机器学习学术速递[8.14]

AI 总结：针对LLM预训练效率问题，提出含局部融合注意力与知识记忆模块的LoKiFormer，使预训练收敛速度提升1.33倍，性能优于现有架构。

链接：https://arxiv.org/abs/2608.12419

机构：AIGCode； South China University of Technology（华南理工大学）； Pazhou Laboratory（琶洲实验室）

作者：Qiuwu Chen, Zimo Liu, Yuchen Li, Ying Sun, Yifan Zhang, Zhijie Qiu, Zeng You, Ryan Dong, Simeng Ma, Yaofo Chen, Mingkui Tan

英文摘要：Large language models (LLMs) have achieved remarkable breakthroughs across various applications. However, their architectures remain inefficient in pretraining due to two main limitations: (i) self-attention lacks an explicit inductive bias for locality, leading to redundant modeling of sequence-internal local information; (ii) mixture-of-experts (MoE) implicitly couples knowledge storage with computational pathways, hindering flexible access to sequence-external global knowledge. To overcome these limitations, we propose LoKiFormer, a novel LLM architecture that augments the standard decoder with two dedicated modules: 1) Local Fusion Attention (LFA), which incorporates a convolutional fusion to attention, explicitly capturing local patterns and allowing the attention to operate on more informative representations; 2) Knowledge Memory Module (KMM), which introduces a parametric key-value memory that explicitly stores global knowledge in addressable slots, decoupling storage from computation and enabling direct knowledge retrieval. Together, these modules enable LoKiFormer to achieve more efficient and effective integration of information at both levels. Experimental results show that LoKiFormer converges 1.33x faster in pre-training than baseline models, underscoring its superiority over existing LLM architectures.

AI 总结：本文提出MARCH架构，通过内容路由状态锚点扩展循环记忆，在长序列上保持计算效率，经预训练后在多个长程任务中优于线性注意力变体，增强了循环长程记忆能力。

链接：https://arxiv.org/abs/2608.12435

机构：Shanghai AI Laboratory（上海人工智能实验室）； Tsinghua University（清华大学）； Fudan University（复旦大学）

作者：Ming Zhang, Kaisen Yang, Shu Yu, Ermo Hua, Ning Ding, Xia Hu, Bowen Zhou, Chaochao Lu, Youbang Sun

英文摘要：Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length. This flexibility, however, incurs a quadratic computation complexity during training and a key--value cache that grows linearly during autoregressive inference. Recurrent alternatives offer efficient decoding by compressing the entire history into a fixed-size state, but often underperform on recall-intensive tasks since earlier associations usually get overwritten by subsequent updates, and only the most recent contextual information is retained. In this paper, we introduce Memory-Anchor Routing across Context History (MARCH), a network architecture that effectively scales state-space models beyond a fixed-size dimension, while maintaining computational efficiency over long-sequences. MARCH periodically caches cumulative recurrent-state checkpoints as state anchors and associates each anchor with a compact, content-conditioned anchor key. This lets MARCH maintain a memory bank, which can grow as context length increases, providing a controllable trade-off between historical resolution and memory cost. At each token, MARCH produces an anchor query to attend all causally available state anchors, and the output is calculated as an attention-style aggregation over all historical anchors along the current state. We show that after standard pretraining, MARCH consistently outperforms multiple linear attention variants across commonsense reasoning, LongBench, and in-context retrieval. These results demonstrate that content-routed state caching substantially strengthens recurrent long-range memory while preserving its native computation path.

AI 总结：本研究提出基于学习的个性化评分者建模框架 LBH，利用多评分者数据集构建更可靠的睡眠阶段参考标签，在 DOD-H、DOD-O 数据集上较基线方法提升了睡眠分期性能。

链接：https://arxiv.org/abs/2608.12446

作者：Seyyed Ali Hoseini, Javad Baseri, Hamid Saadatfar, Edris Hoseini Gol, AmirHossein Eshghi

英文摘要：Sleep stage classification is important for the diagnosis and management of sleep disorders, yet most automatic staging studies evaluate models against a single reference hypnogram despite known inter-scorer variability. This study investigates whether multi-scored datasets can be used to construct more reliable reference labels from the collective behavior of multiple experts. We use the publicly available DOD-H and DOD-O datasets. EEG (C3-M2) and chin EMG signals were segmented into 30-s epochs, and 30 features were extracted from each modality, yielding 60 features for EEG+EMG. We propose a learning-based hypnogram (LBH) that models the stage-specific behavior of each scorer using confusion matrices derived from machine-learning models. After column normalization, these matrices estimate the probability of each true sleep stage given each scorer's label; probabilities are aggregated across scorers to assign the final label for each epoch. LBH was evaluated with random forest, support vector machine, and multilayer perceptron classifiers under EEG-only and EEG+EMG settings, and compared with the dataset hypnogram (DH) and best-scorer hypnogram (BSH). LBH consistently improved overall performance. The best results were obtained with random forest and EEG+EMG, reaching 86.07% accuracy, 85.46% precision, and 85.29% F1-score on DOD-H, and 86.04% accuracy, 85.21% precision, and 84.70% F1-score on DOD-O. These findings suggest that personalized scorer modeling can improve reference hypnogram construction without discarding information from individual experts.

AI 总结：该研究发现Transformer残差流的预测方向是特权锚点，其附近区域高度结构化，远端区域平缓，破坏近端方差方向会导致任务框架转移，为高维计算与线性读出的共存提供了几何解释。

链接：https://arxiv.org/abs/2608.12447

作者：Nelson Guda

英文摘要：Trained transformer models develop privileged bases: coordinate axes whose statistics differ from the rest of the residual stream. But what kind of direction does such a basis select? We investigate the prediction direction, the unembedding direction of the token a model currently predicts, and find that it functions as a content-defined privileged anchor. Measured with respect to this anchor, residual-stream variation is geometrically and behaviorally stratified by proximity to the prediction. The stratification holds in all eighteen models tested (dense and mixture-of-experts, 7B-120B, base and instruction-tuned). A narrow, scale-invariant prediction interface concentrates readout-relevant structure, while the vast prediction-distal complement expands with model scale. Because the prediction direction sits nearly orthogonal to the principal variance axes, variance-based analyses recover this organization only partly, and the shortfall grows with prompt heterogeneity. Anchoring reveals a steep geometric gradient: prediction-proximal regions are highly structured and cluster related prompts, while the complement is flatter and anti-discriminates among prompt groups. The interface is a narrow slice but functionally decisive. Disrupting the variance directions closest to the prediction causes immediate divergence and frequent task-frame shifts; disrupting the next level down delays divergence and preserves framing. The complement is weakly readout-aligned per direction yet causally and temporally load-bearing, and behavior is driven by direction rather than magnitude. These results establish the prediction direction as a privileged anchor distinct from previously described coordinate axes, and give a geometric account of how high-dimensional computation coexists with linear readout.

AI 总结：该研究证明在布尔特征有限简单无向图的布尔查询表达上，ReLU-MPLang 表达能力强于 Σ-MPLang，解决了 ReLU-MPLang 是否比 trReLU-MPLang 更强大的开放问题，表明 ReLU-GNN 比 {TrReLU,id}-GNN 表达能力更强。

链接：https://arxiv.org/abs/2608.12617

机构：Pontifical Catholic University（宗座天主教大学）； IMFD； CENIA Chile（智利CENIA）； University of Antwerp（安特卫普大学）； TU Wien（维也纳技术大学）； Universiteit Hasselt（哈塞尔特大学）

作者：Pablo Barceló, Floris Geerts, Matthias Lanzinger, Klara Pakhomenko, Jan Van den Bussche

英文摘要：We prove that, on finite simple undirected graphs equipped with a single Boolean node feature, the Boolean queries expressible in $\Sigma$-MPLang, for any collection $\Sigma$ of eventually constant activation functions and with arbitrary real coefficients, form a strict subclass of the Boolean queries expressible in ReLU-MPLang. We thereby settle a recently posed open problem: whether ReLU-MPLang is more powerful than trReLU-MPLang when it comes to Boolean queries. In particular, this implies that ReLU-GNNs are strictly more expressive than {TrReLU,id}-GNNs with respect to Boolean queries on Boolean-featured graphs.

AI 总结：本文针对关系深度学习（RDL）现有评估忽略数据随时间演化的局限，提出增量多轮评估与训练范式，发现多数RDL任务存在时间概念漂移，增量微调模型性能优于从头训练基线。

链接：https://arxiv.org/abs/2608.13023

机构：Czech Technical University in Prague（布拉格捷克技术大学）

作者：Jakub Peleška, Gustav Šír

英文摘要： Relational Deep Learning (RDL) models multi-tabular databases as temporal heterogeneous graphs to enable end-to-end representation learning. However, prevailing RDL evaluation practices rely on static, single-episode dataset snapshots, overlooking the continuous, time-evolving nature of real-world databases. Consequently, current RDL benchmarks fail to capture how model performance changes as new data accumulates over time. To address this limitation, we introduce an incremental, multi-episode evaluation and training paradigm to assess and improve the temporal robustness and adaptability of state-of-the-art RDL models. Using established large-scale datasets, we examine data evolution and model training dynamics, demonstrating that temporal concept drifts occur in the majority of predictive tasks. We present multiple incremental training regimes for fine-tuning the models and demonstrate that transfer learning is both feasible and highly effective in the RDL setting. Alongside a new temporal evaluation metric that prioritizes near-future accuracy, we show that our incrementally fine-tuned models consistently outperform the standard, expensive, from-scratch trained baselines.

AI 总结：该研究提出神经二次型模型，统一描述感知机等多种架构的突发学习与标度律，通过对称性推导其训练动力学为洛特卡-沃尔泰拉方程，经数值验证符合相关行为。

链接：https://arxiv.org/abs/2608.13335

机构：Massachusetts Institute of Technology（麻省理工学院）； École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）

作者：Liu Ziyin, Yizhou Xu, Tomaso Poggio, Isaac Chuang

英文摘要：Neural networks trained by gradient descent on a smooth cost function can nevertheless learn in steps: the cost holds on long plateaus and then drops abruptly. Meanwhile, training losses instead follow smooth power laws. Variants of both behaviors occur in architectures with very different microscopic structures, which is the signature of a few relevant collective variables. We show that a symmetry fixes what those variables are: a network layer is a sum over interchangeable units, so relabeling the units leaves it unchanged; given smoothness and the condition that a unit's gradient vanish at the origin, symmetry then enforces a universal leading form for the expansion about the near-zero weights present at the start of training, the quadratic $\Tr[WW^{\top}A(x)]$, in which every architectural detail is confined to a single ``structure matrix" $A(x)$ that we compute for each architecture. Perceptrons, attention layers, mixtures of experts, and convolutions become one model at different $A$. Its training dynamics then close on the ``order parameter" $M=WW^{\top}$ and, whenever the data matrices share an eigenbasis, reduce to a Lotka--Volterra equation whose modes switch on one after another. The smaller the initial weights, the further apart the switch-on times, and the plateaus appear as a singular limit of a smooth flow; when many modes are unresolved the same events merge into a power law in training time whose exponent the theory predicts. We confirm both numerically across training methods and architectures.

AI 总结：本研究针对Transformer语言模型推理开销高的问题，提出无需训练的输入自适应RMM方法，通过选择矩阵乘积信息切片减少计算，在多任务多模型上验证其鲁棒性，可提升长序列推理效率，且适用于多模态场景。

链接：https://arxiv.org/abs/2608.13426

机构：University of Chicago（芝加哥大学）； Stony Brook University（石溪大学）

作者：Zixuan Lan, Yanhong Li, Jiawei Zhou

英文摘要：Transformer-based language models achieve strong performance but incur substantial inference cost due to repeated high-dimensional matrix multiplications. We propose Reduced Matrix Multiplication (RMM), a training-free, input-adaptive inference method that reduces Transformer matrix products by selecting informative slices along their contraction dimensions, without modifying model weights. Under a simple retention-ratio control, RMM provides a smooth and predictable accuracy-efficiency trade-off. Across language models ranging from 1B to 70B parameters, we find that reduction tolerance depends on the model family, task, component, and retention ratio, although it often improves with model scale. Under moderate reduction, RMM remains robust across the evaluated discriminative, autoregressive generation, and long-context settings. We further show that the same principle extends to multimodal vision-language inference. Mechanistic ablations reveal a structural asymmetry within Transformers: attention-side computations are substantially more reducible than MLP components. Finally, wall-clock benchmarks with custom kernels on an NVIDIA A100 show that these computational savings can translate into practical runtime gains, especially at longer sequence lengths. Together, these results position RMM as a scalable direction for input-adaptive inference-time optimization.

AI 总结：本研究针对恶意软件分类模型，提出基于OCSVM等的概念漂移检测方法，结合漂移感知重训练策略，可在保持准确率的同时提升训练效率，且OCSVM方法表现更优。

链接：https://arxiv.org/abs/2608.13465

机构：San Jose State University（圣何塞州立大学）； Czech Technical University in Prague（布拉格捷克技术大学）

作者：Christofer Washington Berruz Chungata, Martin Jurecek, Katerina Potika, William B. Andreopoulos, Mark Stamp

英文摘要： Concept drift refers to changes over time in the statistical properties of data, as compared to the data that was used to train a learning model. Machine learning models for malware detection or classification are particularly susceptible to performance degradation caused by concept drift, as attackers constantly modify existing malware. In this chapter, we analyze two machine learning-based approaches to automated concept drift detection-a novel approach based on One-Class Support Vector Machines (OCSVM) and a previously-studied technique based on Minibatch K-Means (MK-Means). For comparison we also consider Maximum Mean Discrepancy (MMD), a statistical technique for detecting changes in multidimensional data. We conduct an extensive series of experiments comparing the effectiveness of four learning models, namely, Multilayer Perceptron, Random Forest, Support Vector Machines, and eXtreme Gradient Boosting. For each of these models, we consider three distinct scenarios: A static scenario where no model retraining occurs, a periodic scenario where models are constantly retrained irrespective of concept drift, and a drift-aware scenario where models are only retrained when concept drift is detected. Under the drift-aware scenario, we analyze the tradeoff between accuracy and training efficiency using Pareto Front analysis. We find that all three concept drift detection techniques achieve classification accuracy comparable to periodic retraining, while offering substantially greater efficiency in terms of the number of models that must be retrained. In addition, drift-aware retraining based on our OCSVM technique generally outperforms the MK-Means and MMD approaches. Overall, these results provide strong evidence that we can accurately detect concept drift in malware classification models.

AI 总结：该研究在Icentia11k数据集上对比不同时间上下文长度与编码策略，发现扩展上下文、采用连续补丁嵌入的自监督ECG模型在心律检测与跨会话检索任务中性能更优，为临床ECG模型构建提供了指导。

链接：https://arxiv.org/abs/2608.12695

机构：University of Minnesota Twin Cities（明尼苏达大学双子城分校）

作者：Ahmed Sameh, Ramzi Al-Sharawi, Yogatheesan Varatharajah

英文摘要：Self-supervised electrocardiogram (ECG) models are often trained on a few seconds of ECG signal and, increasingly, on discretized token sequences. It remains unclear whether these choices sacrifice information needed for rhythm inference and longitudinal consistency in real-world ambulatory recordings. We present a controlled study on the Icentia11k single-lead dataset that varies (i) the input horizon (16 seconds, 1 minute, 5 minutes, and 10 minutes) and (ii) the front-end representation (continuous convolutional patch embeddings vs. fixed vector-quantized tokens), while holding the Transformer backbone and training protocol constant. Representations are assessed by downstream abnormal rhythm detection and by patient-level retrieval that probes cross-session stability. Our results show that increasing temporal context beyond 16-second snapshots yields stronger transfer and higher retrieval accuracy, with the strongest performance achieved by the 5- and 10-minute models, indicating improved capture of slow-varying rhythm dynamics and individual-specific structure. Across all evaluated horizons, continuous patch embeddings outperform discretized tokens, suggesting that quantization can discard clinically relevant waveform detail. These findings motivate ECG foundation models that emphasize extended context and continuous encoders for clinical prediction and similarity-based applications. Our code and pretrained models are publicly available at this https URL.

AI 总结：本研究提出一种非侵入式多光谱框架，结合XGBoost算法可区分芒果、香蕉的电石催熟样本与安全催熟样本，还能估算催熟进度和货架期，在两类果实上分别达到95%、81%的分类准确率。

链接：https://arxiv.org/abs/2608.13073

机构：National Institute of Technology Delhi（德里国家理工学院）； ICAR-Indian Agricultural Research Institute（印度农业研究委员会-印度农业研究院）

作者：Gurbhit Chaurakoti, Harshit Kumar, Hani Kumar, Anurag Singh, Ram Asrey

英文摘要：Significant health risks are associated with the illegal, yet commonly practiced use of industrial-grade Calcium Carbide (CaC2) for ripening climacteric fruits like mango and banana, which leaves behind trace residues of arsenic and phosphorus. To address this, the proposed study explores a novel, non-invasive multispectral framework for distinguishing safely ripened fruits (naturally ripened and ethephon-induced) from calcium carbide-ripened samples, while also estimating their ripening progression (in percentage) and remaining shelf life (in days). The spectral profiles of mango (Mangifera indica) and banana (Musa acuminata) at 18 discrete wavelengths in the visible-near infrared (NIR) range (410 nm - 940 nm) are studied using the AS7265x spectral triad sensor. CaC2-treated samples exhibit sharper spectral intensity drops in the visible region, consistent with accelerated chlorophyll degradation and carotenoid development. To characterize these physiological changes, the feature engineering strategy integrates inter-method spectral variance, intensity ratios at distinct wavelengths, and environmental parameters including temperature and humidity. Dimensionality reduction using Principal Component Analysis (PCA) retains >90% of spectral variance within the first 5-7 components. The resulting feature set is used to train three independent eXtreme Gradient Boosting (XGBoost)-based learning algorithms for ripening method classification, along with quantitative estimation of remaining shelf life and ripening progression. A classification accuracy of 95% along with carbide class recall of 0.67 is observed for mango samples, while the model achieves an accuracy of 81% and carbide class recall of 0.74 for banana. This instrumentation and data-driven approach demonstrates the effectiveness of the proposed non-invasive framework.

AI 总结：本文提出知识引导方法，通过耦合张量分解联合分析真实与模拟数据，在代谢组学数据实验中提升了模式发现性能，还揭示了数据与计算模型的潜在差异。

链接：https://arxiv.org/abs/2608.13234

作者：Gaute Johannessen, Geert Roelof van der Ploeg, Evrim Acar

英文摘要：In order to understand complex systems such as the human metabolome or human brain, different sensing technologies are used, generating complex data. These datasets are often multiway, i.e., with more than two axes of variation such as a subjects by metabolites by time array. While tensor factorizations have successfully revealed interpretable patterns from such complex data, they have so far been mainly data-driven. On the other hand, there is more to data -- there are computational models (of these systems), which are rich sources of prior information. In this paper, we introduce a knowledge-guided approach that brings together data and computational models by jointly analyzing real data and simulated data (generated using a computational model) using coupled tensor factorizations with linear coupling. Our experiments on real metabolomics measurements demonstrate that guiding the analysis of such noisy data with simulated data improves the pattern discovery performance while also revealing potential discrepancies between data and computational models.

