机器学习学术速递[9.25]

AI 总结：SpaFactor提出轻量级低秩分解框架，融合多尺度组织上下文与基因程序建模，从HE图像预测空间转录组，在五个公共队列中实现最佳性能并提升生物学保真度。

链接：https://arxiv.org/abs/2609.28563

机构：Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）； Fuzhou University（福州大学）； Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University（清华大学附属北京清华长庚医院，清华大学临床医学院）； Chinese Academy of Medical Sciences and Peking Union Medical College（中国医学科学院 北京协和医学院）

作者：Shiting Ruan, Xitong Ling, Qiming He, Ziyou Yan, Huaitian Yuan, Tian Guan, Ying Xiao, Xu Guan, Yonghong He

英文摘要：Spatial transcriptomics (ST) profiles gene expression within tissue architecture, but its cost and experimental complexity limit routine use. Predicting spatial expression from routinely available hematoxylin and eosin (HE) images therefore offers a scalable alternative. However, conventional methods often fit high-dimensional gene outputs as independent targets, overlooking the biological coordination among genes while remaining vulnerable to high-dimensional noise and overfitting. Existing attempts to address this limitation often rely on computationally heavy graph networks or complex auxiliary supervision. We therefore introduce SpaFactor, a lightweight and efficient low-rank morphology-program-gene factorization framework. At the input, SpaFactor efficiently fuses the visual representation of the central spot with multiscale local and regional neighborhood context, yielding a histologic representation that captures cellular morphology and microenvironmental heterogeneity. For modeling, a residual MLP stably learns a nonlinear mapping from the tissue microenvironment to low-dimensional latent gene programs. These activities are decoded through shared gene loadings into coordinated multi-gene expression predictions. Across five public cohorts, SpaFactor achieves the best aggregate performance, with particularly clear improvements for spatially variable genes, and more faithfully recovers biologically organized spatial patterns. These results demonstrate that lightweight joint modeling of tissue context and gene programs can improve both predictive accuracy and biological fidelity.

AI 总结：本研究通过因果中介框架审计混合推理模型在NoThink后训练中的思维泄漏，发现泄漏是真实且显著的，泄漏比率达42%-79%，表明表面性能提升可能源于向Think模式的漂移。

链接：https://arxiv.org/abs/2609.28682

机构：College of Information Sciences and Technology（信息科学与技术学院）； Pennsylvania State University（宾夕法尼亚州立大学）

作者：Zehao Liu, Vasant G. Honavar

英文摘要：Post-training hybrid reasoning models in NoThink mode has attracted growing interest as a way to improve performance while keeping inference fast. However, these gains may draw on thinking behavior already accessible through the base model's Think mode. We formulate this thinking leakage in a causal mediation framework and audit its contribution using bidirectional interventions along a simple base-derived activation direction. Across three models and three post-training methods on competition math benchmarks, we find that leakage is real, causal, and substantial: behavioral and representational analyses reveal shifts toward Think, steering the base model along this direction reproduces most of the post-training accuracy gain, and counter-steering a checkpoint removes a substantial share of what it gains. Across nine aligned checkpoints with positive NoThink gains, the resulting leakage ratio ranges from 42% to 79%. These interventions support a substantial causal contribution of thinking leakage. Our findings show that a post-training method's apparent advantage can therefore reflect greater drift toward Think, obscuring whether it improves capability within NoThink or more effectively re-invokes existing Think behavior.

AI 总结：提出TM4FF框架，结合残差小波Mamba、Transformer注意力与物理信息损失，在四个CFD数据集上实现高精度与稳健泛化。

链接：https://arxiv.org/abs/2609.29087

机构：National University of Defense Technology（国防科技大学）； Nanjing Agricultural University（南京农业大学）； National Key Laboratory of Parallel and Distributed Computing（并行与分布式计算国家重点实验室）； National SuperComputer Center in Tianjin（国家超级计算天津中心）

作者：Zhuo Zhang, Shun Zou, Canqun Yang, Xi Yang

英文摘要： While deep learning accelerates expensive partial differential equation solving in computational fluid dynamics (CFD), existing methods like PINNs and FNOs often struggle with generalization, noise robustness, and physical consistency. We introduce the Transformer-Mamba for Flow Field (TM4FF) framework, a physics-constrained operator learning model with three key innovations: a Residual Wavelet Mamba (RWM) layer for feature denoising, a Transformer-based attention mechanism for enhanced feature fusion, and a physics-informed loss using Fourier derivatives to enforce the Navier-Stokes equations. Experiments on four CFD datasets show TM4FF achieves high accuracy and robust generalization across varying flow conditions.

AI 总结：本文提出谱引导扩散方法，利用谱集中比与Frobenius范数离线调度冻结网络层，在不需路由器或输入搜索下加速扩散推理，在多个模型上实现2.8-3.0倍墙钟加速并保持生成质量。

链接：https://arxiv.org/abs/2609.29505

机构：Iowa State University（爱荷华州立大学）； BRAC University（BRAC大学）

作者：Ibne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Anuj Sharma

英文摘要：Diffusion inference repeatedly evaluates the same large network. We ask whether pretrained weights alone can identify residual branches that need not be recomputed throughout the trajectory. Our \textbf{Spectral Concentration Ratio (SCR)} measures leading-versus-tail singular-value energy. Combined with Frobenius magnitude, it yields an offline sensitivity proxy and a deterministic lifetime for each scheduled unit. A frozen unit reuses its cached residual-branch update while the current residual stream and all external conditioning continue to propagate. The method needs no router, calibration prompts, or input-dependent search. At matched layer-step budgets, SCR/Frobenius preserves quality better than random, depth, norm, stable-rank, and Frobenius--stable-rank schedules on LLaDA-8B, DiT-XL/2, U-ViT-L, and SDXL. Broader LLaDA tests cover retrieval, reasoning, code, summarization, and open-ended generation; matched-horizon controls retain the ranking down to ten denoising steps. The complete captured-graph system reaches $2.8\times$--$3.0\times$ wall-clock speedup over eager inference. This is a systems-level number: on LLaDA, padded graph execution already gives $2.7\times$, while eliminating inactive branch work raises it to $3.0\times$. The perturbation analysis motivates pre-norm attention and MLP components under explicit local assumptions; results on AdaLN, U-shaped, convolutional, and cross-attention blocks are empirical transfer, not certified guarantees.

AI 总结：本研究系统评估了六种分类器在CICMalDroid 2020数据集上的伪标签半监督学习效果，发现收益强依赖分类器类型，SVM增益最大，随机森林在低标注比例下受损，并指出约10%标注样本即可达到近最优性能。

链接：https://arxiv.org/abs/2609.29564

机构：North South University（南北大学）

作者：Md Rafid Islam, Zahid Hasan, Hafiz Abdur Rahman

英文摘要：Detecting and classifying Android malware families remains challenging due to high feature dimensionality, class imbalance, and the high cost of expert-labeled data. Semi-supervised learning (SSL) offers a way to leverage unlabeled samples, but prior works rarely test whether SSL benefits generalize across classifier types or report statistical significance. We present a systematic evaluation of pseudo-labeling across six classifiers (LightGBM, XGBoost, Random Forest, Logistic Regression, MLP, and SVM) on the CICMalDroid 2020 dataset, using five-fold stratified cross-validation and paired t-tests across five labeled ratios (1-20%). We find that SSL benefit is strongly classifier-dependent: SVM shows the largest significant gain (+4.4% accuracy at 5% labels, p = 0.0028), LightGBM improves modestly (+0.8 to +1.3% at 2-5% labels), while Random Forest is significantly harmed at low label ratios (-3.1% at 1% labels). Per-class analysis reveals SSL disproportionately benefits the hardest-to-classify families, with Adware F1 improving by +13.8 percentage points versus only +0.8 for the already well-classified Benign class. We further show that approximately 800 labeled samples (10% of the dataset) yield near-optimal performance across all classifiers. These findings offer practical guidance on when and with which classifier pseudo-labeling is worthwhile for Android malware classification.

AI 总结：提出免训练的MARETopic框架，通过基于秩的原型选择在流形上发现主题，无需梯度更新即可在多个基准上提升纯度和NMI，并加速运行。

链接：https://arxiv.org/abs/2609.29630

机构：State University of São Paulo (UNESP)（圣保罗州立大学）

作者：Thiago César Castilho Almeida, Daniel Carlos Guimarães Pedronette

英文摘要：Recent topic models leverage pretrained embeddings, but neural architectures produce latent representations without grounding in specific texts, and clustering-based pipelines assign representative documents only post hoc, relying on absolute distances distorted by hubness and anisotropy in high-dimensional spaces. We introduce MARETopic, a training-free framework that casts topic discovery as rank-based prototype selection. After projecting embeddings onto a low-dimensional manifold, MARETopic builds ranked lists encoding ordinal neighborhood structure. A greedy algorithm selects exactly K exemplar documents, real corpus texts, whose neighborhoods cover the corpus. Two variants share this criterion. MARETopic$_\text{Corr}$ scores candidates with a query performance predictor and a rank correlation measure, leading Purity and NMI on the two benchmarks with the most categories, ahead of both neural and clustering-based topic models. MARETopic$_\text{Diff}$ scores them with a rank-based diffusion matrix, needs neither measure, and runs 1.7 to 1.9 times faster. Without a single gradient update, MARETopic leads topic coherence on two of three datasets. A novel inter-topic Maximal Marginal Relevance step raises vocabulary diversity at little cost in coherence. Our code is available at this https URL.

AI 总结：本研究提出一种安全导向的行人轨迹预测框架，结合碰撞时间与穿越区域上下文，利用加权损失和池化LSTM，在inD数据集上显著降低预测误差及超限次数。

链接：https://arxiv.org/abs/2609.29706

作者：Erel Avineri, Yftach Gil, Yehudit Aperstein

英文摘要： Accurate pedestrian trajectory prediction is important for proactive road-safety applications, particularly at urban intersections where pedestrian motion is shaped by both vehicle interactions and crossing context. This study presents a safety-oriented trajectory-prediction framework that combines pedestrian motion history with Time-to-Collision (TTC) information and crossing-zone indicators. Using naturalistic trajectories from one urban intersection in the inD (Intersection Drone) dataset, several neural architectures were evaluated with 1.6 s observation and 2.4 s prediction horizons. A pooled Long Short-Term Memory (LSTM) separately encodes TTC histories and crossing-zone context before integrating them with pedestrian positions. In addition to conventional Average Displacement Error (ADE) and Final Displacement Error (FDE), prediction performance was assessed using the frequency and magnitude of errors exceeding a study-defined 1 m tolerance. A weighted loss was also introduced to place greater training emphasis on large coordinate-wise errors. Applying this loss to the position-only LSTM reduced ADE from 0.210 to 0.190 m and FDE from 0.550 to 0.503 m, while reducing ADE and FDE exceedance counts by 34.8% and 19.8%, respectively. The final pooled configuration incorporating TTC and crossing-zone information achieved an ADE of 0.184 m and FDE of 0.491 m, with further reductions of 33.5% and 6.3% in ADE and FDE exceedance counts relative to the safety-oriented position-only LSTM. The results indicate that safety-oriented training and structured integration of interaction and contextual information can reduce large trajectory-prediction errors, although broader validation across pedestrians, sites, and datasets is required.

AI 总结：提出物理信息自监督学习框架，联合校准多丝平行板雪崩计数器丝线增益并重建相互作用位置，无需标签数据，实验验证提升均匀性与分辨率。

链接：https://arxiv.org/abs/2609.28604

机构：GANIL, CEA/DRF - CNRS/IN2P3（GANIL，CEA/DRF - CNRS/IN2P3）

作者：Antoine Lemasson, Maurycy Rejmund

英文摘要：Scientific instruments require accurate calibration to convert detector signals into reliable physical observables. Conventional calibration procedures typically rely on dedicated calibration measurements, analytical response models or labelled reference data, limiting their ability to adapt to changing operating conditions and detector aging. We present a physics-informed self-supervised learning framework that jointly performs wire calibration and interaction position reconstruction in Multi-Wire Parallel Plate Avalanche Counters (MWPPACs) without requiring labelled position measurements or dedicated calibration runs. The method formulates detector calibration as a latent optimization problem in which global wire gains and event-wise interaction positions are estimated simultaneously using supervision derived exclusively from detector geometry and charge-energy consistency constraints. A detector-independent neural network reconstructs sub-wire interaction positions from local charge distributions, eliminating the need to assume analytical induction profiles by learning the detector response directly from experimental data. The end-to-end differentiable framework enables continuous detector self-calibration while improving the uniformity and accuracy of position reconstruction. Experimental evaluation on the entrance MWPPAC tracking detectors of the VAMOS++ magnetic spectrometer demonstrates stable convergence, improved spatial homogeneity and enhanced position resolution. Beyond the detector studied, the method establishes a general framework for physics-informed self-supervised calibration of scientific instruments and is a step toward autonomous intelligent instrumentation capable of continuous adaptation during operation. In this paradigm, detector calibration is no longer a prerequisite for an experiment but an integral part of the measurement process itself.

AI 总结：该文提出一种整合语义表示学习、图建模与时间演变的计算框架，从纵向文本中推断可解释的组织级语义身份，并以K-pop歌词语料验证其有效性。

链接：https://arxiv.org/abs/2609.29584

机构：Cardiff University（卡迪夫大学）； National Defence University（国防大学）

作者：Brinda Murali Krishna, Oktay Karakuş, Can Eyupoglu

英文摘要：Organisations continuously generate large volumes of textual data that capture how they communicate, evolve and differentiate themselves over time. Although recent advances in natural language processing have substantially improved organisation-level text analytics, existing approaches primarily represent organisations as latent embeddings or predictive feature vectors for similarity estimation, classification or retrieval. Consequently, there is currently no general computational framework for modelling organisation-level semantic identity as an interpretable and evolving semantic construct derived from longitudinal textual evidence. This paper introduces a computational framework that integrates semantic representation learning, graph-based semantic modelling, organisation-level semantic fingerprints, temporal semantic evolution and evidence-driven validation within a unified analytical methodology. Organisations are characterised through complementary semantic dimensions describing diversity, concentration, connectivity, novelty and semantic community composition, which are analysed longitudinally to infer evidence-supported semantic identities. The framework is demonstrated using a longitudinal corpus of K-pop lyrics from artists affiliated with the four major South Korean entertainment companies. The empirical analyses reveal distinguishable multidimensional semantic identities, diverse temporal evolutionary trajectories and coherent integrated identity profiles. Comprehensive validation demonstrates that the inferred identities are statistically supported, robust under alternative analytical assumptions, reproducible and operationally informative. Beyond the case study, the proposed framework establishes organisation-level semantic identity and provides a transferable methodology for modelling organisational behaviour from longitudinal textual data.

AI 总结：针对现有LBVS基准的缺陷，构建了覆盖93个靶标、含硬阴性诱饵的多目标基准TopU-LBVS，提供三种固定协议，并证明硬阴性筛选下基线性能显著下降。

链接：https://arxiv.org/abs/2609.29740

机构：UT Dallas（达拉斯德州大学）； National Institute of Biological Sciences（国家生物科学研究所）

作者：Surbhi Kumar, Yuhe Zhou, Varun Shiralkar, Niu Huang, Baris Coskunuzer

英文摘要： Ligand-based virtual screening (LBVS) is a practical first-pass tool in early-stage drug discovery, but existing benchmarks can overestimate performance through random negatives, easy decoys, limited target coverage, and non-standardized evaluation protocols. We introduce TopU-LBVS, a multi-target benchmark for LBVS under hard-negative screening conditions. Starting from curated ChEMBL~35 bioactivity data, TopU-LBVS covers 93 protein targets across 7 protein classes and constructs target-specific screening libraries with property-matched, structurally similar decoys at a fixed 1:40 active-to-decoy ratio. Libraries contain roughly 400 to 10,000 compounds and are designed to reduce simple physicochemical and nearest-neighbor fingerprint shortcuts. TopU-LBVS provides three fixed protocols. TopU-LBVS-full evaluates ChEMBL$^\ast \rightarrow$ TopU generalization across all 93 targets. TopU-LBVS-low evaluates low-data TopU $\rightarrow$ TopU learning within the hard-negative distribution. TopU-LBVS-mini provides a compact seven-target protocol with a paired random-decoy control that changes only the test decoys, enabling low-cost development and direct measurement of the gap between random ChEMBL$^\ast$ and TopU decoys. Across ten reference baselines spanning fingerprint methods, molecular GNNs, fingerprint hybrids, and modern molecular models, performance under random-decoy evaluation degrades sharply under hard-negative screening. We release data, fixed splits, evaluation code, and baseline implementations for reproducible comparison of future LBVS and molecular representation learning methods. Code and data are available at this https URL and this https URL.

AI 总结：提出AT-SKM-Net框架，通过混合采样与Cholesky更新，在动态图上实现线性硬约束可行性求解，迭代减少85%，加速2.95-7.29倍，零违规。

链接：https://arxiv.org/abs/2609.30088

机构：Zhejiang University（浙江大学）

作者：Xiaochen Zhang, Haoyu Zhu, Yao Zhang, Qingchun Hou

英文摘要：Graph-structured optimization with linear constraints is fundamental to critical infrastructure but faces scalability limits due to massive strict hard constraints and high dimensionality. While recent projection-based methods such as Trainable Sampling Kaczmarz-Motzkin Net (T-SKM-Net) guarantee feasibility, they face high computational costs in dynamic environments by processing the entire constraint set and requiring expensive matrix factorizations. To bridge this gap, we propose the Accelerated Trainable-SKM (AT-SKM) Net framework. To concentrate computation on the active constraints and eliminate redundant calculations, we introduce a hybrid sampling strategy guided by a topology-aware heterogeneous GNN model. To efficiently handle topological shifts in graph-based constraints, we employ a Cholesky Update mechanism that theoretically reduces the equality projection complexity from O(N^3) to O(N^2) under low-rank perturbations. Experiments on random geometric graphs, N-1 Security-Constrained DC-OPF, and minimum-cost gas transport problem demonstrate that AT-SKM reduces iteration counts by up to 85% and achieves 2.95x-7.29x SKM layer speedups, while maintaining zero constraint violations.

AI 总结：本文提出将强化学习策略的可审计性分解为六个可测试属性，通过规则提取与组合协议验证，发现规则重叠不保证行为一致，融合策略仅选择现有规则而非生成新技能。

链接：https://arxiv.org/abs/2609.28581

机构：PARRAWA AI

作者：Liu Hung Ming

英文摘要：Reinforcement-learning (RL) policies are often distributed as opaque neural checkpoints, while training logs show that a run occurred without explaining what the policy learned. We study whether independently trained policies can be represented and composed through auditable discrete behavioral rules. We define auditability as six separately testable predicates: trace integrity, lossless coding, rule coverage, behavioral agreement, composition quality, and value-model reliability. Our protocol uses a shared frozen symbolizer, passive rule extraction, an append-only hash-bound ledger, exact environment replay, and offline confidence-ranked arbitration with an explicit blind-spot fallback. The results place strict limits on this description layer. Rule-set overlap does not imply behavioral agreement: policies may share symbolic rules while choosing near-chance-matching actions on fresh states. The fused policy therefore selects among existing rules rather than generating a new skill. On a conflict-dominated task, an apparent fusion failure is traced to an induction/deployment mismatch: rules induced from sampled actions were evaluated under argmax actions, and deployment-consistent re-induction reverses the arbitration ordering. A fitted-Q generalized-policy-improvement diagnostic also fails in both environments, limiting claims that rule fusion is superior to value-based composition. One exploratory comparison favors rule fusion, but its comparator is post hoc, the task is partly saturated, and the fused policy remains below the strongest held-out actor. We contribute an evidence-bounded audit and composition protocol, not a claim of universal interpretability or autonomous skill generation. Future work must add temporally extended skills, cross-skill interfaces, composition search, and independent novelty audits.

AI 总结：本研究通过自旋玻璃理论证明，在迭代乘法等算法任务上，RLVR的优化景观是良性的，实际困难源于扩散障碍和梯度估计误差，可通过熵正则化缓解，且Transformer能成功学习此类任务。

链接：https://arxiv.org/abs/2609.28625

机构：Racah Institute of Physics（拉卡物理研究所）； The Hebrew University of Jerusalem（耶路撒冷希伯来大学）

作者：Noa Rubin, Zohar Ringel

英文摘要： Despite the importance of reinforcement learning with verifiable rewards (RLVR), the extent to which it can learn new reasoning capabilities remains debated. Here we study the optimization landscape of RLVR on algorithmic tasks, such as iterated group and quasigroup multiplication. To this end, we map entropy-regularized RLVR over myopic tabular policies onto an energy-based (spin-glass) model over deterministic policies. This mapping upper-bounds what RLVR can achieve, and lets us rigorously characterize the landscape in this tabular setting. We show, both theoretically and experimentally, that for a wide class of models and tasks with uncorrelated inputs, this landscape is benign, containing no local minima that could trap RLVR training. Rather, the practical difficulty of these tasks appears to stem, at least in part, from issues such as diffusive barriers and gradient-estimation error in traversing the landscape. These are genuine obstacles that can prevent a solution from being found, but they are distinct from the landscape itself being rugged. We show that these obstacles can often be mitigated through the choice of entropy regulator. Consistent with this theory, we find that a transformer trained from scratch, using only last-token rewards, successfully learns an algorithmic chain of thought for iterated non-Abelian group multiplications.

AI 总结：本文提出MI-SARSA算法，通过互信息正则化在强化学习中引入认知约束，实现策略复杂度与反应时间的权衡，并揭示鲁棒性与容量的权衡，为有界理性下的序列学习提供模型。

链接：https://arxiv.org/abs/2609.28737

作者：James Wu, Chris R. Sims

英文摘要：Biological agents do not learn under conditions of unlimited computation. For humans, learning and choice are shaped by constraints on perception, attention, and working memory, which limit how much state information guides behavior and therefore bound policy complexity. Standard reinforcement learning models typically optimize reward without explicitly representing these internal costs, making them less suitable as models of biological intelligence. We derive MI-SARSA, an on-policy temporal-difference algorithm that incorporates mutual-information regularization through a learned marginal action prior and a penalty on state-specific deviations from that prior. This yields a sequential learning model in which state information is used selectively when its expected return benefit justifies the added informational cost. Critically, the same state-specific information cost that governs policy compression also generates trial-level predictions for reaction time, distinguishing MI-SARSA from most reinforcement learning models, which predict choices or returns but not latency. Empirically, MI-SARSA produces a reward-complexity tradeoff, and stronger information penalties produce simpler policies with lower control costs and faster reaction times. Under environment shift, increasing regularization reduces post-switch performance degradation but also lowers asymptotic return, revealing a robustness-capacity tradeoff. Together, these results position MI-SARSA as a model of bounded sequential learning under cognitive constraints.

