机器学习学术速递[8.19]

AI 总结：本研究提出一种无参考工具，可在混合PDE参数学习中仅通过一次拟合区分算子误设定与参数不可识别问题，实验验证其在样本内可有效判别两类失败情况。

链接：https://arxiv.org/abs/2608.16925

机构：Université de La Réunion（留尼汪大学）

作者：Eric Fock

英文摘要：We build an instrument that reads, from a single fit and with no oracle, whether the operator a hybrid PDE-parameter estimator postulates is wrong-and separates that from a merely unidentifiable parameter. On one self-adjoint parabolic inverse problem, an information-matrix statistic with plug-in scale and per-seed parameter has median 0.19 under correct specification, rejection rate $0.033$ against a pre-registered ceiling of $0.10$, and rises to $224$ and $85$ under two misspecifications, firing in every replicate. On a correctly specified but non-identifiable design it stays mute-$0.050$ at $n=200$, Clopper-Pearson $[0.024, 0.090]$-while a rank statistic collapses to zero at a pre-registered boundary $c_5^*=2.15\times10^{-3}.$ Two readings of one fit therefore separate the two failures across the three designs a deployable test reaches. That separation is the contribution; detection alone is a crowded flank. In sample it is a bound, out of sample a direction. It is needed because the usual accuracy check is blind: the misspecified estimator's in-domain RMSE is $2.7\times 10^{-2}$, below the observation noise for $\sigma\geq 0.05,$ while the coefficient is wrong by $29.7\%$ at zero noise, $31.2\%$ at the loudest. Nor is the failure architectural: a one-parameter curve fit, a bare parameter and multilayer perceptrons of $49$ and $241$ parameters converge to the same pseudo-true, matched in closed form to $0.07\%,$ whereas a physics-informed network, with its composite objective, converges to a disjoint one. We report where the instrument is blind, a pre-registered negative where a neural estimator loses to Tikhonov-regularized inversion at recovery, and the hypothesis under which its guarantee holds but a trained network violates it.

AI 总结：针对现有数据选择方法忽略数据与目标模型能力分布兼容性的问题，提出Data-DPO方法，结合目标模型偏好、外部质量评分与边际多样性筛选数据，在Vision-Flan和LLaVA-CoT上性能优于基线及全数据训练。

链接：https://arxiv.org/abs/2608.16926

作者：Peng Sun, Yi Yang, Antong Zhang, Chunxiao Li, Yanbo Wang, Dianbo Liu, xin chen, Kai Yu, Lu Chen, Tianfan Fu

英文摘要：Data selection in supervised fine-tuning aims to select a small set of effective samples from large-scale candidate data, reducing training cost while preserving model performance. However, existing methods usually treat data value as a relatively static property, and pay limited attention to the compatibility between data and the capability distribution of the target model. To address this issue, we propose Data-DPO, a target model-oriented SFT data selection method. Data-DPO observes the local training feedback of the target model on different samples through one-step probing, transforms activation differences among samples into pairwise data preferences, and trains a lightweight reward model to learn target-model-aware data preferences. In the final selection stage, Data-DPO further combines target model preference, external quality scores, and marginal diversity to construct a more stable and effective training subset. Experimental results on Vision-Flan and LLaVA-CoT show that Data-DPO consistently outperforms existing data selection baselines under multiple data budgets and stably surpasses full data training performance.

AI 总结：本文提出MASS算法，将LLM后训练的数据选择建模为分层覆盖问题，在Vision Flan与LLaVA-CoT上仅用少量数据即可达到或超过全量训练效果，且优于现有基线方法。

链接：https://arxiv.org/abs/2608.16927

作者： Peng Sun, Yi Yang, Antong Zhang, Chunxiao Li, Yanbo Wang, Dianbo Liu, xin chen, Kai Yu, Lu Chen, Tianfan Fu

英文摘要：As supervised fine-tuning data continues to scale, selecting high-value subsets from large candidate pools is crucial for reducing training cost and improving model performance. Existing methods often measure diversity directly in the original embedding space, where geometric metrics entangle dominant semantic directions, fine-grained supervision differences, and local noise. We address this limitation by formulating data selection as a coarse-to-fine hierarchical coverage problem and propose MASS. MASS learns low-dimensional principal manifold coordinates with a dense autoencoder for coarse semantic grouping, and then performs quality-aware sparse feature coverage within each group using a TopK sparse autoencoder. Experiments on Vision Flan and LLaVA-CoT show that MASS consistently outperforms strong data selection baselines across multiple budgets, and in several settings matches or surpasses full data training with only a small subset of data.

