relative power, and higher aperiodic exponent. These findings demonstrate that deep latent representations extract clinically relevant signatures from noisy signals, enabling precise, rapid, and data-efficient diagnosis.

AI 总结：本文提出SOMTab架构，将表格上下文学习的表示构建与查询条件检索分离，结合DCH-TailMix合成先验，在接近Transformer模型性能的同时提升了效率。

链接：https://arxiv.org/abs/2608.27882

机构：Institute of Statistics and Big Data, Renmin University of China（中国人民大学统计与大数据研究院）

作者：Hao Wang, Siyu Zhang, Wei Ma

英文摘要：Tabular foundation models based on in-context learning have recently emerged as strong alternatives to task-specific model fitting. However, the current performance frontier remains dominated by attention-heavy architectures, where attention is used throughout the modeling pipeline. This raises a natural question: is attention necessary at every stage of tabular in-context learning? We introduce SOMTab, a Set-Order Mamba architecture for efficient tabular in-context learning. SOMTab separates representation construction from query-conditioned retrieval. For row and column representations, it maps unordered table tokens into stable latent slots and applies Mamba-based state-space mixing to construct compact representations. For final prediction, it retains attention-based in-context learning to preserve query-conditioned retrieval from labeled context examples. We further introduce DCH-TailMix, a synthetic prior that combines degree-corrected graph heterogeneity with mixed heavy-tailed regimes to diversify synthetic dependency structures. Across tabular benchmarks, SOMTab approaches the performance of strong Transformer-based tabular foundation models while achieving faster inference and lower GPU memory usage, yielding a favorable efficiency--accuracy trade-off.

AI 总结：针对现有多模态转换方法的不足，提出BIT双向图像-文本扩散桥，实现双向生成且性能优于基线。

链接：https://arxiv.org/abs/2608.27885

机构：Stanford University（斯坦福大学）

作者：Gabe Guo, Elon Litman, Thanawat Sornwanee, Jose Blanchet, Stefano Ermon

英文摘要：Multimodality translation (e.g., text-to-image) is a core generative AI task. However, existing approaches (1) follow generative paths that do not directly represent the source modality, limiting the flexibility of some sampling algorithms; and (2) are unidirectional, preventing inversion (e.g., image-to-text). We propose BIT: Bidirectional Image-Text Diffusion Bridges. In contrast to previous approaches, BIT starts directly from text and interpolates into images, providing (1) a source-aware generative path that enables diverse and flexible sampling algorithms; and (2) an endpoint-conditioned process that can be traversed from image to text, providing a unified, bidirectional generative framework. BIT is derived through stochastic calculus, yielding SDE forms amenable to simulation and tractable loss functions that scale to high dimensions. Our experiments show that BIT is competitive with denoising-diffusion and deterministic-flow baselines, and outperforms them on several vision--language and natural-science evaluations.

AI 总结：TACIT-SWITCH从审查式监督学习切换策略，在可比成本下提升大语言模型智能体成功率7.4-11.1个百分点，在ALFWorld和DABench上取得最优保留成功率。

链接：https://arxiv.org/abs/2608.27911

机构：The Hong Kong Polytechnic University（香港理工大学）

作者：Ji'an Lei, Jian Huang

英文摘要：Agents with smaller language-model backbones are less expensive but can drift into persistent failure modes, whereas those with larger backbones are generally more reliable but more costly. This reliability-cost trade-off motivates routing methods that decide when to invoke an agent with a larger backbone: before execution, after a fixed trajectory prefix, or locally at individual steps. Our method, TACIT-SWITCH, learns permanent handoff policies from accumulated trajectory evidence and Teacher-Annotated Censored Intervention Times (TACIT). It represents each annotation as an interval-censored observation on a cumulative-risk scale. The resulting mixture-cure threshold model estimates the probability that the paired Strong rollout succeeds and, conditional on success, the handoff threshold; no teacher is required at deployment. In a mechanism-based multi-step simulation, TACIT-SWITCH improves success by 7.4-11.1 percentage points over task-level, step-level, and fixed-prefix routing baselines at comparable cost. Within that controlled simulation, ablations show that task features and cumulative trajectory risk provide complementary information. With operating points selected on development data, TACIT-SWITCH achieves the highest held-out success among learned policies on both ALFWorld (48.5% with 4B Cheap; 45.5% with 9B Cheap) and DABench (73.1%).