AI 总结：本文提出多链鲁棒平均奖励MDP的向量贝尔曼理论，通过增益-偏差系统求解状态依赖的最优鲁棒奖励，并设计近似移位Halpern算法实现有限收敛。

链接：https://arxiv.org/abs/2609.28792

机构：University of Central Florida（中佛罗里达大学）

作者：Yue Wang, George Atia

英文摘要：Robust average-reward Markov decision processes provide a fundamental framework for long-term performance optimization under uncertainty, and can have optimal long-run rewards that depend on the initial state. This state dependence requires a vector Bellman theory that accounts for both recurrent-class rewards and transition uncertainty. We develop such a theory for finite models with compact, post-action $(s,a)$-rectangular ambiguity. A gain-first, bias-second optimization principle yields a coupled vector gain-bias system, and every finite solution identifies the optimal robust gain and supplies stationary saddle strategies against history-dependent opponents, simultaneously from all initial states. We further characterize solvability through stationary gain conditions and a uniform bound on canonical transient corrections, and give sufficient conditions that permit distinct recurrent-class gains. The certificates also yield asymptotically affine trajectories of the robust Bellman operator, based on which we design a robust approximately shifted Halpern planning algorithm. Under finite Bellman solvability, the gain estimates and Bellman displacements converge to the optimal gain vector, and every extracted greedy controller is average-optimal after a finite, instance-dependent budget. These results thus connect finite Bellman certificates to undiscounted planning for state-dependent robust average rewards, providing theoretical understandings.

AI 总结：针对机器人部署后混合质量经验利用问题，提出预测性动作块学习（PACL），通过块级评论家与未来预测增强价值估计，并指导扩散演员学习，实验证明其优于现有基线。

链接：https://arxiv.org/abs/2609.29000

机构：Nanyang Technological University（南洋理工大学）； Chongqing Changan Automobile Co., Ltd（重庆长安汽车股份有限公司）； Guangzhou Cloudbutterfly Technology Co., Ltd.（广州云蝶科技有限公司）

作者：Yangang Ren, Yujie Yan, Zirui Li, Jiaming Guo, Di Zeng, Ji Tao, Lan Yu, Xuesong Tian, Chen Lv

英文摘要：Robot policies deployed in real environments naturally accumulate mixed-quality experience, including successful executions, partial progress, and failures. Although these rollouts provide valuable information for further learning, directly incorporating them into imitation learning may reinforce undesirable behaviors, while offline reinforcement learning often suffers from unreliable value estimation under sparse rewards and limited data coverage. We consider a practical post-deployment setting where learning relies only on naturally accumulated autonomous rollouts, without additional human corrections or exploratory interaction. To effectively exploit such experience, we propose Predictive Action Chunk Learning (PACL). PACL first learns a predictive chunk-level critic that evaluates temporally extended action sequences and augments temporal difference learning with future latent prediction, providing richer supervision for long-horizon value estimation. The learned critic then converts chunk-level Q-values into discrete quality conditions, which guide a diffusion actor to learn jointly from these mixed-quality experiences without treating all behaviors as equivalent supervision. At inference, the actor generates multiple action chunks and the critic selects the highest valued candidate. Experiments across simulated and real-world robot manipulation tasks show that PACL consistently improves the pretrained policy and outperforms strong imitation learning and offline reinforcement learning baselines.

AI 总结：本文针对长期平均奖励设置下的双时间尺度actor-critic算法，推导了均匀全时浓度界，证明actor参数以高概率进入并保持在安全区域，误差随更新次数减小。

链接：https://arxiv.org/abs/2609.29117

机构：IISc Bangalore（印度科学研究所班加罗尔）

作者：Prashansa Panda, Shalabh Bhatnagar

英文摘要：Significant research effort has been directed in recent years towards establishing both asymptotic and non-asymptotic convergence guarantees for two-timescale actor--critic algorithms, where the actor recursion is run on a slower timescale than the critic recursion. This work derives a uniform all-time concentration bound for the actor--critic algorithm with function approximation in the long-run average-reward setting. This bound helps us analyze the behavior of the actor parameter with high probability. We show that, after some finite time, the actor parameter enters a safe region and remains within it thereafter with high probability. Specifically, with probability at least $1-\epsilon_1-\epsilon_2$, the actor error $\Vert \theta_k-\theta^{*}\Vert$ is $O\left(\frac{n_0^{3/4}}{k}\frac{1}{\sqrt{\epsilon_2}}+\left(\frac{1}{n_0}\right)^{1/4}\log^{1/4}\left(\frac{1}{\epsilon_1}\right)+\left(\frac{1}{n_0}\right)^{1/4}\right)$ for all $k\geq n_0$ and sufficiently large $n_0$. We also present experimental results demonstrating that the aforementioned actor error diminishes with the number of actor-parameter updates.

AI 总结：针对Direct-OPD中低散度状态监督无效的问题，提出选择性监督方法S$^2$D-OPD，仅保留前10%高散度状态进行蒸馏，在多个模型和基准上提升准确率且无需额外计算。

链接：https://arxiv.org/abs/2609.29142

机构：East China Normal University（华东师范大学）； Hugging Face

作者：Yibo Zhao, Zixuan Yang, Yunshi Lan, Xiang Li

英文摘要：Direct On-Policy Distillation (Direct-OPD) transfers reinforcement-learning-induced policy improvements from a small model to a larger student by using the token-level log-ratio between post-RL and pre-RL checkpoints as dense supervision on the student's own rollouts. This transfer rewards the policy shift at every state, yet the log-ratio measures only relative change: it can stay fixed even as the probability mass that both checkpoints assign to the student's candidate tokens vanishes. Through an exact construction, we show that the Direct-OPD reward and its update can remain unchanged while the Jensen-Shannon divergence (JSD) and both KL directions between the checkpoints vanish with this mass, and we note that a small JSD bounds how much the teacher's behavior changed. Motivated by this analysis, we propose Selective Supervision for Direct-OPD (S$^2$D-OPD), which ranks student-sampled states by their teacher-reference JSD and masks Direct-OPD supervision at low-divergence states, retaining only the top 10% of states per response. Across two teacher pairs and four student models ranging from 1.7B to 8B parameters, S$^2$D-OPD improves held-out accuracy over dense Direct-OPD on AIME and HMMT benchmarks in seven of eight settings and matches it in the eighth, without extra forward passes. Our code is available at this https URL.

AI 总结：本研究提出一种基于预测价值下界和动作证书的成本感知建议门控方法，在BabyAI上以显著减少的查询次数提升了回报，但逐状态优势未获充分验证。

链接：https://arxiv.org/abs/2609.29548

机构：Iowa State University（爱荷华州立大学）； Standard Chartered, Bangladesh（渣打银行（孟加拉国））； BRAC University（BRAC大学）

作者：Ibne Farabi Shihab, Md Najmus Swaqeeb, Abu Sa-Adat Mohamed Moon-Im Al Ahsan

英文摘要：Language-model advice can accelerate reinforcement learning, but calls are costly and returned actions may be stale or wrong. We formulate advice acquisition as a response-contingent metareasoning problem: before querying, the controller predicts possible parsed responses, evaluates the decision and declared continuation that would follow each response, and queries only when a lower confidence bound on predictive value exceeds the priced cost. Execution is governed separately by an action-specific certificate. Under explicit assumptions, certified advice is near-optimal, a wrapped learner inherits fallback regret only under intervention stability, and conservative allocation loses at most the declared query-value estimation error relative to a myopic oracle. On BabyAI, a proxy-calibrated controller with Qwen2.5-1.5B and 7B advisors improves GoToObj return over no querying by 0.029 +/- 0.016 and 0.030 +/- 0.015 across 20 seeds while reducing calls by more than 97% relative to always-query. GoToLocal is a null result. Exactly matched-call tests show an advantage over random placement only for the 1.5B advisor and no advantage over an equal-budget early schedule. Mondrian calibration improves decision-relevant empirical coverage from 0.47 to 0.85, still below the 0.90 target, while the formally covered radius is vacuous. The demonstrated benefit is therefore robust sparse advice volume on a useful task, not a proven per-state placement advantage.

AI 总结：针对多保真度树优化问题，提出CANOPY方法，通过在线学习分段平滑先验的有效区域，引导昂贵评估，在多种推理任务中显著提升性能。

链接：https://arxiv.org/abs/2609.30017

机构：Amazon（亚马逊）； Columbia University（哥伦比亚大学）

作者：Michael Jerge, Suman Jana

英文摘要：Many LLM inference problems, including model routing, prefix-cache management, prompt trimming, and test-time search, can be viewed as optimization over a tree. This structure arises naturally from autoregressive generation: every prefix defines a node, and its continuations form a subtree below it. Internal nodes of the tree provide cheap but biased estimates of a region's value, while leaf evaluations are expensive but accurate. Hierarchical bandit methods can exploit this structure, but typically require a specific smoothness schedule to be specified in advance, even though real objectives are often only piecewise smooth and their optima may lie near sharp boundaries. We introduce CANOPY, a multi-fidelity tree bandit that learns where the smoothness prior is valid rather than assuming it globally. CANOPY uses cheap random-path probes to construct an online certificate of local aggregation bias, then directs expensive leaf evaluations toward cells where the certificate detects a smoothness violation. We prove fixed-budget and regret guarantees whose additional cost is additive in the number of discontinuities, recovering the smooth-tree rate when no violations are present and approaching structure-blind search as violations become dense. Across routing, top-$k$ identification, test-time search, caching, and prompt trimming, CANOPY consistently improves matched-budget performance, including $2.9\times$ higher top-10 recall on a 1000-model pool, $1.6\times$ more SWE-bench Verified issues resolved than best-of-$N$, and $3.6\times$ lower median time-to-first-token with prefix caching.

AI 总结：针对大规模铁路网络管理，提出结合图推理与拓扑感知多智能体强化学习框架，实现零样本迁移，显著优于现有基线。

链接：https://arxiv.org/abs/2609.30150

机构：ETH Zürich（苏黎世联邦理工学院）； University of Oxford（牛津大学）； The Pennsylvania State University（宾夕法尼亚州立大学）； Technical University of Munich（慕尼黑工业大学）

作者：Giacomo Arcieri, Gregory Duthé, Christophe Muller, Konstantinos G. Papakonstantinou, Daniel Straub, Eleni Chatzi

英文摘要：Modern infrastructure asset management constitutes a complex sequential decision-making problem, characterized by long planning horizons and system-level interactions, such as spatial deterioration correlations and economies of scale. While deep reinforcement learning has shown promise in optimizing maintenance policies, scaling to real-world networks remains challenging. Centralized approaches become computationally intractable in large-scale systems, whereas decentralized approaches often fail to capture essential coordination mechanisms. To address these challenges, we propose a graph-based framework that integrates accurate environment modeling with scalable decision support. First, we employ a hierarchical Bayesian model leveraging a Gaussian Process on Graph kernel to infer a realistic, spatially correlated networked environment of railway maintenance planning from real-world data provided by the Swiss Federal Railways. Second, we introduce a topology-aware Multi-Agent Reinforcement Learning (MARL) framework by integrating graph neural networks and graph Transformers to optimize network-level policies. A central contribution of this work is the demonstration of scalability through zero-shot transfer learning: graph-based agents, trained only on small network portions, are successfully deployed in a zero-shot manner on large-scale unseen networks without any retraining. Numerical results indicate that the proposed method significantly outperforms optimized heuristics and standard MARL baselines, reducing computational training time while maintaining superior performance on large-scale networks.

AI 总结：PoEM框架利用现有策略预测新奖励函数下的强化学习结果，无需额外RL训练，通过线性组合对数策略实现，并在文本和图像任务上验证有效。

链接：https://arxiv.org/abs/2609.30226

机构：MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）

作者：Kimia Hamidieh, Giannis Daras, Antonio Torralba

英文摘要：Foundation models are post-trained with reinforcement learning (RL) to maximize specific rewards, such as human alignment, correctness, or instruction following. This post-training process is computationally intensive, sometimes unstable, and has to be run from scratch every time the reward model changes or when we want to combine multiple rewards. We hence ask: given a new reward function, is it possible to predict the RL outcomes without actually running RL on it? We answer this in the affirmative by introducing PoEM, a framework to predict the outputs of RL on a new reward function using a set of models already post-trained on other rewards. First, we show that if the new reward function can be written as a linear combination of existing ones, then the new policy in log-space can be written as a linear combination of the existing log-policies. Surprisingly, even in cases where the rewards are not linearly connected, we observe that often log-policies from RL training span an approximately low-rank subspace across rewards. To our benefit, the weighting coefficients for this combination can be estimated using only the reward or basis policy outputs on the samples. We turn these observations into an algorithm that takes post-trained models and a new reward function, and approximates the target RL policy without actually running any additional RL training. We experimentally validate our approach across synthetic and real rewards, spanning both text and image modalities.

AI 总结：针对具身强化学习分布式训练，提出TRACE时间梯度反演攻击，利用跨时间相关性与闭式动作恢复，自回归重建私有轨迹，实现高PSNR与近完美动作恢复，且速度远超基线。

链接：https://arxiv.org/abs/2609.30258

机构：University of Kentucky（肯塔基大学）； Washington University in St. Louis（圣路易斯华盛顿大学）

作者：Sudip Bhujel, Shanghao Shi, Ruiquan Huang, Ning Zhang, Yang Xiao

英文摘要：Distributed learning in embodied reinforcement-learning agents offers a degree of privacy by retaining raw sensor data on-device and transmitting only policy gradients to the server. Yet temporal structure can amplify this leakage beyond single-frame attacks. We introduce Temporal Reconstruction Attack on Consecutive Encodings (TRACE), an amortized temporal gradient-inversion attack that autoregressively reconstructs the sequence of private observation-action trajectories from per-step policy-learning gradients. The attack exploits two structural signals ignored by prior single-frame methods: (i) cross-time correlation between successive embodied gradients, which we formalize via a conditional mutual-information bound, and (ii) closed-form action recovery from policy-head gradient structure, which we prove exact when standard entropy regularization is sufficiently small. On held-out embodied scenes, TRACE reaches $18.8$ dB PSNR with near-perfect action recovery at $3$-$4.5$ ms per reconstructed frame, dominating the learning-based baseline across all reconstruction metrics and exceeding optimization attacks while running orders of magnitude faster. Further evaluation demonstrates TRACE's broader applicability across recurrent, residual, and compact transformer victim architectures, multi-modal inputs, and larger discrete action spaces. Defense experiments suggest that protecting temporal gradient streams may require sequence-aware privacy mechanisms.

AI 总结：提出基于VAE潜空间自适应的非侵入式修正方法，利用166个CFD场训练VAE和12个配对工况训练低秩适配器，将压气机叶栅开口叶尖间隙流动的CFD误差显著降低（MAE从0.1335降至0.0473）。

链接：https://arxiv.org/abs/2609.28558

机构：School of Aeronautics and Astronautics, Shanghai Jiao Tong University（上海交通大学航空航天学院）； Global Institute of Future Technology, Shanghai Jiao Tong University（上海交通大学未来技术学院）

作者：Xiang Zuo, Hefang Deng, Caiyan Chen, Honglin He, Mingmin Zhu, Songan Zhang, Jinfang Teng

英文摘要：CFD predictions of open tip clearance flow in compressor cascades are subject to discrepancies relative to experiments, while experimental observations are sparse and high-resolution experimental ground truth is unavailable. This study proposes a non-intrusive correction method based on a variational autoencoder (VAE) and latent-space adaptation. A VAE is first trained using a dataset of 166 parametrically sampled CFD total pressure loss fields to learn a low-dimensional statistical representation of these fields. The VAE is then frozen, and a low-rank latent-space adapter is trained using only 12 paired CFD--experiment operating conditions. An observation operator maps the corrected high-resolution fields to the experimental observation space, allowing supervision to be applied only at the available measurement locations and within the measured pitchwise windows. In the current 12-fold cross-validation, the mean absolute error decreases from 0.1335 to 0.0473, the root mean square error from 0.1717 to 0.0621, and the relative $L_2$ error from 0.5108 to 0.1871. These results indicate that the method improves agreement between CFD predictions and sparse experimental observations of open tip clearance flow without modifying the RANS solver or constructing artificial high-resolution experimental labels.

AI 总结：针对扩散模型正则化忽视条件信号的问题，提出条件感知表示正则化框架CARE，动态调节特征分布，在ImageNet和文本到图像任务中显著降低FID并提升训练效率。

链接：https://arxiv.org/abs/2609.28561

机构：Tsinghua University（清华大学）

作者：Fengjia Guo, Zhuoyi Yang, Jie Tang

英文摘要：Recent advances in diffusion models highlight the importance of representation regularization for improving sample quality and training efficiency. However, commonly used regularization methods often overlook the built-in conditions (such as labels or texts) which directly determine the generation target. In this work, we demonstrate how conditioning signals affect the feature distribution and introduce the CARE (Condition-Aware REpresentation regularization). CARE is a lightweight plug-and-play regularization framework that dynamically modulates feature distribution based on condition similarity. CARE leverages built-in conditioning signals to judiciously guide the representation space, promoting tighter feature clusters for similar conditions without relying on explicit alignment losses or external supervision. Empirically, CARE consistently improves both visual fidelity and convergence stability across both class-to-image and text-to-image tasks. On ImageNet, CARE achieves a 19.08\% reduction in FID in 400k training steps, leading to a 3.5$\times$ speed-up. When applied to text-to-image generation, CARE lowers FID by 16.61\% in 200k iterations and improves semantic alignment between generated samples and text prompts. Moreover, CARE can be seamlessly integrated with existing regularization methods, yielding additional performance gains.

AI 总结：本研究基于小波扩散模型评估降水降尺度的跨区域泛化能力，发现全区域训练模型性能最佳，且样本级空间自相关与检测性能高度相关，支持向数据稀缺区域迁移。

链接：https://arxiv.org/abs/2609.28749

作者：Weikang Qian, Yixin Wen, Chugang Yi, Zhi Li, Lingcheng Li, Haizhao Yang

英文摘要：Diffusion models have shown strong potential for kilometer-scale precipitation downscaling, but their performance in geographically unseen regions and event regimes remains insufficiently understood. Building on the wavelet diffusion model (WDM) framework, this study evaluates cross-region and cross-event generalization. Six 3 x 3 deg U.S. regions represent convective, winter, tropical, and atmospheric-river precipitation regimes. Low-resolution inputs are generated by block averaging NOAA Multi-Radar/Multi-Sensor (MRMS) composite reflectivity fields. A WDM trained only on Oklahoma (OK) samples and a WDM trained on all six regions are compared with nearest-neighbor and Bicubic interpolation. Model performance is evaluated using three metric families that measure image-domain reconstruction, spectral and distributional fidelity, and bin-wise precipitation detection. The OK-trained WDM remains competitive outside OK. Although the all-region WDM delivers the best and most consistent overall image-domain and detection performance, its gains are uneven across precipitation intensities. Bin-wise critical success index (CSI) over 5-dBZ reflectivity bins shows that WDM improvements concentrate in localized higher-reflectivity structures, which image-domain metrics partly obscure. In addition, the performance differences among samples are strongly associated with the spatial organization of the precipitation field, quantified by Moran's I as the spatial autocorrelation of each reflectivity bin. The sample-level Moran's I-CSI correlation stratified by sample intensity reaches 0.901 in all six regions, including regions unseen during training. Overall, these findings support future efforts to transfer downscaling models to regions with limited local training data and to generate globally consistent, high-resolution precipitation products.

AI 总结：针对大气观测稀疏异构的问题，提出可组合观测接口，使预训练扩散模型融合无线电探空仪、飞机和地面站数据，实现生成式超分辨率重建，显著降低RMSE和CRPS，无需重新训练模型。

链接：https://arxiv.org/abs/2609.29027

机构：Purdue University（普渡大学）； The Pennsylvania State University（宾夕法尼亚州立大学）

作者：Yang Xu, Dibyajyoti Chakraborty, Haiwen Guan, Sen Wang, Romit Maulik

英文摘要： Atmospheric observations are sparse, heterogeneous, and unevenly distributed, whereas many generative atmospheric models learn distributions over regularly gridded multivariate states. Once pretrained, diffusion models can supply atmospheric priors that can be combined with observation-derived likelihood factors in a Bayesian formulation. However, these observation sources differ substantially in geometry and sampling density, complicating the consistent use of their observations within a common inference framework. Here, we formulate this reconstruction problem as generative atmospheric super-resolution and introduce composable observation interfaces for conditioning a single pretrained 13-variable atmospheric diffusion model. The interfaces convert sparse radiosonde (R), clustered aircraft (A), and dense irregular surface-station (S) observations into source-specific likelihood factors that specify where observations constrain the gridded state, how residuals are counted under uneven sampling, and how strongly each source guides posterior sampling. We developed the aircraft and surface observation interfaces using 2019 observations and evaluated the selected interfaces throughout 2020 without further tuning. Compared with reconstructions conditioned only on radiosonde observations, the composed R+A+S interface reduces RMSE evaluated against ERA5 by $9.24\%$ across all 13 state variables over the CONUS domain. The aircraft and surface factors provide complementary improvements in upper-air and surface variables. The R+A+S combination also lowers the Continuous Ranked Probability Score (CRPS), while evaluations at held-out aircraft and surface-station observations show reduced prediction errors. Together, these results demonstrate a modular route for conditioning a pretrained atmospheric generative prior on heterogeneous in situ observations without retraining the underlying model.

AI 总结：FB-GDM提出全贝叶斯引导扩散模型，通过变分推断自动学习精度参数，无需噪声水平或真实值校准，在高维线性逆问题中性能优于DPS和$\Pi$GDM，并具备跨任务鲁棒性。

链接：https://arxiv.org/abs/2609.29216

作者：Gatien Séguy, Thomas Rodet (SATIE)

英文摘要：Diffusion models are powerful priors for linear inverse problems, but the reference guidance methods, Diffusion Posterior Sampling (DPS) and Pseudoinverse-Guided Diffusion Models ($\Pi$GDM), rely on scalar hyperparameters tuned per task, usually against the ground truth. We introduce FB-GDM, a fully-Bayesian guided diffusion method that removes this calibration step. Starting from the Gaussian approximation of $\Pi$GDM, we derive a closed-form conditional score that depends on two precision parameters (inverse variances), one associated with the denoising approximation and one with the observation likelihood, and treat them as latent variables inferred by variational inference at each reverse step. A separable factorization makes each update scale linearly with the number of pixels, so the inference stays tractable at full image resolution, at a cost comparable to one $\Pi$GDM run. FB-GDM requires neither the noise level nor the ground truth: its only inputs are the observation and the forward operator. Experiments on CelebA-HQ inverse problems establish two results. (i) The precision parameters, inferred from the observation alone, allow FB-GDM to outperform $\Pi$GDM at its nominal setting, even when the latter is given the true noise level, by up to 14 dB depending on the operator, and to match the ground-truth-calibrated $\Pi$GDM oracle within 0.1 dB. (ii) FB-GDM is robust when the forward operator, the noise level, or the image distribution changes: it stays close to a per-problem $\Pi$GDM oracle throughout and does not exhibit the hallucinations observed with DPS, whereas DPS substantially degrades at a fixed scale and $\Pi$GDM stays competitive only if it is re-tuned against the ground truth for each new problem. When the prior is applied to images outside its training set, this re-balancing between data and prior keeps FB-GDM faithful where a fixed face-prior guidance can otherwise hallucinate.