AI 总结：该研究针对基于GRPO的LLM遗忘，探究奖励规范与基准可靠性问题，对比四种奖励设计开展实验，发现优化成功与行为遗忘并不等价，并分析了分歧的来源。

链接：https://arxiv.org/abs/2608.17804

机构：University of Valencia（瓦伦西亚大学）

作者：Rubén Balbastre, Juan Manuel Orduña, Mariano Pérez

英文摘要：Practical LLM unlearning is usually evaluated through two objectives: suppress target-specific knowledge and preserve non-target utility. In generative QA, this leaves a third behavior underspecified: when a target-adjacent prompt admits a broader answer without target-specific leakage, the model should answer at that level rather than leak, evade, or refuse. We study this specification problem in a controlled LoRA-GRPO RWKU setting, comparing four reward designs that span lexical suppression, anti-refusal shaping, rubric-based broad answering, and an explicit refusal contrast, with and without SFT warm-up. The experiments show that optimization success is not equivalent to behavioral unlearning: RWKU forget scores, held-out completion audits, terminal training-rollout audits, and training dynamics can point to different conclusions. We trace these disagreements to reward-hacking endpoints, policy-support limits in GRPO, benchmark probes that miss endpoint changes, and rewards that can select broad-topic answering with low semantic leakage during optimization.

AI 总结：本研究提出Mr.Dec模型，通过Transformer解码器整合每日EHR与CXR数据，结合疾病特异性监督对比学习，在MIMIC-IV等数据集上实现30天再入院预测的SOTA性能，还可识别住院关键天数提供临床解释。

链接：https://arxiv.org/abs/2608.16929

机构：Yeji X

作者：Minjun Kim, Jong Hak Moon

英文摘要：Predicting 30-day hospital readmission is essential for assessing patient stability and optimizing healthcare resources. As clinical risk evolves with the accumulation of evidence during hospitalization, capturing these dynamic trajectories is essential. However, many existing approaches compress the complex longitudinal history into fixed representations, often losing the granular, day-level clinical signals that reflect a patient's evolving physiological state. To address this, we propose this http URL (Multimodal Readmission-risk prediction Decoder), which models each admission as a natural chronological sequence of daily multimodal events. By leveraging a Transformer Decoder, this http URL integrates daily Electronic Health Record(EHR) updates and intermittent Chest X-ray(CXR) findings in a time-aligned stream, reflecting the actual clinical workflow. To ensure robustness, we utilize Disease-Specific Supervised Contrastive Learning as an auxiliary regularization to induce a diagnosis-aware structure in the latent space. Evaluations on the MIMIC-IV and MIMIC-CXR datasets show that this http URL achieves state-of-the-art performance by preserving the integrity of the clinical sequence. Furthermore, our model identifies "Critical Days" within an admission, providing actionable and clinically grounded interpretations for real-time risk stratification. Code is available at: this https URL

AI 总结：本研究提出基于路径特征表示的多模态序列生存建模框架MultiSigBERT，结合电子健康记录的多模态数据与时间特性，在含2500余名患者的肿瘤队列上取得0.743的一致性指数，提升了生存预测性能。

链接：https://arxiv.org/abs/2608.16972

机构：Université Lumière Lyon 2（里昂第二大学）； Léon Bérard Center（莱昂·贝拉尔中心）； EPITA（EPITA（法国高等计算机与技术学院））