AI 总结：针对多AUV自组织网络目标跟踪的训练不稳定、跟踪性能差问题，提出VGG-MADiffRL算法与MDCA架构，实现了更快收敛、更高跟踪精度与平稳训练动态，具有工程应用价值。

链接：https://arxiv.org/abs/2608.12436

机构：Software College, Northeastern University（东北大学软件学院）； Hohai University（河海大学）

作者：Jiaao Ma, Chuan Lin, Guangjie Han, Shengchao Zhu, Qian Zhu, Ying Liu, Zhenyu Wang

英文摘要：Multi-AUV ad-hoc network-based target tracking requires networked autonomous underwater vehicles (AUVs) to cooperatively track maneuvering targets under constrained acoustic communication, dynamic topology, and uncertain ocean disturbances. Although multi-agent reinforcement learning (MARL) enables decentralized coordination through centralized training, existing methods suffer from high-dimensional joint state-action modeling, noise-sensitive policy generation, leading to unstable training and degraded tracking. To address these issues, we propose VGG-MADiffRL, a value-gradient-guided multi-agent diffusion RL algorithm, and MDCA, a diffusion?based hierarchical control architecture. Leveraging underwater mission characteristics, we model sonar detection mechanisms and ocean current disturbances, formulating cooperative tracking for multi-AUV ad-hoc networks as an MDP. The proposed MDCA constitutes a three-tier closed-loop control framework: a global intelligent control layer, a local online training layer, and a physical action execution layer. This structure enables synergistic optimization across task allocation, local decision processes, and execution feedback. Within MDCA, the local online training layer is the policy learning framework; VGG-MADiffRL builds on diffusion policies and incorporates value gradients to guide action generation in the reverse denoising process, steering the generated actions towards higher expected returns. It employs twin value networks with joint optimization and soft target updates to mitigate overestimation and training oscillations, promoting more stable convergence. Experimental results show that VGG-MADiffRL consistently achieves faster convergence, higher tracking accuracy, and smoother training dynamics in cooperative tracking scenarios, validating its effectiveness and practical engineering value in dynamic underwater settings.

AI 总结：针对自动研究智能体扩展时的训练瓶颈，提出WMRL方法，结合两种缓解措施提升收敛性，训练加速3-4倍且性能优于更大规模智能体，还可迁移至多类任务。

链接：https://arxiv.org/abs/2608.12564

机构：University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； Amazon（亚马逊公司）

作者：Xiyuan Yang, Sheikh Sarwar, Jingru Cheng, Zhan Shi, Duanshun Li, Huiyuan Chen, Haiyang Zhang, Chenlei Guo, Jingrui He, Zhenyu Liao

英文摘要：Automating empirical research is a long-standing direction of AI. Recent automatic research (AutoResearch) agents bring this goal within reach, as modern LLMs show the capability to independently implement solutions and learn from the execution outcomes. Behind these gains, post-training (especially RL) plays a central role. In this paper, we identify a fundamental tension when scaling RL for these agents: the two components of every AutoResearch trajectory (agent generation and environment execution) scale in very different manners, since all generation shares compute through batching, while each execution occupies its exclusive sandbox and real machine time. As a result, the environment execution dominates the training cost and becomes the bottleneck as trajectories grow. To resolve this tension, we propose World Model RL (WMRL), which replaces environment execution with a world model to remove this bottleneck. Additionally, the world model can be imperfect, as its rewards are corrupted by bias and noise. Therefore, we further equip WMRL with two mitigations, Online Debiasing and Inverse-Variance Denoising, which offset the bias and suppress the noise respectively. Theoretically, we prove that both mitigations of WMRL strictly improve the convergence guarantee. Empirically, WMRL accelerates training by 3-4x on various tasks at different agent scales, while exceeding the performance of standard RL baselines. Moreover, our post-trained 4B and 9B agents outperform much larger open-weight agents of 48B and 120B on held-out benchmarks. Beyond AutoResearch, WMRL also transfers to post-training embodied VLA policies, which demonstrates the generalizability of our method.

AI 总结：

链接：https://arxiv.org/abs/2608.12753

机构：University of California, Los Angeles（加州大学洛杉矶分校）

作者：Larissa Xu, King Bi, William Chang

英文摘要：We study decentralized multi-player reinforcement learning in episodic tabular Markov decision processes (MDPs) under three forms of information asymmetry: (A) unobserved actions with common rewards, (B) observed actions with independent rewards, and (C) unobserved actions with independent rewards. Players cannot communicate during learning but may agree on a protocol a priori. For Problems A and B we propose \texttt{mQ-learning} and \texttt{mQ-learning-intervals}, achieving $\tilde{O}(\sqrt{H^4 S A_{\text{joint}}\, T})$ regret, where $H$ is the horizon, $S$ the state count, $T = KH$ the total steps, and $A_{\text{joint}} = \prod_{i=1}^M |\mathcal{A}_i|$ the joint action space across $M$ players. For Problem C we give \texttt{mEXC} and \texttt{mEXC-Bellman}, two-phase explore-then-commit algorithms with regret $\tilde{O}(H (S A_{\text{joint}})^{1/3} T^{2/3})$. Against the centralized joint-action benchmark, decentralized learning under information asymmetry matches the single-agent Q-learning rate of \cite{jin2018q} up to logarithmic factors. Because $A_{\text{joint}}$ grows exponentially in $M$, the bounds are most meaningful for small $M$ or small per-player action sets.

AI 总结：该研究针对深度搜索智能体信用分配稀疏问题，提出 SSPO 方法，通过证据锚点与步骤级优势权重优化策略，在多个数据集上性能优于 GRPO 且开销低。

链接：https://arxiv.org/abs/2608.12764

机构：Huawei Technologies Ltd.（华为技术有限公司）； The Hong Kong University of Science Technology（香港科技大学）

作者：Haoze Wu, Chuqiao Kuang, Tianyi Zhuang, Xiaoguang Li

英文摘要：Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sparse for effective credit assignment. On-policy self-distillation (OPSD) addresses this by using the model's own logits as dense token-level teachers, but extending it to search agents introduces a fundamental tension: the teacher, having access to privileged information such as the correct answer, produces a distribution that differs systematically from the student's exploration-based reasoning, and naive distillation causes the student to inherit this information asymmetry rather than learn better search strategies. We resolve this tension through two contributions. First, we construct Evidence Anchors, which are concise, step-level evidence snippets extracted from the web, as privileged information that captures key reasoning steps without revealing the entire answer path. Second, we propose Step-Level Self-Distilled Policy Optimization (SSPO), which converts teacher-student disagreement into step-level advantage weights within GRPO, applied exclusively to incorrect trajectories. This design decouples what to update from how much to update: the outcome reward determines the direction of policy change, while the teacher modulates its magnitude at each step. Correct trajectories are left untouched, preserving their diversity. On Qwen3-8B, SSPO consistently outperforms GRPO across BrowseComp, GAIA, and FRAMES, surpassing or matching GRPO trained with twice as many gradient steps while adding only about 5 percent overhead per step from a single additional forward pass.

AI 总结：该研究提出树耦合A/B测试（TCAB）方法，通过树耦合反馈共享实现多策略精确比较，将奖励查询数从JT降至T+o(T)，实验显示其在成本-精度上有显著提升。

链接：https://arxiv.org/abs/2608.12831

机构：Courant Institute of Mathematical Sciences, New York University（纽约大学柯朗数学科学研究所）

作者：Yuxiao Wen

英文摘要：Online platforms increasingly compare many adaptive decision policies---ranking systems, recommendation algorithms, pricing rules, and language-model agents---while each reward-bearing interaction can be costly or risky. A direct A/B/n design gives each of $J$ policies its own horizon-$T$ trajectory and therefore uses $JT$ outcomes. We introduce Tree-Coupled A/B Testing (\TCAB), an exact feedback-sharing design for arbitrary history-dependent contextual-bandit policies. At each round, a predictable tree connects the current policy histories; every parent--child context--action law is maximally coupled, and one reward is shared within each component of matched tree edges. Every policy retains exactly its standalone finite-horizon trajectory law, even though the policies are deliberately dependent. If $D_{e,t}$ records a mismatch on tree edge $e$ at round $t$, the number of reward queries satisfies the pathwise identity $N(T)=T+\sum_{t,e}D_{e,t}$ and hence equals $T$ plus cumulative tree-edge total variation in expectation. This cost is conditionally optimal among exact edge-local designs on the selected tree, and a current-round minimum-spanning tree is myopically optimal among tree designs. For fixed $J$, sublinear pseudo-regret of every policy and almost-sure uniqueness of the oracle action imply $\mathbb{E}[N(T)]=T+o(T)$, versus $JT$ for independent runs. We also obtain finite-sample variance bounds for pairwise policy contrasts. Experiments on reward-model evaluation, multiple-choice language-model evaluation, and adaptive search policies demonstrate substantial improvements in the cost--precision frontier.

AI 总结：本文针对大动作空间下Q学习的高估偏差问题，提出动作交集策略实现半解耦，在表格型与深度强化学习实验中大幅优于多个SOTA基线方法。

链接：https://arxiv.org/abs/2608.12912

机构：Chongqing Institute of Green and Intelligent Technology（重庆绿色智能技术研究院）； University of Science and Technology of China（中国科学技术大学）

作者：Pu Li, Tao Tan, Hong Xie, Xiaoyu Shi, Mingsheng Shang

英文摘要：This paper considers the overestimation bias problem of Q-learning in the setting of a large action space, for the purpose of relieving the bottleneck of existing methods. We find that the large action space increases the randomness in Q-value estimation. The randomness makes two paradigms that drive the major literature on the overestimation problem have their own bottlenecks: the coupling paradigm, i.e., the optimal action and its Q-value are estimated with the same Q-function, always has a positive bias. This is because randomness leads to some actions having abnormally high estimated values than their true values, and the coupling methods prefer these actions. The decoupling paradigm, i.e., the optimal action and its Q-value are estimated with two independent Q-functions, always has a negative bias. This is because randomness increases the estimation gap between the two independent Q-tables for the same action. This paper shows that action intersection can be a simple yet powerful strategy to relieve these bottlenecks. The action intersection strategy enables semi-decoupling via two designs: (1) it allows two Q-functions to share a certain fraction of trajectory data; (2) if a data sample is shared, each Q-function is updated using the coupling paradigm; otherwise, using the decoupling paradigm. Two properties make the action intersection strategy powerful: (1) attaining a large bias range, i.e., varying the data sharing fraction, the estimation bias varies from underestimating to overestimating; (2) fine granularity: the action intersection size can be made arbitrarily finer to enable finer control. We consider two experiment settings, i.e., tabular and deep RL, deep RL experiments show that our method outperforms several SOTA baselines drastically; tabular experiments reveal why our method can achieve superior performance.

AI 总结：该研究针对DRL社会导航中社会合规目标不足的问题，提出基于近体学的奖励建模方法，经模拟验证可提升社会指标且保持导航性能。

链接：https://arxiv.org/abs/2608.12917

作者：Takieddine Soualhi (CHROMA), Jacques Saraydaryan (CPE, CHROMA), Laetitia Matignon (UCBL)

英文摘要：Developing effective robot navigation methods in crowded environments is essential for real-world applications. Although recent deep reinforcement learning (DRL) methods have improved navigation performance in crowded environments, they often focus primarily on task-centric objectives and underrepresent social compliance objectives. In this paper, we introduce a novel proxemics-based reward formulation for DRL social navigation that provides a dense, interpretable social learning signal while maintaining navigation efficiency. Our approach models each human's personal space as a radial Gaussian-mixture field derived from Hall's proxemics theory and computes a robot-centric local cost over the robot's field of view. We integrate the proposed reward into established DRL navigation methods and evaluate it in simulation across multiple crowd scenarios, reward baselines, and crowd densities using both navigation metrics and social metrics. Results show that the proposed reward consistently improves social metrics in simulation while maintaining competitive navigation performance relative to the compared reward models.

AI 总结：本研究提出AIM框架将动量解释为残差驱动乘子校正，并基于此开发RADAR优化器，经多任务实验验证其性能优于现有强自适应优化器基线。

链接：https://arxiv.org/abs/2608.12925

作者：Zhixin Ren, Yau Lyu, Congrong Li, Liping Zhang, Shengbo Eben Li

英文摘要：Momentum-based optimizers are widely used in modern deep learning, yet the relations among momentum recursion, update geometry, and acceleration remain only partially understood. We develop an $\textbf{A}$DMM-$\textbf{I}$nspired $\textbf{M}$omentum (AIM) framework based on residual-penalty variable splitting, which interprets momentum as a multiplier-like correction driven by the splitting residual. AIM recovers the exponential moving average of gradients from an ADMM-style multiplier update and separates two mechanisms that are usually intertwined in practical optimizers: the residual penalty determines the update geometry, whereas the approximation of the objective-related subproblem determines the acceleration form. Building on AIM, we propose $\textbf{R}$elativistic $\textbf{A}$daptive gradient $\textbf{D}$escent with $\textbf{A}$ccelerated $\textbf{R}$esidual (RADAR), which combines relativistic adaptive geometry, decoupled residual correction, and second-order momentum filtering to improve the update direction and momentum estimation. We establish stochastic convergence through a variance-perturbed Lyapunov drift analysis. Experiments on supervised vision learning, language modeling, and reinforcement learning show that RADAR achieves consistent improvements over strong adaptive optimizer baselines.

AI 总结：该研究通过监督与无监督ML方法，对比多类特征对6G物联网波束成形优化的预测能力，明确关键影响因素，为后续应用深度学习与强化学习优化奠定基础。

链接：https://arxiv.org/abs/2608.12929

机构：University of Hertfordshire（赫特福德大学）； Joint Admissions & Matn. Board（联合招生与 matn 委员会）； Lightenet Technologies Ltd.（莱特尼特科技有限公司）

作者：Chukwunonso Henry Nwokoye, Blessing Oluchi Iloka, Chikwue V. Umeugoji, Christopher Anene Egemba, Nnenna D. Duroha

英文摘要：The study presents a systematic machine learning (ML) study of 6G-IoT beamforming optimization (6GBO) using supervised and unsupervised approaches. We compared the predictive power of network, environmental, device, and vision feature groups for 6GBO. Additionally, it addressed other unsupervised perspectives that can enhance 6GBO, including clustering network scenarios using methods such as K-means, DBSCAN, and hierarchical clustering. Several imbalance-aware experiments revealed that network features possess better prediction power than device, environmental, and vision feature groups, as evidenced by their recall, F1-score and ROC-AUC values. For unsupervised ML exploration (assessed using Elbow, Silhouette score, and Davies-Bouldin Index methods), the results indicate that the deployment environment and type of device primarily influence clustering, rather than mobility-based attributes. Furthermore, the explainability analysis showed that bandwidth, IoT sensors, and mobility possess higher global feature importance across the feature groups. In the future, we would apply deep and reinforcement learning techniques to predict throughput/latency or to optimize rewards determined by performance indicators like SNR enhancement

AI 总结：该研究提出LVPG框架，将进化的时间价值形式化，通过长视野信用分配加速有限预算搜索，提升了自动交易策略发现的性能。

链接：https://arxiv.org/abs/2608.13297

机构：New York University（纽约大学）； University of Malta（马耳他大学）

作者：Matthew Siper, Ahmed Khalifa, Julian Togelius

英文摘要： In evolutionary search, a weak child can be a valuable ancestor that makes high-fitness regions reachable. Immediate-return control is blind to this delayed utility, penalizing mutations through their immediate offspring even when they open productive future lineages. We formalize this hidden dynamic as the time value of evolution within a finite-horizon Markov decision process. To exploit it, we introduce Lineage-Value Policy Gradients (LVPG), a long-horizon actor-critic framework for automated trading policy discovery. Our architecture decouples search control into specialized policy heads over a shared generative backbone: a bootstrapped critic head estimates the value of finite-horizon lineage potential from multi-step mutation trees, while an actor head dynamically modulates mutation intensity over the remaining search budget. We isolate the impact of long-horizon credit assignment against immediate-return optimization across 90 paired runs under matched operators, lineage supervision, folds, seeds, and budgets. Path-based credit assignment substantially accelerates finite-budget search, increasing validation best-so-far AUC by 0.394 Sharpe units. LVPG also produces fewer temporary regressions than immediate-return optimization and recovers from them more often. Finite-horizon lineage value yields more selective non-monotonic search and stronger policies within identical resource constraints.

AI 总结：本研究提出Intern-S2-Preview系列科学智能体基础模型，通过多阶段训练与架构优化，在多类基准上取得领先结果，相关模块可提升科学任务表现且无需修改主干模型。

链接：https://arxiv.org/abs/2608.13505

机构：Shanghai AI Laboratory（上海人工智能实验室）

作者：Lei Bai, Jiaqi Cao, Chiyu Chen, Guanzhou Chen, Kai Chen, Guangran Cheng, Erfei Cui, Xuanlang Dai, Shengyuan Ding, Shangheng Du, Yanhui Duan, Yue Fan, Youqing Fang, Quan Gan, Yuanyuan Gao, Jiaye Ge, Lixin Gu, Yuzhe Gu, Qipeng Guo, Junjun He, Xin Hong, Ming Hu, Zhouqi Hua, Haian Huang, Junhao Huang, Zixian Huang, Minxi Jin, Lingkai Kong, Alexander Lam, Zehao Li, Zonglin Li, Tianhao Liang, Dahua Lin, Junyao Lin, Tianyang Lin, Zhouhan Lin, Jiangning Liu, Jin Liu, Kuikun Liu, Wenran Liu, Yifei Liu, Yuhong Liu, Yuhong Liu, Zhoumianze Liu, Ziyan Liu, Ziyu Liu, Haijun Lv, Han Lv, Chengqi Lyu, Le Ma, Ningsheng Ma, Zerun Ma, Haoyang Peng, Runyu Peng, Jifei Shan, Zixin Shang, Kou Shi, Xiang Shi, Qisheng Su, Xuerui Su, Hao Sun, Xiao Sun, Yanan Sun, Yu Sun, Huanze Tang, Yinghao Tang, Wenhui Tian, Zhongbo Tian, Bingli Wang, Haomin Wang, Jiarui Wang, Jingzhi Wang, Rui Wang, Xiquan Wang, Yi Wang, Zhecan Wang, Ziyi Wang, Zun Wang, Rubin Wei, Lianyi Wu, Wen Wu, Yue Wu, Yuhan Wu, Zhenyu Wu, Zijian Wu, Shuhao Xing, Jun Xu, Xingle Xu, Xuenan Xu, Xiangchao Yan, Ziang Yan, Bowen Yang, Danni Yang, Lin Yang, Zhiqi Yang, Qian Yao, Haochen Ye, Peng Ye, Jinhui Yin, Jiashuo Yu

英文摘要：Scientific discovery increasingly requires AI systems that can reason over scientific evidence of heterogeneous modalities, interact with scientific tools and environments, and sustain progress across long task horizons. We present Intern-S2-Preview, a series of scientific agentic foundation models designed to support multimodal scientific understanding, reasoning, generation, and long-horizon tasks. The training pipeline begins with scientific multimodal pre-training over rendered scientific documents, interleaved image-text data, and diverse scientific corpora. Starting from the pretrained checkpoint, we apply a unified post-training pipeline consisting of supervised fine-tuning, scalable multi-task reinforcement learning (RL), black- and white-box agentic RL, and on-policy distillation. This pipeline is supported by practical techniques that improve rollout and training stability and efficiency, including partial rollout with off-policy correction, adaptive length regularization, online speculative decoding, robust multi-task optimization, and trace-aware experience assembly for agentic tasks. At the architecture level, Intern-S2-Preview-397B extends time series modelling from efficient long-sequence understanding to numerical forecasting, while Memory Decoder is studied as a separate memory-augmented path for rapid scientific specialization without modifying the frozen 397B backbone. Evaluations across scientific, multimodal, agentic, and general-purpose benchmarks show that Intern-S2-Preview-397B achieves competitive or leading results in multiple settings. The time series modules improve scientific signal understanding and forecasting on SciTS, while the separate Intern-MemDec-4B extension improves the Biology-Instructions average score from 56.92 to 60.32 without modifying the frozen 397B backbone.