AI 总结：提出神经传输嵌套采样（NTNS），结合嵌套采样与神经流，高效估计高维分子系统配分函数，在Lennard-Jones簇基准上显著降低误差并恢复相结构。

链接：https://arxiv.org/abs/2609.29413

机构：Kavli Institute for Cosmology Cambridge（剑桥卡夫利宇宙学研究所）； Institute of Astronomy, University of Cambridge（剑桥大学天文研究所）

作者：David Yallup, Will Handley

英文摘要：Sampling from Boltzmann distributions of molecular systems is an inference problem that has seen significant recent developments fuelled by advances in neural density estimation. We develop a novel sampling algorithm, Neural Transport Nested Sampling (NTNS), which combines the classical strengths of nested sampling with modern neural flow-based methods. NTNS uses a flow matching velocity as the drift in a Metropolis--Hastings corrected Langevin kernel inside a nested sampling outer loop, requiring only evaluations of the target energy function and providing scalable estimation of the full partition function of high-dimensional particle systems. We benchmark NTNS on challenging molecular sampling benchmarks, scaling up to Lennard--Jones clusters of 55 interacting particles, where it reduces both interatomic distance and energy Wasserstein errors to reference MCMC by over an order of magnitude relative to the strongest neural baselines at lower wall-clock cost. To our knowledge, NTNS is also the first neural sampler to return a calibrated, temperature resolved partition function estimate at this scale, recovering the phase structure across temperature from a single run.

AI 总结：该研究提出广义图变分自编码器（GGVA），用Rényi-Tsallis散度族替换KL散度，证明有界性是控制后验坍缩的关键，在多个图上显著提升保留信息量，但未改善链路预测准确性。

链接：https://arxiv.org/abs/2609.29546

机构：UCL（伦敦大学学院）； Holistic AI； University of Utah（犹他大学）； PUC-Rio（里约热内卢天主教大学）

作者：Kleyton da Costa, Bernardo Modenesi, Ivan F.M. Menezes, Helio Lopes

英文摘要：The variational graph autoencoder (VGAE) regularizes its posterior toward the prior with the Kullback-Leibler divergence, a choice inherited from the variational autoencoder rather than argued for. We introduce the generalized graph variational autoencoder (GGVA), which replaces that term with any member of the Rényi-Tsallis family of order $q$ while leaving every other part of the model untouched. Both members admit closed forms for diagonal Gaussians and both recover the KL exactly as $q \to 1$, so the VGAE is the $q=1$ arm of our own model rather than a separate baseline, and any measured difference is attributable to a single scalar. Our analysis identifies boundedness, not the order, as the operative property: for $q<1$ the Tsallis divergence is bounded above by $1/(1-q)$, independently of the latent width, whereas the KL and the Rényi divergence of the same order are unbounded. On ten graphs spanning three synthetic families, a social network, three citation networks, a connectome, a power grid and a road network, $q$ moves the retained posterior information by up to $49\times$ relative to the VGAE, while the Rényi arm at the same order stays within $1.02$-$1.30\times$ of it on all six larger real graphs (isolating the bound as the cause). The retained information is usable: probing the frozen embedding for node class, a label absent from the objective, gives GGVA up to $+0.14$ macro-F1 over the VGAE on CiteSeer, with the Rényi control again tracking the VGAE. We also report what the design was built to expose: none of this reaches held-out link-prediction accuracy on any of the six larger real graphs, and boundedness delays posterior collapse rather than preventing it.

AI 总结：针对自动驾驶碰撞伤害严重性预测中数据不平衡与合成样本可信度不足的问题，提出专家委员会审计筛选（ECAS）框架，通过多维审计与帕累托筛选提升少数类样本质量，显著改善预测性能。

链接：https://arxiv.org/abs/2609.29687

作者：Zewei Li, Qiaoqiao Ren, Hang Yang, S.C. Wong, Stergios-Aristoteles Mitoulis, Yun Ye

英文摘要：Automated driving systems (ADSs) are increasingly operating on public roads, raising safety concerns, yet reliable prediction of crash injury severity remains difficult because crash reports are limited, severe outcomes are rare, and injury classes are highly imbalanced. Existing augmentation methods mainly increase minority-class sample size but rarely assess whether generated samples are credible for safety-critical prediction. This study proposes Expert-Committee Audit Screening (ECAS), a credibility-aware sample acceptance framework for ADS crash injury severity prediction under data imbalance. Using 1,477 incident-level ADS crashes from the National Highway Traffic Safety Administration Standing General Order records, ECAS audits generated minority samples through a real-data-only expert committee based on label support, boundary separation, committee agreement, and local plausibility. Within-class percentile normalization and Pareto non-dominated sorting select accepted samples without manually assigned evidence weights. With a fixed backbone combining normalizing flow augmentation and a Tabular Prior-data Fitted Network (TabPFN) classifier, the best ECAS configuration achieved the highest balanced accuracy, macro-F1, and minor-injury recall among all evidence configurations. Local neighborhood analysis showed that ECAS-accepted samples were better supported by nearby real minority crashes than unscreened retained samples. Shapley additive explanations and partial dependence plots further indicated that lower injury severity classes were mainly associated with crash counterpart and pre-crash movement, whereas moderate-plus injuries were more sensitive to posted speed limit and operating context. These findings support a shift from quantity-oriented augmentation to credibility-aware sample acceptance for ADS safety prediction and risk governance.

AI 总结：针对馈线生成需满足电气与辐射状规则的问题，提出约束引导扩散模型PG-DiGress，通过软掩码注入约束，将严格通过率从13.7%提升至96.8%。

链接：https://arxiv.org/abs/2609.29879

机构：National Laboratory of the Rockies（落基山国家实验室）

作者：Yu Qin, Andrew Glaws, Aadil Latif, Ryan King

英文摘要：Generative modeling approaches often focus on recovering broad statistical characteristics from the training data. In the context of graph generation, this may refer to degree distributions, clustering coefficients, or spectral properties. However, generating usable distribution feeders when detailed feeder models are unavailable requires more than matching generic graph statistics: the sampled topology must also obey electrical compatibility and radiality rules. We therefore formulate feeder synthesis as a constraint-guided graph generation problem and propose the Power-Grid-constrained Discrete Denoising Diffusion model, PG-DiGress, which learns categorical node and edge patterns from feeder data, while respecting domain-specific rules. Specifically, it injects feeder constraints into the reverse diffusion process through soft masks that suppress incompatible edge classes during denoising, followed by a final projection step that rebuilds a connected, rule-compliant feeder graph. We evaluate PG-DiGress using graph-distribution similarity, feeder-rule satisfaction, structural validity, and downstream model construction. Compared with the unconstrained baseline, PG-DiGress increases the strict feeder pass rate from 13.7% to 96.8%. We also successfully convert the generated graphs into executable feeder models for downstream analysis.

AI 总结：本研究提出残差相关性诊断指标D_logdet，用于预测多输出高斯过程协同区域化在联合不确定性量化中的增益，并据此提出Residual-ICM模型，在16个基准上验证了其有效性。

链接：https://arxiv.org/abs/2609.30085

机构：Eindhoven University of Technology（埃因霍温理工大学）

作者：Fangqin Zhou, Joaquin Vanschoren

英文摘要：In multi-target regression, correlated targets are often coupled through multi-output Gaussian processes with an intrinsic model of coregionalisation (GP-ICM), assuming that sharing statistical strength improves overall performance. In practice, the benefits are inconsistent. Across the settings studied, we find that the main benefit of coregionalisation is joint uncertainty quantification rather than point prediction. Raw target correlation does not predict when coupling helps; in the separable GP-ICM settings studied here, residual correlation, the cross-target dependence left unexplained by independent per-target predictors, is the strongest predictor of joint-uncertainty gains. We introduce a lightweight diagnostic, $D_{\rm logdet}=-\frac{1}{2}\log\det R_{\rm res}$, which represents the idealised joint negative log-likelihood (NLL) gain from modelling a full rather than diagonal residual covariance and is computable from independent GPs alone. Across a controlled synthetic study, 16 multi-target benchmarks, and frozen transformer and convolutional neural network representations for keypoint regression, point prediction remains largely unchanged ($\Delta R^2\approx 0$). In contrast, $D_{\rm logdet}$ strongly predicts observed ICM NLL improvements ($\rho_s=-0.83$, $p<0.001$), outperforming heuristics such as the feature-to-sample ratio. We also propose Residual-ICM, which preserves independent marginal variances while adding residual-correlation structure to the joint covariance. Residual-ICM achieves the best average joint NLL among the compared methods, while the diagnostic indicates when covariance coupling is likely to be useful. The diagnostic is specific to global Gaussian residual dependence, the structure captured by separable coregionalisation.

AI 总结：OPDiv 通过整数优化在虚拟筛选中平衡评分与多样性，实现 top-k 高评分多样化化合物的最优选择，并提供公平基准。

链接： https://arxiv.org/abs/2609.28665

机构：Deep MedChem

作者：Miroslav Lžičař (Deep MedChem)

英文摘要：A virtual screening campaign may produce thousands of promising candidates, but only a small number can be purchased, synthesized, or tested. The practical question is how to select a set of compounds that both rank well and are diverse enough: this poses a genuine tradeoff, where selecting the highest-scoring molecules yields limited diversity, while diversity selection sacrifices some well-scoring molecules. We introduce OPDiv, a diversity selection and evaluation algorithm solving this tradeoff by finding an optimal subset of molecules using integer optimization. We demonstrate the selection algorithm in practice with fingerprint distance, shape and electrostatic diversity and compare the resulting diversity spectra. We argue that virtual screening is not merely a ranking problem, but also an implicit constrained optimization task: when redundant chemotypes are undesirable, pipelines should be compared based on the top-k compound selections satisfying the desired diversity constraints. OPDiv makes it possible to find the optimal compound set under a given diversity threshold efficiently and serves as a fair benchmark of the best diverse selection achievable by a given structure-based or ligand-based virtual screening pipeline, molecular search or generative model.

AI 总结：针对裁剪随机梯度下降，提出收紧的收敛分析，简化证明并扩展适用范围，强化收敛准则并降低最终损失。

链接：https://arxiv.org/abs/2609.29458

机构：LAMSADE, Université Paris-Dauphine, PSL Research University（巴黎多菲纳大学PSL研究大学LAMSADE）

作者：David A. R. Robin

英文摘要：We present a tightened convergence analysis of clipped gradient descent on $(L_0, L_1)$-smooth functions, with quantitative constants. Building on the ideas of Koloskova et al (2023), we refactor several case disjunctions to reveal the central role of a control of the bias derived from fundamental properties of $\ell_2$-projection, simplifying proofs. We also extend the domain of validity from $\eta \leq 1 / (9 \beta)$ to $\eta < 1 /\beta$ where $\beta = L_0 + c L_1$ for clipping constant $c$, which matches the more traditional analysis of smooth functions. We strengthen the convergence criterion from $\left( \min_{t < T} \mathbb{E}[\lVert \nabla f(x_t) \rVert_2] \right)$ to $\left( \frac{1}{T} \sum_{t < T} \mathbb{E}[\lVert \nabla f(x_t) \rVert_2] \right)$ with matching speed, and lower the final achievable loss from $\mathcal{O}(\min(\sigma^2/c, \sigma))$ to the more precise $6 \min(\sigma^2 /c, 3 \sigma)$.

AI 总结：针对多任务学习，提出样本加权端到端迹范数几何，推导精确Rademacher复杂度，实验表明加权联合核正则化在252次比较中平均超额降低0.00764，优于未加权方法。

链接：https://arxiv.org/abs/2609.29520

机构：Free University of Bozen–Bolzano（博尔扎诺自由大学）

作者：Mahdi Mohammadigohari

英文摘要：Multitask models combine a shared representation with task-specific outputs, but generalization bounds often control the two components separately. Such products can discard relative orientation and cancellation and can change under equivalent transformations of intermediate coordinates even when the represented predictors are unchanged. We study instead the sample-size-weighted trace norm of the end-to-end map from task coefficients to input-space predictors. For its fixed-radius class, we derive the exact empirical Rademacher complexity. The same quantity is characterized by eliminating a positive-definite task covariance after the representation acts and, in finite-dimensional intermediate spaces, by optimizing the separated product over all equivalent invertible refactorizations. Explicit constructions show unbounded orientation and factorization gaps and an exponential depth gap for cancelling linear layers. As a geometric application, finite-to-one Lipschitz shared maps yield an exact Sobolev task Gram matrix determined by multiplicity and local directional distortion. We evaluate the corresponding convex regularizer in two protocol-locked unseen suites. Across 252 paired held-out comparisons, weighted joint nuclear regularization improves average population excess over unweighted nuclear regularization by 0.00764, with a stratified-bootstrap 95% interval [0.00465, 0.01110]. Correct task counts improve average and least-sampled-quartile excess over shifted counts by 0.01072 and 0.02847; all 15 imbalanced rank-suite cells are positive and the balanced effect is zero. Weighted joint nuclear also outperforms weighted Frobenius and independent ridge. The least-sampled-quartile comparison with unweighted nuclear remains unresolved, delimiting rather than contradicting the average advantage. All seven predeclared gates pass.

AI 总结：本研究修正了 Bandit 多类 PAC 学习的下界，引入锚定维数 aBDS，移除标签数 K 的上界依赖，并发现置信度直和现象，表明仅凭维数无法精确刻画样本复杂度。

链接：https://arxiv.org/abs/2609.29694

作者：Guangjian Zhang

英文摘要： We study realizable multiclass PAC learning with bandit feedback: the learner observes an i.i.d. instance, predicts one of $K$ labels, and learns only whether the prediction was correct. Hanneke, Meng, Moran, and Shaeiri ( arXiv:2605.25678 ) characterized the optimal sample complexity via the bandit DS dimension $\mathrm{BDS}$ up to logarithmic factors, and asked whether every class admits sample complexity $O((\mathrm{BDS}+\log(1/\delta))/\epsilon)$. First, we show that the published lower bound $\Omega((\mathrm{BDS}+\log(1/\delta))/\epsilon)$ is incorrect as stated: we exhibit explicit classes with $\mathrm{BDS}=K-1$ whose sample complexity is exponentially smaller, and locate two independent gaps in its proof. We repair the lower-bound theory around a new anchored dimension $\mathrm{aBDS}\le\mathrm{BDS}$, proving a constant-free three-part lower bound. On the upper-bound side we remove the ambient label count $K$ entirely, proving $O((B\log^3 B+B\log(1/\delta))/\epsilon)$ for $B=\mathrm{BDS}$, plus a constant-confidence bound via a new fiberization lemma; for two natural families we determine the sample complexity up to constant factors. Finally, we answer the open question in the negative under its uniform-constant reading, and show the failure is intrinsic: for an explicit affine multiplexer class we establish the full confidence profile $\Theta((n\min{n,\log(1/\delta)}+\log(1/\delta))/\epsilon)$, a confidence direct-sum regime where a multiplicative $\log(1/\delta)$ cost is information-theoretically necessary, followed by a rank-saturation phase transition. Two classes with identical dimension profiles can have polynomially different sample complexities, so no characterization by these dimensions alone is accurate to polylogarithmic factors. We also show these results are consistent with additive-confidence list-PAC guarantees via the ListCascade bridge.

AI 总结：本研究通过教师-学生框架和微分方程解析了辅助学习机制，推导出线性网络泛化误差闭式解及非线性情形的涨落-耗散理论，揭示任务相关性与噪声的作用。

链接：https://arxiv.org/abs/2609.29774

机构：University of Turin（都灵大学）； Radboud University（拉德堡德大学）

作者：Federico Milanesio, Alessandro Ingrosso, Matteo Osella

英文摘要：Auxiliary learning is an optimization paradigm in which a neural network's performance on a target task is improved by jointly training it on additional tasks. However, the mechanisms behind this improvement remain poorly understood. We study this problem using a teacher-student framework and derive a closed system of differential equations describing the dynamics of online stochastic gradient descent in the large-input limit. For linear networks, we obtain a closed-form expression for the generalization error to leading order in the learning rate, quantifying how task correlations and label noise determine the benefit of auxiliary learning. For non-linear activation functions, we develop a fluctuation-dissipation analytical theory that establishes a general relation linking the main and auxiliary errors to the corresponding single-task error. Numerical experiments support the theoretical predictions and show how auxiliary tasks improve generalization by balancing the forcing dynamics towards the optimal solution with gradient noise.

AI 总结：针对高维黑箱约束优化中多保真度与高维性、约束及非嵌套采样难以兼顾的问题，提出MF-SCBO方法，实验表明其收敛性优于单保真度SCBO及其他多保真度方法。

链接：https://arxiv.org/abs/2609.29941

机构：Université Côte d’Azur（蔚蓝海岸大学）； Inria（法国国家信息与自动化研究所）； CNRS（法国国家科学研究中心）

作者：Lucas Palazzolo, Mickaël Binois, Laëtitia Giraldi

英文摘要：Many real-world optimization problems rely on expensive simulations or experiments, making the efficient use of available data essential. Multi-fidelity optimization of high-dimensional black-box functions subject to black-box constraints is increasingly relevant as the cost of objective evaluations continues to rise in applications such as machine learning, engineering, and control. To our knowledge, no existing method simultaneously addresses high-dimensionality, black-box constraints, an arbitrary number of fidelity levels, and non-nested sampling. In this work, we extend the Scalable Constrained Bayesian Optimization method to the multi-fidelity setting, resulting in the MF-SCBO method. The proposed approach is evaluated on standard benchmark functions as well as challenging problems. The experimental results demonstrate that MF-SCBO generally achieves better convergence than both the single-fidelity SCBO and the other multi-fidelity method considered in this high-dimensional and constrained settings.

AI 总结：本文提出机会约束的大语言模型微调方法，限制安全示例退化比例，通过可微上界和约束感知梯度下降实现尾部感知的安全校正，实验证明其优于现有基线。

链接：https://arxiv.org/abs/2609.29960

机构：Johns Hopkins University（约翰霍普金斯大学）

作者：Taha Entesari, Mahyar Fazlyab

英文摘要：Fine-tuning large language models on new objectives can improve helpfulness, instruction following, or domain-specific performance, but it can also induce regressions on safety-critical prompts. Existing safety-preserving fine-tuning methods typically control average safety loss or use weighted auxiliary penalties, which can obscure rare but severe failures. We propose a chance-constrained formulation for safety-preserving fine-tuning that limits the fraction of safety examples whose degradation relative to a reference model exceeds a prescribed threshold. Because the resulting empirical chance constraint contains a discontinuous indicator, we introduce a differentiable majorization of the violation rate, yielding a tractable conservative constraint. We then develop a constraint-aware gradient descent method that treats the majorized constraint as a safe set in parameter space and minimally modifies the fine-tuning direction to preserve feasibility. The resulting update admits a closed form and produces a tail-aware safety correction that emphasizes examples near or above the degradation threshold. We conduct an extensive set of experiments on harmful fine-tuning across three different tasks and three models and show that our approach consistently outperforms the baselines that exist in the literature. These results suggest that safety preservation in LLM fine-tuning is better viewed as a reliability-constrained optimization problem than as average-risk regularization.

AI 总结：提出联邦学习框架训练AnDE分类器，支持任意依赖阶数，通过本地学习与全局聚合保护隐私，实验表明n≥1的判别模型优于联邦朴素贝叶斯，且隐私聚合损失有限。

链接：https://arxiv.org/abs/2609.28695

机构：Universidad de Castilla-La Mancha（卡斯蒂利亚-拉曼恰大学）； Instituto de Investigación en Informática de Albacete（阿尔瓦塞特信息学研究所）

作者：Pablo Torrijos, Juan C. Alfaro, José A. Gámez, José M. Puerta

英文摘要： This work presents a federated framework for training Averaged $n$-Dependence Estimators (AnDE) in distributed environments. The proposed method focuses on the discriminative setting, where model weights are learned locally and aggregated globally, supporting any dependency order $n$. This design allows federated training without transmitting semantically meaningful parameters, improving privacy. Additionally, generative AnDE models are federated to provide a comparative baseline, with optional differential privacy applied to the aggregation of probability tables. Experiments on 12 discrete datasets show that discriminative models with $n \geq 1$ consistently outperform federated Naive Bayes (NB, $n=0$), and that privacy-preserving aggregation is effective with limited accuracy loss. These results establish federated AnDE as a viable and privacy-preserving framework, showing that probabilistic models remain applicable in modern federated learning settings.

AI 总结：本文从威胁、聚合策略和防御策略三个角度综合综述联邦学习的鲁棒性，分类攻击面与防御方法，并评估现有实践，指出开放挑战以指导未来研究。

链接：https://arxiv.org/abs/2609.28722

机构：BITS Pilani Dubai Campus（BITS Pilani迪拜校区）； University of Palermo（巴勒莫大学）； Missouri University of Science and Technology（密苏里科技大学）

作者：Pravija Raj P V, Ashish Gupta, Andrea Augello, Sajal K. Das

英文摘要：While Federated Learning (FL) has been widely adopted for protecting user privacy in machine learning, it remains vulnerable to various robustness challenges, including performance-impairment risks, information-stealing threats, and aggregation vulnerabilities. This work offers a holistic synthesis of FL robustness along three tightly coupled angles: (i) a threat-centric view of robustness that categorizes the multifaceted attack surfaces, (ii) a structured taxonomy of robust aggregation strategies distinguishing outcome-centric approaches from security-centric strategies, and (iii) a layered taxonomy of defensive strategies. We rigorously examine current evaluation practices for FL robustness and identify major applications and open research challenges to guide future research.

AI 总结：提出SPADE-DFL，一种基于无导数线性化ADMM的去中心化联邦学习方法，通过控制局部更新不一致实现通信高效，在非凸目标下达到T^{-1/3}收敛界，并支持私有训练，实验显示更高准确率。

链接：https://arxiv.org/abs/2609.29446

机构：Southeast University（东南大学）； Jiangsu Province Scientific Research Center for Applied Mathematics（江苏省应用数学科学研究中心）

作者：Mengli Wei, Mengkai Zhu, Jiawen Chen, Wenwu Yu, Duxin Che

英文摘要：Reducing communication in derivative-free decentralized learning requires controlling the disagreement accumulated over multiple local updates. This paper develops SPADE-DFL, a primal--dual method that allows the number of local function-value updates between neighbor exchanges to grow with the computation budget while preserving the nonprivate convergence order. For smooth nonconvex objectives under uniform query-moment bounds, the prescribed nonprivate schedule achieves a time-averaged stationarity and consensus bound of $\mathcal{O}(T^{-1/3})$ using only $\Theta(T^{2/3})$ communication rounds, where $T$ is the number of local updates per client. For private training, the accumulated data-dependent increment is isolated from the graph correction, allowing one protected state per client and round to generate all outgoing messages. We prove client-level differential privacy for the full interactive transcript and quantify the resulting optimization error over a finite horizon. Experiments on four classification tasks show that SPADE-DFL achieves higher mean test accuracy than existing decentralized learning methods.

AI 总结：本研究提出榜单推荐中解耦评分学习与选择的方法，通过差分隐私范围契约和日志边际证书，在噪声评分下保证排序稳定性，实验验证了其有效性。

链接：https://arxiv.org/abs/2609.29453

机构：University of Bergen（卑尔根大学）； Centre for the Science of Learning & Technology (SLATE)（学习与技术科学中心（SLATE））； City University of Macau（澳门城市大学）

作者：Sam Urmian, Qinyi Liu, Mohammad Khalil

英文摘要：We formalize slate recommendation as a randomized score learner followed by deterministic selection. First, an appropriately scoped differential-privacy guarantee passes through selection and its audit trace by post-processing. End-to-end privacy holds only when selector inputs are public or independent, previous private outputs, or separately privacy-accounted; fixing raw state or candidate information instead yields only a conditional guarantee. Second, we derive a logged margin certificate: bounded score-induced objective movement below half the smallest greedy decision margin guarantees that the ordered slate is unchanged. Controlled fixed-margin tests show near-linear exponent scaling, with an empirical slope of $-0.220$ (95% CI $[-0.231,-0.210]$) against the independent-noise reference $-1/4$. Real-anchor experiments on OULAD, MovieLens-25M, and Amazon Musical Instruments show that greater anchor weight reduces score-noise-induced ranking churn. OULAD and EdNet certificate checks validate the implementation of the logged inequality, while closed-loop simulations show bounded target drift and setting-dependent downstream utility. The contribution is therefore a privacy-scope contract and a certifiable score-to-slate stability mechanism, not a universal utility claim.