作者：Paul Minchella, Stéphane Chrétien, Guillaume Metzler, Loïc Verlingue, Rémi Vaucher

英文摘要： Machine learning has become an essential component of modern healthcare, where the integration of heterogeneous data sources offers unprecedented opportunities to improve clinical decision-making. Electronic Health Records (EHR) contain complementary information -- including narrative clinical reports, numerical measurements, and structured variables -- yet most survival models remain limited to a single modality or fail to exploit the temporal nature of patient trajectories. We propose MultiSigBERT, a unified framework for multimodal sequential survival modeling in oncology based on path signature representations. Here, narrative medical reports (free-text) are converted into sentence embeddings by extracting and averaging contextual word embeddings. These representations are then compressed via modality-specific PCA and concatenated with structured covariates to form joint temporal trajectories which are then encoded using the Signature transform, a tool from Rough Paths theory that efficiently captures higher-order temporal interactions across modalities without supervision needed. The computed Signature features are finally incorporated as high dimensional features into a LASSO-regularized Cox model to estimate individualized risk scores. The performance of our novel MultiSigBERT pipeline is illustrated on the analysis of a real-world oncology cohort from the Léon Bérard Center, comprising over 120,000 medical reports and structured records from more than 2,500 patients. The model achieves a concordance index of 0.743 (sd 0.029) on an independent test set, demonstrating the benefit of jointly modeling multimodal temporal dynamics together with patient-level geometric structure for survival prediction.

AI 总结：Delta2Gamma是一种自监督EEG表征学习框架，通过分解EEG为5个神经节律并自适应平衡各频带，在ADFTD队列上以92.4%的准确率实现阿尔茨海默病检测，性能优于相关方法。

链接：https://arxiv.org/abs/2608.17231

机构：Korea University（高丽大学）

作者：Chanwoo Park, Chanwoo Kim

英文摘要：Low-cost, scalable screening for dementia remains an open problem. Imaging-based diagnosis is costly and hard to deploy widely. Electroencephalography (EEG) is portable and inexpensive, but its recordings are noisy, vary widely across subjects, and carry few clinical labels. We tackle this with Delta2Gamma, a self-supervised framework that learns EEG representations from unlabeled data by contrasting augmented views of each signal. Rather than treat EEG as a single stream, Delta2Gamma decomposes every recording into the five canonical neural rhythms (delta, theta, alpha, beta, gamma). Each band gets its own encoder and projection head. Each also gets a temperature that is predicted adaptively during contrastive training, so bands with different signal statistics are balanced automatically. On the ADFTD cohort under a strict leave-one-subject-out protocol, Delta2Gamma separates Alzheimer's disease from cognitively normal controls with 92.4\% accuracy. This exceeds both supervised backbones and recent dedicated EEG methods.

AI 总结：MoRAX是增强地理空间基础模型的轻量级框架，利用人类移动性数据补充区域功能结构，其教师模型在多国多城市的八项预测任务中优于基线，学生模型性能接近教师，可实现零样本部署与跨国家迁移。

链接：https://arxiv.org/abs/2608.17848

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

作者：Ya Wen, Jixuan Cai, Yulun Zhou, Alec Kirkley

英文摘要：Geospatial Foundation Models (GFMs) are emerging as a powerful paradigm for learning semantically rich and geographically consistent visual and physical representations. However, their reliance on Earth-observation (EO) data leaves information about human activity largely underrepresented. Human mobility data reveals the functional and relational structure between regions that is missing from EO data, but is often limited only to the city where it is observed, making it challenging to use for transferable urban representation learning. We introduce MoRAX, a lightweight framework for augmenting geospatial embeddings with functional structure derived from human mobility. MoRAX preserves the coverage and consistency of a GFM while providing information about the functional connectivity among urban regions, permitting zero-shot deployment in unseen cities with or without available mobility data. Across four target cities spanning two countries, the MoRAX teacher model, which observes mobility, consistently outperforms GFMs and strong urban representation baselines in eight socioeconomic and environmental prediction tasks. Meanwhile, the student model, which never takes mobility data as input, approaches the teacher in performance on most tasks. Transfer results across countries further demonstrate that modulation conditioned on mobility flows provides a general mechanism for grounding geospatial foundations in the human dimension of cities.