AI 总结：提出ReCoGen两阶段框架，将多模态条件表征与生成分离，在三个生理基准的16项任务中超越6种生成器，可合成缺失生理信号以实现低侵入性临床监测。

链接：https://arxiv.org/abs/2608.12592

作者：Haochen Zhang, Jiaheng Guo, Yu-Chao Huang, Nicholas Knoz, Tianlong Chen

英文摘要：Continuous physiological time series underpin modern clinical monitoring, yet many of the most informative signals are invasive, expensive, or simply unavailable for a given patient. Conditional generation offers a remedy: an absent signal can be synthesized from co-recorded signals and routine clinical variables. Existing generators, however, are built around a single conditioning modality and degrade when forced to handle the heterogeneous, irregularly missing mix of time-variant signals and static covariates seen in practice. We propose ReCoGen (Represent Conditions, then Generate), a two-stage framework that decouples multimodal condition representation from target generation. Stage I trains one masked autoencoder per modality, distilling each time-variant condition into a compact and missingness-tolerant token sequence. Stage II trains a flow-matching generator that fuses these tokens with static conditions to synthesize the target signal. Across three physiological benchmarks, including continuous glucose monitoring on AI-READI and arterial blood pressure generation on MIMIC-III and MIMIC-IV, ReCoGen attains the best downstream utility on all sixteen (dataset, task, metric) settings, surpassing six representative conditional generators; on thirteen of them its utility also reaches or exceeds the utility measured on the real signal, a reference we read as an approximate anchor rather than a ceiling. Ablations trace the gains to the conditioning path: learnable cross-attention over the frozen per-modality encoders, and a dual token-plus-AdaLN route for the static conditions. ReCoGen thus turns routinely collected signals into informative surrogates for invasive or unavailable ones, a step toward less invasive, lower-cost continuous clinical monitoring.

AI 总结：该研究将条件因果发现转化为贝叶斯推理问题，采用稀有事件估计技术解决小后验质量事件的计算挑战，经合成图和Sachs蛋白质数据集验证了方法的准确性与辅助科学探索的作用。

链接：https://arxiv.org/abs/2608.12640

机构：Yale University（耶鲁大学）； University of California, Los Angeles（加利福尼亚大学洛杉矶分校）

作者：Cixuan Zhang, Guy Van den Broeck, Benjie Wang

英文摘要：Causal discovery aims to uncover the underlying causal relationships given data generated from a system. The goal, however, is not merely to predict causal edges given data, but also to be able to interpret and explain either observed or hypothesized phenomena, such as a particularly large causal effect. We consider this task of conditional causal discovery and cast it as a Bayesian inference problem, in which we target the posterior over causal graphs and parameters conditional on an event such as a causal-effect constraint. Unfortunately, this poses a computational challenge: existing approaches to Bayesian causal discovery struggle when the event has small posterior mass. To address this, we adapt rare-event estimation techniques to perform inference the joint graph-parameter space. Our method gradually drives a particle population toward the constrained region while maintaining samples that approximate the conditional posterior. Empirical evaluation on synthetic graphs validates the accuracy of our approach at small and large scales, and we show in a case study on the Sachs protein dataset how our method can be used to aid scientific exploration by providing pathway-level summaries.

AI 总结：该研究提出Constrained Graph Diffusion（CGD）框架，结合图扩散模型与可行性投影算子求解混合整数规划，在两类任务上较基线方法提升可行性与质量，且最高加速425倍。

链接：https://arxiv.org/abs/2608.13079

机构：University of Virginia（弗吉尼亚大学）； MIT（麻省理工学院）； Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）

作者：Vincenzo Di Vito, Mehdi Taghizadeh, Deepjyoti Deka, Kaarthik Sundar, Ferdinando Fioretto

英文摘要：This paper proposes a novel learning-based approach to approximately solve instances of mixed-integer optimization problems. These problems are computationally challenging, as they require jointly determining discrete and continuous decisions while satisfying complex combinatorial constraints. The proposed method relies on a graph-based generative diffusion model that learns the discrete component of mixed-integer optimization problems while integrating a training-free feasibility projection operator directly into the reverse diffusion process to steer intermediate samples toward the feasible set throughout generation. Once the discrete decisions are generated, the remaining optimization reduces to a continuous problem that can be solved efficiently (relative to the original problem) using existing numerical methods. The resulting framework named Constrained Graph Diffusion (CGD), is problem-agnostic and can accommodate a broad class of mixed-integer optimization problems through suitable projection operators. We evaluate CGD on optimal transmission switching for ACOPF and discrete portfolio optimization, demonstrating substantial improvements in feasibility and solution quality over learning-based baselines while achieving speedups of up to $425\times$ over state-of-the-art numerical solvers for MINLPs.

AI 总结：本文提出FlowLOB，一种基于流匹配的LOB轨迹生成模型，经HKEX数据训练可泛化至未见过的交易品种，采样效率与可控性优于基准模型，且能零样本泛化。

链接：https://arxiv.org/abs/2608.13096

机构：Simudyne（思慕迪恩）； King’s College London（伦敦国王学院）

作者：Zhuohan Wang, Andreea Bacalum, Ollie Olby, Carmine Ventre, Namid Stillman

英文摘要：Limit order book (LOB) simulators are most useful to practitioners when they combine realistic market dynamics, computationally efficient sampling, controllable scenario generation, and the ability to generalize beyond the instruments seen during training---properties that existing agent-based and deep generative simulators provide only partially. We present \textbf{FlowLOB}, a conditional \textbf{flow}-matching generator of \textbf{LOB} trajectories, trained on multiple Hong Kong Exchange (HKEX) symbols at three sampling frequencies ($0.1$s, $1$s, $10$s) in tick-relative representation that transfers to unseen instruments. Because flow and diffusion models admit a common formulation, we train both with identical data, architecture, and budget, and sample both through the same fixed-step ODE solvers, yielding a controlled comparison of sampling efficiency and fidelity. Flow matching attains its best quality with only $10$ ODE-solver steps, whereas diffusion needs many more function evaluations to approach the same fidelity. At this efficient operating point, FlowLOB improves realism over baselines, two learned and two agent-based models, in most distributional metrics at the two finer sampling frequencies. We evaluate counterfactual controllability with a distributional test that asks whether changing a scenario condition moves the generated statistic toward the corresponding real tail regime; FlowLOB satisfies this criterion in most tested settings. Both realism and control effects transfer zero-shot on a held-out symbol. We additionally conduct ablation studies on the network architecture and the learning rate.

AI 总结：该研究针对转录组数据的获取限制，提出并基准测试三种生成对抗网络变体，其中MK-TGAN模型结合图神经网络整合先验知识，生成的合成转录组数据真实性与实用性更优。

链接：https://arxiv.org/abs/2608.13256

机构：Politecnico di Milano（米兰理工大学）

作者：Francesca Pia Panaccione, Sofia Mongardi, Marco Masseroli, Pietro Pinoli

英文摘要： As biomedical research increasingly relies on data-intensive tools, the quality and utility of datasets are critical. Challenges such as imbalances, biases, and ethical or legal constraints often limit access to high-quality data. Synthetic data generation can help overcome these limitations. Here, we present a comparative analysis of generative models for transcriptomic data, investigating strategies to incorporate prior biological knowledge via gene graphs. This ensures that synthetic data capture real-world gene patterns, maintaining their usefulness for downstream tasks. In particular, we introduce and benchmark three variants of the Generative Adversarial Network. Among the alternatives, MK-TGAN - an innovative multi-kernel, Graph Neural Network-based model - stands out for its performance in terms of both the realism and utility of the generated data. Unlike other methods, MK-TGAN leverages prior knowledge graphs by exploiting graph neural networks. Our results show that prior knowledge integration strategies improve performance, and that MK-TGAN consistently produces synthetic samples with superior realism and biological plausibility.

AI 总结：本文提出TTARO框架，通过测试时自适应调整电路表示优化贝叶斯优化，在40种设置下较传统方法降低后悔曲线下面积15.2%至20.7%，性能优于现有技术。

链接：https://arxiv.org/abs/2608.12687

机构：North Carolina State University（北卡罗来纳州立大学）

作者：Fin Amin, Sounak Dutta, Paul D. Franzon

英文摘要：Bayesian optimization (BO) is a sample-efficient framework for analog circuit topology search, where evaluating each candidate topology can require costly simulation. However, representation-based BO methods typically treat circuit embeddings as fixed after encoder training. This creates a mismatch between representation learning and optimization: embeddings learned to encode or reconstruct circuit structure are not necessarily organized according to the figure of merit (FoM) being optimized. This paper introduces Test-Time Analog Representation Adaptation for Bayesian Optimization (TTARO), an online deep-kernel BO framework that adapts circuit representations throughout the search process. Starting from pretrained circuit embeddings, TTARO jointly learns a nonlinear feature transformation and a Gaussian-process surrogate using the FoM labels of the circuits evaluated so far. Following each new evaluation, TTARO updates the representation and surrogate before selecting the next candidate. We compare TTARO with conventional Gaussian Process-based BO over fixed embeddings and with Deep Kernel Learning (DKL), which learns the representation only from the initial evaluated designs and keeps it fixed throughout the remainder of the search. By continually incorporating newly observed FoM labels into representation learning, TTARO aligns the search space with the optimization objective as BO progresses. In our experiments, TTARO reduces regret AUC by 15.2% on average relative to BO and by 20.7% relative to DKL across 40 encoder/kernel/acquisition settings, outperforming prior art in most settings with reductions as large as 46.7%.

AI 总结：针对现有Muon优化器不适用于分层结构化问题的缺陷，提出FedCoMuon及FedCoMuon-VR优化器，理论分析其收敛性并通过实验验证其在联邦学习等任务中的性能优于基线方法。

链接：https://arxiv.org/abs/2608.12710

机构：College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院）

作者：Wang Yan, Feihu Huang

英文摘要：Muon, a more recently developed optimizer, is useful for matrix-wise models in AI areas. Although many works have studied Muon and its variants, these methods are still not particularly well-suited for hierarchical structured problems. To fill this gap, we propose an effective federated compositional Muon (FedCoMuon) optimizer to solve distributed matrix-wise compositional optimization problems. Specifically, our FedCoMuon optimizer builds on compositional gradient tracking and orthogonalized momentum. Moreover, we propose a variance reduced variant of FedCoMuon (FedCoMuon-VR) based on a momentum-based variance reduced technique. In theory, we analyze the convergence properties of our algorithms under the non-i.i.d. and non-convex settings. In particular, we prove that our FedCoMuon-VR obtains a lower sample complexity of $O(\epsilon^{-3})$ for finding an $\epsilon$-stationary solution than the existing FedMuon algorithms. Extensive numerical experiments on robust federated learning and task-distributed risk-sensitive meta learning show that our proposed methods are competitive with existing compositional baselines and achieve the best reported accuracy in several settings.

AI 总结：本文针对CVR因果估计的样本选择偏差问题，提出带理论保障的双重鲁棒估计量，结合目标正则化提升稳定性，实验验证其优于简单去偏结合的方法。

链接：https://arxiv.org/abs/2608.13461

机构：Tsinghua University（清华大学）； Tencent Inc.（腾讯公司）

作者：Jiayi Dan, Bo Li, Lu Deng, Yong Wang

英文摘要： Post-click conversion rate (CVR) is a key metric in various scenarios including e-commerce and advertising, reflecting the efficiency and user experience in the second stage of the conversion process. Estimating the causal effect on CVR is therefore of great practical importance. However, directly applying existing causal inference methods to clicked samples introduces sample selection bias and increased variance due to the exclusion of non-click data. Recent studies on CVR prediction introduce "ideal loss", which optimizes model parameters using an unbiased estimate of the loss over the full sample. Nevertheless, there is no guarantee that unbiasedness of the loss implies unbiasedness of the final estimator. We revisit this challenge from the perspective of semiparametric theory. Specifically, we develop a new doubly robust causal effect estimator for chain-structured outcomes such as CVR, and derive its theoretical properties in detail. It achieves a faster convergence rate compared to nuisance parameters estimation and is therefore more robust when using flexible nonparametric estimators, including neural networks. Based on these theoretical findings, we further design a framework based on targeted regularization to improve numerical stability and practical applicability. Extensive experiments on synthetic and real-world data demonstrate the effectiveness and robustness of our method. In addition, we find that naively combining loss debiasing with standard causal estimators underperforms our method, highlighting the necessity of developing the new estimator tailored to this CVR-style objective with solid theoretical guarantees.

AI 总结：本文针对垂直联邦学习（VFL）的后门漏洞开展面向实践的系统性研究，发现现有研究与实践存在差距，提出实用后门工作流并引入BVBench基准，为相关研究奠定基础。

链接：https://arxiv.org/abs/2608.12962

机构：School of Computing and Data Science, The University of Hong Kong（香港大学计算机与数据科学学院）

作者：Ziqi Zhao, Jialin Lu, Junjie Shan, Junyuan Zhang, Shuya Yang, Ka-Ho Chow

英文摘要：Vertical Federated Learning (VFL) enables organizations holding complementary features of shared entities to collaborate and train models. In this setting, the initiator can withhold information about the learning task, while other contributors participate without exposing their local datasets, creating an asymmetric information structure aligned with growing privacy demands. However, this asymmetry is a double-edged sword. Among various threats, backdoor attacks are particularly concerning because VFL not only enables malicious contributors to poison the model during training, but also allows them to activate the backdoor at inference time to manipulate predictions. Although prior work has reported near-perfect attack success rates and proposed effective defenses, we find that most findings fail to hold under realistic conditions, exposing a fundamental gap between research and practice. In this paper, we present a systematic, practice-oriented study of backdoor vulnerabilities in VFL, revealing this gap in both methodological design and evaluation practices. We show that existing approaches overlook key practical constraints and therefore rely on unrealistic prior knowledge. Furthermore, these limitations have remained hidden due to poorly designed evaluation practices in the literature. To bridge this gap, we redefine threat models under realistic constraints, propose practical backdoor workflows, and introduce BVBench, a backdoor-centric benchmark that enables fair, practical, and comprehensive evaluation, preloaded with state-of-the-art baselines. BVBench provides strong evidence of the fragility of the current understanding of VFL backdoor risks and establishes a foundation for steering research toward uncovering practical vulnerabilities and developing more meaningful defenses.

AI 总结：该研究针对时间序列分析深度学习模型的对抗攻击问题，提出GENADA框架，通过生成模型单次前向传播生成扰动，在保持攻击质量的同时缩短推理耗时，提升了攻击效率。

链接：https://arxiv.org/abs/2608.12535

机构：Moscow Independent Research Institute of Artificial Intelligence（莫斯科独立人工智能研究院）； HSE University（高等经济大学）

作者：Michael Baronov, Denis Vorobev, Margarita Rusanova, Petr Sokerin, Alexey Zaytsev

英文摘要：Deep learning models are widely used for time series analysis in domains such as healthcare, finance, energy systems, and environmental monitoring. However, these models remain vulnerable to adversarial attacks, where small input perturbations cause severe degradation in predictive performance. Commonly used gradient-based attacks, iterative first-order methods, are computationally burdensome, as they repeatedly backpropagate through the victim model to compute input gradients during a number of iterative refinement steps. We propose a GENerative ADversarial Attack (GENADA) that learns a generative model to produce deceptive perturbations directly in a single forward pass and a procedure to train it. Variants include single-step and iterative generative attack schemes. The validation considers attacks on several neural models and datasets in the time-series domain, a controlled, low-dimensional setting. Empirically, GENADA achieves comparable attack quality to strong baselines while requiring less time to generate perturbations during inference.

AI 总结：本研究提出保结构认知神经网络（S-PENNs）框架，用于带硬架构约束的科学机器学习模型的不确定性量化，在GENERIC动力学算例中验证其可生成符合热力学一致性的结果，且计算成本远低于深度集成。

链接：https://arxiv.org/abs/2608.12624

机构：University of Pennsylvania（宾夕法尼亚大学）

作者：Zequn He, Celia Reina

英文摘要： Structure-preserving machine learning embeds physical structure directly into model architectures, yet uncertainty quantification (UQ) for such hard-constrained models remains limited because standard UQ methods may violate the encoded admissibility conditions, require architectural modifications, or impose substantial computational costs. In this work, we propose Structure-Preserving Epistemic Neural Networks (S-PENNs), a general framework for UQ in scientific machine learning models with hard architectural constraints, and instantiate it for GENERIC (General Equation for Non-Equilibrium Reversible-Irreversible Coupling) dynamics. S-PENNs preserve the structural constraints of a pretrained model by attaching lightweight epinets to its constrained components, ensuring that every sampled realization remains physically admissible by construction. When applied to GENERIC dynamics, such a proposed framework yields thermodynamically consistent rollouts that preserve the first and second laws. Furthermore, we combine S-PENNs with split conformal prediction as a post-hoc calibration method to produce prediction intervals with finite-sample marginal coverage guarantees. We validate S-PENNs on three numerical examples: a harmonic oscillator coupled to a heat bath and an idealized chemical motor, both governed by ODEs, and a one-dimensional viscoplastic model governed by PDEs. Across all three examples, S-PENNs produce thermodynamically consistent stochastic realizations and well-calibrated prediction intervals while reducing the computational cost by about one to three orders of magnitude compared to deep ensembles. Although the present study focuses on GENERIC dynamics, S-PENNs can be extended more broadly to scientific machine learning models in computational mechanics with either hard or soft constraints.

AI 总结：本文提出CAKE编译器-智能体协同设计方案，通过硬件显式IR实现GPU核函数演进，在Flash-KMeans等基准测试中性能优于CUDA/PTX，相关成果已提交上游PR。

链接：https://arxiv.org/abs/2608.12629

机构：Carnegie Mellon University（卡内基梅隆大学）； NVIDIA（英伟达公司）

作者：Zihao Ye, Yingyi Huang, Hongyi Jin, Bohan Hou, Junru Shao, Zhongming Yu, Jinqi Chen, Meghan Cowan, Shiyi Cao, Shanli Xing, Hanfeng Chen, Vinod Grover, Tianqi Chen, Luis Ceze

英文摘要：GPU kernel agents and GPU programming languages have advanced separately, leaving expert kernels difficult to reproduce. Agents usually treat the compiler as a fixed black box and receive only errors, correctness outcomes, and timing, while existing DSLs either hide critical scheduling decisions or expose them through difficult layout abstractions. We present CAKE, a compiler-agent co-design in which agents author CAKE IR, a typed, hardware-explicit schedule representation. CAKE exposes warp roles, memory movement, synchronization, and pipelines while supporting verification, cost modeling, and localized diagnostics. The harness itself evolves: recurring failures become verifier rules, IR primitives, model calibrations, and reusable optimization tactics. In matched implementation-hidden Flash-KMeans clean starts on B200, the best CAKE IR candidate at an 80-million-token budget runs at 1.144x the tuned FlashML baseline, compared with 0.928x for direct CUDA/PTX. Beyond this benchmark, agent-generated Kimi Delta Attention achieves a 2.05x geometric-mean speedup over official FlashKDA and passes end-to-end serving validation. Dispatcher-backed KNN and KMeans improve performance by 1.42x to 2.12x across more than 400 shapes, and four kernel changes are available as upstream PRs. CAKE targets NVIDIA GPUs from Ampere through Blackwell and separates single-shape evolution from library generalization and dispatch.