AI 总结：针对联邦轨迹预测中场景不确定性与复杂度异质性挑战，提出不确定性感知及联合复杂度-不确定性感知的主动客户端选择方法，在Argoverse上加速收敛并提升预测性能。

链接：https://arxiv.org/abs/2609.29600

机构：Northeastern University（东北大学）； University of Connecticut（康涅狄格大学）

作者：Yiming Xie, Muzi Peng, Fei Miao, Ningfang Mi, Lili Su

英文摘要： Training sequence models such as transformers is now standard for autonomous vehicle trajectory prediction, yet assembling high-quality centralized datasets remains challenging because real-world trajectories are fragmented across regions and vehicles. Federated Learning (FL) offers a natural alternative, but faces two distinctive challenges: high scene uncertainty arising from trajectory or map ambiguity, and cross-scene complexity heterogeneity caused by diverse map topology, traffic density, agent composition, and driving behaviors. We propose a family of active client selection methods that progressively incorporate awareness of scene uncertainty and complexity to prioritize informative clients. Our uncertainty-aware selectors use per-client negative log-likelihood under an uncertainty-aware global objective and estimated aleatoric uncertainty. We further develop a selector that jointly considers scene complexity and uncertainty, motivated by the intuition that knowledge from complex scenes can transfer to easier ones. Experiments on Argoverse show that federated trajectory prediction outperforms locally trained models. Uncertainty-aware selection accelerates convergence and improves minADE, minFDE, and MR. Under strong scene-complexity heterogeneity, our joint complexity- and uncertainty-aware selector achieves the best generalization and further accelerates convergence, demonstrating the benefit of prioritizing complex and informative scenes.

AI 总结：针对SEM图像分类中的信息泄漏问题，提出区域留出协议（LORO），在316L不锈钢氢脆检测中，LBP+SVM以0.79平衡准确率优于深度学习模型，并经置换检验验证，证明纹理特征可有效识别充氢特征。

链接：https://arxiv.org/abs/2609.28567

机构：Institute of Physics, Bahauddin Zakariya University（巴哈丁·扎卡里亚大学物理研究所）

作者：Muhammad Awais, Muhammad Yaseen, Abdul Shakoor, Niaz Ahmed Niaz, Huria Zia, Muhammad Zain Shakoor

英文摘要：Scanning electron microscopy (SEM) is routinely used to characterize the microstructural changes caused by hydrogen embrittlement (HE) in structural steels. Machine learning can automate this characterization, but models are often evaluated using image-level splits. When several images come from the same specimen region, such splits leak information between the training and test sets. Here, we propose a region-held-out protocol for classifying as-received (AR) and hydrogen-charged (H2) SEM micrographs of 316L stainless steel, based on Leave-One-Region-Out (LORO) cross-validation over 14 spatial regions (8 AR, 6 H2; 31 images). We compared six feature-classifier combinations built on local binary patterns (LBP), grey-level co-occurrence matrices (GLCM), self-supervised convolutional embeddings pretrained on 143 unlabeled SEM images, and a convolutional neural network (CNN). The simplest texture approach, LBP with a support vector machine (LBP+SVM), performed best, achieving a balanced accuracy of 0.79, H2 recall of 0.69, and H2 precision of 0.82, outperforming every deep-learning and combined-feature model. A group-level permutation test (500 permutations sampled from the 3,003 possible region-to-label assignments) yielded p = 0.008, indicating that the result cannot be explained by a chance alignment of the region structure. Grad-CAM maps from a CNN trained on the full dataset tended to concentrate on localized surface and grain-boundary features, where hydrogen-induced morphological changes are known to occur. Under a leakage-safe, statistically validated protocol, texture descriptors recover a hydrogen-charging signature from SEM micrographs even with few samples, and the same protocol can be extended to larger HE detection studies in other alloy systems.

AI 总结：提出SGA方法，通过有向无环图刻画预测分支拓扑并整合随机性量化多步TSFM预测不确定性，实验验证其排序性能和缩放定律。

链接：https://arxiv.org/abs/2609.28582

机构：Siemens Data and AI Research（西门子数据与人工智能研究院）； Nanjing University – Siemens Joint Research Center on Industrial AI（南京大学-西门子工业人工智能联合研究中心）

作者：Xin-Yu Hu, Shuang Liang, Cheng Feng, Shao-Qun Zhang

英文摘要：The recent emergence of Time Series Foundation Models (TSFMs) has significantly advanced multi-step forecasting performance, enabling accurate predictions over extended future horizons. However, existing TSFMs often suffer from significantly inherent uncertainty, which typically manifests as derived forecast branches emerging at each time step and spreading to subsequent steps; different forecast branches often exhibit varying forecasting performance, thereby undermining the credibility of TSFM forecasts. In this paper, we propose the Slicing-Graphing-Alignment (SGA) method to quantify the uncertainty of multi-step TSFM forecasts. The proposed SGA first characterizes the topology of all potential forecast branches using a directed acyclic graph, such that the graph complexity bounds the uncertainty of multi-step forecasts, and then precisely measures the graph complexity by integrating both topological information and TSFM-inherent stochasticity. Experimental results conducted on 11 TSFMs and 27 datasets demonstrate that (i) SGA achieves the best performance when ranking predictive errors with uncertainty estimates; (ii) SGA works with a more extensive and more precise sampling coverage than those of existing UQ methods, deriving a quantification mechanism fundamentally different from those of established ones; and (iii) larger model scales of TSFMs correlate with lower uncertainty estimates of multi-step forecasts, suggesting another empirical scaling law for uncertainty quantification of multi-step TSFM forecasts.

AI 总结：针对甲状腺FNAB细胞学分类中假阴性率高和域偏移下的过度自信问题，提出基于吸收马尔可夫链和香农熵不确定性量化的多尺度框架TAM-Chain，通过最优停止与人机协同转诊，实现高准确率与零假阴性。

链接：https://arxiv.org/abs/2609.28590

作者：Hai Pham Ngoc

英文摘要： Background & Problem: Thyroid Fine-Needle Aspiration Biopsy (FNAB) cytology based on the Bethesda System plays a pivotal role in early thyroid cancer detection; however, deep learning approaches face substantial challenges regarding high false-negative rates and overconfidence under clinical domain shift. Methods: In this study, we propose TAM-Chain, a multi-scale (10x, 20x, 40x) thyroid cytology classification framework leveraging Absorbing Markov Chain theory combined with Shannon Entropy-based Uncertainty Quantification. The framework dynamically models multi-magnification feature extraction as an absorbing stochastic process, enabling optimal stopping criteria and a human-in-the-loop referral mechanism to strictly suppress critical diagnostic errors. Results: Extensive evaluation on an internal test set (N = 235) demonstrates a Macro F1 score of 0.9741 with an absolute False-Negative Rate (FNR) of 0.00%. On an independent external validation set (N = 1015) presenting severe domain shift, TAM-Chain maintains superior stability and classification performance (Macro F1 = 0.7026) by adaptively adjusting the expected stopping step and triggering specialist referrals, significantly outperforming single-magnification baselines. Conclusion: The TAM-Chain framework proves to be a highly effective, safe, and adaptable solution for digital pathology workflows, successfully harmonizing automated diagnostic efficiency with stringent biological safety.

AI 总结：该研究提出以证明与陈述长度比定义定理趣味性，训练27B模型预测证明难度，生成更有趣且分布外的数学定理，并构建自我扩展的数学库。

链接：https://arxiv.org/abs/2609.28603

机构：CERMICS, ENPC, Institut Polytechnique de Paris（巴黎高科路桥学校 CERMICS 实验室，巴黎综合理工学院）； New York University（纽约大学）

作者：Niket Patel, Ahmad Rammal, Amaury Hayat, Remi Munos, Julia Kempe

英文摘要：Recently, Large Language Models (LLMs) have been increasingly able to solve advanced mathematical problems, including many that have been open for decades. This opens the door to expansion of mathematical knowledge at unprecedented scale. Yet, while LLMs may be able to conjecture and prove more and more theorems, it remains open whether this new mathematical knowledge is interesting or useful. We define intrinsic interestingness of a theorem as the ratio between the length of its proof and the length of its statement. We show that this correlates strongly with an extrinsic measure of the downstream utility of a theorem. We identify the difficulty of a proof conditioned on a set of premises as a useful primitive for computing these metrics, and train a 27B model that predicts proof difficulty more accurately than frontier general-purpose models. Optimizing for our metric creates a model capable of producing more interesting theorems, while also reducing substantial or full overlap with Mathlib from 91.9% to 30.6%, showcasing the creation of more out-of-distribution math. We show that our system can generate candidate theorems, select the most interesting among them, and iteratively build on a self-expanding mathematical library. These metrics provide a practical and quantifiable signal for ranking conjectures and guiding proof search within formal mathematical libraries. Our framework provides a path towards self-expanding, machine-verified mathematical libraries that can choose worthwhile statements without relying on human-supplied targets.

AI 总结：提出直接消息近似（DMA）框架，通过直接近似因子到变量消息并定义一致性条件，在因子图上实现可处理的近似推断，避免了EP和VMP的缺陷，并验证了其在贝叶斯神经网络中产生数据稀疏区域更宽的不确定性。

链接：https://arxiv.org/abs/2609.29466

机构：Hasso Plattner Institute（哈索·普拉特纳研究所）； University of Potsdam（波茨坦大学）

作者：Ralf Herbrich, Rainer Schlosser, Jan Lemcke, Johann Ukrow, Anna Kazachkova, Nicolas Alder, Leonhard Hennicke, Theo Bardey, Nico Grimm, Luca Kleinschmidt, Philipp Kolbe, Cezary Kujath, Johanna Schlimme, Karl Matti Schütz

英文摘要：Approximate message passing on factor graphs underlies two dominant families of probabilistic inference algorithms: expectation propagation (EP) and variational message passing (VMP). Both methods approximate the marginal at each factor edge, forcing an iterative round-robin schedule, risking negative-precision messages, and, for VMP, collapsing to point estimates at Dirac-delta factors. We introduce Direct Message Approximation (DMA), which approximates factor-to-variable messages directly rather than the marginal. For normalisable factors, we define a consistency condition (requiring exactness when all other incoming messages are Dirac deltas) to guide message construction. We prove a master theorem (proper messages, any graph) bounding marginal KL from message KL, with three structural corollaries: Dirac-input consistency, no EP-style inner-loop iteration, and no negative-precision messages. Further, we prove a complementary $O(1/r^2)$ guarantee for the inherently improper backward message of the product factor, whose closed-form treatment has resisted prior work. As a concrete instantiation, we derive explicit DMA messages for the product and leaky-ReLU factors and assemble a Bayesian neural network (BNN) inference algorithm with one forward/backward sweep per training example and no gradient learning-rate hyperparameter, validating that the structural guarantees translate to predictive uncertainty that widens in data-sparse regions, including under model mismatch.

AI 总结：CataOPD通过教师作为催化剂而非目标，结合自救援路由、催化引导自求解和屏障加权内化，扩展学生推理可达性，提升大语言模型推理性能与泛化能力。

链接：https://arxiv.org/abs/2609.29518

机构：Nanyang Technological University（南洋理工大学）； Hithink Research（海天瑞声研究院）； Nanjing University of Science and Technology（南京理工大学）

作者：Wenjin Liu, Chenxi Wang, Jiapu Wang, Zhe Cui, Anh Tuan Luu, Haoran Luo

英文摘要：Reinforcement learning (RL) and on-policy distillation (OPD) are two representative paradigms for improving large language model reasoning. However, when no correct trajectory is sampled, RL lacks a positive correctness signal, while OPD remains constrained by the reasoning trajectories reachable under the student's on-policy distribution. Therefore, we propose CataOPD, where the teacher acts as a catalyst rather than a target, expanding reachability while internalizing verified student-produced trajectories into a catalyst-free policy. Self-Rescue Routing uses empirically all-failed groups as routing signals rather than teacher-intervention triggers, first seeking correct trajectories through additional on-policy self-sampling. For problems unresolved after self-rescue, Catalytic-Guided Self-Resolution uses catalytic guidance to elicit a verified student-produced trajectory in the guided student distribution. Barrier-Weighted Internalization weights tokens by guided-to-unguided log-probability gaps, focusing updates on decisive tokens difficult without guidance. Experimental results show that CataOPD outperforms current baselines, extends independent student reasoning to still-unrecovered problems, and improves out-of-distribution generalization under catalyst-free inference. Our project is available at this https URL.

AI 总结：本研究通过流式基准RegimeShift-Surrogates比较再验证与有状态路由，发现基于当前窗口重新验证模型选择更优，平均对数遗憾更低，且优于所有有状态自适应方法。

链接： https://arxiv.org/abs/2609.29715

机构：SlicedHealth

作者：Harshil Lodhiya

英文摘要：Surrogate models are often chosen during development and then left in place as new measurements arrive. That practice becomes risky when noise, input support, or physical parameters change. We asked whether such changes call for a stateful adaptive controller, or whether it is enough to validate the candidate models again on each new batch. To study this question, we built RegimeShift-Surrogates, a reproducible streaming benchmark spanning eight analytic and dynamical tasks, four stationary or shifting regimes, ten held-out seeds, and eight classical, multilayer-perceptron, and Kolmogorov-Arnold network surrogates. The confirmatory run contains 30,720 model fits and 3,200 scored deployment windows. Choosing the model with the lowest validation loss in the current window yields mean log regret 0.091 against a per-window oracle; the best fixed model chosen in hindsight yields 0.192. The paired difference is -0.101 (hierarchical bootstrap 95% CI [-0.165, -0.040]; Holm-adjusted p = 0.0469), with revalidation ahead in 26 of 32 task-scenario combinations. None of the stateful alternatives, including exponential smoothing, dual-timescale adaptation, Page-Hinkley resets, or margin gating, improves the pooled result, and delayed bias correction makes it worse. Oracle choices also differ substantially by task: k-nearest neighbors dominate the damped oscillator, vanilla KAN is often selected for two-dimensional surfaces, and MLPs lead on the Runge and Van der Pol tasks. In this benchmark, fresh validation evidence is useful; carrying old evidence forward is often not.

AI 总结：提出一种模型无关的测试时增强框架，仅通过输入输出访问改进黑盒放射学AI的校准，在肺栓塞和颅内出血任务中显著降低校准误差，优于需访问模型内部的方法。

链接：https://arxiv.org/abs/2609.29931

机构：Stanford University（斯坦福大学）； Medical University of Vienna（维也纳医科大学）

作者：Nathan Le, Magdalini Paschali, Arogya Koirala, Andrew Johnston, Zhongnan Fang, David B. Larson, Akshay S. Chaudhari, Camila Gonzalez

英文摘要：Radiology AI systems increasingly inform clinical decisions such as triage, follow-up imaging, and treatment planning. For these decisions to be made safely, model outputs must be well calibrated, meaning predicted probabilities accurately reflect true risk. Many standard techniques for improving calibration, such as MC Dropout and Deep Ensembles, require access to model parameters or retraining. However, proprietary clinical AI systems operate as black boxes, preventing access to the model's internals. To that end, we propose a model-agnostic framework for improving calibration of black-box models using clinically grounded test-time augmentation (TTA). Our framework applies geometric and physics-inspired 3D CT perturbations and learns probability-level aggregation strategies without access to model internals or the original training data. Across pulmonary embolism and intracranial hemorrhage detection tasks, DualTTA achieved the strongest overall calibration among TTA methods, reducing the Expected Calibration Error by 54% (0.239 -> 0.109) and 43% (0.051 -> 0.029), respectively, while requiring only input-output access. Additionally, DualTTA outperformed uncertainty estimation techniques that require access to model internals, such as Temperature Scaling, MC Dropout, and Deep Ensembles, in most calibration metrics. These results demonstrate that learned TTA aggregation can improve the calibration of clinical AI systems, providing a practical approach for improving the reliability of black-box medical AI.

AI 总结：SMILESGNN通过SMILES与图编码器的交叉注意力融合，在保持高预测性能的同时支持基于图的可解释毒性分析，并在ClinTox和Tox21基准上验证了其有效性。

链接：https://arxiv.org/abs/2609.28553

机构：National Economics University（国民经济大学）； VNU University of Science（越南国立大学自然科学大学）

作者：Quang Minh Nguyen, Thuy Quynh Nguyen, Duc Minh Le, Ho Nhat Minh Nguyen, Thanh Long Dai Doan, Trong Nghia Nguyen

英文摘要：Drug toxicity prediction is critical for reducing late-stage attrition in drug discovery, yet remains challenging due to severe class imbalance, scaffold-based generalization, and the clinical need for interpretable predictions. Single-modality approaches-SMILES Transformers or graph neural networks capture complementary aspects of molecular structure, while sequence-only models cannot directly provide graph-attributed explanations. We present SMILESGNN, a multimodal architecture that fuses a SMILES Transformer encoder and a GATv2 graph encoder via cross-attention, and SMILESGNN-PT, a variant using a ChemBERTa-2 pretrained backbone. The design retains an explicit graph branch within the predictive pipeline, supporting GNNExplainer-based analysis of substructures associated with toxic predictions. On ClinTox, SMILESGNN achieves AUC-ROC 0.987 and F1 0.906 with only 0.4M parameters, performing competitively with a strong SMILESTransformer and a larger ChemBERTa-2/GATv2 concat-fusion baseline. On Tox21 (12 tasks), SMILESGNN-PT obtains mean AUC-ROC 0.750, comparable to ChemBERTa-2 alone and the same-backbone concat-fusion baseline. Overall, the results suggest that cross-attention is a practical fusion alternative that preserves competitive predictive performance while enabling graph-based interpretability support.

AI 总结：本研究提出HermNet，一种基于Hermite多项式的谱图神经网络，通过归一化传播避免特征分解，并分析其在不同训练预算下的优化行为，实验表明其在特定条件下优于其他多项式基方法。

链接：https://arxiv.org/abs/2609.28979

机构：UCLA（加州大学洛杉矶分校）

作者：Shuang Wu

英文摘要： We study spectral graph neural networks built from Hermite polynomials and propose HermNet, a simple model that combines a nodewise predictor with normalized Hermite propagation. Its sparse recurrence requires neither eigendecomposition nor a learned basis. We distinguish the basic model from optional coordinate calibration, response normalization and Gaussian derivative regularization. Hermite and other complete polynomial bases span the same degree-bounded filter space, but their coordinates can produce different optimization behavior under limited training budgets. We analyze this behavior through spectral signal energy, label sampling, changes in learned features and the bias--variance trade-off of regularization. Controlled synthetic experiments identify a regime in which plain HermNet outperforms matched polynomial-basis alternatives, including with a jointly trained nonlinear predictor. Curvature regularization further improves HermNet when the same functional penalty is available to every comparator. Fixed-predictor controls support the advantage under short training budgets, but longer training removes the plain-model lead. Matched real-data comparisons show accuracy deficits, and architectural and numerical studies identify further limits. Together, the analysis and experiments clarify when Hermite propagation is useful and how calibration and regularization affect its performance.

AI 总结：TinyCardioUNet利用图神经网络编码IMU轴间依赖，并通过张量分解缩减参数，以轻量级UNet实现从IMU到ECG的准确重建，在公共数据集上以36.0k参数达到0.098的RMSE和0.677的相关系数。

链接：https://arxiv.org/abs/2609.29322

机构：Tokyo University of Agriculture and Technology（东京农工大学）

作者：Seungwoo Han, Ingon Chanpornpakdi, Motoi Noda, Puwadej Leelasiri, Ibuki Hiruma, Toshihisa Tanaka

英文摘要：Estimating electrocardiography (ECG) from a chest-worn inertial measurement unit (IMU) enables continuous heart rate (HR) monitoring without the discomfort of electrodes. We propose TinyCardioUNet, a lightweight UNet that uses all six IMU axes without prior channel selection, refines its bottleneck with a graph neural network that encodes inter-axis dependencies, and employs tensor decomposition with automatic variational Bayesian rank selection for parameter reduction. On a public dataset, TinyCardioUNet achieves an RMSE of $0.098$ and a Pearson correlation coefficient of $0.677$ with only $36.0$k parameters and remains comparatively robust to additive noise, demonstrating accurate ECG reconstruction with a compact model.

AI 总结：本文提出GraphStar集扩展NNV框架，实现GNN形式化验证，在电力系统任务和图分类基准上提供更紧致的鲁棒性保证。

链接：https://arxiv.org/abs/2609.30079

机构：Vanderbilt University（范德堡大学）

作者：Anne M. Tumlin, Ben Wooding, Zhenxuan Shao, Diego Manzanas Lopez, Tyler Derr, Taylor T. Johnson

英文摘要：Graph neural networks (GNNs) have become a prominent approach for developing fast, topology-aware surrogates in electric power systems, supporting tasks such as power flow (PF) analysis, optimal power flow (OPF) estimation, and cascading failure analysis (CFA). Despite this growing use, formally verifying GNN-based models remains challenging, with existing methods limited in scope. We extend the neural network verification (NNV) framework to graph-structured inputs through GraphStar sets, a generalization of Star sets that captures uncertainty over both node and edge features. This extension enables the propagation of linear message-passing operations and the sound approximation of ReLU nonlinearities for GNN architectures, including graph convolutional network (GCN) and graph isomorphism network with edge features (GINE) layers. We evaluate GNNV across three power system tasks, PF, OPF, and CFA, on the IEEE-24, IEEE-39, and IEEE-118 test cases, as well as two standard graph classification benchmarks, ENZYMES and PROTEINS. Our results show that GNNV provides tighter robustness guarantees than CORA on graph classification models with ReLU-based activations and, for the first time, delivers edge-aware robustness guarantees for GINE-based PF and OPF models under joint node and edge perturbations.

AI 总结：UO-FIE结合精确标签与分级效用，通过分布预测、软目标和有序损失，在FIE2026微调赛道以0.8316宏效用夺冠。

链接：https://arxiv.org/abs/2609.28605

机构：Xinjiang University（新疆大学）

作者：Xinchen Xiao

英文摘要：The Factivity Inference Evaluation 2026 (FIE2026) classifies Chinese context-hypothesis pairs into nine ordered factivity intervals. Its evaluation metric rewards both exact predictions and proximity to the correct interval, while 64.1% of the 566 training examples belong to a single class. In preliminary experiments, several mDeBERTa classification models predominantly predict the dominant class, whereas a Huber-regression baseline produces more predictions near the correct interval but fewer exact matches. We introduce Utility-Oriented Factivity Inference (UO-FIE), a parameter-efficient system that combines exact-label supervision with graded utility. UO-FIE predicts a distribution over the nine classes and combines hard-label supervision, utility-based soft targets, scheduled class weights, and an ordinal loss. We evaluate expected-utility decoding in controlled comparisons and use ordinal calibration selected on out-of-fold predictions for the submitted system. Based on Qwen3.5-9B with LoRA, UO-FIE ranks first in the fine-tuning track with a macro utility of 0.8316. A separate prompt-based ensemble ranks third in the non-fine-tuning track with a macro utility of 0.8450.