AI 总结：该研究提出TabNSM框架，通过自适应稀疏交互模块、多阶段回归头等组件，在9个真实回归基准上实现高维表格回归的优性能与可扩展性。

链接：https://arxiv.org/abs/2608.18026

机构：University of Kentucky（肯塔基大学）； Institute for Biomedical Informatics（生物医学信息学研究所）

作者：Ali Eslamian, Qiang Cheng

英文摘要：Large-scale, high-dimensional tabular regression remains challenging: tree-based models are robust but lack end-to-end representation learning, while deep models enable flexible feature learning but often incur costly interaction modeling and sensitivity to noisy or redundant features. We propose TabNSM, a scalable regression framework that extends our earlier sparse-attention and mixer architectures. At its core, the Adaptive Sparse Interaction Module (ASIM) integrates foreground feature discovery, sparse local interaction encoding, and Feature-Token Mixing, providing near-linear complexity under fixed sparse configurations. For regression, TabNSM introduces three complementary components: a Multi-Stage Regression Head for progressive prediction refinement; GridLoss, an ordinal-aware soft-binning objective that incorporates target structure into representation learning; and RISE (Reweighted Instance Sampling by Error), a difficulty-aware sampling strategy based on loss-quantile bins. Across nine real-world regression benchmarks, TabNSM delivers strong predictive performance and practical scalability, with particularly consistent gains on high-dimensional and heterogeneous datasets. These results demonstrate that selective interaction modeling, structured regression supervision, and difficulty-aware sampling provide an effective and scalable approach to deep tabular regression.

AI 总结：本研究提出QWM框架，将世界模型与标准Q学习结合，在真实环境训练中避免复合模型偏差，在Robomimic和LIBERO基准上的样本效率与性能均优于现有SOTA方法。

链接：https://arxiv.org/abs/2608.17163

机构：Stanford University（斯坦福大学）； Peking University（北京大学）

作者：Perry Dong, Yueru Jia, Chelsea Finn, Dorsa Sadigh

英文摘要：Off-policy reinforcement learning (RL) has become increasingly sample-efficient, enabling applications such as RL fine-tuning of Vision-Language-Action models into reliable, high-performing policies. World models offer a further lever for sample efficiency, as they predict state changes rather than actions alone, but their success has largely been confined to supervised policy learning. Prior model-based RL methods often optimize the policy or value function directly on imagined rollouts, which is prone to compounding bias and struggles to scale to large, high-dimensional problems such as real-world robotics, a problem that worsens with task horizon and visual complexity. In this work, we instead ask whether we can leverage world models directly on top of standard Q-learning to improve performance, while remaining trained and grounded in the real, online setting. We propose QWM, a framework that leverages world models to perform test-time search over imagined trajectories on top of Q-learning to select high-value actions during both online rollouts and evaluation. Since the policy and value function are trained only on real transitions, QWM avoids compounding model bias while still gaining the sample-efficiency benefits of predictive search. On challenging manipulation benchmarks Robomimic and LIBERO, QWM significantly outperforms strong prior state-of-the-art methods on both sample efficiency and performance.

AI 总结：针对上下文强化学习的任务专业化微调难题，提出TSFT框架，通过整数线性规划分配微调预算，在多领域实验中提升了任务覆盖性能。

链接：https://arxiv.org/abs/2608.17180

机构：Nanyang Technological University（南洋理工大学）； MIT（麻省理工学院）； UIUC（伊利诺伊大学厄巴纳-香槟分校）

作者：Jianan Zhou, Jung-Hoon Cho, Tianyue Zhou, Han Zheng, Jie Zhang, Roy Dong, Yining Ma, Cathy Wu