AI 总结：本研究提出TI²PS框架，整合贝蒂向量与逆向代理建模，以斑马鱼色素模式为验证对象，仅用10%训练数据即优于全数据训练的PointNet++，实现多细胞ABBM参数的高效准确估计。

链接：https://arxiv.org/abs/2608.27931

机构：NTT, Inc.（NTT公司）； Georgia Institute of Technology（佐治亚理工学院）

作者：Kenji Komiya, Andrew Kailiang Jin, Ryo Nishikimi, Kunio Kashino

英文摘要：This study proposes a novel framework to estimate parameters for reproducing target multicellular patterns using an agent-based model (ABM). Two major challenges in multicellular ABMs are estimating cell-level parameters (agent-specific variables) and quantitatively evaluating the topological characteristics of multicellular arrangements under stochastic cell proliferation and death. To address these challenges, we integrate two approaches: Betti vectors and inverse surrogate modeling. The Betti vectors obtained through topological data analysis can consistently represent features of a wide range of multicellular spatial configurations. The inverse surrogate modeling enables direct inference of the corresponding ABM parameters from the target patterns. We validated the proposed framework using zebrafish pigment pattern formation, a representative model of pattern formation driven by multicellular interactions. The results demonstrate that our framework successfully estimates ABM parameters and outperforms conventional methods such as PointNet++. Notably, the proposed method, which used only 10% of the training data, outperformed PointNet++, which used 100% of the data, across all evaluation metrics.

AI 总结：PhyMamba是一种两阶段物理调制Mamba框架，将电化学老化融入序列建模，在三个公共数据集上使电池健康预测整体平均误差降低31.8%，实现最优聚合性能与精度效率权衡，支持实际部署。

链接：https://arxiv.org/abs/2608.27978

机构：Singapore Institute of Technology（新加坡理工学院）； National University of Singapore（新加坡国立大学）； Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局高性能计算研究所）； Nanyang Technological University (NTU)（南洋理工大学）

作者：Sara Sameer, Yunyi Zhao, Wei Zhang, Minggang Zeng, Wenqing Li, Man-Fai Ng, Yonggang Wen

英文摘要：Battery health prognostics is a core function in battery management systems (BMSs), yet long-horizon health forecasting from BMS signals remains challenging due to operating-condition dependency and sensor noise. In this paper, we propose PhyMamba, a two-stage physics-modulated Mamba framework that integrates electrochemical aging into sequence modelling. PhyMamba does not require explicit identification of internal aging parameters, which often relies on intrusive measurements. In stage-1, a lightweight Mamba encoder first processes BMS signals and produces a latent representation that is transformed via an aging parameterization module, into physics-informed aging features. In stage-2, a customized Mamba forecasting backbone performs multi-cycle prediction, where physics is tightly integrated to regulate the model's internal temporal updates toward degradation-consistent evolution. Experiments on three public datasets under multiple forecast horizons show that PhyMamba achieves the best aggregated performance, with an overall mean error reduction of 31.8% compared with a diverse range of baselines. PhyMamba also offers an optimized accuracy-efficiency trade-off, which supports practical deployment for robust battery health prognostics.

AI 总结：本文针对Gemma-3-1B提出质量退化约束下性能最大化的层级位宽分配方法，结合SA-PTQ敏感性分布优化TensorRT-LLM量化，在RTX 5090上实现最高19.1%延迟降低，为LLM量化提供新方案。

链接：https://arxiv.org/abs/2608.28003

作者：Artem Safronov

英文摘要：This paper proposes a layer bit allocation method for Gemma-3-1B, formulating the problem as performance maximization (latency decrease) given a degradation budget constraint (allowable level of generation quality loss). This approach is different from time- and resource-consuming uniform layer quantization methods that are used in the literature (like GPTQ or AWQ) or allocation methods without proven performance-accelerating effect (like MixLLM or TorchAO). The layer sensitivity profile resulting from our prior work SA-PTQ is applied using the activation pass-through mode inside TensorRT-LLM. For each layer precision is determined individually in blocks, according to a grouping introduced in the prior step (5+5, 10+10, all26), differentiating the contribution of FFN, Attention, and lm_head to the overall speedup. The clock speed was measured for 13 W8A8 variants on an RTX 5090. We find that for FFN and lm_head the time cost of quantization/dequantization is compensated for by the use of integer arithmetic, while for short context lengths, the opposite holds true for Attention: an additional step of quantization slows execution down. We propose a manual implementation of SmoothQuant for TensorRT-LLM which was necessary due to export failures, unavailable for lm_head. The best solution found under joint consideration of all three criteria with minimal degradation was FFN 5+5 with lm_head, providing an 11.0% reduction in latency with negligible quality loss (98.90% Top-1 agreement, +0.85% perplexity degradation). With acceptable quality loss for FFN all26 + lm_head, a speedup up to 19.1% was found possible. We suggest further optimizations: fused attention kernels in INT8, KV-cache quantization, using FP8 instead of INT8 and partial Attention quantization analogous to FFN.