AI 总结：本文提出基于lp正则化的自动秩分配方法，通过正则化秩一组件能量并推导隐式阈值准则，在自然语言理解与问答任务上达到与现有LoRA基线相当的性能。

链接：https://arxiv.org/abs/2609.28998

机构：National University of Singapore（新加坡国立大学）； Huawei（华为）； The University of Hong Kong（香港大学）； Hong Kong Baptist University（香港浸会大学）

作者： Zebang Xie, Chuanyang Zheng, Yik-Chung Wu, Yihang Gao

英文摘要：Low-rank adaptation (LoRA) has become a popular parameter-efficient fine-tuning method for large language models. A key challenge in LoRA is how to determine the rank of each adaptation matrix, as rank directly controls its capacity and efficiency. Existing adaptive-rank methods typically allocate ranks according to manually designed importance scores, which are not directly derived from an optimization objective. In this work, we propose $\ell_p$-LoRA, a principled rank-allocation method based on $\ell_p$ regularization with $0

AI 总结：提出粒子群辅助梯度元学习算法，联合优化发射预编码与STAR-RIS系数，提升多用户下行加权和速率，性能优于传统交替优化。

链接：https://arxiv.org/abs/2609.29150

机构：Mianyang City College（绵阳城市学院）

作者：Kang Zhou

英文摘要：This paper investigates the joint optimization of the transmit precoder and the transmission/reflection coefficients of a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) to maximize the weighted sum rate (WSR) in a multi-user downlink. We propose a particle-swarm-assisted gradient meta-learning (PSA-GML) algorithm for this non-convex problem. The original problem is first equivalently transformed via an amplitude-split parameterization and a collapsed precoder representation, which automatically satisfy the energy-conservation constraint and reduce the search dimension. Particle swarm optimization (PSO) then performs a global search over the STAR-RIS coefficients to yield a high-quality, initialization-robust warm start, with the transmit precoder obtained in closed form. Departing from conventional alternating optimization (AO), a coordinate-wise long short-term memory (LSTM) meta-optimizer trained by first-order gradient meta-learning further refines the coefficients and precoder jointly, learning per-coordinate adaptive update rules from data. The meta-optimizer is trained offline and applied to unseen channels without further adaptation. Numerical results show that PSA-GML attains an 11.06 bits/s/Hz WSR at 10 dB with N=32 elements and K=4 users, exceeding AO by 13.1% (and by 6.2% even with multiple random restarts) and the random-phase scheme by 35.1%. In the interference-limited regime it reaches 83.9% of the hand-designed Adam refinement without manual hyper-parameter tuning, and it transfers zero-shot across regimes, indicating that the learned update rule captures the intrinsic WSR landscape structure.

AI 总结：本研究在过参数化线性回归模型中证明持续学习的序列更新产生额外代价，其平稳极限可精确分解，并分析EWC的缓解作用，在Jester数据集上验证理论。

链接：https://arxiv.org/abs/2609.29674

作者：Zonghuan Xu, Xingjun Ma

英文摘要：Sequential task updates are fundamental to continual learning, but their recency bias can impose a lasting performance cost. We study this cost in an overparameterized linear-regression model with i.i.d. task sampling. We prove that distribution-level forgetting and population loss converge to the same stationary limit. This common limit separates exactly into the intrinsic loss asymptotically attained by joint training and an additional sequential price, and in more homogeneous task geometries the two terms coincide, making the total loss twice that of joint training. We further analyze fixed-strength elastic weight consolidation (EWC) under general task curvatures and characterize its stationary sequential price at every regularization strength. Under strong regularization, the price decays inversely with EWC strength while convergence to stationarity slows at the same scale. On the Jester joke-rating dataset, the theory exactly quantifies both the sequential price generated by naturally conflicting user preferences and its reduction by EWC.

AI 总结：针对隐私保护持续学习中保留与纠正的粒度冲突，提出SPARK分解方法，先冻结任务后分布再选择性纠正，实现有效PII抑制并保持知识保留。

链接：https://arxiv.org/abs/2609.29711

机构：Nanjing University of Aeronautics and Astronautics（南京航空航天大学）； Nanjing University（南京大学）； Tsinghua University（清华大学）

作者：Shengtao Wen, Yunying Yang, Xiang Chen, Lingbing Guo, Yu Tian, Sheng-Jun Huang

英文摘要：Privacy-preserving continual learning (PPCL) must reduce the reproduction of sensitive content while retaining useful knowledge across sequential tasks. Formal privacy guarantees characterize randomized mechanisms, whereas operational output control concerns whether a trained model selectively reduces the likelihood of sensitive content in its outputs. In this work, we investigate the latter together with continual-learning utility under realistic task evolution. Retention and privacy correction operate at different granularities: task acquisition requires broad preservation of current- and old-task behavior, whereas privacy correction targets sparse annotated positions. Joint optimization leaves the current-task preservation target continually changing. We propose SPARK, a retention-correction decomposition that first freezes the learned post-task distribution and then applies selective correction around this stable reference. Self-Distillation Replay learns the current task while distilling behavior from previous tasks, and Post-Task Privacy Correction reduces annotated-PII likelihood while anchoring current- and old-task non-PII behavior to the resulting checkpoint. Extensive evaluations demonstrate that SPARK achieves effective selective PII suppression while preserving strong continual-learning utility and knowledge retention across diverse settings. Code and data will be released upon publication.

AI 总结：本文利用智能电表数据，通过DTW聚类和BiLSTM检测，揭示住宅光伏与电动汽车共同采用模式，助力需求侧规划。

链接：https://arxiv.org/abs/2609.28578

机构：Monash University（莫纳什大学）； Monash Energy Institute（莫纳什能源研究所）

作者：Jack Zheng, Hao Wang

英文摘要：The increasing adoption of electric vehicles (EVs) and rooftop photovoltaic (PV) systems is reshaping residential electricity demand and creating new challenges for demand-side management (DSM), tariff design, and low-voltage network planning. Much of the existing literature examines EV charging or PV generation in isolation, leaving the behavioral dynamics of household co-adoption less understood. We develop an integrated, two-part workflow to analyze advanced metering infrastructure (AMI) data. A discovery component applies dynamic time warping (DTW) k-means with DTW barycenter averaging to cluster daily import or export profiles into interpretable behavioral archetypes, while a predictive component trains a bidirectional long short-term memory (BiLSTM) model on 21-day windows and benchmarks it against tabular baselines for PV/EV activity detection. The EV activity labels are inferred from charging-like load signatures because charger measurements are unavailable. Using half-hourly AusNet residential data from Victoria, Australia, the clustering uncovers distinct patterns across PV-only, EV-only, co-adoption, and neither cohorts; for co-adopters, a midday-centered weekday export archetype accounts for approximately 50% of days. At validation-tuned thresholds, both BiLSTM and XGBoost achieve strong discrimination. BiLSTM obtains 0.991 for the area under the receiver operating characteristic curve (AUROC), 0.906 for macro-F1, and the highest recall on the most difficult class (0.836 for EV-only recall). Tree-based baselines remain competitive. Performance remains stable across plausible labeling rules (macro-F1: 0.894--0.914) and strictly forward temporal splits (macro-F1: 0.894--0.906).

AI 总结：本文介绍 R 包 fable.intermittent，统一实现多种间歇性时间序列概率预测方法，提出 TWEES 模型及加速的 tweedieDistr 包，并在四个数据集上评估。

链接：https://arxiv.org/abs/2609.28607

机构：SUPSI, Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA)（瑞士南部应用科学与艺术大学，达勒莫勒人工智能研究所）

作者：Stefano Damato, Lorenzo Zambon, Giorgio Corani, Dario Azzimonti

英文摘要：Intermittent time series are common in spare-parts demand and retail sales. Since the cost of forecast errors is typically asymmetric, decisions such as inventory control require the full predictive distribution rather than a point forecast. Many probabilistic forecasting methods have been proposed; their implementations, however, are scattered across different software frameworks, making it difficult to compare them systematically. We introduce this http URL, an R package that implements several probabilistic forecasting methods for intermittent series within the fable framework. The package allows several models to be fitted and evaluated on a collection of time series through a single, simple forecasting pipeline. We also introduce TWEES, a new exponential smoothing model with a Tweedie predictive distribution. Fitting TWEES requires repeated evaluation of the computationally demanding Tweedie density. We also release the R package tweedieDistr, whose implementation of the Tweedie distribution is substantially faster than the existing one while preserving the same numerical accuracy. We evaluate the methods implemented in this http URL on four datasets, also released in the package.

AI 总结：本研究对孟加拉语医学NER进行了大规模基准测试，发现微调的XLM-RoBERTa以F1 0.5959创下新最先进水平，且多语言模型优于语言特定模型，提示仅流程效果远逊于微调模型。

链接：https://arxiv.org/abs/2609.29101

作者：Rakib Abdullah, Md. Maruful Islam Maruf

英文摘要：Medical Named Entity Recognition (NER) for low-resource languages remains a challenging task due to high linguistic variability and a scarcity of domain-specific annotated corpora. This work presents a comprehensive empirical benchmark evaluating three fine-tuned transformer encoders-BanglaBERT, multilingual BERT (mBERT), and XLM-RoBERTa-against GPT-4o mini under zero-shot and few-shot prompting configurations for Bangla medical NER. In contrast to prior studies that evaluated large language models on limited subsets of only 50 samples, we conduct a large-scale evaluation across the full test set of 3,179 samples, providing statistically robust and reproducible baselines. Our fine-tuned XLM-RoBERTa model achieves an F1- score of 0.5959, establishing a new state-of-the-art and surpassing the previously reported best result of 0.5848. Crucially, we demonstrate that the language-specific BanglaBERT model consistently underperforms its multilingual counterparts with an F1-score of 0.4937, indicating that pretraining domain diversity can outweigh language specificity in highly specialized clinical settings. Furthermore, we present a detailed per-entity-type analysis for this task, revealing that Medicine and Specialist categories are recognized with high reliability, achieving F1- scores above 0.83, while the Symptom category remains the most challenging with an F1-score of 0.4367 despite being the most frequent training class. Finally, fine-tuned transformer models outperform the optimal prompting configuration by a factor of 3.76, confirming that prompt-only pipelines remain inadequate for structured clinical entity extraction in low-resource language environments.

AI 总结：通过四维审计七个公共教育预测数据集，发现多数存在跨组脆弱性，基准可靠性受数据结构限制而非算法，提出建模前审计作为质量门槛。

链接：https://arxiv.org/abs/2609.29625

机构：Changsha University of Science and Technology（长沙理工大学）； Hunan Agricultural University（湖南农业大学）

作者：Yan Ma, Lizhuo Zhang

英文摘要： Across seven public educational prediction datasets, three passed all four pre-modeling reliability checks; the remaining four either failed group-aware generalization tests or lacked the provenance metadata needed to run them. One dataset was initially classified as failing but corrected after excluding group-identifier features from the holdout matrix, demonstrating that the audit can distinguish genuine cross-group confounding from feature-encoding artifacts. Each dataset was audited before model optimization using four checks: baseline gap, split instability, null separation, and metadata adequacy under group-aware holdout. The dominant failure mode was not weak iid performance alone but cross-group fragility: in the clearest case, UCI Student declined from iid R-squared 0.242 to group-holdout R-squared -0.097, while Higher Ed collapsed from 0.041 to -8.79. Increasing model complexity did not remove this pattern: ensemble models improved structurally sound datasets but amplified instability or failed under group holdout on fragile ones. An exploratory cross-dataset comparison further showed that stronger profiles clustered in larger, richer-grouped, performance-proximal datasets, while random-split performance severely overstated deployable signal in fragile datasets. Classification-metric sensitivity analyses reached the same substantive conclusions. The results show that benchmark reliability in educational AI is constrained less by algorithm choice than by data structure, group heterogeneity, and evaluation design. A reusable pre-modeling audit offers a minimum quality gate before public educational datasets support strong benchmark or deployment claims.

AI 总结：针对噪声、离群点和类别不平衡问题，提出基于粒球计算的模糊随机向量功能链接网络GBFRVFL，通过两种隶属度方案增强鲁棒性，在37个基准数据集上优于基线模型。

链接：https://arxiv.org/abs/2609.29670

机构：Indian Institute of Technology Indore（印度理工学院印多尔分校）； Qatar University（卡塔尔大学）

作者：A. Quadir, A. Rahaman, P. N. Suganthan, M. Tanveer

英文摘要：In practical machine learning tasks, data are often contaminated with noise, outliers, and class imbalance, which can degrade the performance of conventional models. While random vector functional link (RVFL) networks offer fast training and strong generalization, they do not explicitly handle uncertainty or exploit local data structure. To address these limitations, we propose a fuzzy granular-ball random vector functional link (GBFRVFL) framework that leverages granular-ball computing to abstract raw samples into adaptive granular balls. Within this framework, we introduce two membership assignment schemes: (i) F-GBRVFL, which incorporates fuzzy membership to quantify the reliability of each granular ball, and (ii) SDAP-GBRVFL, which we propose, incorporates a novel statistical density-adaptive pythagorean membership (SDAPM) scheme that dynamically adjusts membership and non-membership values based on class variance, local sparsity, and granular-ball compactness. These schemes enhance robustness to noise, outliers, class imbalance, and uncertainty in granular-ball distributions, while retaining the computational efficiency of RVFL networks. Extensive experiments on 37 benchmark UCI and KEEL datasets under both clean and noisy conditions demonstrate that the proposed models consistently outperform baseline models, achieving superior accuracy and stability. The results validate the effectiveness of integrating granular-ball computing with adaptive membership schemes for reliable, scalable, and noise-tolerant learning.

AI 总结：针对语音错误信息，提出VeriSpeak基准，发现文本到语音存在模态差距，检索加显式推理可提升语音事实核查准确率至86.1%。

链接：https://arxiv.org/abs/2609.30227

机构：IISER Bhopal（印度科学教育与研究学院博帕尔分校）； King’s College London（伦敦国王学院）； MBZUAI（穆罕默德·本·扎耶德人工智能大学）

作者：Debajyoti Mazumder, Mamta, Abhirama Subramanyam Penamakuri

英文摘要：Online misinformation increasingly appears in spoken formats such as news clips, podcasts, interviews, political speeches, and social media videos, creating a need for fact-checking systems that can verify claims directly from speech. We introduce VeriSpeak, a probe benchmark for studying speech-based fact verification in Large Audio Language Models (LALMs). VeriSpeak contains 3,879 spoken claims spanning temporal, geographical, and relational facts, with balanced true and false labels. The benchmark is designed to examine whether factual verification ability transfers from text to speech, and whether retrieval-augmented LALMs can use textual evidence to correctly support or refute spoken claims. Our experiments reveal a consistent text-speech modality gap: LALMs that verify written claims reliably often fail on the same claims when spoken. Moreover, retrieval alone provides limited gains because models frequently conflate retrieved evidence with the spoken claim. In contrast, retrieval combined with explicit reasoning improves claim-evidence comparison, with a thinking-tuned LALM reaching 86.1% accuracy. VeriSpeak highlights that effective speech misinformation detection requires not only speech understanding, but also grounded reasoning over retrieved evidence. The dataset is publicly available via Hugging Face at this https URL.

AI 总结：本文揭示残差尺度不足以衡量可学习性，提出尺度归一化图狄利克雷粗糙度作为诊断指标，并确立基线互补性为靶标设计核心原则，以提升科学机器学习泛化能力。

链接：https://arxiv.org/abs/2609.28782

机构：University of Toronto Scarborough（多伦多大学士嘉堡校区）； Alliance for AI-Accelerated Materials Discovery (A3MD)（AI加速材料发现联盟）； University of Toronto（多伦多大学）

作者：Kareem M. Gameel, Ihor Neporozhnii, Sjoerd Hoogland, Oleksandr Voznyy

英文摘要：In scientific machine learning, $\Delta$-learning trains models on residual errors relative to physical baselines, assuming that more accurate baselines with smaller residual scales inherently improve downstream performance. Here, we demonstrate that residual scale alone is an insufficient heuristic for learnability. Evaluating molecular graph neural networks on total energy targets, we show that complex local descriptor baselines can yield small residual targets that are disproportionately rough within architecture-informed proxy spaces and harder to learn relative to their scale. Conversely, semi-empirical baseline reduces both scale and normalized roughness, improving in-domain and out-of-domain prediction. We introduce scale-normalized graph Dirichlet roughness ($D_{\text{IQR}}$) as a pre-training diagnostic for residual learnability and establish baseline complementarity as a core target-design principle, elevating target space formulation alongside model architecture as a key axis for scientific machine learning.

AI 总结：本文从子空间几何视角揭示重建式无监督学习失败机制，提出动态推拉与嵌套流形雕刻方法，在无需异常标签下提升异常检测性能。

链接：https://arxiv.org/abs/2609.28832

机构：Tampere University（坦佩雷大学）； Radboud University（拉德堡德大学）

作者：Mehmet Yamaç, Yagmur Mustu, Muhammad Numan Yousaf, Lei Xu, Marcel van Gerven

英文摘要：Reconstruction-based unsupervised learning can fail in two opposing ways: a model may reconstruct anomalies too accurately or discard valid nominal variation. Using the Pursuit of Subspaces hypothesis, we characterize these failures through the meet, union, and join geometries induced by the nominal components. Excess learned range produces join blindness, while insufficient capacity produces meet preference and loss of nominal fidelity. We show that the compact nominal union is optimal among nominal faithful ranges and generally requires a nonlinear reconstruction map. Based on this geometry, we introduce Dynamic Push and Pull, which learns from controlled perturbations without anomaly labels, and nested manifold carving, which applies the same principle recursively in latent space. Experiments confirm the predicted changes in latent geometry across every tested Push and Pull configuration. The proposed methods improve reconstruction-based anomaly detection across standard benchmarks and unseen image degradations, while also improving pretrained ECG representations for downstream classification. These results connect reconstruction failures to identifiable geometric conditions and provide practical mechanisms for learning compact representations.

AI 总结：本研究提出一种下行受控的在线预测组合方法，结合冻结预测器与静态及在线修正器，在延迟和修正结果下实现不劣于初始预测的性能，并在多个基准和负荷预测中验证了其有效性。

链接：https://arxiv.org/abs/2609.29096

机构：Yonsei University（延世大学）

作者：Minkyoung Kim, Hyunjung Byun, Yohan Lee, Beakcheol Jang

英文摘要：Post-hoc correction adjusts a forecaster that cannot be retrained, such as a foundation model, but a correction fitted where errors are stable can hurt where they shift. We aim for downside control: not much worse than the starting forecast. We combine the frozen forecaster, a static corrector and an online corrector on the simplex, using only losses that mature after the horizon. Across seven benchmarks and four base models, two of them foundation models, the worst deterioration over 28 pairs at the main horizon is 0.15% and gains reach 11.5%. On day-ahead load for seven European bidding zones it lowers mean MSE in all seven zones, while single correctors raise mean MSE by up to 102% where the published forecast is most accurate. Three empirical conditions on expert speed, stream length and outcome alignment, each fixed by a documented failure, delimit its scope. Learning from the provisional outcome improves four zones on the settled one; learning on the settled outcome restores all seven.

AI 总结：BridgeMem通过残差校正建模查询主体与候选对象间的二元转移证据，在五个基准上全面超越九种基线，验证了显式二元转移建模对时序知识图谱预测的价值。

链接：https://arxiv.org/abs/2609.29268

机构：Shanghai Jiao Tong University（上海交通大学）； University of Chicago（芝加哥大学）； Jinan University（暨南大学）

作者：Zeyan Li, Libing Chen, Shengda Zhuo, Yin Tang, Jianfeng Xu

英文摘要：Temporal knowledge graph forecasting aims to infer future relational facts from the temporal structure of observed events. Existing forecasters mainly summarize history through entity states, relation states, paths, or exact recurrence. These views often miss pair-specific transition evidence, that is, the way prior relations between the query actor and a candidate change the odds of the target relation. We introduce BridgeMem, which estimates this quantity as a residual added to the log scores of a frozen full-vocabulary forecaster. For each candidate, BridgeMem retrieves the pair's events that strictly precede t, encodes their relations, directions, and lags, and converts them into a likelihood-ratio correction. A support-adaptive empirical-Bayes reader trusts exact transition counts where they are abundant and backs off to a learned attention estimator where they are sparse. The backbone's own uncertainty gates the correction, so confident queries and candidates without dyadic history are left unchanged. On five benchmarks, BridgeMem improves on the strongest of nine baselines from 2021--2026 in all 20 filtered MRR and Hits@{1,3,10} comparisons, with MRR gains of 0.0213, 0.0164, 0.0216, 0.0112, and 0.0028 over the best prior result. These results show the value of explicit dyadic transition modeling.

AI 总结：提出m-WCN框架，通过神经化GHM多小波分解联合提取时间与频率特征，并构建TFBC和FTB分别用于分类与预测，在64个UCR数据集和七个基准上平均提升19.97%和19.92%。

链接：https://arxiv.org/abs/2609.29317

机构：Beihang University（北京航空航天大学）

作者：Xiaohan Jiang, Jingyuan Wang, Jiahao Ji, Yongyao Wang, Chen Yang, Junjie Wu

英文摘要： Time series analysis is fundamental in domains such as finance, healthcare, and meteorology. Real-world time series often exhibit multiscale characteristics shaped by diverse latent factors, resulting in intricate temporal patterns and rich frequency structures. However, existing approaches typically focus on either frequency-domain decomposition or time-domain pattern extraction in isolation, neglecting their joint structure. This decoupled modeling limits representation expressiveness and undermines performance in tasks requiring simultaneous temporal and spectral reasoning. To address this gap, we propose m-WCN, a novel end-to-end deep learning framework that neuralizes multi-wavelet decomposition for joint extraction of temporal patterns and frequency components. By approximating the classical GHM multi-wavelet transform with trainable convolutional operators and enforcing orthogonality constraints, m-WCN produces interpretable multi-resolution representations. Built on this foundation, we introduce two task-specific architectures: TFBC for time series classification, which boosts discriminative features across frequency scales, and FTB for forecasting, which ensembles frequency-aware predictors. Extensive experiments on 64 UCR datasets and seven public forecasting benchmarks demonstrate the effectiveness of our approach. Built on the neuralized m-WCN, our TFBC and FTB outperform various baseline models across diverse datasets, achieving average improvements of 19.97% in classification and 19.92% in forecasting tasks.