AI 总结：该研究审计神经组合优化测试时预算分配的增益，发现样本内存在幻象增益，样本外消失，而分布偏移下分配可提升性能，还提供校正流程并发布相关数据代码。

链接：https://arxiv.org/abs/2608.13087

机构：Hankuk University of Foreign Studies（韩国外国语大学）

作者：Jinhyung Bae

英文摘要：Neural combinatorial optimization (NCO) solvers report the best of many sampled solutions per instance, and the sample count is, by convention, identical for every instance. Whether a non-uniform allocation of a fixed total budget would buy anything has not been measured. We measure it, and we audit the measurement itself. First, on in-distribution workloads the allocation headroom is not detectable. Across three pretrained solvers (POMO, AM, SymNCO) on uniform TSP-100, an oracle allocation computed and evaluated on the same stored samples reports a 2.2-2.6% gain with intervals excluding zero; measured out of sample the same gain is indistinguishable from zero (0.457, 0.015, -0.512 percent). Following the customary in-sample procedure, all three solvers would have supported a published 2%-level gain that does not exist. We calibrate this bias against an instance-wise null in which the true gain is zero by construction; over the ranges we test it does not shrink with more samples or more instances. Second, the same correction that removes the phantom gains preserves a real one. Under distribution shift (a workload mixing uniform and clustered instances), a pre-registered confirmatory experiment finds that allocation guided by held-out sample statistics improves best-of-k by 11.5% (AM, primary endpoint; 95% CI [7.4, 19.7]) and 12.0% (SymNCO, replication) at equal evaluation budget, with the signal-acquisition cost not charged; a pre-registered negative control (POMO, an order of magnitude more robust to shift) shows -0.3% [-0.7, 0.24]. The gain exceeds a frozen distribution-label baseline by 4.2 points [1.9, 7.7]. An exploratory policy charging a 20-sample probe against the same budget retains 3.4% (AM) and 4.6% (SymNCO). We give a correction procedure and a reporting checklist, and release all data, code, and the pre-registration record.

AI 总结：针对无训练组标签的组鲁棒学习问题，提出ProME方法，通过划分原型边际构建平衡环境并对齐决策与部署预测器，实验显示其平均最坏组准确性优于对比方法。

链接：https://arxiv.org/abs/2608.13190

机构：Shenzhen Key Laboratory of Safety and Security for Next Generation of Industrial Internet（深圳市下一代工业互联网安全重点实验室）； Department of Statistics and Data Science, Southern University of Science and Technology（南方科技大学统计与数据科学系）

作者：Qianqian Wang, Yunshan Li, Dawei Huang, Wenwu Gong, Lili Yang

英文摘要： Group-robust learning is crucial for maintaining accuracy on rare subpopulations when training-group labels are unavailable. However, existing methods often infer environments from a separate reference model and select representations before fitting the classifier used at deployment, leaving both decisions misaligned with the deployed predictor. In this work, we formulate group robustness without training-group labels as the endogenous environments with repair-aware selection (ERAS) problem, and propose ProME (Prototype-Margin Environments) to align both decisions with the deployed predictor. ProME splits prototype margins at their median to construct approximately balanced environments along the training trajectory, and fits a group-balanced linear head on group-annotated validation data to rank the resulting predictors by validation worst-group accuracy. We theoretically bound the worst risk across the inferred environments for a fixed predictor and partition, showing that this bound transfers to the oracle groups under an explicit alignment condition. Extensive experiments show that prototype margins enrich shortcut-conflicting examples, classifier repair reshapes candidate evaluation, and ProME achieves the highest average worst-group accuracy among the compared methods with the same group-label access.

AI 总结：该研究提出黑盒对抗攻击（BBAA）相关任务可作为高维全局优化基准，通过实验验证多种进化算法与元启发式算法解决BBAA问题的效率，助力全局优化方法适配现代机器学习需求。

链接：https://arxiv.org/abs/2608.13296

作者：Wojciech Zarzecki, Jarosław Arabas

英文摘要：Existing global optimization benchmark suites are of a moderate size and are based on a small number of analytical functions that date back even to the 1970s. This causes a risk of biasing the development of global optimization methods. We argue that the tasks related to the black-box adversarial attack (BBAA) can serve as valuable global optimization benchmark in many-dimensional space. We demonstrate the efficiency of several types of evolutionary algorithms and other metaheuristics in solving example BBAA problems. Thus, we take a step towards convergence of global optimization methods to the challenges and needs that arise in the modern machine learning field.

AI 总结：该研究提出合成角色预训练（SPP），在预训练token零阶段植入助手角色，通过标注反思、预训练及角色绑定，提升模型价值构成遵循度与鲁棒性，降低对齐错误率，证明预训练时角色干预是对齐的有效方法。

链接：https://arxiv.org/abs/2608.13482

机构：EPFL（洛桑联邦理工学院）； University of Toronto（多伦多大学）； Northeastern University（东北大学）； SJTU（上海交通大学）； Saarland University（萨尔大学）； Hereon（亥姆霍兹极地与海洋研究中心）； TUHH（汉堡工业大学）； Ontocord AI（Ontocord人工智能公司）； TUC（德累斯顿工业大学）； DFKI（德国人工智能研究中心）

作者：Julian Minder, Viktor Moskvoretskii, Raghav Singhal, Difan Jiao, Andy Arditi, Shaobo Cui, Yiderigun Borjigin, Kartik Bali, Stefan Krsteski, Harsh Raj, Huu Nguyen, Jannik Brinkmann, Ashton Anderson, Roland Aydin, Robert West

英文摘要：As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical. Today, alignment, and the assistant identity itself, are typically introduced only after pretraining, once behavioral priors are already established. This can make values a thin overlay, rather than deeply rooted, and facilitate subsequent misalignment. Pursuing a different paradigm, we introduce Synthetic Persona Pretraining (SPP), which installs the desired assistant persona from token zero in pretraining. First, we annotate pretraining documents with value-aligned first-person reflections derived from a normative value constitution. Second, we pretrain via the standard cross-entropy loss on standard pretraining documents as well as their reflections, which installs the desired persona among a multitude of other personas. Finally, we post-train on user-assistant dialogue data, which binds this desired persona to the assistant identity, a process we call persona binding. By pretraining models up to 3B parameters on 500B tokens, we show that SPP improves constitution following and jailbreak robustness, and reduces the misalignment rate in out-of-distribution moral dilemmas, while preserving capabilities. Early intervention matters: compared with alignment from token zero, introducing SPP only at the end of pretraining yields weaker constitution adherence, does not shift value priorities, and leads to less aligned choices in dilemmas. This advantage depends on persona binding and, importantly, increases with pretraining budget. Overall, our results show that shaping values early is critical for alignment and establish pretraining-time persona interventions as an effective approach to do so.

AI 总结：针对深度图神经网络的过平滑问题，提出HouseGNN模型，利用豪斯霍尔德反射器与GroupSort构建分段正交层，证明其核心性质以缓解过平滑。

链接：https://arxiv.org/abs/2608.12514

作者：Bhaskar Karol

英文摘要：Deep graph neural networks(GNNs) suffer from oversmoothing- a progressive collapse of node representation towards a low information subspace as network depth increases because the normalized graph propagation operator is repeatedly applied directly to the hidden representations. In this work we study Householder Graph Neural Network (HouseGNN). Rather than updating the hidden state like standard GCN, HouseGNN uses the aggregated neighbourhood message solely to estimate a reflection direction; the node embedding is then updated by a Householder reflector followed by GroupSort, yielding a piecewise orthogonal layer that preserves Euclidean norm at every node and at every depth. We prove three core properties: (i) every internal layer preserves the node-wise Euclidean norm; (ii) the Householder reflector is scale scale and sign-invariant in the message; and (iii) pairwise distance between nodes can change through mismatch between node-wise orthogonal operators.

AI 总结：EGRL是一种用于RNA-蛋白质相互作用预测的新型深度学习框架，通过边生成引导的关系感知学习，在未知分子的冷启动场景中相比现有方法实现了显著的性能提升。

链接：https://arxiv.org/abs/2608.12906

机构：Macau University of Science and Technology（澳门科技大学）； Macau University of Science and Technology Zhuhai Research Institute（澳门科技大学珠海研究院）； Wuhan University of Technology（武汉理工大学）； Jiangsu University（江苏大学）； Harbin Institute of Technology（哈尔滨工业大学）

作者：Danyu Li, Ling Zhou, Rubing Huang, Xian Zhong, Bin Zou, Kui Jiang

英文摘要：RNA-Protein Interactions (RPIs) are critical for regulating cellular functions. While traditional wet-lab experiments for RPI detection are costly and time-consuming, Deep Learning (DL) methods provide an efficient computational alternative for RPI Prediction (RPIP). In particular, Graph Neural Networks (GNNs) are promising, as they naturally model RPI networks. However, existing GNN-based methods often rely on homogeneous graphs or predefined meta-paths, which limit their ability to handle data sparsity and to generalize to cold-start scenarios involving unknown molecules. To address these limitations, we propose Edge Generation-guided Relation-aware Learning (EGRL), a novel framework with several key components: implicit meta-path learning to capture relational semantics without handcrafted paths; a multi-relation-aware attention mechanism for adaptive fusion of interaction patterns; a graph generator that predicts potential ("soft") edges to support cold-start nodes; and a multi-feature fusion predictor for final interaction scoring. EGRL is jointly trained with a primary task loss and an auxiliary generator loss. Comprehensive evaluations on four benchmark datasets demonstrate that EGRL achieves competitive overall performance. More importantly, it exhibits superior generalization in cold-start settings, achieving an Area Under the Receiver Operating Characteristic curve (AUROC) of 0.867 and an Area Under the Precision-Recall curve (AUPR) of 0.861 on unknown molecules, corresponding to improvements of 8.6% in AUROC and 5.0% in AUPR over prior state-of-the-art methods. The code will be released soon.

AI 总结：TANGCO是一种拓扑感知神经图引导的容量优化模型，可应对过载驱动的级联故障，在人工与真实网络上均优于手动启发式方法，具备良好迁移性，部署成本低且训练效率高。

链接：https://arxiv.org/abs/2608.13212

机构：Carnegie Mellon University（卡内基梅隆大学）

作者：Orkun Irsoy, Leman Akoglu, Osman Yagan

英文摘要：Networked systems, from power grids to traffic networks and cloud clusters, carry loads across nodes with limited capacity. A node whose load exceeds its capacity fails and sheds its load onto its neighbors, which can trigger a system-wide cascade. We study how to allocate a fixed capacity budget across nodes to resist these cascades under local load redistribution. The problem is difficult because no optimal allocation is known, and the fail-or-survive objective is non-differentiable and piecewise constant, so exact and gradient-based optimization methods do not directly apply. We introduce TANGCO (Topology-Aware Neural Graph-Guided Capacity Optimization), which uses a graph neural network policy trained through the cascade simulator with policy-gradient learning and a heuristic anchor. We evaluate TANGCO on five synthetic graph families and five real networks spanning power, road, air, and Internet topologies. The learned policy improves on the best of four hand-designed heuristics in all 450 synthetic instances and in 40 of 45 real-network conditions, with robustness gains ranging from 1.6% to 246%. The learned policies transfer to unseen graphs within a family and partially across related topologies, and TANGCO$^{pre}$, pre-trained on synthetic graphs, matches per-network training on unseen real networks. Training scales near-linearly with graph size, and TANGCO$^{pre}$ allocates on a new network with no per-target training, matching the deployment cost of a hand-designed heuristic. Free-vector variants without the GNN, stay close to the heuristics, so the graph representation carries the gain beyond numerical search. Finally, analysis of the learned allocations identifies when local risk is sufficient, leads to an improved closed-form heuristic, and reveals the regimes where a topology-aware learned policy remains necessary.

AI 总结：针对持续学习的可塑性损失与谱偏差问题，提出可学习小波激活及动态小波注入等方法，在多基准上实现了先进性能。

链接：https://arxiv.org/abs/2608.12874

机构：Institute of Multimedia Knowledge Fusion and Engineering（多媒体知识融合与工程研究院）

作者：Zeyang Zhang, Tieliang Gong, Junyan Lu, Weizhan Zhang

英文摘要：Plasticity loss has emerged as a critical challenge in continual learning that significantly hinders the acquisition of sequential tasks. While optimizing activation designs offers a potential solution, current fixed-form functions suffer from an inherent spectral bias towards low-frequency variations, whereas learnable variants permit unconstrained updates that induce catastrophic forgetting. To address these limitations, we propose a novel learnable wavelet activation that decomposes the activation function into low-frequency and high-frequency components to explicitly counter spectral bias. Furthermore, we employ dynamic wavelet injection to adaptively enhance plasticity for new tasks, alongside a regularization strategy to ensure the stability of previous learned knowledge. Theoretically, we provide rigorous mathematical guarantees for the proposed framework, proving the structural necessity of the hybrid wavelet architecture for efficient $L^2$ approximation and demonstrating that the decoupled learning rate mechanism successfully restores network plasticity for high-frequency information. Additionally, we provide a formal derivation of the loss-driven injection trigger mechanism to precisely guide the injection. Extensive empirical evaluations demonstrate that our approach maintains superior trainability and generalization throughout the learning process and achieves state-of-the-art performance across diverse continual learning benchmarks.

AI 总结：本文针对M&G关于通过MAML将贝叶斯先验蒸馏到ANNs以实现快速语言学习的研究，指出其未真正植入先验、宽松解释存挑战且模型过拟合泛化差的问题。

链接：https://arxiv.org/abs/2608.12974

作者：Orr Well, Idan Tarshish, Nur Lan, Roni Katzir

英文摘要：McCoy & Griffiths (2025, henceforth M&G) suggest that a Bayesian prior can be distilled into Artificial Neural Networks (ANNs) through Model-Agnostic Meta-Learning (MAML, Finn et al., 2017). They support this empirically by showing that meta-trained networks demonstrate formal language learning abilities comparable to Yang & Piantadosi (2023)'s Bayesian learner, significantly outperforming standard ANNs. We point out that under the standard interpretation of a prior, M&G's procedure does not actually instill one; it merely initializes network weights favorably, leaving the objective function unchanged. We then consider a more permissive interpretation, where the system as a whole can be seen as implementing a Bayesian learner even without an explicit prior in the objective. We show that this interpretation faces nontrivial challenges. Finally, we assess how well MAML approximates the empirical results of Bayesian learning, showing that unlike genuine Bayesian learners, M&G's model overfits and generalizes poorly to unseen data.

AI 总结：研究针对红外光谱化学传感的迁移难题，提出超1亿参数的红外光谱基础模型UltraIR，经6000万仿真光谱预训练后，在多类化学分析任务中性能优于基线，且适配性与数据效率优异。

链接：https://arxiv.org/abs/2608.13341

机构：The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； Jilin University（吉林大学）； University of Auckland（奥克兰大学）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； Hunan University（湖南大学）； The Hong Kong University of Science and Technology（香港科技大学）

作者：Yusen Tan, Yixuan Chen, Zheng Fang, Pan Liu, Yifan Li, Qinyu Guo, Zhedong Lin, Yuqiang Li, Xiangxiang Zeng, Tong Wang, Jun Xia

英文摘要：Infrared (IR) spectroscopy is widely used for chemical sensing, but extracting reliable chemical information from spectra remains challenging. Conventional interpretation is labor-intensive, relies on prior knowledge and reference spectra, and is difficult to scale, whereas most machine-learning methods are tailored to individual tasks or datasets, require large labeled training sets, and transfer poorly across analytical objectives and experimental datasets. Here we introduce UltraIR, a foundation model for IR spectroscopy with more than 100 million parameters that enables simulation-to-real transfer learning for chemical sensing and analysis from molecules to complex samples. UltraIR is pretrained on approximately 60 million simulated IR spectra using spectral reconstruction, molecular fingerprint similarity alignment, and functional-group prediction, then adapted to downstream objectives with task-specific labels or targets. Across functional-group prediction, molecular structure elucidation, physicochemical property prediction, mixture-component identification and quantification, bacterial classification, medicinal-herb geographic origin traceability and constituent quantification, microplastics classification, and soil property prediction, UltraIR outperforms conventional machine-learning and task-specific deep-learning baselines. It performs strongly with limited labeled experimental spectra and in zero-shot inference for the same analytical task across Fourier-transform infrared spectrometers and laboratories, providing a route to adaptable, data-efficient chemical sensing from complex real-world samples.

AI 总结：该研究构建等开销Top-k分配离线评估基准，分析弱重叠、优化器诅咒、倾向估计误差等问题，验证相关机制并发布仅含公开数据的可复现基准。

链接：https://arxiv.org/abs/2608.12489

作者：Binshuang Li

英文摘要：Organizations decide whom to treat under a budget and want to know what a targeting rule would have earned before deploying it. Off-policy evaluation promises this from logged data, but the deployable rule is a deterministic top-k policy: it removes all averaging over actions, so weak overlap hits the estimate directly. We benchmark six estimators across five datasets and two known-effect sweeps, and validate the mechanisms against a non-simulated paired reference. First, weak overlap is governed by logger-target action alignment, not by logging sharpness alone: what governs support is the logger's probability of the target's actions. Sharpening a logger built from the target's own score barely moves overlap over the tested range; action-level disagreement collapses it. Effective sample size ranks this risk across logging environments, but is weak at ranking candidates within the single log a practitioner holds, and its cut point does not transfer. Second, the optimizer's curse is not fixed by cross-fitting the outcome nuisance. When the rule is fit on the data used to evaluate it, cross-fitting the nuisance alone leaves the reuse bias in place and makes it worse. Honest policy-level splitting avoids the reuse by targeting the learning procedure's value -- a change of estimand, not a de-biasing of the full-sample policy. Third, propensity-estimation error is the largest degradation we measure: an out-of-fold estimate hurts IPS more than any other stress we apply, leaves doubly-robust estimation almost unchanged, and can invert the overlap diagnostic itself. Logging is synthesized and propensities floored at 0.02, so every failure occurs with bounded weights; the floor also reduces the two tuned hybrids to their untuned parents, leaving four practically distinct estimators, and all exact-value surfaces are synthetic or semi-synthetic. We release the benchmark; public data only.