AI 总结：该研究解决了线性回归加权数据选择的开放问题，确定了$d

链接：https://arxiv.org/abs/2608.28007

机构：University of New South Wales（新南威尔士大学）

作者：Guangjian Zhang

英文摘要：Hanneke, Moran, Shlimovich and Yehudayoff (COLT 2025) posed the following open problem. A selector sees a finite dataset $D \subseteq \mathbb{R}^d \times \mathbb{R}$, picks at most $n$ examples together with nonnegative weights, and hands the weighted least squares objective to the minimum-norm ERM. Writing $F_w(d,n)$ for the worst-case ratio between the loss of the returned predictor on all of $D$ and the optimal loss, they proved $F_w(d,n)=\infty$ for $n

AI 总结：该研究提出将不确定性估计与XAI统一的egRUE方法，可量化并分解不确定性为特征贡献，经实验和专家研究验证，能提升医疗AI的可靠性与可解释性，优化临床决策支持。

链接：https://arxiv.org/abs/2608.28052

机构：College of Computing and Data Science (CCDS)（计算与数据科学学院）； Nanyang Technological University (NTU)（南洋理工大学）； A*STAR Centre for Frontier AI Research（新加坡科技研究局前沿人工智能研究中心）； School Of Computing and Digital Technologies（计算与数字技术学院）； Sheffield Hallam University（谢菲尔德哈勒姆大学）； School of Computing（计算机学院）； University of Utah（犹他大学）； Tan Tock Seng Hospital (TTSH)（陈笃生医院）； Lee Kong Chian School of Medicine（李光前医学院）

作者： Li Rong Wang, Jamie Duell, Xinran Xu, Thomas C. Henderson, Yu Yue Hew, Pik Wan Erica Chiang, Xiao Wei Alstar Ang, Bingwen Eugene Fan, Xiuyi Fan

英文摘要：Artificial intelligence has strong potential to support clinical decision-making, yet its adoption in healthcare remains limited due to a lack of trust. Uncertainty estimation can signal unreliable predictions, and explainable AI (XAI) can clarify how predictions are made but existing methods treat them separately, providing no feature-level insight into why a prediction is uncertain or which tests to prioritize to reduce it. To address this gap, we propose explainable uncertainty estimation, which unifies uncertainty estimation and XAI to both quantify uncertainty and explain feature-level contributions. We introduce the Expected Gradients Reconstruction Uncertainty Estimate (egRUE), which incorporates prediction explanations into its uncertainty computation and decomposes uncertainty into feature-wise contributions. We prove theoretical properties of egRUE and show through experiments that it improves reliability and interpretability compared to existing methods. A user study with medical experts further demonstrates that egRUE's explanations improve calibrated trust over uncertainty scores alone, increasing confidence in correct predictions and reducing confidence in incorrect ones. By combining prediction uncertainty with feature-level explanations, egRUE strengthens decision-making support in safety-critical healthcare settings, clarifying both when predictions may be unreliable and which features drive that uncertainty.

AI 总结：该研究明确了控制Softmax注意力秩复杂度的几何规律，推导了球形、全球等支撑下的近似秩公式，经BERT-base校准集验证，将支撑几何与交互几何的作用区分开。