AI 总结：本文提出基于改进U-Net的轻量级概率降尺度模型，采用两阶段训练（确定性预训练+概率微调），在CORDEX-ML-Bench上超越现有RMSE最先进水平，兼顾计算效率与分布拟合。

链接：https://arxiv.org/abs/2609.29383

机构：University of Glasgow（格拉斯哥大学）； NORCE Research AS（挪威研究中心）； Bjerknes Centre for Climate Research（皮耶克尼斯气候研究中心）

作者：Joseph McLean, Tiffany Vlaar, Sigrid Passano Hellan, Linus Ericsson

英文摘要：Climate data downscaling is the task of increasing the spatial resolution of climate data, typically by generating fine-resolution regional climate data from coarse global model output. Recent machine learning (ML) work in the related task of weather forecasting has seen significant improvements due to newly devised training methods and architectural components, but these have not yet benefited downscaling. We adapt two of these methods to create a family of lightweight probabilistic ML downscaling models built on a modified U-Net backbone and evaluate them on the CORDEX-ML-Bench suite for daily maximum temperature and precipitation across three geographic regions: the Alps, New Zealand and South Africa. We find that a two-stage training curriculum, combining deterministic pretraining with probabilistic tuning, transfers well to downscaling, beating the state-of-the-art for RMSE. Our work provides an advancement towards lightweight, probabilistic downscaling models, reducing the current trade-off between computational intensity and distributional fit.

AI 总结：针对数据表中重复行导致的评估歧义，提出SCOUT因子化异常检测器，分离复制不变支持证据与计数证据，实现复制鲁棒的异常检测，并在686个数据集上验证其有效性。

链接：https://arxiv.org/abs/2609.29580

作者：Jie Deng

英文摘要：A released table is often treated as an i.i.d. sample, although its repeated rows may encode business frequency, repeated entities, joins, resampling, or extraction errors. We show that this ambiguity creates a hidden measurement layer with three consequences: feature-identical rows impose an attained evaluation ceiling, row-weighted AUROC is sensitive to replication, and row-trained detectors learn a multiplicity-size-biased law. An exact-row audit of all 690 OddBench datasets finds train-test overlap in 355, feature-identical label conflict in 147, and a test anomaly identical to a training normal in 137. Switching from row to support weighting changes AUROC by at least 0.05 on 50-61 datasets across four classical detector geometries. We introduce SCOUT (Support-Count Orthogonalized Unsupervised Testing), a factorized anomaly detector that separates replication-invariant support evidence from exposure-aware count evidence. Factorwise split-conformal calibration yields marginal false-positive-rate control, while the support channel is exactly invariant to arbitrary positive row replication. On 686 OddBench datasets and five seeds, support-only SCOUT is non-inferior to row-wise Isolation Forest in raw AUROC and improves replication-invariant AUROC. External normal-support evaluations track nominal false-positive levels, and four backbones remain exactly unchanged under controlled replication. Semi-synthetic interventions show that conditional count modeling helps materially only under strong rate heterogeneity. These results specify when multiplicity should be treated as signal, nuisance, or uninterpretable without additional information.

AI 总结：本研究提出一种验证协议，结合预测竞争力、解释稳定性和重训练忠实性，通过重建ASSISTments 2009数据并比较XGBoost与深度模型，证明解释差异源于信息而非模型，且TreeSHAP特征排名稳定有效。

链接：https://arxiv.org/abs/2609.28502

作者：Praveena Padi, Arun Morampudi, Ujval Sai Gopal Irrinki, Pradeep Kumar Dolabehera Kakitapelli

英文摘要：Knowledge tracing (KT) models predict student performance opaquely, limiting pedagogical action. This study contributes a validation protocol testing predictive competitiveness (RQ1), explanation stability (RQ2) and retraining-based faithfulness (RQ3) together. Thirteen behavioral features across five pedagogical themes were engineered from ASSISTments 2009 and 2012, with history features computed from temporally preceding interactions and current response latency retained only for retrospective analysis. ASSISTments 2009 was rebuilt: the uncorrected skill-builder release duplicates each multi-skill interaction across one row per skill, and because those rows share one correctness label, they leak it into preceding-interaction features. Rebuilding lowered model AUC and reordered the explanation results. An Extreme Gradient Boosting (XGBoost) model explained with Tree SHapley Additive exPlanations (TreeSHAP) was compared against four deep baselines (DKT, SAKT, AKT and SimpleKT) under an information-matched protocol giving the deep models the same behavioral signals and restricting XGBoost to what is derivable from the identifier-and-correctness stream they consume. XGBoost reached an area under the curve (AUC) of 0.777 on 2012 and 0.786 on rebuilt 2009, with prediction-time AUCs of 0.771 and 0.775, respectively, after excluding current response latency; restricted to the baselines' information it performed as they did (0.697 against 0.700, and 0.717 against 0.720), locating the difference in information supplied, not model family. Rankings were consistent across folds, seeds and conditioning schemes (Spearman rho = 0.989-1.000), and removing top-ranked TreeSHAP features harmed AUC more than random removal, though split-gain and permutation rankings performed comparably. Student-level examples are illustrative interpretations, not validated recommendations.

AI 总结：针对SHAP和LIME在从右到左语言中可视化失败的问题，提出SHAP-RTL渲染层，纠正阅读方向和文字塑形，保留归因值，在多种语言数据集上显著降低字符错误率。

链接：https://arxiv.org/abs/2609.28565

作者：Rameesha Zia, Muhammad Shahid Iqbal Malik

英文摘要：Post hoc explanation methods such as SHAP and LIME are widely used to interpret text classifiers, but their visualizations are mainly designed for left-to-right languages. When applied to right-to-left (RTL) languages such as Urdu, Arabic, Persian, and Hebrew, the attribution values remain mathematically valid, while their visual presentation fails. Tokens appear out of sequence, connected letterforms break apart, and plot layouts do not follow the natural reading direction. This study addresses this gap as a visualization problem rather than a limitation of the explanation methods themselves. We present SHAP-RTL, a rendering layer that corrects reading direction and script shaping in SHAP and LIME visualizations, with per-language font selection, while preserving the original attribution values, feature ordering, and model outputs. The approach is evaluated on Urdu, Arabic, Hebrew, and Persian hate and offensive-language datasets using TF-IDF and logistic regression classifiers. Rendering correctness is measured by an OCR round trip over 200 feature words per language. Default rendering yields character error rates of 0.820 to 0.979, meaning the label no longer carries its token; the common reshape-and-reorder workaround fails for Urdu at 0.998, worse than no correction; and the Matplotlib 3.11.0 text rewrite inverts that workaround, while SHAP-RTL remains correct under both versions. The framework also verbalizes the same attributions as short contextual explanations in the reader's language, constrained to the identified features. Evaluation in this paper concerns rendering correctness; assessment of the generated explanations is left to future work. The study highlights the importance of language-aware visualization in making post hoc explainability more accessible across different writing systems.

AI 总结：针对历史数据修订导致预测信息泄露的问题，提出修订感知的时间序列基础模型VINTAGE-TS，区分观测时间与信息可用时间，通过联合预测分布建模首次发布值及后续值，并设计了评估框架与软件验证流程。

链接：https://arxiv.org/abs/2609.28576

机构：Superior University Lahore（拉合尔卓越大学）

作者：Taimoor Ahmad

英文摘要：Historical observations are not always fixed: statistical agencies revise previously published values as new evidence arrives. Forecasting from a contemporary download can therefore expose a model to information unavailable at the date it purportedly made a prediction. We propose VINTAGE-TS, a revision-aware adaptation of a time-series foundation model that distinguishes observation time from information-availability time. Its targets are the next period's first-published value and the value available a fixed number of days after that publication; neither is declared final truth. A joint predictive distribution preserves dependence between these targets and exposes uncertainty about their difference. We specify an ALFRED-based rolling evaluation, a matched Chronos-2 comparison, conventional and revision-aware baselines, and a separate audit of pretraining overlap. The accompanying software implements validity-interval reconstruction, delayed-label filtering, a frozen-backbone adapter interface, and reproducible diagnostics. An executed synthetic demonstration and a 25-configuration sensitivity suite verify the workflow, expose variation across seeds and revision regimes, and illustrate how hindsight contamination changes measured performance. Thirty one automated tests check temporal and integration contracts. Real ALFRED and Chronos-2 experiments have not been executed; no empirical foundation-model advantage is claimed.

AI 总结：本文提出图动力学模型（GDM），用于随机和部分可观测环境中演化拓扑的图世界模型，并引入图分布距离（GDD）度量，实验证明其优于基线并具备大图零样本泛化能力。

链接：https://arxiv.org/abs/2609.28670

机构：Oxford Robotics Institute（牛津机器人研究所）； University of Oxford（牛津大学）

作者：Alex Schutz, Nick Hawes, Victor-Alexandru Darvariu

英文摘要：Graph-based world models have recently emerged as a means of learning transitions over relational state representations. However, existing approaches are largely limited to fixed-topology graphs or deterministic, fully observable environments. We propose the Graph Dynamics Model (GDM), a world model for graph-structured observations that is designed to handle the more general setting of evolving topologies in stochastic and partially observable environments. The GDM uses a sparse recurrent adjacency matrix to model topology updates and perform message passing, together with a recurrent state-space architecture for modelling stochastic transitions. Furthermore, we identify a gap in the evaluation of graph-based world models, as existing methods do not provide a means of comparing predicted and true distributions over the joint graph state comprising the interdependent topology, node features, and graph features. We therefore introduce the Graph Distribution Distance (GDD) metric, which uses maximum mean discrepancy with a graph kernel to comprehensively compare joint next-state distributions. We evaluate the GDM across several environments, including stochastic and partially observable settings. We demonstrate that GDM outperforms baseline models and displays zero-shot generalisation on large graphs.

AI 总结：LabFactory框架让AI构建者将科学简报转化为可执行AI实验室，通过独立主机评估交付系统，在28个构建、33个子测试中全部超过参考值，证明AI可端到端实现科学任务。

链接：https://arxiv.org/abs/2609.28697

机构：University of Oxford（牛津大学）； University College London（伦敦大学学院）； Technical University of Munich（慕尼黑工业大学）； Oxford-Suzhou Centre for Advanced Research, China（牛津-苏州先进研究中心）

作者：Jinge Wu, Hongjian Zhou, Mingde Zeng, Jiayuan Zhu, Junde Wu, Jiazhen Pan, Lei Clifton, Andrew Liu, David A. Clifton

英文摘要： Scientific tasks specify a desired capability, but realizing it often requires building a computational system tailored to the task---acquiring data, designing representations, training models, implementing tools, and deciding how they are used at inference. We present LabFactory, a framework in which an AI builder turns a scientific brief into an executable AI lab: a task-specific solver that integrates models, knowledge resources, tools, and a controller behind a fixed interface. The builder develops and packages the lab in a metered workspace; a separate host then executes the delivered artifact on held-out inputs, with reference labels kept outside the solver's input interface, and scores its outputs under the task's protocol. This makes the delivered system, rather than the builder's account of its progress, the object of evaluation. We document 28 selected constructions across seven scientific task categories---from molecular and genomic prediction to physiological signals, clinical decision support, and biomedical text---whose delivered labs exceeded their configured reference values on all 33 subtests under host-side execution. Ten contain predictive models fitted during construction; the others assemble retrieval systems, executable analysis environments, and tool-driven workflows around a fixed platform LLM. Together they show that an AI agent can carry a scientific brief all the way to a working lab that can still be invoked, inspected, and checked after construction ends.

AI 总结：本研究利用分布式声学传感和深度学习，构建了高时空分辨率的城市交通监测框架，实现了车辆轨迹检测与交通状态推断，为实时交通动态观测提供了高效方案。

链接：https://arxiv.org/abs/2609.28793

作者：Hao Tian, Heng Cai, Xiaowei Chen, Yifan Yang

英文摘要：Mapping the distribution of traffic dynamics at high spatiotemporal resolution is a fundamental question in transportation research. Distributed acoustic sensing (DAS), an innovative seismic observation tool, emerges as a promising solution for real-time urban traffic monitoring at high spatial and temporal scales. Distributed acoustic sensing repurposes existing underground fiber-optic cables as dense, continuous sensor arrays, enabling passive and privacy-preserving monitoring of roadway traffic activity at meter-level spatial and second-level temporal resolution. This study examines whether integrating DAS and deep learning models can serve as a continuous and efficient urban traffic observatory for revealing urban traffic dynamics (i.e. traffic volume and congestion, event-driven changes) at high spatiotemporal resolution. Using a DAS deployment along a roadway network in the City of College Station, Texas, USA, this study develops a deep learning-empowered analytical framework that converts raw ground vibration waveforms into spatiotemporal representations, detects vehicle trajectory, and infers traffic states from aggregated traffic volume and speed. A hybrid training strategy combining synthetic and manually annotated DAS images is used to improve vehicle detection under noisy and congested conditions, with model outputs further aggregated to characterize system-level traffic dynamics.

AI 总结：本文提出流递归模型（SRM），通过多潜在流递归细化暴露内部计算结构，在每参数性能上与GPT-2相当，为可扩展机制可解释性提供实用架构基础。

链接：https://arxiv.org/abs/2609.28809

机构：Sandia National Laboratories（桑迪亚国家实验室）； New Mexico Institute of Mining and Technology（新墨西哥矿业理工大学）； Institute for Complex Additive Systems Analysis（复杂增材系统分析研究所）

作者：Asael Sorensen, Charles Brock, David Chamberlain, Jennifer Minnich, Matthew Hoffman, Ramyaa Ramyaa

英文摘要：Mechanistic interpretability seeks to make verifiable statements about the internal behavior of large language models (LLMs). Many interpretability techniques struggle to scale with the increasing size and depth of architectures. Our solution to this is to introduce smaller models with structures that lend themselves to interpretability. In this work, we introduce the Stream Recursion Model (SRM), a modification of the Hierarchical Reasoning Model (HRM) designed to expose internal computational structure while remaining scalable. SRM organizes computation into multiple interacting latent streams that are updated through recursive refinement, enabling direct analysis of stream dynamics, causal contribution, and routing behavior. SRM achieves performance comparable to GPT-2 on a per-parameter basis. Our analysis reveals consistent and distinct behavior across streams, indicating structured specialization and interaction. These results suggest that SRM provides a practical architectural foundation for scalable mechanistic interpretability and opens up promising avenues for future research in both reasoning performance and interpretability.

AI 总结：LastOPD通过在最后层状态仅短暂应用潜在监督并交叉淡入词元级在线策略蒸馏，解决了潜在在线策略蒸馏中的后期崩溃问题，显著提升数学推理性能。

链接：https://arxiv.org/abs/2609.28845

机构：University of Illinois at Chicago（伊利诺伊大学芝加哥分校）； Visa Research（Visa研究院）； Case Western Reserve University（凯斯西储大学）； University of Florida（佛罗里达大学）； The Ohio State University（俄亥俄州立大学）

作者：Jie Yang, Zhengyu Fang, Zelin Xu, Jiarui Sun, Xiran Fan, Junpeng Wang, Liang Wang, Qinghua Liu, Yiwei Cai, Yan Zheng

英文摘要：On-policy distillation (OPD) corrects a student on the responses it writes, but its signal is the teacher's next-token distribution: it tells the student what the teacher says but misses how it thinks. Latent supervision promises the missing part by aligning the student's latent states to the teacher's. Recent methods such as OPRD bring this signal into on-policy distillation. However, we observe two failures of this recipe when distilling Qwen3-4B and Qwen3-8B into Qwen3-1.7B-Base. Early gain, late collapse: latent supervision alone lifts MATH-500 accuracy from 25 to 46 in 10 steps, but subsequent training degrades performance down to 11 with no recovery. Better alignment, worse behavior: although the alignment metric steadily improves throughout this collapse, the most aligned model turns out to be the worst performing. Further analysis suggests a mismatch in how the latent signal is applied: layers paired by depth play different roles in the two models, so continued alignment may pull the student toward teacher states it cannot understand. To address this, we propose LastOPD, which applies the latent signal only at the last-layer state, the common interface both LM heads read, and only during a 10-step crossfade into token-level OPD. This keeps the useful part of the latent signal and hands the student to token-level supervision before the collapse sets in. Extensive experiments show that LastOPD improves MATH-500 over token-only OPD by 5.55 and 4.02 points with the 4B and 8B teachers, leads on most held-out datasets, and reaches the final score of token-only OPD in about half the steps. Code is available at this https URL.

AI 总结：针对神经断层扫描中图像误差不能保证物理场准确的问题，提出CoroNeRF联合重建电子密度和温度场，并利用跨种子不稳定性实现无真值误差定位，在太阳日冕测试中验证了图像保真与场保真的差异及误差定位的有效性。

链接：https://arxiv.org/abs/2609.28868

机构：Harvard University（哈佛大学）； Center for Astrophysics | Harvard & Smithsonian（哈佛-史密森天体物理中心）； National Solar Observatory（国家太阳天文台）

作者：Alan Hsu, Jenna Samra, Alin Razvan Paraschiv, Liam Connor

英文摘要：Neural fields for scientific tomography are optimized from 2D images, but the actual quantity of interest is often a latent 3D physical field. Because the forward map is many-to-one, low 2D image error need not certify a correct 3D field. Moreover, the latent field is not directly supervised during training, and its error cannot be evaluated against truth at deployment. We develop CoroNeRF to jointly optimize 3D electron density and temperature fields directly from multiview, multiline intensities through a differentiable atomic-emission renderer. Using solar coronal tomography as a controlled testbed, we evaluate physical-field recovery and test whether cross-seed instability provides a ground-truth-free-at-inference indicator of local physical-field error. We underscore the following two observations. (i) Image fidelity is not field fidelity: spectral ablations show that limited-channel reconstructions can fit their available observations well while recovering substantially worse fields, whereas evaluation on a common richer probe exposes the discrepancy. (ii) Cross-seed instability ranks local physical-field error across tested matched-model conditions, supported by sparsification and physical signal-strength controls. Seed-deviation projections provide complementary directional validation, but shared forward-model mismatch can still produce incorrect cross-seed consensus. These results characterize joint thermodynamic recovery and the usefulness and limits of seed-based error localization in a controlled, single-scene solar tomography testbed.

AI 总结：针对振动光谱预测受立体电子环境扰动而失准的问题，提出SENK模型，融合等变Transformer、神经卡尔曼桥及NBO电子先验校准，在QM9S和QMe14S上超越DetaNet，实现可迁移的IR/拉曼光谱预测。

链接：https://arxiv.org/abs/2609.28935

作者：Zetong Li, Zhuosong Xie, Hengyu Fan, Jiaao Yu, Qiyao Hua, Zheng Lu, Liming Xu, Juanni Wu, Honglin Li

英文摘要：Vibrational spectral prediction can become inaccurate when localized stereoelectronic environments perturb intermediate response states and high-risk response units dominate characteristic spectral fingerprints, making prediction across external chemical space difficult. SO(3) Equivariant Neural Kalman Networks (SENK) form a response-state cascade that combines an equivariant transformer backbone for Hessian, dipole-derivative and polarizability-derivative learning, an Equivariant Neural Kalman bridge for state-dependent refinement and reliability sensing, and an NBO-informed electronic-prior pathway coupling consistency regularization with bounded, branch-specific guided spectral calibration. SENK outperforms DetaNet on QM9S and QMe14S while preserving full-spectrum IR and Raman fidelity from small molecules to drug-like systems. SENK remains stable and selectively improves spectrally sensitive features in biomolecular systems with complex stereoelectronic effects. It therefore integrates tensor prediction, reliability diagnosis and physics-informed calibration, supporting transferable vibrational spectroscopy from molecular systems to functional molecular materials.

AI 总结：受生物生长启发，提出基于点阵增强和GCNN的机械晶格生成与逆向设计框架，实现刚度预测及目标性能设计。

链接：https://arxiv.org/abs/2609.29024

作者：Weiyun Xu, Jiamu Liu

英文摘要：Natural load-bearing and transport networks are not assembled in a single step; they emerge through a temporally ordered process of growth, branching, reinforcement, and loop formation. Inspired by this developmental logic, this work introduces a morphogenetic graph-generation framework for mechanical lattices in which a discrete dot matrix provides potential nodes and the final architecture is created by sequential cross-layer and intra-layer growth. The same rule is visualized in two dimensions as a leaf-vein-like developmental sequence and implemented in three dimensions on a 3x3x3 nodal matrix containing 27 candidate nodes. A dataset of distinct three-dimensional lattices was evaluated by beam-based finite element analysis and represented directly as graphs. A graph convolutional neural network (GCNN) with three graph-convolution layers and dual global pooling learns the topology-property mapping and predicts effective compressive stiffness. Coupling the GCNN surrogate with rapid structural sampling enables inverse design: for a target stiffness of 1000 MPa, the selected design was predicted at 1042.43 MPa and validated by finite element analysis at 1027.49 MPa. Beyond straight members, the framework has also been extended to parameterized horseshoe-shaped curved beams made of nonlinear materials, enabling topology-geometry design toward prescribed deformation shapes. Our work provides a paradigm for augmenting the database of mechanical metamaterials, and the resulting perspective links biological morphogenesis, graph learning, and nonlinear shape programming in a unified generative design framework for architected materials.

AI 总结：BranchShine-CR是一个25M参数的紧凑多语言IPA转写模型，通过自条件CTC和一致性正则化，在16,646条测试话语上达到4.47%字符错误率，较ZIPA-CTC-NS相对降低22.3%，参数少十二倍，适用于低资源设备端发音评估。

链接：https://arxiv.org/abs/2609.29069

机构：International Centre for Neuromorphic Systems, Western Sydney University（西悉尼大学国际神经形态系统中心）； Neurabuild

作者：Nikhil Navas, Sergio Chevtchenko, Talisson Damiao, Saeed Afshar

英文摘要： We introduce BranchShine-CR, a 25M-parameter model for multilingual transcription into the International Phonetic Alphabet (IPA). It combines log-mel features, a rotary-position E-Branchformer encoder, intermediate self-conditioned connectionist temporal classification (CTC), and consistency regularization across augmented views. On 16,646 shared IPApack++ test utterances, it achieves 4.47% IPA character error rate, a 22.3% relative reduction from ZIPA-CTC-NS, with approximately one-twelfth as many parameters while being trained from scratch. BranchShine-CR also outperforms a similarly sized NeMo Conformer baseline across all 41 dataset language labels. Ablation studies indicate the individual components synergetically acting in model performance contribution. These findings support compact IPA recognition capabilities under limited compute budget, for applications in low-resource on-device pronunciation assessment.

AI 总结：本研究通过LIMBO沙箱实验探究LLM智能体中精确一次执行的归属，发现模型在可回读时起决定作用，契约在不可回读时主导，幂等键能显著降低重复率。

链接：https://arxiv.org/abs/2609.29095

机构：Microsoft（微软）

作者：Jiapeng Li

英文摘要：When a tool-using agent's write times out or returns a server error, the action may already have taken effect. Retrying blindly duplicates it -- a second charge, a second announcement, a second deployment -- while giving up skips required work. We ask where exactly-once behaviour should be enforced: in the model, in the agent harness, or in the tool contract. We introduce LIMBO, a deterministic sandbox of six services with realistic contracts (optional idempotency keys, eventually consistent and missing read paths) and twelve fault modes injected at the service boundary, including late commits, redelivery and partial batches; every episode is graded against a ledger of committed effects. Across 25,930 episodes spanning nine recent models, three production agent harnesses, two contract variants and fifteen recovery conditions, the answer depends on the fault. When an immediate read-back can reveal what happened, the model decides: frontier models instructed to act exactly once almost never duplicate a write whose acknowledgement was lost (0.5%), weaker models often do, and the model explains 53% of the explained variance. When it cannot -- the request is still in flight, or the transport delivered it twice -- the same frontier models duplicate in 56% and 74% of episodes, and the contract explains 81%. We prove that no verification-only policy is exactly-once under late commits without a bound on in-flight time. Waiting works when such a bound is short and known, but with heavy-tailed in-flight delays even an hour of waiting per episode falls short of offering an idempotency key on every write, which lowers the duplicate rate from 28% to 4% because agents use keys when they exist. The harness barely matters, a guard that attaches keys transfers across harnesses unchanged, and agents reported success in 90% of the episodes in which they had duplicated an effect.