AI 总结： CoMedBench是涵盖多源合成医疗数据的可复现基准，评估多生成器在静态表格和时序ICU任务上的保真度与下游效用，实验显示合成数据可保留多数下游信号，不同生成器表现存在差异。

链接：https://arxiv.org/abs/2608.12805

作者：Akanta Das, Al Amin Farhad, Mrinmoy Sarkar Anto, David Rehkopf, Ayin Vala, Tanmoy Sarkar Pias

英文摘要：Access to clinical data is essential for developing reliable healthcare machine learning systems, but direct use of electronic health records is constrained by privacy regulation, institutional review, data-use agreements, and the risk of re-identification. Synthetic data promises a practical alternative: it can preserve useful statistical and clinical structure while reducing exposure of sensitive patient records. Prior studies often evaluate a single generator, one dataset, or a narrow downstream task, making it difficult to know when synthetic data can support model development and when it fails to preserve task-critical signal. We introduce CoMedBench, a reproducible benchmark that evaluates a family of generators under a common clinical-validity framework and one shared training and evaluation engine, spanning static tabular and temporal downstream tasks on established critical-care datasets. In total the benchmark spans 37 dataset-task pairs across two modalities consists of 20 static tabular and 17 temporal ICU time-series-drawn from seven public data sources: three intensive-care databases (MIMIC-III, MIMIC-IV, and eICU) together with the UCI Machine Learning Repository, the CDC BRFSS diabetes cohort (2015), NHANES (1999-2014), and the pycox survival datasets (GBSG and METABRIC). The benchmark evaluates both statistical fidelity and task utility by comparing models trained and tested across real and synthetic data. In these settings, synthetic training data preserves most of the downstream signal: on tabular tasks the reference generator CoMed-CTGAN retains a mean AUROC utility (the synthetic-to-real performance ratio) of 90.6%, rising to 97.3% for the strongest generator, CoMed-TVAE. Temporal ICU tasks are harder and more generator-sensitive: CoMed-CTGAN retains 81.6% (AUROC) and only 64.0% under the imbalance-sensitive AUPRC, whereas CoMed-TVAE still retains ~95% (AUROC).

AI 总结：本文针对真实世界数据稀缺下的跌倒检测，系统评估了不同运动表示的性能，发现高参数模型在模拟数据表现好但泛化差，增强的符号表示泛化能力最优，为可部署跌倒检测提供了关键参考。

链接：https://arxiv.org/abs/2608.13197

机构：University College Dublin (UCD)（都柏林大学学院）； University of Bologna（博洛尼亚大学）； Robert Bosch Hospital（罗伯特博世医院）； Heidelberg University Hospital（海德堡大学医院）

作者：Timilehin B. Aderinola, Ilaria D'Ascanio, Luca Palmerini, Lorenzo Chiari, Jochen Klenk, Clemens Becker, Brian Caulfield, Georgiana Ifrim

英文摘要：Falls are a major health concern for older adults, and wearable sensors have been widely explored for detecting falls and enabling timely intervention. However, real-world falls are extremely rare: collecting 100 of them requires an estimated 100,000 days of monitoring, resulting in severely limited labelled data for training machine learning models. Consequently, many approaches rely on simulated datasets, often reporting high laboratory performance but limited real-world generalisation. We present a systematic evaluation of motion representations for wearable fall detection under real-world data scarcity. Using accelerometer signals, we compare interval-based, kernel-based, symbolic, and foundation model representations. As an interpretable baseline, we additionally investigate a lightweight symbolic representation that converts short motion segments into symbolic sentences augmented with physically-grounded impact descriptors. Experiments use FallAllD, a simulated falls dataset, and FARSEEING, a clinically verified real-world falls dataset. Through cross-validation, controlled data scarcity, and cross-dataset transfer, we examine how representation choices affect robustness under realistic deployment. Our results reveal that highly parameterised kernel and foundation models excel on simulated data but degrade severely under both data scarcity and domain shift. Although the interval-based representation achieves the strongest absolute real-world performance, augmenting a symbolic representation with physically-grounded impact descriptors yields the smallest degradation under domain shift and retains detection sensitivity under extreme scarcity, albeit at lower precision. These findings highlight the importance of evaluating beyond simulated benchmarks and show that representation choice is critical for deployable fall detection given the scarcity of real-world data.

AI 总结：研究推出首个仓库级验证软件综合基准Vero，含43个多模块实例，评估发现前沿智能体仅解决27个实例，为相关研究提供测试平台。

链接：https://arxiv.org/abs/2608.13522

机构：University of Chicago（芝加哥大学）； California Institute of Technology（加州理工学院）； Stanford University（斯坦福大学）； UC Berkeley（加州大学伯克利分校）； Amazon Web Services（亚马逊云计算服务）； Apodex

作者：Zhe Ye, Hantao Lou, Yuechun Sun, Peiyang Song, Zhengxu Yan, Timothe Kasriel, Qingyang Zhang, Kaiyu Yang, Soonho Kong, Jingxuan He, Dawn Song

英文摘要： AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in which an agent produces both an implementation and a machine-checked proof of its specification, offers a stronger path toward trustworthy AI-generated software. Existing benchmarks in this direction either focus on individual functions or only evaluate proof generation with provided implementations. It is still an open question whether agents can make coherent implementation and proof choices across real multi-module codebases. To bridge this gap, we introduce Vero, the first benchmark to evaluate joint implementation and proof synthesis at the repository level. Vero contains 43 multi-module instances sourced from real-world repositories spanning Python, Dafny, Verus, and Coq, and covering diverse domains from cryptographic protocols to distributed systems. Each instance consists of a multi-module Lean 4 repository with predetermined API interfaces, manually curated formal specifications, and reference implementations, supporting both proof-only and code-and-proof evaluation modes. To improve benchmark reliability, Vero also includes an audit mechanism where agents are allowed to formally prove unsatisfiability of provided specification or incorrectness of reference code, which surfaces and corrects latent code and specification errors during curation. We evaluate frontier coding-agent configurations with Lean toolchain access. The strongest agent fully solves only 27 of 43 instances and closes no specifications on the hardest repositories. Vero provides a concrete testbed for measuring progress toward repository-scale verified software synthesis, where current agents still fall short. We release the benchmark, curation pipeline, and evaluation harness at this https URL.

AI 总结：该研究针对AddGraph框架提出双时空归因机制的事后可解释性框架X-AddGraph，在不损失检测性能的前提下为动态图边级异常检测提供可解释性，其长期归因能力优于空间盲解释器。

链接：https://arxiv.org/abs/2608.12441

机构：National Higher School of Computer Science (ESI)（国家高等计算机科学学院（ESI））； Université Claude Bernard Lyon 1（里昂第一大学（克洛德·贝尔纳里昂第一大学））

作者：Iyad Assaad Nekka, Hamida Seba, Khaled Walid Hidouci, Karima Amrouche

英文摘要：Deep learning detectors for anomalies in dynamic graphs have reached strong accuracy, yet they remain opaque: when an edge is flagged, the analyst receives a score but no reason. This opacity is untenable in the cooperative, regulated information systems where such detectors are deployed, where automated decisions must be auditable and trustworthy. We address this gap for AddGraph, the foundational GCN+GRU framework for edge-level anomaly detection in dynamic graphs, which to our knowledge has never been equipped with any form of explainability. We present a strictly post-hoc explainability framework, X-AddGraph, built on a Dual Spatial-Temporal Attribution (DSTA) mechanism whose three components are each aligned with one of AddGraph's architectural modules: a gradient-based relevance attribution over the current adjacency structure (spatial), a direct reading of the contextual attention weights already computed during inference (short-term temporal, at zero additional cost), and a gradient rollback through the recurrent hidden states (long-term temporal). Because the detector is frozen, detection performance is preserved exactly (Delta AUC = 0, verified empirically to ten decimal places). On the UCI Message benchmark, our trained AddGraph baseline reaches an average per-snapshot AUC of 0.8705, exceeding the originally published result; X-AddGraph reproduces every score identically while adding explanations where none existed. Evaluated across four edge populations - confident true positives, low-confidence true positives, false positives, and random samples - the long-term attribution identifies historical snapshots carrying significantly more counterfactual signal than random selection (0.127 vs. 0.074), a capability that no spatially-blind explainer can provide. We release our implementation for full reproducibility.

AI 总结：针对治疗决策导致部分患者结局不确定的临床预后问题，提出结合确定与不确定病例标签的预测模型及分类型评估框架，揭示两类病例评估的权衡关系。

链接：https://arxiv.org/abs/2608.12477

作者：Xiaobin Shen, Chloe Y.H. Huang, Jonathan Elmer, George H. Chen

英文摘要：Clinical prediction models are often developed as if the outcome of interest were cleanly observed for every patient. This assumption fails when treatment decisions make the clinically relevant outcome permanently unobservable. As a case study of this problem, we consider post-cardiac-arrest neurological prognostication using a cohort of 2,497 patients, including 1,429 patients whose outcomes were rendered indeterminate by treatment decisions. These patients with indeterminate outcomes were reviewed by independent clinical experts, who provided their guesses of counterfactual outcomes about what would have happened to the patients. We refer to these patients as uncertain cases. We also have patients for whom we observe their clinically relevant outcomes; we refer to these patients as certain cases. We propose a framework for evaluating prediction models that explicitly splits the evaluation between certain and uncertain cases. Here, we cannot easily evaluate both types of cases in a uniform manner as the available target labels differ. We then propose a simple prediction model that uses target labels from both certain and uncertain cases in a manner that allows us to trade off between them. Across the proposed neural model and a collection of tabular baselines, models with similar certain-case AUROC can nevertheless differ substantially in both certain-case Brier score and their probability estimates for uncertain cases. Improving alignment with target labels of uncertain cases for our proposed model generally comes at the cost of worse accuracy on certain cases, highlighting an explicit tradeoff that standard evaluation conceals. These results show that when treatment decisions determine whether clinically meaningful outcomes remain observable, conventional evaluation metrics can miss important failure modes in the very patients for whom prognostic support matters most.

AI 总结：本文引入事前可解释AI方法，结合梯度提升法与Partial Dependence、Accumulated Local Effects、SHAP三种事后方法，评估区域供热系统热需求预测ML模型的全局特征重要性，以提升模型可解释性与可信度，解决相关标准、满意度及责任风险问题。

链接：https://arxiv.org/abs/2608.13039

机构：Faculty of Mechanical Engineering（机械工程学院）； University of Niš（尼什大学）

作者：Milan Zdravković

英文摘要： The paper introduces the ante-hoc Explainable AI methodology to assess the global feature importance of the Machine Learning models used for heat demand forecasting in intelligent control of District Heating Systems, with motivation to facilitate their interpretability and trustworthiness, hence addressing the challenges related to adherence to communal standards, customer satisfaction and liability risks. Methodology includes use of four different approaches, namely intrinsic interpretability of Gradient Boosting method and selected post-hoc methods, namely Partial Dependence, Accumulated Local Effects and SHAP. None of the selected methods assume feature permutation or perturbations which can introduce bias due to introduction of random unrealistic values of data instances. Discussion of results is provided, including the assessment of complementarities where applicable, with specific interpretations in context of the district heating processes.

AI 总结：本研究针对心脏病术后结局预测的不规则轨迹问题，提出干预感知临床世界模型，在DECAAF-II数据集上实现心房颤动消融后复发预测及疤痕范围估计的良好性能。

链接：https://arxiv.org/abs/2608.13518

机构：Tulane University（杜兰大学）； Simula Research Laboratory（Simula研究实验室）

作者：Yunsung Chung, Yingshuo Liu, Abboud F. Hassan, Han Feng, Mary M. Maleckar, Nassir Marrouche, Jihun Hamm

英文摘要：Many clinical prediction models treat post-intervention outcomes as a one-step mapping from baseline measurements to a future endpoint. However, recovery after a procedure often unfolds as an irregular trajectory: clinical observations, medication changes, repeat interventions, and physiological measurements are recorded asynchronously and can change risk assessment over time. We propose an intervention-aware clinical world model that represents each patient with a structured latent state and evolves it through time-ordered post-intervention events. The model first encodes baseline imaging into a 3D spatial latent state. It then updates this state using procedural context, static covariates, elapsed time, and peri-event physiological embeddings. Follow-up imaging provides training-only supervision through a latent forecasting objective. We apply the framework to atrial fibrillation ablation. During the 90-day recovery window, irregular post-procedure records provide clinically meaningful evidence for long-term recurrence risk. In repeated internal cross-validation on DECAAF-II, our model achieves AUROC 0.756 and AUPRC 0.777 for recurrence prediction. It also achieves a scar-extent MAE of 2.971 percentage points without requiring follow-up MRI intensities at inference. The learned state supports recurrence-risk queries at different horizons and retrospective input editing of blanking-period records.

AI 总结：本研究提出防御提升器算法，可同时满足在线梯度提升与在线弱到强提升的两种保证，效率高且在合成和真实数据流上预测性能强劲、运行速度快。

链接：https://arxiv.org/abs/2608.13554

作者：Georgy Noarov, Aaron Roth

英文摘要：We study online probabilistic forecasting of binary outcomes chosen by an adaptive adversary. Given an online learning algorithm for a weak hypothesis class $H$, we would like to efficiently obtain two incomparable guarantees that existing online boosting techniques provide separately. Online gradient boosting competes in Brier score with the best predictor induced by the span of $H$ on every sequence, but promises nothing when the span does not contain an accurate predictor. Online weak-to-strong boosting drives classification error to zero under a weak-learning condition, but promises little when that condition fails. We give a simple defensive forecasting algorithm, the Defensive Booster, that obtains both guarantees. On every adaptive sequence, its Brier score is competitive with the best prediction induced by the span of $H$ at the same rate as online gradient boosting; simultaneously, whenever the realized transcript satisfies the smooth weak-learning condition, its Brier score and randomized classification error satisfy the same rate guarantee as online classification boosting. This is achieved by operationalizing the "dual view" of boosting: When the algorithm's randomized classification error is persistently high, its mistake weights form a smooth reweighting on which every weak hypothesis has low edge, yielding an ex-post hard-core certificate that the weak-learning condition fails. We also develop a strongly adaptive variant, which satisfies both guarantees on every time interval. The Defensive Booster is very efficient: it accesses just one weak-class learner, whereas the prior online boosting methods we compare against maintain large weak-learner ensembles. Experiments on synthetic and real data streams demonstrate its strong predictive performance (sometimes substantially improving over all prior baselines) coupled with orders-of-magnitude faster runtime.

AI 总结：该研究利用免费卫星数据，构建模型预测喜马拉雅地区冰川湖溃决、滑坡等三类灾害的易感性地点与触发时间，发现简单梯度提升基线模型表现优于多数深度学习模型，还给出了尼泊尔灾害预警优先级清单。

链接：https://arxiv.org/abs/2608.12422

机构：Cornell University（康奈尔大学）； Institute of Engineering, Tribhuvan University（特里布万大学工程学院）； University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）； University of Bristol（布里斯托大学）

作者：Matthew Kahn, Milan Arjel, Nirmala Adhikari, Mingmar Sherpa, James Pope

英文摘要： Two free satellite signals carry real information about glacial-lake outburst risk in the Nepal Himalaya: radar interferometry sees a moraine dam slowly sagging, and satellite weather marks the weeks when a primed lake is under stress. A companion feasibility study found that deformation indicates which lake is destabilizing and weather indicates when it is at risk, but proposed no predictive model. To address this gap, we propose and evaluate models that predict which site is susceptible and when a trigger arrives. We test three related hazards on free data alone: large moraine- and ice-dammed bursts, rainfall-triggered landslides, and smaller floods from ponds on and around a glacier. Each hazard gets two questions, never blended. Using 589 dated outbursts from HMAGLOFDB and several thousand catalogued landslides, we match each event against similar but unfailed sites, and hold every model to a strong simple baseline under spatial cross-validation that withholds whole map tiles, so no model succeeds by recognising a trained-on neighbourhood. Antecedent weather times the trigger at ROC 0.73 for big bursts, 0.83 for landslides, and 0.82 for small floods. Terrain ranks susceptibility only in part: scored naively it appears near 0.9, largely because catalogued failures cluster in wetter ranges; matched against comparable nearby sites the honest figures are 0.76, 0.71, and 0.54 (no better than chance). The burst signal holds within single regions, reaching 0.89 in Nepal alone. Five deep-learning models do not decisively beat a simple gradient-boosted baseline. Three score marginally higher on landslides, a hint too small to confirm. For the lake hazards the baseline wins outright, reproduced by a three-rule decision tree on ruggedness and monsoon rainfall. We close with a ranked Nepal watchlist, a prioritisation aid, not a prediction, and note where free data reaches its limits.

AI 总结：该研究将生成建模表述为路径积分，提出MSRJD形式的图示微扰理论，为确定性采样器提供无随机采样成本的单圈修正，还推导了响应加权得分匹配目标与EFT幂次计数下的对称等变漂移设计。

链接：https://arxiv.org/abs/2608.12438

机构：Università degli Studi di Milano（米兰大学）； INFN（意大利国家核物理研究院）

作者：Ramon Winterhalder

英文摘要：We formulate generative modeling as a path integral in which flow-based, diffusion-based, variational, and adversarial models arise as different evaluation principles for a single master action. Its Martin-Siggia-Rose-Janssen-de~Dominicis (MSRJD) form separates free from interacting probability flows and opens them to diagrammatic perturbation theory. The expansion yields a one-loop correction to deterministic samplers at no stochastic-sampling cost, which we validate on solvable and nonlinear drifts, where it reduces a 53 % tree-level error to 1.6 %. Imperfect learned scores enter as insertions and yield a response-weighted score-matching objective, and symmetry-equivariant drift design becomes an operator expansion with EFT power counting.

AI 总结：该研究针对多飞行条件下阵风诱导载荷的分类问题，提出基于机器学习表示与范例选择的方法，在3480次飞翼模型压力载荷测量数据中发现9种跨姿态响应类型，可辅助理解流体力学机制。

链接：https://arxiv.org/abs/2608.12448

机构：Institute of Fluid Mechanics, TU Braunschweig（布伦瑞克工业大学流体力学研究所）

作者：Paolo Olivucci, Kowshik Srivatsan, David E. Rival

英文摘要：Is it possible to find an objective classification criterion that organizes the complexity of gust-induced loads across many flight conditions? And one that remains as interpretable as a labelling based on coarse parameters, such as the flight attitude? Our approach encodes a large number of experimental observations through a machine-learned representation and applies a summarization procedure to select a minimal subset of highly significant exemplars. The exemplars provide a similarity-based objective classification criterion of all the observations, they can be more conveniently inspected by experts and can become subject of more refined experiments. We demonstrate the approach on a database of 3480 pressure-load measurements induced by random gusts on a flying-wing model across six flight attitudes. We find nine fundamental response types that recur across multiple attitudes; analysis of a type's transient response enables physical intuition into the underlying fluid mechanics.