英文摘要：Contextual Reinforcement Learning (CRL) seeks to generalize classical RL by maximizing task coverage across a context space of related tasks. While prior works often train from scratch and rely on either multi-task learning for a single policy or strategically training multiple policies, we advocate for a unified alternative: pretraining a single policy with good initial performance, followed by fine-tuning multiple policies for task specialization. This new paradigm, however, introduces unique challenges, such as heterogeneous marginal returns and sample inefficiency. This raises a critical research question: given a pretrained policy and a constrained budget, how much fine-tuning should each task region receive to enable sample-efficient CRL? To this end, we propose Task Specialization Fine-Tuning (TSFT), an online framework that predicts fine-tuning performance with a simple parametric model and exactly solves the resulting discrete budget allocation problem via integer linear programming. Extensive experiments across diverse decision domains, including combinatorial optimization, continuous control, and LLM fine-tuning, demonstrate that TSFT significantly outperforms baselines in task coverage and approaches oracle performance. Our work charts a new direction for model-based CRL, aligning with the modern pretrain-finetune era.

AI 总结：本文回顾强化学习与概率论、势理论的联系，在固定策略假设下从势理论视角研究强化学习的表示与算法，该视角或可提升样本效率并施加形式约束，且该框架可扩展至非线性情形。

链接：https://arxiv.org/abs/2608.17181

机构：SRI International（SRI国际）； Computer Science Laboratory（计算机科学实验室）

作者：Christopher Connolly

英文摘要：Reinforcement learning (RL) theory fundamentally depends on probability theory through the Markov chain. There is a deep connection between probability theory and potential theory. This paper reviews that connection and explores the potential-theoretic viewpoint for core reinforcement learning representations and algorithms under a fixed-policy assumption. This viewpoint may offer a path for improved sample efficiency and formal constraints that can be applied to RL. When the fixed-policy assumption is relaxed, the linear potential theory framework can be naturally extended to the nonlinear case.

AI 总结：本研究提出Co-RL框架，通过参数不共享的多智能体协作训练，利用同伴奖励减少对真实标注的依赖，提升纯文本及多模态任务的推理性能，缓解训练崩溃与响应同质化问题。

链接：https://arxiv.org/abs/2608.17253

机构：University of Exeter（埃克塞特大学）； ByteDance（字节跳动）； Johns Hopkins University（约翰斯·霍普金斯大学）； UC San Diego（加州大学圣迭戈分校）

作者：Yunhao Yang, Yuexin Bian, Yunjie Tian, Di Fu, Tianjin Huang, Yuanyuan Shi, Ziang Xiao, Nuno Vasconcelos, Yijiang Li

英文摘要： Reinforcement learning (RL) has emerged as a powerful approach for improving reasoning in language and vision-language models, yet its strongest successes still depend heavily on ground-truth supervision (e.g., verifiable reward). Such annotations are costly to obtain and become increasingly scarce as reasoning capabilities advance beyond what humans can reliably evaluate. Self-rewarding RL reduces this dependence by enabling models to derive reward signals from their own completions. However, training solely on self-generated feedback can reinforce existing biases and suboptimal behaviors, reduce response diversity, and ultimately lead to homogenized responses and training collapse. In this work, we show that unsupervised reasoning can emerge through cooperative multi-agent training. We introduce Co-RL, a framework in which multiple decoupled models, sharing no parameters, are simultaneously optimized through RL using rewards derived from their peers. We further show that increasing cohort diversity, through heterogeneous model families, sizes, and rephrased training samples, reduces the correlated errors that drive self-reinforcing feedback loops. This diversity consistently improves reasoning performance, maintains behavioral diversity, and mitigates training collapse. Across text-only and multimodal domains, Co-RL consistently outperforms the base models and prior label-free approaches, while matching or surpassing supervised methods, without access to any ground-truth labels. Concretely, Co-RL yields average gains of 3.0-8.6% across seven text-only benchmarks for LLMs and 2.3-7.2% across four multimodal benchmarks for VLMs. Code is available at this https URL.