链接：https://arxiv.org/abs/2608.28150

机构：Nanyang Technological University（南洋理工大学）； Carnegie Mellon University（卡内基梅隆大学）

作者：Yuhe Sui, Jianing Zhang

英文摘要：Which geometry controls the rank complexity of normalized softmax attention? We study maximum-row-$\ell_1$ approximation rank, exactly the least unrestricted rank preserving every bounded vector-valued output. Two sharp worst-case laws isolate support geometry: for fixed $d$ and error $\varepsilon$, spherical self-attention has rank $\Theta_{d,\varepsilon}(\min\{n,(1+\beta)^{(d-1)/2}\})$, while full-ball geometry adds one radial degree and, for $\beta\ge\beta_0(d,\varepsilon)$ and $n\ge C_d e^{\beta/8}$, gives $\Theta_{d,\varepsilon}(\beta^{d/2})$. For a fixed head, row-softmax quotients out row-scalar logit directions: the remaining visible query--key interaction dimension $r$ yields an $r/2$ per-instance upper law, and bounded constructions show this exponent is minimax sharp. Approximate interaction subspaces incur an explicit residual output error and yield a tolerance-indexed SVD dimension. On an 84-head BERT-base calibration set, we observe modest effective-dimension reductions across many head--temperature settings, together with positive associations with finite constructive rank upper certificates. Together, these results separate support geometry, which sets worst-case temperature scaling, from softmax-visible interaction geometry, which controls per-head approximation complexity.

AI 总结：针对随机神经网络单次隐藏单元抽取的局限，提出残差引导的贪婪隐藏层构建方法，在71个UCI基准数据集上验证其性能优于基线模型。

链接：https://arxiv.org/abs/2608.28267

机构：Indian Institute of Technology Indore（印度理工学院印多尔分校）

作者：Mushir Akhtar, M. Tanveer, Mohd. Arshad

英文摘要：Randomized neural networks enable fast and analytically tractable training by fixing the input to hidden layer parameters at random and learning the output weights in closed form; however, their performance critically depends on a single uninformed draw of hidden units. This one shot and task uninformed feature construction often leads to redundant representations and suboptimal utilization of model capacity. To address this limitation, we propose a simple and broadly applicable residual guided procedure that greedily constructs the hidden layer using a closed form residual decrease criterion. At each stage, we (i) generate a pool of random candidate units, (ii) score each candidate by the exact reduction it induces in the ridge regularized objective, (iii) select the top k units, and (iv) refit the readout in closed form using the standard design with direct input links. This procedure yields a progressive training process with a guaranteed monotonic decrease of the training objective. The method is model agnostic: only the candidate generation is architecture specific, while the scoring selection refitting loop is shared across models. Extensive experiments on 71 benchmark datasets from the UCI repository, covering both binary and multiclass classification tasks, demonstrate that the proposed residual-guided models consistently outperform their baseline counterparts in terms of accuracy, stability, and overall ranking performance.

AI 总结：该研究完成了Colombo关于差幂行列式非奇异性的猜想，证明了超临界奇指数d≥n+1时差幂矩阵的非奇异性，得出其秩的统一公式。

链接：https://arxiv.org/abs/2608.28274

作者：Kun Li, Li Tie, Peng Wang, Zihan Liu

英文摘要：Let $n\ge2$ be even, let $\lambda=(\lambda_1,\ldots,\lambda_n)\in\mathbb{R}^n$ have pairwise distinct coordinates, and define the difference-power matrix \[ A_d(\lambda):= \bigl[(\lambda_r-\lambda_s)^d\bigr]_{r,s=1}^n, \qquad d\in\mathbb{N}. \] In 1928, Colombo proved that $\det A_{n-1}(\lambda)\ne0$---and hence $\det A_{n-1}(\lambda)>0$---and that $\operatorname{rank} A_d(\lambda)=d+1$ for $0\le d

AI 总结：针对LLM结构化生成中KV压缩未利用结构信号的问题，提出PASK方法，通过解析器信号优化KV持久化，在Qwen3-4B上显著提升性能并降低资源消耗。

链接：https://arxiv.org/abs/2608.28276

机构：Hangzhou Institute for Advanced Study（杭州高等研究院）； University of Chinese Academy of Sciences（中国科学院大学）

作者：Linze Wu, Xinrui Chen

英文摘要：Structured generation underpins large language model (LLM) agents that produce JSON, SQL, and function calls, where a single wrong field can cause the downstream action to fail. Constrained decoding already tracks parser transitions to enforce formal validity, and these transitions expose how generated tokens participate in schema-critical decisions such as required fields, arguments, and structural boundaries under the active grammar. Existing KV compression largely leaves this task-relevant structural signal unused. We introduce PASK (Parser-Aware Structural KV Persistence), which turns parser-derived structure into layer-group-specific KV persistence decisions. PASK addresses the mismatch between model-side KV sensitivity and task-level structured risk by using task-error sensitivity to set minimum protection floors and attention-output distortion to allocate residual KV capacity. An offline calibration stage compiles these signals into a persistence policy, leaving only lightweight structure-conditioned lookup online. At a targe total KV budget of 0.33, PASK outperforms the strongest compressed baseline by 17.39 percentage points on average across eight BFCL non-live and Live subcategories on Qwen3-4B. In end-to-end serving, PASK achieves up to 2.2x higher throughput and 3.3x lower TPOT, while using 0.53x the peak GPU memory of Full KV.