AI 总结：本文提出概率单趟过滤算法Prof-K，它是与分布无关的高效Top-k选择算法，可提供概率正确性保证，在大规模场景下比PyTorch topk等方法快1.5-10倍，还能实现精度-速度权衡，可用于优化稀疏自编码器训练。

链接：https://arxiv.org/abs/2608.12573

机构：Jagiellonian University（雅盖隆大学）

作者：Tadeusz Dziarmaga, Witold Sikora, Łukasz Struski, Jacek Tabor, Marcin Mazur

英文摘要：Top-k selection is a fundamental computational primitive with applications spanning databases, information retrieval, signal processing, and modern machine learning workloads, including sparse activations and attention pruning. As data sizes grow, existing approaches become inefficient: exact methods incur high memory and compute overhead, while approximate methods often rely on brittle heuristics that degrade under adversarial or heavy-tailed inputs. In this paper, we introduce Prof-K, a fast, scalable, and distribution-agnostic top-k algorithm with probabilistic correctness guarantees. Prof-K performs a single-pass filtering procedure: a small random sample estimates an adaptive threshold, the N input elements are streamed once into a compact buffer, and an exact top-k routine on this buffer recovers the true top-k elements with probability at least 1 - $\epsilon$, where $\epsilon$ > 0 is user specified. We derive high-probability guarantees for correctness and buffer size, together with an approximately optimal sample size that minimizes overhead as a function of N and k. Empirically, Prof-K achieves 1.5x-10x speedups over the highly optimized PyTorch topk and recent RadiK implementations, with the largest gains in the large-scale, small-to-moderate-k regime where prior methods struggle most. Unlike previous approaches, these guarantees hold independently of the input distribution, ensuring robustness to adversarial settings. By relaxing the recall target (e.g., recovering 95% of the true top-k values), Prof-K additionally provides a principled accuracy-speed trade-off. We further demonstrate its impact on training BatchTopK Sparse Autoencoders (SAEs), where top-k selection constitutes a significant portion of the training cost.

AI 总结： 该研究针对随机低维重参数化训练神经网络的潜在空间规模问题，提出取向分辨二次主公式，引入RaMaN模型，实现内存优化，实验验证其预测与转换跟踪性能优于取向无关近似。

链接：https://arxiv.org/abs/2608.12597

机构：Tsinghua University（清华大学）； The University of Manchester（曼彻斯特大学）； University of Kentucky（肯塔基大学）； Miami University（迈阿密大学）； University of Dayton（代顿大学）； Institute for Biomedical Informatics, University of Kentucky（肯塔基大学生物医学信息学研究所）

作者：Andrew Cheng, Ali Eslamian, Jie Cheng, Mehdi Zargham, Qiang Cheng

英文摘要：Neural networks can often be trained or fine-tuned through random low-dimensional reparameterization, where a small latent vector is mapped into a full parameter update by a frozen random map. This raises a practical question: how large must the latent search space be to reach a low-loss region? We first express the known accessibility transition in an equivalent conic form, centered for compact convex targets at the statistical dimension of the polar cone. Our main theoretical contribution is an orientation-resolved quadratic master formula that predicts the random-slice residual from both the curvature spectrum and the reference-to-solution displacement profile. It yields a self-consistent isotropic-orientation predictor and, in a conservative radius-only specialization, recovers the earlier Gaussian-width quadratic bound. Building on this analysis, we introduce Random Mapping Networks (RaMaN), which instantiate the predicted latent dimension using structured Hadamard or seed-regenerated Gaussian maps. These constructions avoid the O(dP) storage of dense random maps and reduce optimizer-state memory from O(P) to O(d). We also develop matrix-free curvature approximations and sweep-free dimension selection. Across controlled quadratic and neural-curvature experiments, the orientation-resolved predictor closely tracks measured transition locations and outperforms orientation-agnostic approximations when displacement direction matters. End-to-end experiments further show sharp, protocol-dependent training transitions across image and language models.

AI 总结：本文提出“挑战下的训练”可执行证书框架，定义资源索引的挑战能力模，通过实验验证其在ResNet-18蒸馏问题中可有效区分解码器欠使用与表征不足，实现对神经网络训练状态的诊断与重新认证。

链接：https://arxiv.org/abs/2608.12655

机构：University of Illinois Chicago（伊利诺伊大学芝加哥分校）

作者：Farhang Yeganegi, Arian Eamaz, Mojtaba Soltanalian

英文摘要：A flat training curve does not reveal whether a neural network has reached a global optimum, is locally trapped, is representation-limited, or is mismatched to its trainer. We introduce Training Under Challenge, an executable-certificate framework in which predeclared, architecture-valid procedures construct complete alternatives in the same certified class and reevaluate the same objective. Any lower-valued candidate is a replayable witness that lower-bounds the checkpoint's empirical global-optimality gap. Passing a finite suite is only suite-relative; global-gap conclusions require a separately justified coverage mechanism. We define a resource-indexed challenge-power modulus that characterizes the largest gap compatible with passage. For squared loss, current block-decrease operators make coverage checkable and yield uniform and realized-residual bounds. We prove the converse frontier: without coverage, a first-order ReLU trainer can reach infinitely many exact conditional head optima while converging to a non-global point. On a channel-gated ResNet-18 distillation problem with known optimum, eight internal challenges cover all 240 audited output directions, and realized-residual bounds lie within factors of 1.74--3.02 of the true gap. Paired predictive certificates separate decoder under-use from representation insufficiency, while quantized-denoising studies demonstrate diagnosis, repair, and current-state recertification.

AI 总结：本文提出基于受限Logit建模的方法，可在百万级商品规模下准确估计需求转移系数，结合独立需求预测与同类商品可得性调整，提升大规模品类组合优化的需求预测效果。

链接：https://arxiv.org/abs/2608.12680

机构：Walmart Global Tech（沃尔玛全球科技）

作者：Lakshya Garg, Deep Narayan Mishra, Swapnil Yadav, Haoan Wang, Sujal Alugubelli, Karthik Kumaran, Anupriya Sharma

英文摘要：Item demand forecasting is an integral component of store assortment optimization. Existing literature focuses on learning a suitable customer choice model and using this model to determine the value of an objective function (i.e. expected demand) with respect to an assortment proposal. However, for large item universe with many categories, this approach can prove inefficient, needing a separate demand forecast for every possible item assortment. An alternate approach exists whereby we combine the efficiency of forecasting item demand independently, while at the same time applying adjustments to the independent forecasts that account for the relations between item demand and the availability of other similar items on the shelf. Central to this approach is the estimation of Demand Transfer (DT) coefficients. These DT coefficients represent the percent of a particular target item's (item that the customer walked in the store to buy) demand that is redirected to each other item in the universe should the target item be removed from the shelf. We introduce an approach that allows us to compute these DT coefficients on large item universes (assortments having 1 million+ items). Experiments on data as well as historical transaction data for multiple locations within categories demonstrate that when certain reasonable assumptions about substitution behavior are satisfied, our procedure is able to accurately estimate underlying DT coefficients and lead to improvements in demand forecasting.

AI 总结：本文提出契约级GPU内核验证器，发现公开系统接受的2638个机器生成内核中39.5%存在无法修复的错误，还构建了GDN族的原生Blackwell反向传播算法，指出现有内核生成正确性信号被高估。

链接：https://arxiv.org/abs/2608.12700

机构：E3A Healthcare（E3A医疗公司）

作者：Rishi Shah, Rishav Shrestha

英文摘要：Systems that generate GPU kernels with language models report high correctness rates. Those rates come from a single loose test: run the kernel on a few random inputs at one fixed shape and accept it if the output is close to a reference. A kernel can pass that test and still be silently wrong. It can return an ordinary number where the true answer is a NaN or an infinity, differ from run to run, break when the shape changes, or accumulate in fp16 where the reference keeps an fp32 total. We build the instrument that checks correctness properly: a contract-grade verifier of twelve adversarial gates, each a property a correct kernel must satisfy, several of them tolerance-free, so no choice of threshold can explain a failure away. Aimed outward, the verifier audits 2,638 machine-generated kernels that a public system's own harness had already accepted as correct. It finds 39.5% broken beyond any tolerance argument and 62.1% carrying at least one violation. The field's standard test accepts 1,487 kernels the verifier rejects, against only 14 the other way. We defend the finding four independent ways: a 7/7 positive control, a threshold-calibration sweep, 98.5% agreement with the reference benchmark's own correctness code, and a stratified hand-audit. Aimed inward, the verifier judges a kernel of our own: the first native Blackwell tcgen05 training backward for the gated-linear-recurrence (GDN) family, including the reverse-state stage the field still runs on a fallback. We establish its correctness independently, against a double-precision oracle, and train five family members through it. The correctness signal behind reported progress in kernel generation is far weaker than the numbers suggest, and a set of tolerance-free contracts would close most of the gap.

AI 总结：本研究开发PRISM方法，将神经成像减法分析适配至Transformer语言模型，对比模型与213名卒中后失语症患者的命名错误模式，验证了音素偏向性分离等结果，为模型功能专业化提供可证伪的空间分辨率测试工具。

链接：https://arxiv.org/abs/2608.12717

机构：University of South Carolina（南卡罗来纳大学）； ALLT.AI, LLC（ALLT.AI有限责任公司）； USC School of Medicine（南卡罗来纳大学医学院）

作者：Xiang Guan, Roger D. Newman-Norlund, Yong Yang, Saeed Ahmadi, Regan Willis, Nadra Salman, Kalil Warren, Srihari Nelakuditi, Chris Rorden, Leonardo Bonilha, Julius Fridriksson

英文摘要：Mechanistic interpretability of large language models lacks spatially resolved, falsifiable tools for testing whether internal components are specialized for distinct cognitive operations. We adapt subtraction analysis, the standard framework of human neuroimaging, from biological brains to perturbed transformers, and apply the same logic to both substrates in parallel. Building on the Brain-LLM Unified Model (BLUM), which showed that layer-perturbed LLaVA-1.6-Vicuna-13B error profiles match the lesion patterns of aphasic patients, we develop PRISM (Perturbation-based Regional Interpretability through Subtraction Mapping). PRISM maps the seven clinical Philadelphia Naming Test categories, subtracts error classes pairwise, and treats each perturbation seed as a subject in a group analysis with threshold-free cluster enhancement along the layer axis. We run a structurally matched analysis on 213 chronic post-stroke aphasia patients using correlation-difference lesion-symptom mapping, and replicate both sides on held-out splits. The designs match in subject dimension (seeds, patients), spatial dimension (layers, atlas-parcellated cortex) and thresholding, but the contrast operator differs: a within-subject error-proportion difference for the LLM, a between-subject correlation difference for the cortex. Both substrates recover a robust phonemic-favoring dissociation, a deep layer cluster and a frontal-perisylvian cortical cluster, both replicating; the semantic-favoring direction is a consistently signed but non-significant trend on both. PRISM thus gives a falsifiable, spatially resolved test of functional-specialization claims in transformer language models. A confirmatory ROI-level intervention (PRISM Stage 3) licensing the strongest causal-mechanism claim is left to subsequent work.

AI 总结：本研究提出MAG框架，通过将未标记多模态数据用于半监督传播的演示选择，提升多模态大语言模型的上下文学习性能，在8个基准的标签稀缺场景下优于强基线。

链接：https://arxiv.org/abs/2608.12724

作者：Zirui Cheng, Xun Xu, Tiankai Chen, Fady Rezk, Bowen Zheng, Xiaodong Shi, Shijie Li, Kangkang Lu, Bharadwaj Veeravalli, Nancy F. Chen

英文摘要：Few-shot in-context learning (ICL) with multi-modal large language models (MLLMs) enables task adaptation without parameter updates, but its performance is highly sensitive to the quality and coverage of the selected demonstrations. While unlabeled multi-modal data is abundant, it remains elusive how to exploit them for ICL. We propose MAG (MAnifold-Guided semi-supervised in-context demonstra- tion selection), an efficient framework that leverages unlabeled data to improve multi-modal ICL. MAG formulates demonstration selection as a semi-supervised propagation problem on a multi-modal graph and adopts a two-stage strategy: (i) relevance score propagation identifies a compact set of high-impact unlabeled samples for pseudo-labeling, reducing MLLM inference cost; (ii) multi-modal relevance is used to select the final demonstrations. We show that textual represen- tations are more effective for relevance propagation, while both visual and textual modalities are crucial for high-quality demonstration selection. Experiments on eight multi-modal benchmarks demonstrate that MAG consistently outperforms strong baselines in label-scarce regimes, achieving significant gains with a limited pseudo-labeling budget.

AI 总结：该研究针对资源受限农村地区的多模态临床筛查问题，提出云边协同架构，经实验验证其诊断性能优异且成本更低，可适配部署约束。

链接：https://arxiv.org/abs/2608.12745

机构：University of Michigan（密歇根大学）； Massachusetts Institute of Technology（麻省理工学院）； Harvard Medical School（哈佛医学院）

作者：Hei Ting (Una) Chan, Chenwei Wu, Xueshen Liu, Zesen Zhao, Boyuan Zheng, Luis Filipe Nakayama, Michael G. Morley, Liyue Shen, Jiasi Chen, Z. Morley Mao

英文摘要：Medical AI has demonstrated specialist-level diagnostic accuracy, yet these capabilities remain largely inaccessible in resource-constrained rural settings where bandwidth is scarce, compute is limited, and clinical decision-making requires integrating heterogeneous modalities. We introduce a cloud--edge collaborative architecture that addresses these constraints: lightweight, domain-specific models on the edge transform raw medical data into compact structured outputs, while a cloud LLM synthesizes these outputs into clinical summaries. An LLM-based orchestrator dynamically selects diagnostic tools based on patient context, promoting comprehensive modality coverage without processing irrelevant inputs. We evaluate on 20 multimodal clinical cases spanning cardiac, obstetric, trauma, and screening scenarios under three simulated network profiles (500,kbps--5,Mbps). The hybrid system achieves 98--99% diagnostic tool recall with 92--96% precision, matches or exceeds cloud-only baselines on clinical accuracy, and maintains bandwidth-invariant latency (25--35,s) at 4--15x lower token cost. These results highlight the role of architectural design in enabling efficient multimodal integration and improving factual grounding compared to cloud-only approaches under deployment constraints.

AI 总结：HiRoute是一种输入自适应分层提示调优框架，通过分层路由器与多粒度提示专家，提升大语言模型安全对齐效果，在多个安全基准上兼顾安全性与响应有用性，减少过度拒绝。

链接：https://arxiv.org/abs/2608.12821

作者：Fangzhou Chen, Shiji Zhao, Mengyang Wang, Qihui Zhu, Ranjie Duan, Maoxun Yuan, Xingxing Wei

英文摘要：Large language models (LLMs) remain vulnerable to harmful requests and jailbreak attacks. Parameter-efficient safety alignment methods based on prompt tuning typically rely on a single global prompt or externally selected prompt modules. Such static designs struggle to maintain a cross-category safety boundary while generating constructive responses tailored to specific risks and avoiding over-refusal of benign inputs. To address these limitations, we propose HiRoute, an input-adaptive hierarchical prompt-tuning framework that separates category-agnostic safety control from category-specific response guidance. HiRoute first trains a lightweight hierarchical router on representations extracted from a frozen LLM to jointly detect harmful intent and predict multi-label risk scores. It then freezes both the backbone model and the router and uses preference optimization with alternating gradient updates to learn a shared coarse-grained prompt and a set of fine-grained prompt experts as continuous embeddings. At inference time, benign inputs bypass the safety branch, whereas risky inputs are processed using the shared prompt together with a router-weighted mixture of risk-specific prompt experts. Experiments across three instruction-tuned models show that HiRoute achieves high safety rates across multiple safety benchmarks while preserving safe-response helpfulness, reducing over-refusal, and maintaining competitive performance on general-purpose tasks.

AI 总结：该研究针对概率电路曲率的组合特性，提出自适应锐度感知正则化，解决全局正则化的深度偏向与欠拟合问题，提升模型泛化能力。

链接：https://arxiv.org/abs/2608.12869

机构：AT&T（美国电话电报公司）

作者：Hrithik Suresh, Sahil Sidheekh, Shelar Parth Vijay, Yasir Z, Sriraam Natarajan, Narayanan Chatapuram Krishnan

英文摘要：Probabilistic Circuits (PCs) are generative models that support exact inference and, unlike deep neural networks, admit an exact and tractable measure of loss-surface curvature: the trace of the Hessian of the log-likelihood. Recent work regularizes this trace globally to bias learning toward flatter, better generalizing optima. We show that treating sharpness as a global regularizer can be misspecified for PCs, whose curvature is inherently compositional. We prove that each sum node's contribution to the Hessian trace factorizes exactly into its circuit flow, which measures how heavily the node is used, and a local sharpness term determined by its output distribution. This decomposition provides insights into why global sharpness regularization is depth biased and can lead to underfitting. Building on it, we introduce an adaptive sharpness aware regularizer that penalizes nodes based on intrinsic local curvature and preserves closed form EM updates. We also show that empirically, this targeted regularization recovers the generalization that global regularization sacrifices while retaining the robustness and benefits of sharpness aware learning.

AI 总结：Weak-Pareto方法结合弱形式与帕累托子集选择，可从含噪数据中鲁棒发现分数阶微分方程，在多基准测试中表现优于无正则化方法及同期神经基线。

链接：https://arxiv.org/abs/2608.12879

机构：Center for Advanced Intelligence Project (AIP), RIKEN（理化学研究所先进智能项目中心（AIP））； Graduate School of Information Science and Technology, The University of Osaka（大阪大学信息科学与技术研究生院）

作者：Pongpisit Thanasutives, Yoshinobu Kawahara

英文摘要： Fractional partial differential equations describe nonlocal dynamics, but discovering them from noisy data is difficult because fractional differentiation amplifies high-frequency measurement noise and the derivative orders are unknown. We propose Weak-Pareto, which combines an adjoint-consistent weak formulation of fractional terms with Pareto-based subset selection over discrete term types and continuous fractional orders. For linear right-hand-side terms, the adjoint transfers fractional operators from measured fields to smooth test functions, replacing noise-sensitive pointwise differentiation with smoothing integration; for nonlinear terms, the noise-suppression effect is partial yet useful. Coefficients are fitted by ridge regression within a branch-aware differential-evolution search over the orders. The support size is then selected at the validation-error-complexity elbow. We show that the variance of fixed linear right-hand-side weak features vanishes under grid refinement, whereas noise amplification in pointwise fractional features increases with derivative order. Across fractional advection-diffusion, reaction-diffusion, and Burgers benchmarks, Weak-Pareto recovers parsimonious structures from clean and noisy measurements. In controlled advection-diffusion and Burgers comparisons, it retains the correct support at every tested multiplicative-noise level, whereas the unregularised strong-form counterpart largely fails once noise is introduced; this advantage persists under additive Gaussian noise. Ablations show that the weak library drives noise robustness and that continuous-order Pareto search avoids the support-selection failure of a dense fixed dictionary. On the advection-diffusion benchmark, Weak-Pareto yields more consistent operator recovery and substantially lower measured runtime than a contemporary neural baseline.

AI 总结：本文提出基于粒球计算的自适应KNN方法，通过训练阶段构建多粒度粒球、预测阶段动态确定有效k值，在多数据集上的准确率和效率均优于现有KNN变体。

链接：https://arxiv.org/abs/2608.12903

机构：Chongqing University of Posts and Telecommunications（重庆邮电大学）； Chongqing Normal University（重庆师范大学）

作者：Xiaoyu Lian, Shuyin Xia, Hongxuan He, Lifeng Shen, Guoyin Wang, Xinbo Gao

英文摘要：The $k$-Nearest Neighbor~(KNN) algorithm is widely used across various tasks. The selection of the $k$ value is a key issue because it significantly impacts performance. In this paper, an adaptive and efficient KNN approach via granular-ball computing is proposed. The method consists of two stages. \textcolor{black}{In the training stage, the dataset is first coarsely partitioned to reduce the complexity of data distributions within a granular ball, and then the Fisher criterion is introduced to control ball splitting and stopping, yielding a multi-granularity granular ball representation. In the prediction stage, the nearest granular ball is first located through a weighted distance mechanism, and an adaptive neighborhood is then constructed around the test sample. The effective $k$ value is dynamically determined by the actual number of samples contained in this neighborhood. The neighborhood induced by the nearest granular ball provides more stable local group information, thereby improving robustness against noise and local perturbations.} Experimental results demonstrate that the proposed method outperforms existing KNN variants across multiple datasets in terms of both accuracy and efficiency. The code has been open-sourced for reproducibility: this https URL.