AI 总结：本文提出Agentic ESOpt框架，用进化策略微调长视野LLM智能体，仅需最小GPU资源，在WebArena-Lite上使Qwen-3.5-27B性能提升6.69%，提示-参数协同演化在多数设置中优于基准。

链接：https://arxiv.org/abs/2608.17310

机构：National University of Singapore（新加坡国立大学）

作者：Zhi Zheng, Rongsheng Chen, Yunpeng Ba, Zhenkun Wang, Yee Whye Teh, Wee Sun Lee

英文摘要：Reinforcement Learning (RL) has been promising in single-turn LLM fine-tuning. However, long-horizon agentic reasoning introduces increasingly branching interactions and sparse rewards, exposing several limitations of RL: its heavyweight backpropagation-based training stack makes it impractical to fine-tune larger LLMs, and longer-horizon trajectories make credit assignment in RL substantially harder. This paper argues that evolution strategies (ES) can be a better choice for fine-tuning long-horizon LLM agents. Compared with agentic RL, ES offers three key advantages: 1) Model Scalability: ES enables full-parameter optimization with only minimal, inference-level GPU memory, making it possible to fine-tune large LLMs. 2) Flexibility: its lightweight, black-box feedback interface makes ES fine-tuning easy to compose with prompt-space evolution (e.g., skill optimization & test-time compute); and 3) Long-Horizon Scalability: ES performs trajectory-level parameter attribution without decomposing rewards across horizons, yielding better scalability than Agentic RL as the horizon length grows. Based on this insight, we propose Agentic ESOpt, a full-parameter agentic fine-tuning framework tailored to flexible parameter--context co-evolution. At each step, Agentic ESOpt samples perturbations around the current LLM parameters, evaluates the resulting agents with rewards, and applies an online reward-weighted update. To improve the exploration--adaptation trade-off, Agentic ESOpt further introduces a cosine decay schedule of the perturbation scale $\sigma$. On WebArena-Lite, full-parameter optimization of Qwen-3.5-27B improves the No Skill baseline by 6.69%. In test-time automatic heuristic design, Agentic ESOpt performs online prompt--parameter co-evolution, improving its matched baseline in 28 of 36 settings.

AI 总结：受人类学习的重复机制启发，提出即时回合重复（IER）机制，将其集成至 SAC、TD3 算法并在多类基准任务上验证，可提升强化学习的样本效率与学习性能。

链接：https://arxiv.org/abs/2608.17347

作者：Hoda Yamani, Yuning Xing, Koen van Rijnsoever, Bruce A. MacDonald, Henry Williams

英文摘要：Repetition is a fundamental mechanism in human learning, where revisiting successful experiences strengthens memory, consolidates skills, and improves future performance. Motivated by this biological principle, we introduce Instant Episode Repetition (IER), a simple and novel mechanism that improves sample efficiency by immediately repeating action sequences from successful episodes during environment interaction. Unlike conventional approaches such as Experience Replay and Self-Imitation Learning (SIL), which passively reuse past experience during training updates, IER directly influences the data collection process. Upon identifying a high-reward episode, the agent repeats its action sequence for a fixed number of subsequent episodes, reinforcing valuable behaviors through renewed interaction with the environment. We integrate IER into state-of-the-art SAC and TD3 algorithms and evaluate its effectiveness on continuous-control benchmarks, including MuJoCo, the DeepMind Control Suite, and a real-world dynamic object translation task with a robotic manipulator. Experimental results demonstrate that this simple mechanism improves learning performance over standard and self-imitation-based baselines.