AI 总结：VISTA 复用标准 OPSD 的 rollout 与损失函数，通过结果验证的 rollout 将教师适配学生分布，在多基准数据集上提升了不同规模 Qwen3 模型的 Avg@12。

链接：https://arxiv.org/abs/2608.28306

机构：University of Science and Technology of China（中国科学技术大学）； State Key Laboratory of Cognitive Intelligence（认知智能国家重点实验室）

作者：Zewen Ding, Zezhong Wu, Zhou Tao, Shida Wang, Shizhuo Hou, YongXiang Hua, Haoyu Cao, Linli Xu

英文摘要：On-policy self-distillation (OPSD) improves reasoning by training a problem-only student on its own rollouts using dense token-level supervision from a privileged teacher that also sees a reference solution. However, standard OPSD treats the teacher distribution as a fixed target along the student's rollout and updates only the student %, although -- even though privileged conditioning does not guarantee that the teacher always provides the most appropriate target for problem-only reasoning. This one-way supervision can therefore misdirect the student when the teacher distribution is misaligned with valid student reasoning. We therefore introduce Verifier-Informed Student-to-Teacher Adaptation (VISTA), which preserves the standard OPSD student update while using outcome-verified rollouts to adapt the teacher toward the student distribution. Within each verified rollout, VISTA further restricts this adaptation to the top-$k$ positions with the largest teacher--student KL divergence. Notably, VISTA reuses the rollout and loss function from standard OPSD, introducing no additional sampling or separate reward objective. Across AIME24, AIME25, and HMMT25 with Qwen3 models at 1.7B, 4B, and 8B, VISTA achieves the highest Avg@12 at every scale, improving over OPSD by $0.6$, $0.7$, and $2.1$ points, respectively. These results demonstrate the value of student supervision from outcome-verified rollouts and highlight student-to-teacher adaptation as a promising direction for OPSD.

AI 总结：SymboLLM-FE将符号回归与LLM结合，通过符号回归提取强相关公式并经LLM优化，在6个真实数据集和4个Kaggle竞赛上性能优于现有AutoFE，解决了可解释性差和迭代多的问题。

链接：https://arxiv.org/abs/2608.28408

机构：Nanjing University（南京大学）； School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）； School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）

作者：Zi-Jian Cheng, Zi-Yi Jia, Zhi Zhou, Yu-Feng Li, Lan-Zhe Guo

英文摘要：Tabular data, as a core data format in machine learning, often lacks the discriminative power needed for high-performance modeling due to insufficient feature informativeness. Automated Feature Engineering (AutoFE) overcomes this by automating feature generation and selection, ensuring both model performance and operational efficiency. However, traditional AutoFE often yield features with poor interpretability because they rely on blind mathematical transformations, while large language models (LLM)-based AutoFE faces challenges in requiring costly multi-round iterations to generate high-utility features to effectively enhance model performance, compounded by inherent risks of bias and hallucination. In this paper, we combine symbolic regression with LLMs for feature engineering (SymboLLM-FE) to solve these challenges. We extract mathematically expressive formulas strongly correlated with the target via symbolic regression, which can enhance model performance, then refine them by LLMs with rich prior knowledge to ensure interpretability. Empirical results on six real-world datasets and four Kaggle competitions demonstrate that SymboLLM-FE outperforms existing AutoFE. SymboLLM-FE also addresses the dual challenges of poor interpretability and numerous iterations by employing a statistical prior-grounded LLM refinement mechanism and single-digit LLM calls.