AI 总结：本文将足球的xT与VAEP框架适配至手球，开发H-xT与H-VAEP模型，利用手球德甲数据验证其有效性并发布代码，实现了手球球员的合理评估。

链接：https://arxiv.org/abs/2608.12926

机构：Paderborn University（帕德博恩大学）； SG Flensburg-Handewitt（弗伦斯堡-汉德维特体育俱乐部）

作者：Julius Broermann, Oliver Müller, Michael Döring, Jochen Baumeister

英文摘要：Traditional player evaluation in professional handball relies on basic box-score metrics or heuristic indices, which fail to credit the multi-player build-up chain. While football (soccer) analytics has adopted Expected Threat (xT) and Valuing Actions by Estimating Probabilities (VAEP), these event-based action valuation frameworks have not yet been adapted to handball. In this paper, we present the first comprehensive adaptation and evaluation of xT and VAEP for handball, utilizing five seasons of tracking-derived event data from the Handball Bundesliga. We develop Handball-xT (H-xT) using a handball-native court zoning layout, demonstrating via simulations that it is systematically more robust than standard rectangular grids. We optimize Handball-VAEP (H-VAEP) by tailoring its feature space and selecting the context length to limit team-identity leakage. Our evaluation shows that H-VAEP yields exceptionally stable, discriminative, and intuitive player ratings that highlight build-up play. Finally, we release our complete code repository to help professional clubs deploy these models.

AI 总结：本研究针对JEPAs世界模型易受视觉扰动影响的问题，提出动作条件预测一致性（ACPC）诊断方法，定义IR与SR指标，经四视觉控制任务实验验证其可预测扰动带来的预测及代价变化。

链接：https://arxiv.org/abs/2608.12939

机构：Huawei（华为）； University of Science and Technology of China（中国科学技术大学）； Zhejiang University（浙江大学）； Tsinghua University（清华大学）； Harbin Institute of Technology（哈尔滨工业大学）； Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东省人工智能与数字经济实验室（深圳））

作者：Guo An, Zijing Wu, Honghua Dong, Yuhao Yan, Zixuan Gui, Haochong Chen, Shanzhao Ruan, Xiang Wang, Yurong Ling, Qi Tian

英文摘要： Joint-embedding predictive architectures (JEPAs) learn world models that predict in a compact latent space rather than in pixels, reducing the pressure to model nuisance appearance. Yet this provides no guarantee against visual perturbations: they can still alter the encoded representation and affect subsequent action-conditioned predictions. Bisimulation captures this requirement precisely: two observations should be treated as the same state only when their action-conditioned consequences agree. Guided by this criterion, we introduce Action-Conditioned Predictive Consistency (ACPC), a diagnostic that measures how far a clean history and a visually perturbed view of it diverge after being rolled forward under the same action sequence. We prove that this divergence bounds the perturbation-induced change in multi-step prediction error and planner cost. Building on pairwise ACPC, we define two complementary measures: the Invariance Radius (IR) summarizes clean-perturbed rollout spread, while the Separation Rate (SR) checks whether different states remain distinguishable after rollout. Experiments on four visual control tasks show that pairwise ACPC predicts perturbation-induced prediction and cost changes. On LeWM, the IR-SR screen transfers across tasks, and the joint diagnostic remains informative under blur and resize. PLDM exhibits similar diagnostic trends under a different architecture.

AI 总结：CardioState-JEPA是一种延迟感知跨模态心脏基础模型，通过对齐ECG、PPG、PCG的共享生理表征，在25项下游任务上显著提升了各模态的分类性能，实现了异质心脏信号的相互监督。

链接：https://arxiv.org/abs/2608.12944

机构：Singapore Management University（新加坡管理大学）； Eindhoven University of Technology（埃因霍温理工大学）

作者：Hamza Shafiq, Hung Manh Pham, Bin Zhu, Pan Zhou, Jun Hu, Aaqib Saeed

英文摘要：Electrocardiography (ECG), photoplethysmography (PPG), and phonocardiography (PCG) provide complementary views of the same cardiac cycle, yet existing cardiac foundation models are trained for a single sensing modality, leaving the shared physiology across sensors unexploited. We introduce CardioState-JEPA, a cardiac foundation model to learn a single shared representation jointly across ECG, PPG, and PCG, built on a physiology-aware joint-embedding predictive architecture. The model maps heterogeneous waveforms into a common token space, processes them with a single shared Transformer encoder, and learns by predicting masked latent cardiac states, placing the pretraining target on shared physiology rather than sensor-specific waveform appearance. To handle the temporal offsets between electrical, mechanical, and hemodynamic events, cross-modal prediction uses a learned delay aligner that matches signals at the corresponding cardiac time. Because synchronized multi-sensor recordings are scarce, CardioState-JEPA first learns within-modality structure from abundant unimodal data and then uses paired data to align modalities in latent cardiac time. Evaluated as a frozen encoder across 25 downstream tasks spanning ECG, PPG, and PCG, our encoder improves average PPG classification by 8.2 AUROC points, PCG murmur detection by 18.8 AUROC points, and ECG classification by 15.5 AUROC points over the best self-supervised signal baseline and matches or exceeds cardiac models trained with privileged clinical text or supervised labels on several ECG benchmarks. These results establish that heterogeneous cardiac signals can mutually supervise a single foundation model of cardiac physiology.

AI 总结：针对GRPO在全错推理组无有效相对信号的问题，提出I-SDPO，按实例路由选择特权自蒸馏或GRPO，在SciKnowEval上实现全领域最优，平均mean@16准确率提升至70.31%。

链接：https://arxiv.org/abs/2608.12957

机构：Qwen Large Model Application Team, Alibaba（阿里通义千问大模型应用团队）

作者：Yubo Zhang, Xinhong Ma, Zezhong Tan, Ziqiang Dong

英文摘要：Group Relative Policy Optimization (GRPO) learns from reward differences within a rollout group, but receives no useful relative signal when every sampled response is incorrect. Privileged self-distillation can fill this gap with dense token supervision, yet applying it throughout training creates a different failure mode: the teacher is a biased, low-variance surrogate for the reward objective, so persistent imitation can oppose reward-improving updates after the policy becomes capable of producing successful trajectories. We introduce I-SDPO (Instance-Level Adaptive Self-Distillation Policy Optimization), which treats teacher reliance as capability-dependent. I-SDPO makes one routing decision per input instance and shares it across that instance's rollout group: all-incorrect groups use a privileged self-distillation objective, whereas any-success groups remain intact for GRPO. This design uses imitation only where group-relative rewards are uninformative. A local analysis characterizes when teacher and reward directions align and shows that a non-vanishing biased distillation weight induces an optimization bias floor. The routing rule automatically reduces the expected distillation rate as success probability rises, withdrawing teacher influence without a hand-designed schedule. On SciKnowEval, I-SDPO obtains the best result in all four scientific domains and improves average mean@16 accuracy from 56.67% with GRPO to 70.31%, with a maximum domain gain of 18.24 points.

AI 总结：该研究发现潜在世界模型的规划瓶颈在于规划器目标而非预测器，通过替换目标无需额外训练即可大幅提升长视野规划性能，揭示模型编码了规划器未利用的可达性信息。

链接：https://arxiv.org/abs/2608.12959

作者：Joyjeet Singh

英文摘要：Latent world models are judged by how well they predict, so when planning fails at long horizons the natural reading is that the predictor degrades. On a reproduction of LeWorldModel on TwoRoom we show the binding constraint is the planner's objective instead. The predictor is not the limit: its imagined state seventy-five environment steps ahead is still only 0.189 as wrong as assuming the world froze, while the planner never imagines beyond twenty-five. The objective is. Cross-entropy-method planning minimises squared latent distance, which tracks true distance at r = 0.426, saturates by about eighty arena units and decreases beyond a hundred and twenty, so moving away from the goal can lower the cost. The information is present throughout: a ridge probe recovers position from the frozen embedding at R^2 0.9922. The pathology is the method's, not one reimplementation's. It is present in the authors' released weights, and across four checkpoints long-horizon success rank-orders exactly with metric quality and inversely with prediction accuracy. Replacing only the objective, with nothing retrained and no GPU, lifts goals reached at offset 100 from 26.0% to 98.0%, equals the 98.0% at offset 25, and reaches 92.0% under a third of the budget: planning stops depending on the horizon. The best cost is not the most accurate. A head learned from frame separation alone predicts spatial distance worse than a position probe (r = 0.819 against 0.9897) yet plans better, charging 24% more to cross the environment's dividing wall where squared latent distance charges 4% less. It has learned reachability, not proximity.

AI 总结：本研究提出一种不依赖数据集的神经网络框架，利用互相干数学性质定义损失函数，构建低互相干二元感知矩阵，降低计算成本并提升通用性与鲁棒性。

链接：https://arxiv.org/abs/2608.12982

机构：Shiv Nadar Institution of Eminence（希夫·纳达尔卓越学院）； Indian Statistical Institute（印度统计研究院）

作者：Rekha, Santosh Singh, S. K. Neogy

英文摘要：In this research work, we are constructing the sensing matrix, which is essential for the success of the compressive sensing technique. We have chosen a learning-based technique for the construction of the sensing matrix. The novelty and uniqueness of the proposed technique is that it does not use any data set and also does not use a specific application. It uses the mathematical property/constraint for the construction of the sensing matrix for the perfect recovery of the signal. The perfect recovery of signals is an old and still very challenging problem in real-world applications. In late 2000, compressive sensing became a popular mathematical tool for the perfect recovery of sparse signals. The core of the compressive technique is the construction of the sensing matrix, which satisfies certain special properties such as restricted isometry property (RIP), null space property (NSP), and spark property (SP). All these properties are NP-hard problems and hence computationally challenging to solve. For all practical purposes, the construction of the sensing matrix needs to achieve low mutual coherence to achieve the perfect recovery of the signals. We have used a neural network for the construction of the sensing matrix, and this framework constructs a binary sensing matrix with low mutual coherence. The entries in the matrix are generated through a shared underlying rule. The proposed architecture is simple and does not use large-scale training data sets. Such uniqueness and novelty bring a drastic reduction in computational cost, and also, for the first time in literature, the use of a mathematical property for defining the loss function. In this proposed research work, the mutual coherence property has been used in the neural network framework. Such a neural network framework brings generality, robustness, and reduces storage requirements.

AI 总结：本文提出BAPS框架，无需修改预训练TabPFN模型，可将百万级表格数据集的上下文压缩约1953倍，用512个原型保留预测性能，实现其在大规模表格数据上的可扩展推理。

链接：https://arxiv.org/abs/2608.12989

机构：Islamic Azad University（伊斯兰阿扎德大学）

作者：Mahboobe Jadid, Melika Rezaye Garkani, Ali Mousavi

英文摘要：Pretrained tabular foundation models have demonstrated strong predictive capability; however, their application to large-scale datasets remains constrained by the limited inference context. This paper introduces Balanced Adaptive Prototype Selection (BAPS), a framework for constructing compact, information-preserving contexts for scalable TabPFN inference. Without modifying or retraining the pretrained model, BAPS jointly preserves representative structure, informative decision boundaries, local density, class balance, and feature-space diversity. Experiments on the million-row HIGGS and SUSY datasets show that 512 prototypes retain strong predictive performance and reliable calibration, corresponding to an approximately 1,953-fold context compression. All experiments were conducted on an Intel Core i7 CPU with 16 GB RAM and no GPU acceleration. These findings establish effective context construction as a practical mechanism for extending pretrained tabular foundation models to million-scale datasets.

AI 总结：本研究提出隐式在线策略自蒸馏（LOPD），将教师的特权上下文改为端到端可学习，在智能体工具使用和代码生成任务上，以远低于对比方法的rollout预算实现了更优性能。

链接：https://arxiv.org/abs/2608.13040

机构：Shanghai Jiao Tong University（上海交通大学）； National University of Singapore（新加坡国立大学）

作者：Guibin Zhang, Jiayang Lyu, Ran Sun, Xinlei Yu, Haoyu Zhao, Qibing Ren, Shuicheng Yan

英文摘要：Enabling agents to learn from experience and internalize it into their policy has become a central problem in self-evolving AI. On-policy self-distillation (OPSD) offers an effective pathway by using a privileged self-teacher to provide dense supervision on the student's own trajectories; however, existing methods still rely heavily on designer-specified privileged artifacts (e.g., answers, feedback, skills, or trajectories), limiting the end-to-end learnability and scalability required for continual self-improvement. In this work, we introduce Latent On-Policy Self-Distillation (LOPD), which, rather than proposing another hand-crafted OPSD variant with a newly prescribed form of privileged context, makes the teacher's privileged context itself learnable end-to-end from experience. Technically, LOPD retrieves relevant experiences and composes them into continuous latent tokens that condition a self-teacher, while the student generates trajectories from the task and interaction history and receives dense token-level supervision at every visited prefix. We further introduce a privileged-margin objective to stabilize and regulate the learning of latent context. Empirically, LOPD demonstrates (I) strong performance, outperforming RLVR and representative OPSD methods including OPSD, SDPO, and Skill-SD across both agentic tool use and code generation; and (II) high learning efficiency, surpassing GRPO and Skill-SD with less than 30% of their rollout budget. Ablation studies further provide direct evidence that making privileged context learnable is necessary for realizing these gains. Together, these results position LOPD as a step toward a more scalable and self-directed paradigm for agent evolution.

AI 总结： 本文提出分支定界（BaB）框架，通过关系神经元拆分及对应选择策略，在817个跨多数据集的验证问题上，使SaBRe在已解决实例数和效率上优于基线方法，提升神经网络关系验证效果。

链接：https://arxiv.org/abs/2608.13118

机构：Graduate School and Faculty of Information Science and Electrical Engineering, Kyushu University（九州大学情报科学与电气工程研究院及学部）； National Institute of Informatics（信息学研究所）； UNSW Sydney（新南威尔士大学悉尼分校）

作者：Kota Fukuda, Zhenya Zhang, Guanqin Zhang, Jianjun Zhao

英文摘要：Verification of neural networks against relational specifications, such as global robustness, is crucial for safety-critical applications of cyber-physical systems (CPS), given their increasing adoption of AI components. Compared to simple trace properties (e.g., local robustness), verifying relational specifications requires reasoning about the relationship between multiple network inferences, which brings significant technical challenges. Existing research has explored abstraction techniques based on sound and convex over-approximation of neural network outputs; however, since these approaches are inherently incomplete and may raise false alarms, they further underscore the need of effective abstraction refinement. In this paper, we propose a branch-and-bound (BaB) framework to mitigate the issue, which iteratively splits the problem until all sub-problems are verified. Specifically, our BaB framework features splitting of relational neurons rather than individual neurons as prior works do, and as the core of our technique, we devise a relational neuron selection strategy based on the dual formulation of the verification problem, which allows us to efficiently select the (most likely) optimal relational neuron that maximizes the refinement brought by problem splitting. We evaluate SaBRe on 817 verification problems across ACAS Xu, MNIST-F, MNIST-C, CIFAR and GTSRB. The results show that SaBRe outperforms different baseline approaches, in terms of the number of solved instances and verification efficiency, which demonstrates the effectiveness of our proposed techniques.

AI 总结：该研究针对拉格朗日神经网络需完整状态输入、参数适应性差的问题，提出HiLNN，通过循环编码器提取历史上下文调制系统参数，经RK4推演优化，在多类系统上实现更优长时程预测精度与能量保持。

链接：https://arxiv.org/abs/2608.13215

机构：College of Intelligent Systems Science and Engineering（智能系统科学与工程学院）； Harbin Engineering University（哈尔滨工程大学）

作者：Tianshuo Zhang, Xianglei Xing, Wenzhe Zhai, Jia Gao, He Cao

英文摘要：Forecasting the long-horizon evolution of mechanical systems from position-only observations is a pivotal yet difficult task, as hidden velocities and trajectory-specific physical properties must be inferred simultaneously. Although physics-guided neural networks like Lagrangian Neural Networks (LNNs) guarantee physical plausibility, they generally require complete state inputs and lack adaptability to changing system parameters. To break these limitations, we introduce History-informed Lagrangian Neural Networks (HiLNN). Grounded in the insight that temporal position sequences implicitly encode underlying dynamics, HiLNN employs a recurrent encoder to extract a latent context from history. This context not only reconstructs the unobserved initial velocity but also adaptively modulates the mass matrix, potential energy, and damping coefficients of a structured Lagrangian system. By leveraging a differentiable RK4 rollout scheme, the entire pipeline is optimized end-to-end under multi-step trajectory supervision and energy-consistency regularization. Empirical evaluations across conservative, dissipative, and heterogeneous variable-parameter systems show that HiLNN delivers superior long-term prediction accuracy and maintains precise energy profiles compared to state-of-the-art baselines. The source code is publicly available at this https URL.

AI 总结：本文提出结合物理知识的神经常微分方程框架，利用15台不同变压器的时间序列数据，实现电力变压器热行为的鲁棒预测，解决了现有方法的局限性。

链接：https://arxiv.org/abs/2608.13260

机构：University of Oslo（奥斯陆大学）； SINTEF AS（辛特夫研究院）； Norwegian University of Life Sciences（挪威生命科学大学）

作者：Berk Hadzhamolla, Alexander Johannes Stasik, Signe Riemer-Sørensen

英文摘要：Accurate modeling and forecasting of power transformer thermal behavior are critical for reliability, asset lifetime, and optimized power system operation. Numerical approaches such as finite element methods (FEM) and computational fluid dynamics (CFD) offer high fidelity but are computationally expensive, require complex mesh generation, and are often impractical for real-time or large-scale applications, particularly when transformer geometries are unknown. Lumped-parameter thermal models are more practical but depend on transformer-specific thermal constants and may fail to capture dynamic responses under varying operating and environmental conditions. Purely data-driven machine learning methods, including artificial neural networks, convolutional neural networks, and long short-term memory (LSTM) networks, have shown success in forecasting transformer temperatures but typically require large volumes of high-quality training data and may produce physically inconsistent or uninterpretable results. This paper develops a physics-aware Neural Ordinary Differential Equation (Neural ODE) framework for forecasting transformer thermal behavior from real-world time-series data. Neural ODEs model system dynamics in continuous time, providing smooth trajectory prediction and a natural representation of continuously evolving thermal dynamics. A key contribution is the integration of simplified heat-transfer equations directly into the Neural ODE formulation. The model is evaluated across datasets from fifteen transformers in different regions of Norway with varying designs and cooling mechanisms. The results demonstrate that the developed Neural ODE framework provides a standardized, physics-aware, and robust forecasting approach for heterogeneous transformer units.