AI 总结：本文提出一种在ESP32-S3上运行的边缘AI多模态系统，结合惯性传感与视觉姿态分类，实现动态环境中二值睡眠-清醒检测，准确率达96.5%和89%，验证了隐私保护的本地睡眠监测可行性。

链接：https://arxiv.org/abs/2609.29163

机构：Chemnitz University of Technology（开姆尼茨工业大学）； University of Hagen（哈根大学）

作者：Stefan Reitmann, Lena Oden

英文摘要：This paper presents an Edge AI-based system for detecting sleep and wake states in non-stationary mobile environments using resource-constrained embedded hardware. Conventional approaches relying on accelerometer-based activity metrics are highly susceptible to motion and vibration artifacts and are limited by strict compute and energy budgets of wearable and IoT devices. To address these challenges, a multimodal pipeline is designed and implemented on an ESP32-S3 microcontroller. The system combines inertial sensing for head movement analysis and visual pose classification. A dual-core architecture with FreeRTOS enables parallel execution of real-time data acquisition and on-device inference. Sleep detection follows a two-stage strategy: low-movement detection over a temporal window, followed by visual validation of poses. Experimental results show accuracies of 96.5% for motion-based detection and 89% for pose classification, yielding robust binary sleep-wake classification. Field tests confirmed feasibility in representative mobile scenarios. The results demonstrate that privacy-preserving, local sleep detection is achievable on edge hardware through careful co-design, while highlighting limitations in sensing intrusiveness, dataset scale, and system integration.

AI 总结：针对时间序列可解释性难题，提出XACT框架，通过学习可逆时频变换系数上的稀疏掩码生成解释，在合成和真实数据上验证了其有效性和灵活性。

链接：https://arxiv.org/abs/2609.29270

机构：Technical University of Denmark（丹麦技术大学）

作者：Theresa Dahl Frehr, Francisco Pelayo, Lukas Raad, Alicia García Sanz, Thea Brüsch, Tommy Sonne Alstrøm

英文摘要：Time-series explainability remains challenging because discriminative information is often encoded in latent frequency or time-frequency features rather than in the raw signal itself. Existing attribution methods typically operate either in the time domain or in a fixed transform domain, limiting their ability to capture salient information across different representations. We propose XACT, a general framework that learns sparse attribution masks over coefficients from arbitrary invertible time-frequency transforms. We evaluate the framework on the STFT, the continuous wavelet transform, and the discrete wavelet transform. In addition, we extend the virtual inspection layer approach from the STFT to both wavelet transforms, enabling LRP to generate explanations in these representations. On a synthetic dataset, XACT produces precise explanations and is less prone to highlighting spurious features than the tested baselines. Across two real-world datasets, XACT produces sparse and structured explanations, although no method performs best across all quantitative evaluation criteria. These results demonstrate that learning explanations directly in time-frequency representations offers a flexible approach to interpreting deep-learning models for time series data.

AI 总结：本文提出一种基于神经细胞自动机的元学习自组织机制，通过快速记忆更新实现无梯度的在线任务自适应，在保留分类任务上显著提升性能。

链接：https://arxiv.org/abs/2609.29281

作者： Krsto Proroković

英文摘要：Neural networks are typically adapted by computing gradients and updating model parameters. We investigate whether task-specific adaptation can instead emerge from a meta-learned self-organising process that requires no gradients at adaptation time. We instantiate this idea with a Neural Cellular Automaton in which locally interacting recurrent cells maintain both a recurrent state and a fast associative memory. During meta-training, backpropagation is used to learn the recurrent dynamics together with how the memory is read and written. Once training is complete, the slow model parameters remain fixed, and online adaptation occurs only through cellwise memory updates driven by local prediction errors and a delta rule. We evaluate whether the learned mechanism can adapt to semantically distinct held-out classification tasks. A single pass over the support data produces substantial improvements in held-out performance without gradient computation or parameter updates during adaptation, and the mechanism remains effective across large changes in the number of examples processed jointly. These results show that task-specific adaptation can be achieved through explicit fast-memory updates while keeping the slow model parameters fixed.

AI 总结：针对脑龄预测中特征可靠性评估无法捕捉联合波动的问题，提出重复信息感知的多重分形曲线回归（RMCR），联合建模曲线结构与重复扫描变异性，在HCP-A和Cam-CAN上分别将单次运行MAE降低6.1%和7.9%，并提升受试者内一致性。

链接：https://arxiv.org/abs/2609.29307

机构：University of Southern California（南加州大学）； University of Toronto（多伦多大学）

作者：Yu Chang, Anzhe Cheng, Jiahao Chen, Heng Ping, Peiyu Zhang, Puquan Pan, Tamoghna Chattopadhyay, Sophia Thomopoulos, Shahin Nazarian, Paul Thompson, Paul Bogdan

英文摘要：Brain-age prediction from resting-state fMRI provides a quantitative framework for characterizing age-related changes in spontaneous brain dynamics and for identifying functional signatures. Existing studies have linked fractal and multifractal scaling to age and examined the reliability of individual features. However, prediction repeatability depends on how features fluctuate jointly and how a predictor combines them, which feature-wise reliability assessments do not capture. To address this problem, we propose Repeat-informed Multifractal Curve Regression (RMCR), a structured framework for learning stable age-predictive patterns from multifractal curves. By jointly modeling curve structure and repeat-scan variability, RMCR learns predictive combinations of fluctuation orders that target both accuracy and within-subject consistency. Relative to a matched run-level ridge baseline, RMCR reduces single-run MAE by 6.1% on HCP-A and 7.9% on an external Cam-CAN cohort, and within-visit repeat absolute difference by 18.5% on HCP-A, using a single scan at inference.

AI 总结：针对混合加密流量中多标签网站指纹识别难题，提出FlowAtom方法，利用无标签流量预训练流编码器并聚合原子证据，在封闭和开放世界评估中均优于基线。

链接：https://arxiv.org/abs/2609.29330

机构：Beijing University of Posts and Telecommunications（北京邮电大学）； Zhongguancun Laboratory（中关村实验室）

作者：Chongru Fan, Wentao Huang, Wei Wang, Zhenquan Ding, Jinqiao Shi, Wei Cai, Zhiyu Hao

英文摘要：Identifying the set of monitored websites in mixed encrypted traffic is challenging because an individual flow often provides only partial evidence of website identity. To address this challenge, we propose FlowAtom, which constructs shared prototypes, called Atoms, from flow representations without website labels. Specifically, FlowAtom pretrains a flow encoder on external unlabeled traffic and aggregates Atom responses across flows within each observation window into a fixed-dimensional, permutation-invariant representation for monitored website-set prediction. Across Direct HTTPS, Trojan, and VMess, FlowAtom achieves micro-F1 scores of 97.82%, 94.43%, and 93.92% in closed-world evaluation, respectively, and consistently outperforms the evaluated baselines in open-world evaluation on windows containing monitored visits. The code is available at this https URL.

AI 总结：针对脉冲神经网络训练中尖锐损失景观与曲率信息利用不足的问题，提出二阶优化方法SpiKFAX，通过Kronecker因子近似Fisher信息矩阵，在多个架构与数据集上提升测试精度与训练稳定性。

链接：https://arxiv.org/abs/2609.29379

机构：Centre for Secure Information Technologies（安全信息技术中心）

作者：Ngoc Phu Doan, Ihsen Alouani

英文摘要：Spiking Neural Networks (SNNs) offer an energy-efficient alternative to conventional neural networks by exploiting sparse, binary spikes, and event-driven computation. However, the training of SNNs remains challenging, as spiking activations create a sharp loss landscape that hinders training, and diagonal-curvature optimizers such as the Adam family may fail to capture this geometry. The extension of curvature-based optimization methods to SNNs is further complicated by the sparse, discrete, and temporally recurrent nature of their underlying dynamics. To address these limitations, we propose SpiKFAX, a second-order optimization method that formulates a computationally tractable, Kronecker-factored approximation of the Fisher information matrix specifically adapted to the structure of SNNs. Empirical evaluation across five architectures and seven datasets demonstrates that SpiKFAX consistently yields improvements in test accuracy and training stability relative to other popular optimizers.

AI 总结：本文提出MORE-PLR，一种基于多输出回归的部分标签排序方法，通过编码器将带并列的排序转化为回归目标，并在推理阶段用后处理层生成桶序，实验证明其性能与现有最先进方法相当。

链接：https://arxiv.org/abs/2609.29386

机构：Ludwig-Maximilians-Universität München（慕尼黑大学）； Universidad de Castilla-La Mancha（卡斯蒂利亚-拉曼恰大学）； Munich Center for Machine Learning（慕尼黑机器学习中心）

作者：Santo M. A. R. Thies, Juan C. Alfaro, Viktor Bengs

英文摘要：The partial label ranking problem is a supervised learning scenario that aims to fit a preference model that predicts a bucket order defined over a set of labels for a given input instance. This problem generalizes the well-known label ranking problem, which, in practice, is limited to outputting total orders of labels. Existing partial label ranking methods have primarily extended label ranking approaches to handle ties in predictions. This paper proposes using multi-output regression to address the partial label ranking problem, introducing an encoder that, during the learning phase, transforms the (possibly incomplete) rankings with ties of labels to multivariate regression targets, an underexplored perspective in both label ranking and partial label ranking. Moreover, during the inference phase, we introduce several post-hoc layers that convert the multi-output regression results into the output bucket order to effectively implement this approach. This framework provides learning strategies that are competitive with the current state-of-the-art partial label ranking methods, as demonstrated through experimental evaluations.

AI 总结：本文提出ICE，一种基于Clifford潜空间的多模态图基础模型，通过任务对齐的几何表示保留实体语义并构建交互状态，在30个监督和小样本任务中均排名第一。

链接：https://arxiv.org/abs/2609.29398

机构：Beijing Institute of Technology（北京理工大学）； Shandong University（山东大学）； Sun Yat-sen University（中山大学）

作者：Xunkai Li, Xu Wang, Yinlin Zhu, Xiong Yongfu, Yi Liu, Rong-Hua Li, Guoren Wang

英文摘要：Multimodal attributed graphs connect entities, visual content, language, and observed relations. Learning one foundation across such graphs requires more than compressing each node into a fused Euclidean vector. The representation must preserve entity semantics, construct interaction state from graph neighborhoods, and expose that state to prediction units with different geometry. Our empirical study shows why these requirements are inseparable. Higher-grade channels recover pair relations across the foundation graphs, specialized queries reveal information hidden by a generic readout, and rigid blade isolation removes cross-grade capacity. We therefore introduce ICE (Interaction-aware Clifford Encoder), a multimodal graph foundation model built on a node-indexed Clifford latent field. Topology, text, and images enter explicit Cl(3) addresses. Edge-aware geometric products transform these directions into scalar, bivector, and trivector relations over observed neighborhoods. A protected Grade-1 route preserves entity semantics, while the full grade and depth bank remains available to fresh node and link heads. We establish exact cross-grade reachability, node-permutation equivariance, and a bound on the task residual around the semantic score. Experiments span one shared foundation over eleven graphs, six node-classification datasets, three link-prediction datasets, and matched few-shot tasks. ICE ranks first in all 30 reported supervised and few-shot comparisons. Core removals reduce every task summary, and mechanism controls connect the gains to higher-order transport, retained multidepth structure, semantic protection, and direct field access.

AI 总结：BLADE通过蒸馏LLM判断作为冻结教师正则化器，分离潜在真相与图谱记录，在五个基准上显著降低校准误差，同时保持排序竞争力，并仅对声明候选分布保证校准。

链接：https://arxiv.org/abs/2609.29487

机构：Iowa State University（爱荷华州立大学）； Brac University（布拉克大学）

作者：Ibne Farabi Shihab, Rabeya Bosri Tamanna, Abdo El Karaky, Sanjeda Akter, Anuj Sharma

英文摘要：Knowledge graph completion models optimize ranking, although many downstream applications require calibrated probabilities. We present BLADE, a variational model that separates latent truth from graph recording and distills offline language-model judgments into a frozen teacher regularizer. The LLM is absent during inference. Posterior samples provide predictive probabilities and epistemic uncertainty, while the compact teacher remains available only as an optional triage factor. Across five benchmarks, BLADE remains competitive under a common ranking protocol and reduces adaptive ECE by a macro-average of 60.1% relative to deep ensembles and 78.1% relative to temperature-scaled RotatE. On identical FB15k-237 candidate sets, BLADE also improves ECE, Brier score, and NLL over validation-selected histogram binning and a matched generative ComplEx2 model, with these improvements persisting on a prespecified near-miss pool. Under controlled injected missingness, the full triage score achieves a mean AUC-PR of 0.863, compared with 0.805 for its strongest non-teacher variant. Leakage stress tests show that aligned semantics matter, but they cannot exclude knowledge acquired during LLM pretraining. We therefore claim calibration only for the declared candidate distributions, not for all unobserved triples.

AI 总结：提出任务感知频谱剪枝（TASP）框架，通过校准模块级频谱描述符并构建任务特定掩码，在43%FLOP减少下保持Llama-3-70B性能97.7%，解码加速1.44倍。

链接：https://arxiv.org/abs/2609.29499

机构：Iowa State University（爱荷华州立大学）； Kalinga Institute of Industrial Technology（卡林加工业技术学院）

作者：Ibne Farabi Shihab, Fariya Afrin, Sanjeda Akter, Anuj Sharma

英文摘要：Static pruning imposes one sparse structure on every prompt, even though reasoning, retrieval, generation, coding, and translation can depend on different parts of a language model. We introduce Task-Aware Spectral Pruning (TASP), a post-training framework that calibrates module-level spectral descriptors against measured task-specific ablation effects, closes grouped-query-attention and SwiGLU dependencies during sparse-mask construction, and routes each user turn to one compiled mask that remains fixed throughout prefill and decoding. A module-disjoint pilot first determines whether the spectral signal is informative before full calibration. Under the stated retrospective operating rule, the pilot passes on the evaluated Llama-3-8B and Llama-3-70B checkpoints but rejects Qwen2.5-1.5B, demonstrating that applicability is model-dependent rather than universal. At a 43% active-FLOP reduction, the Llama-3-70B benchmark harness retains 97.7 +/- 0.2% of the dense BF16 score. In the deployment-matched INT8-weight/BF16-compute runtime on a single A100 80GB, the compiled sparse path retains 97.3 +/- 0.2% relative to dense BF16 and reduces decode latency from 45.2 +/- 0.4 to 31.3 +/- 0.4 ms/token, yielding a 1.44x speedup. Factorized ablations, disjoint-module tests, compiled structured baselines, routing-corruption studies, and an explicit 136-GPU-hour calibration audit further delimit the source and operating regime of these gains

AI 总结：本文针对布朗核梯子引入最小迹公共协方差，通过阈值、图余面积和有效电阻几何给出精确公式与确定性深度定律，并利用半定规划和凸松弛提供上下界证书，实现协方差认证与预测选择的区分。

链接：https://arxiv.org/abs/2609.29525

机构：Free University of Bozen–Bolzano（博尔扎诺自由大学）

作者：Mahdi Mohammadigohari

英文摘要：A representation-adaptive kernel class produces, on a fixed sample, a union of reproducing-kernel Hilbert-space ellipsoids rather than one ellipsoid. We introduce the minimum-trace common covariance that dominates the unrestricted empirical union generated by Brownian kernel ladders and develop its statistical, approximation-theoretic, and computational consequences. The covariance value admits exact formulations through absolutely two-summing operators and covariance-dominated multipliers, and it yields a universal Gaussian-complexity bound. A closed last-layer Dirac-trace reduction and a signed Brownian threshold representation convert the generic covariance problem into threshold, graph-coarea, and effective-resistance geometry. These tools give deterministic depth laws, conditional Gaussian reverses, random-design and perturbation transfers, and an exact empirical Kolmogorov-width formula whose leading covariance eigenspaces approximate the complete adaptive ball simultaneously. Finite contact, active semidefinite programs, verified separation, and a convex resistance-design relaxation provide complementary lower and upper certificates. A finite covariance-indexed Brownian path on frozen representations illustrates the distinction between successful covariance certification and predictive selection: all reported path certificates succeed, whereas the locked predictive study misses one predeclared aggregate criterion. The paper thereby identifies one finite-dimensional covariance object linking unrestricted kernel adaptation, Gaussian geometry, common subspaces, and certifiable computation.

AI 总结：本研究证明时间序列验证中训练充分性、测试覆盖性与时间因果性无法同时满足，并给出量化守恒律，指出扩展walk-forward是因果验证的帕累托最优方案。

链接：https://arxiv.org/abs/2609.29530

作者：Jiayu Li

英文摘要：Validating a model on a time series asks for three things at once: each training run should use most of the sample (sufficiency), the test sets should together cover most of the sample (coverage), and training data should come before test data (causality). We prove that the three cannot be had together and price each one. Let $\alpha$ be the smallest training fraction over folds, $\beta$ the fraction of the sample covered by tests, $\Lambda$ the fraction of the sample used as training data from the future of a test point, and $\delta$ the distance from a test point to the nearest training point in its future. Every scheme on a sample of length $T$ satisfies $\alpha+\beta \le 1+\Lambda$ and $\alpha+\min\{\beta,\delta/T\} \le 1$, and under $\beta$-mixing the leakage bias at a test point is at most $2M\beta_{\mathrm{mix}}(\delta)$. In words: going beyond the causal frontier $\alpha+\beta=1$ requires training on the future; that future data must sit within $(1-\alpha)T$ of a test point; and its harm depends on its distance, not its amount. Hence expanding walk-forward is exactly the Pareto frontier of causal validation, $k$-fold cross-validation buys the most future data, and purged $k$-fold with an embargo pays in distance instead, which is cheap when the process forgets quickly but cannot repair the part of causality demanded by non-stationarity. On pure noise, shuffled 5-fold reports an information coefficient of $+0.32$, while contiguous 5-fold, using the same amount of future data, reports $+0.004$.

AI 总结：针对云数据工程与分析中智能体协调可靠性问题，提出两个零信任框架，通过图、循环和智能体框架工程实现证据门控、有界恢复与零信任执行，实验验证了完成、恢复、授权及OLAP执行等指标。

链接：https://arxiv.org/abs/2609.29668

机构：Tata Research Development and Design Centre（塔塔研发与设计中心）

作者：Sagar Srinivas Sakhinana, Venkataramana Runkana

英文摘要：Large language model agents increasingly automate data workflows, but end-to-end cloud data engineering and analytical execution require reliable coordination across code, data, infrastructure, and runtime environments. We present two zero-trust frameworks. Zero-Trust Agentic Data Engineering generates, deploys, and verifies complete cloud data-engineering solutions from natural-language tasks, with completion conditioned on repository, deployment, runtime, and policy evidence. Zero-Trust Agentic OLAP combines governed Data Preparation with verified Online Analytical Processing (OLAP), permitting production promotion only after validation and evidence-bound approval, and releasing analytical answers only after Same-Snapshot Execution, Exact Result Equivalence, deterministic grounding, and reflection. Both frameworks share three abstractions: graph engineering for evidence-gated workflow structure, loop engineering for bounded recovery, and agent-harness engineering for zero-trust execution. We evaluate both frameworks under nominal execution, controlled failures, bounded recovery, and policy-constrained conditions, measuring verified completion, recovery, authorization enforcement, production promotion, and verified OLAP execution.

AI 总结：针对大学生动机缺乏和快感缺失症状预测中的类别不平衡问题，提出一种利用预测模型生成名义变量的新颖过采样方法，并在GPS数据集上验证其显著优于现有方法。

链接：https://arxiv.org/abs/2609.29690

机构：Deakin University（迪肯大学）； University of New South Wales（新南威尔士大学）

作者：Dang Nguyen, Bao Duong, Arun Kumar, Dat Phan-Trong, Julian Berk, Taylor Braund, Kien Do, Debopriyo Bal, Wu Yi Zheng, Leonard Hoon, Jill Newby, Helen Christensen, Svetha Venkatesh, Alexis Whitton, Sunil Gupta

英文摘要： University students experience disproportionately high rates of common mental health conditions, such as depression, which can impair learning, social functioning, and overall well-being. Within this context, symptoms of amotivation (i.e. loss of motivational drive) and anhedonia (i.e. diminished interest or pleasure) are particularly debilitating, yet they frequently go undetected. Developing new approaches to identify students with prominent amotivation and anhedonia could enable earlier and more targeted intervention. Machine learning (ML) methods have increasingly been used to classify individuals according to symptom severity. However, these ML models often suffer from class imbalance, where the majority of cases fall in the low-symptom group and relatively few in the high-symptom group. This imbalance can reduce model accuracy and bias predictions. To address this, studies commonly employ the popular oversampling strategy SMOTE. However, SMOTE has a notable limitation: it may generate invalid values for nominal variables. In this paper, we introduce a novel and effective oversampling method that addresses this shortcoming. Our approach leverages a predictive model to generate nominal variables, rather than interpolating them. We validate our method on a large-scale GPS location dataset collected from university students and demonstrate that it is significantly better than existing oversampling approaches in predicting elevated symptoms of amotivation and anhedonia.

AI 总结：针对平方损失，构造了大小与脂肪破碎维度近线性、与样本量无关的不可知压缩方案，移除对偶因子，解决了开放问题。

链接：https://arxiv.org/abs/2609.29696

作者：Guangjian Zhang

英文摘要：We construct, for every function class $\mathcal{F}\subseteq[0,1]^{\mathcal{X}}$ and every accuracy $0

AI 总结：本研究揭示经典测量理论三种统计量在LLM评判者评估中的误用，指出其无法单独归因于评判者，并提出四条报告准则以保持归因清晰。

链接：https://arxiv.org/abs/2609.29709

机构：University of Oxford（牛津大学）

作者：Louis Yiven Zhu

英文摘要：An LLM judge scores a bank of responses against a rubric, and the reliability comes back at $0.52$. What has been measured? Judge evaluation has begun borrowing reliability statistics from classical test theory, usually without stating the measurement design each statistic assumes, and we show that three widely portable ones mean something different for a judge than for a test because the judge setting rearranges the roles those designs rest on. First, an internal-consistency coefficient computed over rubric elements contains no scorer facet. Holding one judge's measured error rate fixed at $4.72\%$, KR-20 still ranges from $0.01$ to $0.68$ as the item bank is redesigned around it, and varying judge error moves the coefficient by a comparable amount, so item design and judge error are not separately identified and no single value can be read as a property of the judge. Second, the dependability index $\Phi(\lambda)$ is a ratio of variance components, and the classification probability with which it is sometimes identified differs from it by $0.25$-$0.43$ on our bank and by $0.17$-$0.30$ on simulated data where the underlying model holds exactly. Third, Livingston-Lewis accuracy is indexed to an examinee's own true score on the same instrument, so scoring it against external gold conflates judge unreliability with criterion invalidity. Reviewing the three closest judge-evaluation papers, we found no published instance of these errors, which makes the caution prospective. A coefficient that cannot be attributed to the judge nonetheless travels downstream into deployment decisions and disclosure documents. We therefore close with four reporting lines that keep the attribution attached to the number.