AI 总结：该研究探讨认证代码世界模型中相对于可达性的拓扑，通过LLM合成实验得出三条原则，揭示危险与可达性的关联、修复的限制及缓解措施需匹配错误维度方向的结论。

链接：https://arxiv.org/abs/2608.28541

机构：AGILabs

作者：Javier Aguilar Martín

英文摘要： A code world model accepted by a sampling gate can be exactly right on everything the gate can see and arbitrarily wrong beyond it. We characterize what a certified model can know, and what its errors can cost, when the omission is an annular freeze mode enclosing an unreachable interior. The gate quotient makes the question precise: acceptance-with-certainty determines the model exactly on the reachable query set; beyond reach is gauge. On a minimal ring instrument we prove the extreme case (a wrong-topology filled-disc artifact unfalsifiable by any sampling gate and bitwise harmless at play) and measure, with LLM synthesis across three model families, how one knob (a channel of width gamma) walks the same artifact through three regimes: unfalsifiable-and-harmless, falsifiable-and-costly, and instantly falsified. Three principles organize the empirics. First, danger is topology relative to reach: a channel the planner can use collapses the blind model's exploitation (play cost 1.09 to ~0 over a knee at gamma ~ 0.1), while a hidden channel with the same first Betti number keeps it at full strength (1.12). Second, repair is parameter-bound and sensor-bound: no family recovers the region from outside evidence; from inside, models pose the right topology but cannot pin its parameters, and the posed topology tracks the guiding persistent-homology summary's wrong beta_1 (a sensor with a measured geometric resolution limit), not the truth. Third, mitigation must match the error's dimension and direction: point fences fail against the one-dimensional boundary, a dimension-matched persisted fence collapses exploitation to a two-lesson transient (0.999 to 0.058), and the dual freedom certificate collapses the invented-mode failure symmetrically (1.769 to 0.029). In n dimensions the shell makes misidentification near-certain while the danger stays fully exploitable: the two axes are independent.

AI 总结：针对模型合并中解码器存在的表示偏差挑战，本文提出DARTS方法，通过熵加权L1损失与逐位置加性偏差校正，在三类任务上较标准方法获显著改进且新增参数极少。

链接：https://arxiv.org/abs/2608.28547

机构：ServiceNow（ServiceNow（服务now公司））； University of Twente（特温特大学）

作者：Aaryan Ajay Sharma, Sai Nishanth Padala, Seganrasan Subramanian

英文摘要：Model merging combines multiple task-specific fine-tuned LLMs into a single multi-task model without additional training. However, merged models are known to suffer from representation bias: systematic drift between the merged model's hidden states and those of each individual source model. Prior work (Yang et al., 2024a) study and mitigate this bias for encoder-based vision models using a lightweight correction module trained with L1 loss. However, such bias is not studied for decoder models due to their autoregressive nature. We analyze the problem of representation bias in decoder models, and show two challenges absent in encoders: (1) the causal attention mask causes bias to accumulate across token positions, requiring position-dependent correction; and (2) not all token positions are equally important, i.e., high-entropy (decision-critical) positions matter far more than low-entropy ones. To address these challenges, we propose Decoder-Aware Representation Tuning via Surgery (DARTS). DARTS employs a novel entropy-weighted L1 loss to upweight correction at high-entropy positions where errors most affect generation quality, and a per-position additive bias that captures position-dependent error without overparameterization. We perform extensive evaluation on three domains: code generation (HumanEval), mathematical reasoning (GSM8K), and instruction following (AlpacaEval) on Llama-2-7B models, and show DARTS achieves significant improvement over the standard surgery approach while adding negligible parameters ($0.1\%$ of total parameters).

AI 总结：该综述梳理了2025-2026年神经网络优化的进展，沿四个轴组织相关方法，指出矩阵感知方法是进步但无AdamW的通用替代方案，需结合多因素评估优化器。

链接：https://arxiv.org/abs/2608.28557

作者：Ruoran Xu

英文摘要：Neural-network optimization in 2025-2026 is no longer well described as a succession of new Adam variants. The design space has expanded from coordinates to matrices and layers, from fixed training horizons to policies over time, and from mathematical update rules to state representations that must survive sharding and low-precision computation. This survey organizes recent optimizers and training optimization methods along four largely independent axes: temporal estimation, update geometry, horizon management, and representation and systems. It connects the spectral normalization of Muon, the historical matrix statistics of Shampoo and SOAP, adaptive and hybrid matrix methods, memory-efficient optimizers, schedule-free training, small-batch corrections, and quantized optimizer states. The central empirical conclusion is deliberately non-triumphal: matrix-aware methods represent a genuine advance, but there is no context-independent replacement for AdamW. Rankings change with model scale, data-to-parameter ratio, batch size, schedule, parameter partition, tuning budget, and whether the target metric is tokens, FLOPs, wall-clock time, or memory. The practical consequence is a compositional view of optimizer design and a stricter protocol for evaluating optimizer claims.