AI 总结：该研究提出NSPER及扩展的NSPER+R，将新颖性与意外性结合，在DeepMind Control Suite任务上提升了基于图像的强化学习的训练效率与收敛速度。

链接：https://arxiv.org/abs/2608.17373

机构：University of Auckland（奥克兰大学）

作者：Hoda Yamani, Henry Williams, Bruce A. MacDonald

英文摘要： Sample efficiency is a central challenge in reinforcement learning (RL), particularly in image-based domains where agents must learn from high-dimensional visual inputs. Traditional sampling often relies on random or suboptimal experience selection, leading to redundant updates and slow learning. Improving efficiency requires mechanisms that prioritize informative experiences while also encouraging effective exploration. Prioritized Experience Replay (PER) addresses part of this challenge by reusing high-value transitions, while intrinsic rewards promote the exploration of novel or uncertain states. However, their integration has not been extensively studied. This paper introduces Novelty and Surprise Prioritized Experience Replay (NSPER), which uses novelty to capture underrepresented states and surprise to expose gaps in the agent's understanding of the environment. We further extend this with NSPER+R, integrating these signals as intrinsic rewards to jointly improve replay quality and exploration. Experiments on DeepMind Control Suite tasks show that NSPER and NSPER+R improve training efficiency and convergence speed compared to existing methods in image-based RL.

AI 总结：本文提出EvalXRL基准，通过大型语言模型编码智能体结合XRL方法诊断修复RL智能体故障的效果，实现对多种XRL方法的首次闭环直接对比评估。

链接：https://arxiv.org/abs/2608.17524

机构：University of California, Berkeley（加州大学伯克利分校）； Tufts University（塔夫茨大学）； Carnegie Mellon University（卡内基梅隆大学）

作者：Ram Rachum, Yotam Amitai, Bálint Gyevnár, Reuth Mirsky, Cameron Allen

英文摘要：This preliminary paper outlines a planned evaluation benchmark for Explainable Reinforcement Learning (XRL) methods. Current evaluations rely on functionally-grounded metrics like faithfulness and compactness, and on human-grounded proxies like subjective ratings or prediction accuracy. We suggest evaluating XRL methods by how effectively their generated explanations help to diagnose and fix malfunctioning reinforcement learning (RL) agents. We propose EvalXRL, a benchmark in which a Large Language Model (LLM) coding agent uses different XRL methods to diagnose a held-out malfunction in an RL agent, and then repair it. Our proposed benchmark iterates across (environment $\times$ malfunction $\times$ XRL method) tuples and uses the reward signal of the RL agents to form a final score for each XRL method. The coding agent may use the method interactively: invoke the XRL method, process its output, form new hypotheses on what is broken, and invoke the method again with parameters adjusted for testing these hypotheses. This closed-loop structure may be described as a simplified version of the scientific method. Some XRL methods provide self-evaluations that follow this pattern; we propose the first head-to-head comparison of multiple XRL methods in closed-loop usage.

AI 总结：该研究推出开源库rl-triton，用Triton实现统一关联扫描框架，将7种RL估计算法统一为一阶线性递推，在大规模并行模拟中实现1.6至5.7倍的速度提升。

链接：https://arxiv.org/abs/2608.17641

作者：Lars Simon Zehnder

英文摘要：We present rl-triton, an open-source library of high-performance GPU kernels for reinforcement learning credit assignment, implemented in Triton. The core contribution is a unified associative scan framework that recasts seven distinct RL estimation algorithms - Generalized Advantage Estimation (GAE), V-Trace, Retrace($\lambda$), TD($\lambda$) returns, discounted returns, eligibility traces, and episodic prefix sums - as instances of a single first-order linear recurrence solved in $O(\log T)$ parallel steps. All algorithms share the same associative scan operator, with algorithm-specific fused Triton kernels constructing their recurrence coefficients on-chip. We verify the associative operator algebraically and define the treatment of terminated and truncated episodes explicitly. Benchmarks show a 1.6-5.70$\times$ full-call speedup over a vectorized this http URL baseline in the massively parallel simulation regime (thousands of environments, short rollouts). The reported range covers all seven algorithms on both GPUs, both with and without per-step truncation handling. For most algorithms, speedups increase at longer sequence lengths, as the baseline requires more scan stages as $\log T$ grows, each adding an intermediate HBM round-trip. The library is available at this https URL.