AI 总结：WeatherDiagFlow提出基于证据的雷达临近预报框架，通过诊断流细化和多智能体生成公报与审计，在FJRADAR上提升强回波预报技能。

链接：https://arxiv.org/abs/2609.29772

机构：Southeast University（东南大学）； Beijing Fengyun Meteorological Science and Technology Development Co., Ltd.（北京风云气象科技发展有限公司）； Beihang University（北京航空航天大学）； Fudan University（复旦大学）

作者：Chunlei Shi, Yufeng Zhu, Yixiao Liang, Dan Niu, Yongchao Feng, Qiliang Wu, Jiong Wang

英文摘要：Radar nowcasting is essential for short-term warning and emergency response, yet conventional systems mainly return future radar fields and provide limited support for operational communication and post-event verification. We formulate radar nowcasting as an evidence-grounded forecast--bulletin--audit task, in which a numerical forecaster produces both future radar fields and structured diagnostic evidence. Forecast-time bulletins use only model-available evidence, whereas post-event audits incorporate future radar truth only after the forecast horizon is observed. Based on this task formulation, WeatherDiagFlow predicts motion, growth and decay, heavy-echo risk, and uncertainty to condition rolling flow refinement, while frozen-scaffold residual calibration improves long-lead strong-echo preservation. A multi-agent layer converts the structured evidence into operational bulletins and independently generates verification audits without feeding textual outputs back into the forecaster. Experiments on FJRADAR demonstrate competitive overall performance and improved strong-echo event skill. WeatherDiagFlow therefore connects numerical prediction, evidence-grounded reporting, and auditable verification under a leakage-controlled protocol.

AI 总结：本文提出FlashLoop，一种无需训练的推理框架，通过token稀疏更新、稀疏注意力和KV残差量化减少循环Transformer中的跨循环冗余，实现无损精度下高达1.64倍加速和6倍KV缓存内存缩减。

链接：https://arxiv.org/abs/2609.29812

机构：ELLIS Institute Tübingen（ELLIS 图宾根研究所）； Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）； Tübingen AI Center（图宾根人工智能中心）

作者：Wanqi Yang, Shiwei Liu

英文摘要： Looped Transformers have attracted substantial attention as a parameter-efficient approach to increasing computational depth through repeated application of shared Transformer blocks. However, their practical advantages over conventional Transformers remain under debate: each additional loop incurs another Transformer pass and requires caching another set of KV states, causing inference FLOPs and KV-cache memory to grow continuously with loop depth. This overhead becomes particularly severe at large loop counts and long context, preventing the parameter efficiency of Looped Transformers from translating into practical inference efficiency. In this paper, we find that much of the additional computation and storage introduced by looping is redundant. As recurrence proceeds, state changes become increasingly concentrated on a small subset of tokens; attention-output differences are dominated by a sparse and stable subset of key columns; and KV residuals between adjacent loops become progressively more amenable to low-bit quantization. Building on these observations, we introduce FlashLoop, a training-free inference framework that reduces cross-loop redundancy through token-sparse updates, sparse attention, and KV-residual quantization. Across several Looped Transformers models, \textsc{FlashLoop} delivers lossless accuracy while achieving up to 1.64$\times$ end-to-end speedup and up to 6$\times$ KV-cache memory reduction, substantially improving the practicality of scaling Looped Transformers to greater computational depths and longer context.

AI 总结：SwitchPFN通过共享投影和状态码本为表格基础模型设计时间序列表示，保留局部动态并实现跨样本可比性，在基准上平均准确率最高，相对最强基线提升4.47%。

链接：https://arxiv.org/abs/2609.29814

机构：The Chinese University of Hong Kong（香港中文大学）； Cornell University（康奈尔大学）； Southeast University（东南大学）； University College London（伦敦大学学院）； Dalian Polytechnic University（大连工业大学）； Hainan Normal University（海南师范大学）； Anhui Agricultural University（安徽农业大学）； Beijing University of Posts and Telecommunications（北京邮电大学）； East China Normal University（华东师范大学）； Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）

作者：Zhenyi Zhu, Jacqueline Pang, Peilin Shen, Tianyi Song, Tingwei Zhang, Keyi Hu, Kangjun Yin, Shiwei Pu, Yingbo Zhou, Chen Shao

英文摘要：Tabular foundation models (TFMs) provide a promising route to time-series classification, but their effectiveness depends on how sequential data are converted into tabular representations. Existing representations face two challenges: global aggregation can lose the order of temporal evolution, while features computed in independently fitted coordinate systems may not have consistent meanings across sequences. We therefore view representation design for TFMs as a problem in its own right: the representation should preserve local temporal transitions while maintaining a shared feature definition across samples. We propose SwitchPFN, which learns a shared projection and regime codebook from the training sequences, making local dynamic operators and transition features directly comparable across samples. Across the evaluated benchmarks, SwitchPFN achieves the highest mean accuracy among the evaluated methods, improving over the strongest baseline by 4.47% relatively. Ablation studies, parameter sensitivity analyses, and reduced-training-data experiments further examine the contributions of the representation, its main design choices, and its behavior when labeled data are limited.

AI 总结：针对传感器稀疏导致多年路网AADT估计困难的问题，提出融合稀疏检测器与宏观模型的时空互补特征传播框架，在苏黎世验证误差低于10%。

链接：https://arxiv.org/abs/2609.29906

机构：Institute for Transport Planning and Systems, ETH Zurich（苏黎世联邦理工学院交通规划与系统研究所）； School of Transportation, Jilin University（吉林大学交通学院）

作者：Linghang Sun, Qishen Zhou, Michail A. Makridis, Anastasios Kouvelas

英文摘要：The estimation of Annual Average Daily Traffic (AADT) is vital for transportation planning and infrastructure maintenance, yet obtaining accurate values for an entire urban network across multiple years remains challenging due to the high cost and spatial sparsity of physical sensors. This research proposes a novel spatio-temporally complementary feature propagation framework that leverages the strengths of two distinct data sources: spatially sparse but temporally dense loop detector data, and a spatially complete but temporally sparse macroscopic transportation model. The methodology highlights a feature propagation algorithm on directed graphs, formulated as a Poisson energy minimization considering residues. The standard binary adjacency matrix is replaced with flow ratio matrices to capture real-world vehicle turn ratios at intersections. Validated in the city of Zurich, the algorithm demonstrates high computational efficiency, achieving convergence within minutes. Results indicate that the framework effectively reconciles theoretical models with empirical ground truths, yielding a normalized mean absolute error below $10\%$. This scalable approach provides a feasible solution for spatio-temporal network-wide AADT estimation through combining real-world limited sensor coverage and traffic models.

AI 总结：提出SpectrumAudit，一种无标签审计方法，通过相位随机化刺激和直流/交流重放，诊断可穿戴活动识别器对传感器偏置的依赖，在27个受害者上实现2.87-40.83点准确率损失。

链接：https://arxiv.org/abs/2609.29937

机构：Defense Innovation Institute, Academy of Military Science（军事科学院国防科技创新研究院）； School of Software Engineering, South China University of Technology（华南理工大学软件学院）

作者：Qingyu Wu, Yuan Wei, Renju Liu, Hua Cheng

英文摘要：Wearable human-activity recognition (HAR) models operate across sensors, subjects, and backbones, yet a smooth waveform may appear temporal while exploiting a persistent sensor offset primarily. We introduce SpectrumAudit, a label-sealed audit that fits a phase-randomized full-window stimulus on calibration windows from subjects held out from training and testing. After selection, it replays its exact DC projection and budget-constrained zero-mean residual on the same frozen victim without refitting. Across 27 victims from three datasets and three backbones, the selected waveforms cause 2.87-40.83-point three-phase robust accuracy losses. Under this replay budget, DC is more damaging than AC on 24/27 victims and recovers at least 90% of the full drop on 22/27; all 5 failures occur on WISDM. In a held-out UTD-MHAD check, the selected waveform causes 13.49-pp accuracy and 11.68-pp macro-F1 losses, versus -0.66 pp for matched random changes. The audit diagnoses offset versus zero-mean variation under a common peak-budget cap. The code will be released upon acceptance.

AI 总结：针对延迟反馈下的鲁棒控制难题，提出受小脑启发的多路复用预测与内部反馈框架，实现快速在线修正并将学习时间减少一个数量级。

链接：https://arxiv.org/abs/2609.29945

机构：NOVA School of Science and Technology（新里斯本大学科学与技术学院）； University of Oxford（牛津大学）

作者：Ana Carolina Filipe, Rui Ponte Costa, Cláudia Soares

英文摘要：Robust control under delayed sensory feedback remains a key challenge in both robotics and neuroscience. Classical cerebellar models explain delay compensation through forward prediction but fail to account for fast online corrections and rapid adaptation observed in biological systems. We propose a cerebellum-inspired control framework that combines multiplexed predictive representations with internal feedback. By jointly encoding kinematic variables and task-relevant error signals, the model enables accurate online correction despite delayed feedback. Furthermore, incorporating feedback within the cerebellar loop significantly accelerates adaptation, reducing learning time by an order of magnitude. Our results show that single-signal predictions are insufficient under delay, while multiplexing and feedback together provide a unified mechanism for online control and rapid learning.

AI 总结：本研究通过群论陪集视角，揭示Transformer和循环网络在状态跟踪任务中学习到的内部表示，连接部分准确性与学习阶段。

链接：https://arxiv.org/abs/2609.29951

机构：Conflux Labs Ltd； Michigan State University（密歇根州立大学）

作者：Zhiyu Zhang, Yupeng Li

英文摘要：State tracking requires composing a sequence of updates, but accuracy alone does not reveal what a model has learned. We study neural networks trained to predict the running product of group elements. We identify quotient solutions in Transformers, where models recover the quotient class while predicting nearly uniformly among its members. The reciprocal of class size predicts partial accuracy without a fitted parameter, extending parity-based accounts to non-parity quotients. Our baseline Transformers' predictions change little under prefix reordering beyond the exact-tracking frontier. We prove that, for finite groups under uniform i.i.d. full-group inputs, optimal order-blind exact accuracy converges to the reciprocal of abelianization class size as prefix length grows, consistent with the observed abelianization plateaus. Sequential updates permit more: any partition into right cosets of a subgroup, normal or not, survives sequential updates. In our census of standard Transformers, every recovered coset partition comes from a normal subgroup, whereas parameter-matched recurrent networks pass through both normal and non-normal right-coset stages during training. On $A_5$, we identify low-dimensional subspaces of the recurrent state that encode non-normal cosets. In the three-dimensional cases, coset mean vectors form approximate dodecahedra, and swapping the state components in these subspaces transfers the donor's coset state through a shared input suffix. Our results connect partial accuracy, learning stages, and internal computation through the subgroup cosets that models learn to track.

AI 总结：本文提出一个通用收缩框架，将带自举的随机更新建模为随机算子，在无需梯度结构且允许采样误差增长的情况下，推导出TD学习等算法的有限时间收敛界，并统一了现有确定性及随机梯度型结果。

链接：https://arxiv.org/abs/2609.29961

机构：Delft University of Technology（代尔夫特理工大学）； Rey Juan Carlos University（胡安卡洛斯国王大学）

作者：Ids van der Werf, Sergio Rozada, Antonio G. Marques

英文摘要：Many iterative algorithms rely on bootstrapping. A variable is updated using a second, frozen copy as a target, which is periodically replaced with the updated variable. Majorize-minimize and inexact proximal-point methods share this structure, as does temporal-difference (TD) learning. However, existing convergence guarantees for scenarios that combine sampled updates with targets refreshed only every $K$ steps rely on the specific structure of the update, such as linear approximation or gradient-based inner steps, and on uniformly bounded sampling error. We instead model the sampled update as a stochastic operator on the parameter space, which reduces the analysis to a contraction argument that needs no gradient structure and allows the sampling error to grow with the iterates. Within this framework, we derive a finite-time bound for i.i.d. samples and any target-update period $K$. We show that the iterates converge geometrically in root mean square to a ball around the fixed point, provided the sensitivity to the frozen target is smaller than the contraction slack of the inner map. Existing deterministic frozen-target contraction and stochastic-gradient-type bounds follow as special cases of our framework, and simulations of TD learning reproduce the predicted contraction rate and scaling of the error floor with the step size.

AI 总结：针对观测数据中异质性处理效应估计的归纳偏置选择难题，提出五专家集成框架GeoACE，融合多种几何并冻结权重，在多个基准上取得稳健性能，验证了多样几何与无泄漏聚合的鲁棒性策略。

链接：https://arxiv.org/abs/2609.29974

机构：University of Shiraz（设拉子大学）

作者：Ali Haghpanah Jahromi, Mohammad Taheri

英文摘要： Estimating heterogeneous treatment effects from observational data is difficult because the most appropriate inductive bias varies with overlap, treatment imbalance, prognostic structure, and sample size. We introduce the Geometry-Diverse Anchor-Correction Expert Ensemble (GeoACE), a five-expert framework that combines a common anchor-correction estimator with complementary overlap-aware and outcome-guided geometries. Its task-level ensemble weights are learned only from internal validation predictions, frozen before test evaluation, and then applied to experts refitted on the complete development sample. The fifth expert, O-Phi-ACE, constructs an outcome-free, overlap-aware statistical projection from covariates and treatment assignment and replaces the anchor input with this lower-dimensional geometry. We evaluate GeoACE against 11 comparators on eight benchmark protocols. Adding O-Phi-ACE reduced mean sqrt(PEHE) relative to the four-expert ensemble on all seven benchmarks with individual-effect truth, winning 998 of 1,225 paired tasks; the change on JOBS policy risk was negligible. The five-expert ensemble ranked first on IHDP100, IHDPA, and IHDPB and second on NEWS, differing from the NEWS leader by 0.13%. Across the seven sqrt(PEHE) benchmarks it obtained the lowest observed average rank (3.714), although the omnibus Friedman and Iman-Davenport tests were not significant (p=0.328 and p=0.330). Using the same five frozen experts, inverse-DR weighting was consistently better than winner-take-all selection, convex DR fitting, R-stacking, and causal Q-aggregation in benchmark-balanced analyses, but was statistically indistinguishable from equal weighting and DR ridge shrinkage. The evidence therefore supports geometry-diverse expert libraries and leakage-free aggregation as a robustness strategy, not universal superiority of either GeoACE or one weighting rule.

AI 总结：提出FROST在线框架，利用真实数据锚定的梯度反馈估计合成数据效用，动态过滤噪声样本，在图像分类、文本到SQL及工业广告重排序中提升性能。

链接：https://arxiv.org/abs/2609.29988

机构：Purdue University（普渡大学）； Meta

作者：Yanran Wu, Sana Lakdawala, Renzo Tassara Miller, Chongyang Bai, Sharath Ciddu, Shivendra Pratap Singh, Kungang Li, Sandeep Pandey, Chunwei Liu

英文摘要：Synthetic data can scale training supervision when real-world data are limited, but noise and distribution mismatch can reduce its value. Existing synthetic data selection methods often emphasize fidelity or diversity rather than the learner's evolving needs. We propose FROST, an online framework that estimates synthetic-data utility through gradient feedback anchored in real training data. It calibrates batch utility against recent history to determine when filtering is needed and filters samples only in out-of-band batches to determine what to retain, without an external verifier or held-out validation set. Experiments on two public benchmarks for image classification and LLM fine-tuning for text-to-SQL show that FROST filters out around 20--30% of the synthetic data while improving real-task performance compared with training on the full synthetic data pool. We further apply FROST during training in a large-scale industrial ads re-ranking system, achieving significant performance gains over a highly optimized production baseline, demonstrating its effectiveness and generalizability.

AI 总结：本文提出锚定规划，通过检索与当前和目标观察相似的记录片段并瞄准中间目标，使冻结世界模型在无需训练的情况下超越最终目标评分，显著提升长程控制性能。

链接：https://arxiv.org/abs/2609.30036

机构：Tsinghua University（清华大学）

作者：Xvyuan Liu, Jianjie Fang, Chen Gao, Yong Li

英文摘要：Planners built on visual world models commonly score each predicted outcome by its distance to the encoded goal image. We show that this target can limit control even with exact dynamics and globally optimal short-horizon search: reaching a goal may require actions that initially move away from it. With frozen LeWM models, intermediate targets substantially improve action synthesis and recorded-action ranking on Cube, PushT, Reacher, and TwoRoom. Learned targets and targets drawn from observed experience both produce these gains. We introduce Anchored Planning, which retrieves a recorded segment whose start and end resemble the current and goal observations, then aims at an observation shortly after its start. The frozen model scores actions toward this target from the current state. Without additional training, planning toward observed targets outperforms the released LeWM planner on every task in our long-range evaluation. Additional final-goal search falls short of the same gains. Lower successor-prediction error need not translate into better control. Success also depends on how far ahead the target is placed and on shrinking the retrieval span as execution advances. Changing only the target lets the same frozen model and planner reach goals that final-goal scoring misses.

AI 总结：本文证明各向同性对数凹分布的多项式矩不等式为平方和，消除庞加莱常数依赖，获得最优矩界，并由此得到高维统计估计的维度无关误差高效算法。

链接：https://arxiv.org/abs/2609.30105

机构：Princeton University（普林斯顿大学）

作者：Aleksandr Storozhenko

英文摘要：For an arbitrary isotropic log-concave distribution $P$ on $\mathbb{R}^d$, we prove that the polynomial $(Cm)^m\|v\|_2^m - \mathbb{E}_{X\sim P}\langle X,v\rangle^m$ is a sum of squares for every even $m\ge2$, where $C>0$ is a universal constant. This removes the dependence on the Poincaré constant in the theorem of Kothari and Steinhardt ( arXiv:1711.07465 ), recovering the optimal moment bounds for log-concave distributions. As an immediate corollary, we obtain computationally efficient algorithms with dimension-free error guarantees for a wide range of high-dimensional statistical estimation problems. Our proof uses stochastic localization to decompose $P$ as an average of random strongly log-concave measures, whose centered moments admit the subgaussian certificates of Diakonikolas, Hopkins, Pensia, and Tiegel (STOC 2025; arXiv:2410.21194 ). With a covariance-adapted choice of localization, we show that a fourth-moment certificate derived from Letwin's variance inequality for quadratic forms ( arXiv:2607.24164 ) suffices to control this averaging at every even degree.

AI 总结：本文提出内在-外在耦合框架，通过延续条件干预价值分析学习动力学，证明重放等外部延续与内在干预存在非加性交互，且耦合不必然带来正协同。

链接：https://arxiv.org/abs/2609.30185

作者：Qinyou Wang

英文摘要： A learner's current observations need not determine its response to further training. We formulate intrinsic-extrinsic coupling through the continuation-conditioned value of a constrained learning-state intervention, with observation-relative fibers describing present agreement. An executable finite-frame classifier-head write protects current logits while repairing specified historical margins under finite-precision acceptance checks. We distinguish local admissibility, continuation-conditioned intervention value, and complete-policy performance. A matched four-cell contrast identifies readout-specific non-additivity between the same intrinsic intervention and alternative external continuations. In a CLINC-derived class-incremental setting, replay changes the write's 32-update contribution from five correct predictions to zero. Nonzero interactions also occur under output distillation, with a RoBERTa backbone, and under optimizer-native SGDW dynamics. Under SGDW, correct-count interactions are negative in all three activated roots at 128 updates, showing that coupling need not imply positive synergy. The mathematical analysis distinguishes feasible local repairs and favorable terminal outputs from training-reachable repair regions. Separate coordination tests show that content controls match or exceed the development gain, while a five-root fresh-test comparison with Fiber present in every arm shows root-dependent rather than uniformly beneficial correct-count effects. On the secondary cross-entropy readout, guided allocation yields lower mean loss than standard replay in all five pairs. Together, these results make intrinsic-extrinsic coupling operational by connecting executable state geometry to continuation-conditioned value, matched interaction identification, and closed-loop coordination, while separating identified coupling from complete-policy performance.

AI 总结：针对潜在神经代理求解器长时程展开误差累积问题，本文提出训练层面干预措施，将潜在表示与长时程展开对齐，将长展开误差降低约40%，并达到或超过全分辨率模型精度，同时大幅降低计算成本。

链接：https://arxiv.org/abs/2609.30198

机构：Sandia National Laboratories（桑迪亚国家实验室）； University of Southern California（南加州大学）； Brown University（布朗大学）； Oak Ridge National Laboratory（橡树岭国家实验室）

作者：Andreas E. Robertson, Ashley T. Lenau, John D. Shimanek, Benjamin A. Jasperson, Vivek Oommen, David L. Damm, Krishna Garikipati, Remi Dingreville

英文摘要：Latent neural surrogate solvers, or latent dynamics models, accelerate simulations of time-dependent physical systems by evolving a compressed latent space rather than resolving full-resolution fields directly. In principle this reduces computational cost and simplifies learning, but in practice errors often accumulate rapidly during long autoregressive rollouts, limiting predictive utility. We show that this instability does not stem from the latent representation itself, but arises when it is trained solely for reconstruction, producing representations poorly suited to long-horizon forecasting. We systematically evaluate training-level interventions that align latent representations with long-horizon rollout: Koopman operator learning and Hamming noise injection during autoencoder training to improve compression, together with noise injection and multi-step rollout fine-tuning to improve dynamics. Interventions that improve long-horizon rollout stability often degrade conventional training metrics, including reconstruction and one-step prediction accuracy. Collectively, these interventions reduce long-rollout error by approximately 40\% and match or exceed the accuracy of full-resolution models on two physics benchmarks, while requiring 2 orders of magnitude fewer floating point operations and half the GPU memory. Applied to mesoscale crystal-plasticity simulations of high-cycle fatigue, the resulting surrogate achieves stable extrapolation over horizons orders of magnitude beyond those observed during training. More broadly, these results show that neural compression should be designed not merely to reduce dimensionality, but to restructure the solution space for stable dynamical evolution, a key requirement for reliable, efficient neural surrogates in scientific applications.

AI 总结：提出微创引导向量优化（MISVO），通过局部KL几何惩罚干预，在不更新参数的情况下优化位置特定干预，在约1B-14B参数的偏好和代码生成任务中取得最高平均奖励。

链接：https://arxiv.org/abs/2609.30218

机构：Johns Hopkins University（约翰斯·霍普金斯大学）

作者：Taha Entesari, Jingyu Zhang, Daniel Khashabi, Mahyar Fazlyab

英文摘要：Pre-logit steering adapts a frozen language model to a test-time reward by adding vectors to its final hidden states. Unregularized reward optimization can substantially alter the output distribution and degrade generation quality. We propose Minimally Invasive Steering Vector Optimization (MISVO), which penalizes interventions using the local KL geometry of the induced token distribution. The resulting Fisher quadratic measures distributional sensitivity and admits an analytic gradient computed through matrix--vector products with the frozen language-model head. We derive an exact decomposition of the sequence-level KL gradient into an analytic Fisher term and a suffix score-function term. For a fixed generation horizon, we show that the suffix term is second order in the steering magnitude and that three Fisher surrogates agree with the full KL gradient to first order. MISVO uses the frozen-reference surrogate to optimize position-specific interventions without updating model parameters. Across preference and code-generation tasks on models with approximately 1B--14B parameters, MISVO achieves the highest mean reward in six of seven model--task settings, with diversity and coherence scores close to those of Best-of-N.