AI 总结： 该研究针对时间序列基础模型训练分布控制不足的问题，提出ORBIT训练范式，结合多级采样与增量训练，训练Falcon-2.0模型并引入Rank引导跨深度对齐，在多基准测试中展现优异零样本预测性能。

链接：https://arxiv.org/abs/2608.13262

作者：Hongjie Xia, Yiding Liu, Yifan Hu, Peiyuan Liu, Zewei Dong

英文摘要：Time series foundation models (TSFMs) have advanced primarily through architectural innovation, while training regimes for large-scale heterogeneous corpora remain under-explored. As a result, pre-training distributions are often poorly controlled with respect to domain imbalance, context requirements, prediction horizons, and missingness. We introduce ORBIT (Omni-Range Bootstrap Incremental Training), a training paradigm that makes this distribution explicit and controllable. ORBIT combines Bootstrap Multi-Level Sampling, which controls dataset exposure and samples records, target variables, context windows, and prediction horizons, with Omni-Range Incremental Training, which varies context lengths and prediction horizons throughout a single training stage. Under ORBIT, we train Falcon-2.0, a simple univariate encoder-only Transformer with missingness-aware triple-channel patch tokenization and parallel patch prediction. We further introduce Rank-Guided Cross-Depth Alignment, a training objective that uses late-layer representations as stop-gradient teachers for shallow layers without additional inference cost. Evaluations on GIFT-Eval and fev-bench demonstrate strong zero-shot forecasting performance across diverse domains and frequencies.

AI 总结：本研究提出CNN与bi-LSTM结合的混合深度学习架构，用于MI-EEG解码，在公开与私有数据集上实现稳健的二、三类运动想象分类，具备良好的被试独立解码能力。

链接：https://arxiv.org/abs/2608.13285

机构：School of Science（理学院）

作者：Athanasios Karagounis

英文摘要：Motor imagery (MI) brain--computer interfaces (BCIs) have emerged as a promising approach for establishing flexible communication pathways between the human brain and external devices, particularly for individuals affected by stroke or neurodegenerative disorders. Reliable decoding of motor-imagery electroencephalography (MI-EEG) remains challenging because EEG recordings contain substantial noise and exhibit complex, weakly informative relationships with the underlying brain activity. Although deep learning provides an effective means of learning representations directly from EEG signals, its application to MI-EEG feature learning remains comparatively limited. This study introduces a hybrid deep-learning architecture that integrates a convolutional neural network (CNN) with a bidirectional long short-term memory (bi-LSTM) network. The CNN is used to learn high-level spatial and temporal representations directly from raw MI-EEG recordings, whereas the bi-LSTM models temporal dependencies and relationships among the extracted features. The proposed approach is evaluated using both a publicly available dataset and a privately acquired dataset obtained with an EEG acquisition system. The experimental results indicate that the CNN\&bi-LSTM architecture provides robust performance for both two- and three-class motor-imagery classification and demonstrates promising subject-independent decoding capability across the evaluated methods.

AI 总结：该研究发现探测方向由提示而非模型决定，单一提示设计无法比较模型，需一定数量的提示才能实现合理的模型间比较。

链接：https://arxiv.org/abs/2608.13329

机构：Devoteam（德沃泰姆）

作者：Valentin Noël

英文摘要：A model that behaves differently when it senses it is being tested would undermine the evaluations we rely on, so recent work has sought to read that sense directly from a model's activations. The standard instrument contrasts activations on prompts that announce an evaluation against prompts that do not, and reports how well the resulting direction separates held-out cases. That number is then compared across models and correlated with scale. We observe that the instrument has a free parameter its readings do not disclose: "a prompt that announces an evaluation" is not a prompt but a choice among many, and nothing in the method fixes which. Holding the task text fixed and varying only that choice, we find that the reported score, and even the direction in which it trends with model size, follows the prompt rather than the model; two published studies that disagree about the sign of that trend are both reproducible from a single design, by choice of prompt alone. Treating the prompt as a facet of a measurement design rather than an implementation detail, we find the model under study accounts for a small share of the variance in the number reported about it, and most of the rest lies in how each model responds to each prompt: collecting more evaluation items cannot repair the measurement, while varying prompts can. A further check finds that the split these probes are scored on is largely separable from surface form alone, so a direction carrying no information about evaluation at all still reproduces a substantial fraction of each published score. We conclude that a single-prompt design cannot support comparison between models, and we give the number of prompts a defensible comparison requires.

AI 总结：本研究开发了可扩展的论文复现任务空间Replica，后训练出270亿参数的AI科学家Faraday，其在复现任务上表现优于Claude Opus 4.8和GPT-5.5，为长期科学创新AI智能体奠定基础。

链接：https://arxiv.org/abs/2608.13331

机构：Inherent（因赫伦特）

作者：Damon Falck, Samer Sabri, Anja Surina, Thom Foster, Anya Sims, Sam Devlin, Dylan Rogers, Tantum Collins, Kaloyan Aleksiev, Louis Kirsch, Edward Hughes

英文摘要： The replicability of papers is a cornerstone of scientific knowledge, ensuring the reliability of existing results and providing a base for further experiments. The act of replication typically illuminates details that were previously underspecified, and thus requires similar hypothesis-driven exploration to open-ended research. In this work, we develop Replica, a scalable task space for paper replication. To provide reward signal, we introduce an auto-generated rubric-based judge that has low noise and agrees with human assessment of replication quality. We post-train Faraday, a 27B-parameter "AI Scientist" agent that leverages coding agents as tools, surpassing the performance of Claude Opus 4.8 and GPT-5.5 on held-out replication tasks. Qualitative analysis of individual rollouts reveals that Faraday adopts a more scientifically-principled approach. We believe that our results provide a stepping stone towards AI agents capable of long-horizon scientific innovation without requiring complex harnesses.

AI 总结：研究发现基于消融的SAE评估中，测量位置的选择会影响结果，提出需统一测量位置的评估协议，修正方法仅需一行代码，且随语料库规模扩大问题更严重。

链接：https://arxiv.org/abs/2608.13337

机构：Devoteam（德孚替）

作者：Valentin Noël

英文摘要：Sparse autoencoders are meant to name the things a language model computes, and the usual way to check that a latent matters is to switch it off and see what changes. But a latent fires at many tokens, and the effect has to be measured at one of them. The convention is to measure where the latent fires hardest. That choice is almost never reported, and it is not made by the experimenter: it is made by the dictionary under evaluation. Change the dictionary and the measurement moves to a different token. We show this is not a detail. Take two sparse autoencoders released by Google for the same model and match their latents by decoder similarity: even among the pairs the two dictionaries encode almost identically, they pick different tokens for a large share of them. Two dictionaries compared under the usual protocol are therefore very often compared at different places. To separate the convention from the dictionaries we train six autoencoders from one initialisation, differing only in fitting choices, so that a latent means the same thing in each. Most of the variance such a comparison reads as "these dictionaries disagree about this latent" turns out to be the position instead: it falls from 7.6% and 11.9% of variance to near zero once every dictionary is measured at the same token. More evaluation data does not rescue it. Across a sixteenfold range of corpus sizes the dictionaries agree less about where to measure, not more, so the problem grows with scale. The correction is one line of evaluation code. We give the protocol an ablation-based causal number must report to be comparable across papers, and an audit of five published papers against it. In short: a causal number reported without its position describes the token it was taken at as much as the latent it was taken from.

AI 总结：本文针对动态4比特量化，研究RoPE对齐的Q/K旋转，推导了相关旋转角度，发现结构化代理最优性在与量化器尺度统计量不匹配时无法降低量化误差。

链接：https://arxiv.org/abs/2608.13365

作者：Shuhan Wang, Yilin Luo, Nan Xu, Chi Wang Cheung

英文摘要：Rotation-based post-training quantisation commonly applies an orthogonal transform across an entire attention head to reduce outlier-induced error. RoPE instead partitions each head into two-dimensional frequency pairs, raising the question of whether a transform respecting this decomposition can improve on full-head mixing. Prior work has established the per-pair rotations that commute with RoPE. We state the converse result that, for distinct frequencies, no other single-head orthogonal map commutes with RoPE. For the head-shared parameterisation used in our experiments, we then derive the rotation angle that minimises the larger channel variance under a pooled-covariance, position-averaged surrogate and verify that the implementation attains its analytic minimum. The evaluated head-shared pairwise configuration does not improve accuracy in the tested dynamic W4A4KV4 setting. Across four checkpoints, replacing the full-head Hadamard with this configuration increases perplexity at both short and long context lengths. Composing the pairwise rotation with the Hadamard satisfies the selected $\pm0.05$-PPL interval criterion under the default estimator. Estimating the shared angle from K alone improves pairwise-only on every checkpoint but does not close its gap to full-head mixing. The analytic objective controls a position-averaged second moment of a pooled calibration covariance, whereas the dynamic quantiser sets its step from a tokenwise group range. The pairwise transform also has only two-channel mixing support. Along a controlled interpolation from two-channel to full-head mixing, K range, relative quantisation error, and perplexity degradation decrease as support increases. These results show that optimality for a structured surrogate need not reduce quantisation error when the surrogate and mixing support are misaligned with the quantiser's scale-setting statistic.

AI 总结：该研究针对现有晶体生成模型难以捕捉全局对称性的问题，提出SbCD模型，通过马尔可夫跳跃扩散过程实现对称性破缺，在MP20和MPTS-52数据集上表现优于保对称性模型，为晶体生成建模提供新方案。

链接：https://arxiv.org/abs/2608.13457

机构：HES-SO Geneva（日内瓦高等教育学院）； University of Geneva（日内瓦大学）

作者：Van Khoa Nguyen, Alexandros Kalousis

英文摘要： Generating crystals has recently attracted significant interest due to their broad applications in materials science. However, existing generative models struggle to produce complete crystallographic specifications, limiting their ability to capture global symmetry and structural dependencies. In particular, current state-of-the-art approaches generate crystals only up to site symmetries and rely on sampling space groups from empirical distributions during generation. Inspired by \emph{spontaneous symmetry breaking} in physics, where crystals break symmetries under external conditions, we propose a novel diffusion-based framework that generates full structure specifications by reversing from the lowest-symmetry priors. Our method leverages a Markovian jump-diffusion process to model these symmetry-breaking dynamics, enabling it to traverse different space groups in a physically motivated manner. Our model, dubbed \emph{Symmetry-breaking Crystal Diffusion} (SbCD), introduces a principled approach to explicitly incorporate inter-space-group transitions into the generative process. In de novo generation experiments on MP20 and MPTS-52, SbCD outperforms its symmetry-preserving counterpart by a substantial margin, offering a promising perspective for generative modeling of crystalline materials.

AI 总结：该研究针对非光滑复合目标的MYULA，推导其离散化误差由参考活动迹控制，证明Moreau偏差界，给出迭代次数复杂度，针对结构化惩罚得到更优的精度依赖关系。

链接：https://arxiv.org/abs/2608.13467

机构：School of Mathematical Sciences, Peking University（北京大学数学科学学院）

作者：Yuchen Xin, Zhihua Zhang

英文摘要：We study the Moreau--Yosida unadjusted Langevin algorithm (MYULA) for the nonsmooth composite target \[ \pi(dx)\propto \exp\{-f(x)-g(x)\}\,dx, \qquad x\in\mathbb R^d, \] where \(f\) is \(m\)-strongly convex with \(L_f\)-Lipschitz gradient and \(g\) is convex and \(G\)-Lipschitz. Let \(g_\lambda\) be the Moreau envelope of \(g\), \(\pi_\lambda\) the corresponding smoothed target, and \(a_\lambda=\operatorname{tr}H_\lambda\), where \(H_\lambda\) is the a.e./weak Hessian of \(g_\lambda\). We show that the leading MYULA discretization error is controlled by the reference active trace \(B_{\mathrm{ref}}\), the average of \(a_\lambda\) along the heat substep of one MYULA update started from \(\pi_\lambda\), rather than by the global curvature bound \(d/\lambda\). If \(M_\lambda\) is an a.e. upper bound for \(a_\lambda\), then, up to logarithmic factors, \[ N \lesssim \frac{1}{m} \left[ L_f + \frac{ \tau_f+G^2+B_{\mathrm{ref}} }{ \varepsilon_{\mathrm{alg}}^2 } + \frac{M_\lambda}{\varepsilon_{\mathrm{alg}}} \right], \qquad \tau_f:= \sup_x\operatorname{tr}\nabla^2 f(x), \] iterations suffice to ensure \(\sqrt m\,W_2(\mu_N,\pi_\lambda)\leq\varepsilon_{\mathrm{alg}}\), where \(\mu_N\) is the law of the \(N\)-th iterate and \(W_2\) is the quadratic Wasserstein distance. We also prove the Moreau-bias bound \[ \sqrt m\,W_2(\pi_\lambda,\pi) \leq \frac{G^2\lambda}{4}. \] Thus, choosing \(\lambda\asymp\varepsilon/G^2\) gives an end-to-end guarantee for \(\pi\). The universal estimate \(B_{\mathrm{ref}}\leq d/\lambda\) yields \(\widetilde O(\varepsilon^{-3})\) accuracy dependence. For the structured piecewise-linear, lasso-type, group, and total-variation penalties considered here, curvature--tube estimates make \(B_{\mathrm{ref}}\) independent of \(\lambda\), yielding \(\widetilde O(\varepsilon^{-2})\) for the same classical MYULA kernel.

AI 总结：本文提出SORT稀疏正交回归技术，作为从含噪不规则采样数据学习正交基展开的稀疏谱框架，可用于方程发现、近似与积分，在动力系统实验中表现优于基线方法，性能下降更稳定。

链接：https://arxiv.org/abs/2608.13504

机构：Jožef Stefan Institute（约热夫·斯泰凡研究所）； University of Ljubljana（卢布尔雅那大学）

作者：Sabin Roman, Ljupco Todorovski, Saso Dzeroski

英文摘要：We develop the Sparse Orthogonal Regression Technique (SORT), a sparse spectral framework for learning orthonormal-basis expansions from noisy and irregularly sampled data. SORT estimates expansion coefficients directly from observations using L1-regularized regression, avoiding explicit quadrature or analytic inner-product evaluation. The central application is data-driven discovery of ordinary differential equations: vector fields are represented in chosen orthogonal bases and learned as sparse coefficient expansions. This provides a complementary route to symbolic regression, grammar-based discovery, and SINDy-style sparse identification by first recovering a compact spectral representation, which can later guide searches for simpler analytic forms. Across the dynamical-system experiments, SORT matches or improves upon library-based sparse-regression baselines when the basis is well adapted to the problem, and shows more stable degradation under sparse sampling, noisy derivative estimates, and representation mismatch. Specific examples illustrate why this representation is useful: if a finite library misses the problem-specific nonlinearity, the resulting model can fail. SORT is not immune to mismatch, but it shifts the problem away from brittle selection among generic terms to basis design adapted to the problem domain. The experiments also show that dominant low-order coefficients persist as model order increases, supporting order-consistent model growth. Beyond equation discovery, the same learned expansion supports nonlinear approximation and estimation of complex, high-dimensional integrals by coefficient readout. Overall, SORT provides a reusable intermediate representation for system identification, approximation, and integration, while making basis design an explicit part of the scientific modeling problem.

AI 总结：该研究引入去掩蔽增长复杂度（UGC）度量，推导了离散采样掩码扩散的可验证最优调度，得到适配数据几何的采样器，其迭代复杂度接近神谕过程，且在维度相关收益上优于粗调度。

链接：https://arxiv.org/abs/2608.13520

机构：Massachusetts Institute of Technology（麻省理工学院）

作者：Martin J. Wainwright

英文摘要： We study masking diffusion for discrete sampling and introduce a path-resolved measure of data geometry called the \emph{unmasking growth complexity} ({\textsf{UGC}\xspace}). Its local increments directly control Kullback--Leibler (KL) discretization error, yielding a unified analysis of Bernoulli-subset and fixed-cardinality unmasking schemes. In log-reveal-odds coordinates, this structure yields optimized single-block and multi-block schedules, and quantifies the gains from adapting computational effort to data geometry. Crucially, we show how {\textsf{UGC}\xspace} increments can be estimated from samples via KL increments along coupled reveal trajectories. This leads to \emph{certified-optimal} samplers that achieve a prescribed KL error with high probability and iteration complexity within a constant factor of the corresponding oracle procedure. Collapsing the \ugc path yields the aggregate {\textsf{UGC}\xspace} mass, which connects to classical multivariate dependence measures and complexity measures from previous analyses of discrete diffusion. In the fine-partition limit, the squared integral of the square-root {\textsf{UGC}\xspace} density determines the sharp leading-order optimal Euler discretization error. Examples exhibit substantial dimension-dependent gains over coarse schedules, including $\widetilde{\Omega}(\sqrt{d})$ improvements achievable with a constant number of adaptively placed blocks.

AI 总结：DARTree是无需训练的推测式解码方法，将AR修正头从链扩展至树，在7个数学、代码、聊天基准的4种模型-温度配置下，实现最高平均接受长度与加速比，达9.73倍无损加速。

链接：https://arxiv.org/abs/2608.13524

作者：Tianyi Li, Yaxin Luo, Xinyi Shang, Zhiqiang Shen

英文摘要：Speculative decoding losslessly accelerates autoregressive language models by verifying multiple draft tokens in parallel. Diffusion-based drafters further reduce proposal latency by predicting an entire token block in parallel, but their position-wise distributions are marginal rather than conditioned on tokens selected along each draft path. Existing recurrent correction incorporates causal information along a single draft chain, whereas diffusion-based tree construction broadens candidate coverage without carrying this correction along individual branches. We introduce DARTree, a training-free speculative decoding method that extends a pretrained AR correction head from chains to trees. DARTree first constructs a fixed-width candidate tree by expanding and scoring all nodes at each depth in a single batch, and then only applies best-first pruning to select the verification tree, decoupling AR-head inference from sequential heap operations. Across seven math, code, and chat benchmarks, DARTree achieves the highest average acceptance length and speedup in all four model--temperature configurations, accepting up to 12.97 tokens per verification round, 98.6\% more than DFlash and 27.9\% more than Domino in the same setting, and reaching up to 9.73$\times$ lossless speedup over locally measured autoregressive decoding.

AI 总结：该研究针对多标签Jaccard测度，证明精确校准的凸代理需指数级预测坐标，同时给出多项式维度的近似校准保证及显式遗憾传递结果。

链接：https://arxiv.org/abs/2608.13549

作者：Mingyuan Zhang

英文摘要：The per-instance Jaccard score, or intersection over union (IoU), is standard in multi-label classification and binary segmentation. With $s$ labels, its loss matrix has $2^s$ outcomes and reports. Under the convention $\mathrm{Jac}(\varnothing,\varnothing)=1$, we prove that the Jaccard score, shifted-loss, and ordinary loss matrices are nonsingular and that the loss columns have affine dimension $2^s-1$. The proof combines a finite MinHash Gram representation with Boolean Möbius inversion. For exact calibration, we prove $2^{s-1} \leq \mathrm{CCdim}(L^{\mathrm{Jac}}) \leq 2^s-1$. The lower bound uses a factorially weighted distribution with $2^{s-1}+1$ supported outcomes and Bayes-optimal reports. Consequently, every exactly calibrated convex surrogate requires exponentially many prediction coordinates. We also give two polynomial-dimensional approximation guarantees with explicit regret transfers. A new $F_1$-to-Jaccard transfer turns an existing $(s^2+1)$-dimensional $F_1$ surrogate into a polynomial-time rule with asymptotic Jaccard regret at most $3-2\sqrt{2}$. For any $\alpha>0$ and $0