AI 总结：该研究提出用辩论训练替代RLAIF基线，在数学任务中可减少奖励黑客行为，维持裁判性能并恢复45%的性能差距，还验证了多方面相关实验结论。

链接：https://arxiv.org/abs/2608.17776

作者：Zachary Kenton, Lili Janzer, Rory Greig, Tian Huey Teh, Kirill Tyshchuk, Jonah Brown-Cohen, Harri Edwards, Senthooran Rajamanoharan, Noah Y. Siegel, Natasha Jaques, Rohin Shah

英文摘要：We demonstrate that RL finetuning an LLM using debate, a two-player adversarial game between a generator and a critic adjudicated by a weaker LLM judge, reduces reward hacking compared to a reinforcement learning from AI feedback (RLAIF) baseline. Reward hacking is a central obstacle in RLAIF: as training progresses, the policy learns to exploit systematic errors in its AI judge, degrading task performance, a problem that worsens precisely when the judge is weaker than the policy, the setting most relevant to overseeing increasingly capable AI systems. We study mathematics tasks, where final-answer correctness is verifiable, allowing us to measure reward hacking dynamics. We train a Gemini~2.5 Flash-class policy with a frozen, weaker Gemini~2.5 Flash Lite judge, comparing a single-player RLAIF baseline against debate. While the baseline quickly hacks the judge, debate maintains judge performance throughout training, leading to a higher peak validation accuracy (45\% performance gap recovered) that persists through many RL steps. Additional experiments show that: 1) further weakening the judge leads to faster hacking, but this can be compensated by adding an additional debate round; 2) debate incentives override prompted misalignment; 3) RL using an LLM judge has a smaller train/validation reward gap than RL from verifiable rewards; 4) learning to critique to convince the judge using ground truth labels is possible but slow. Taken together, our results are a positive update on the feasibility of debate, while highlighting that balancing multi-agent training is critical: without player constraints, adversarial training risks defaulting to critic judge-hacking. We show that critique word limits (effective up to 150 words) successfully balance the game and avoid judge hacking, though this introduces a trade-off by restricting critic expressive clarity.

AI 总结： 该研究针对RLVR中探索预算分配低效问题，提出即插即用的图结构在线难度估计器，可跨样本共享反馈、缓解冷启动与过时问题，集成后实现难度自适应探索，在多模型与基准上性能更优。

链接：https://arxiv.org/abs/2608.17941

作者：Zhizhao Liu, Zhiliang Tian, Xi Wang, Zhihua Wen, Yihang Xiong, Zhiquan Lai, Dongsheng Li

英文摘要：Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models but relies on costly rollout exploration. Assigning the same exploration budget to samples with different difficulty levels is inefficient: easy samples may receive redundant rollouts, whereas difficult but learnable samples may receive too little exploration. Existing adaptive schedulers address this mismatch through curriculum-based sample selection or non-uniform rollout allocation based on estimated sample difficulty. However, obtaining reliable online difficulty estimates remains challenging: dedicated probing adds substantial generation overhead, whereas history-based estimators face a cold start with no initial observations and stale feedback, and typically ignore relations among samples. To address these limitations, we propose a plug-and-play graph-based online difficulty estimator that shares rollout feedback across related samples and continuously updates their difficulty estimates, mitigating cold start and staleness without dedicated probing. Specifically, we first construct a difficulty-aware sample graph based on semantic and reasoning similarities. Based on this graph, we introduce latent difficulty states and use a Potts prior to encourage neighboring samples to share the same state. We then employ a state-level Beta-Binomial model to aggregate the rollout outcomes associated with each state. Finally, we use an online mean-field variational algorithm to continuously update the latent-state assignments and state-level difficulty as new feedback arrives. Our framework can be integrated into sample-selection and rollout-allocation schedulers, enabling difficulty-adaptive exploration without dedicated probing. Experiments across multiple base models, RL schedulers, and benchmarks demonstrate that our framework achieves better performance.

AI 总结：该研究针对LLM衍生奖励信号的理论模糊问题，提出基于LLM反馈的策略不变奖励塑形框架，将混合架构形式化为目标增强MDP，证明其最优策略集保留保证更强，并通过数值实验验证了结果。

链接：https://arxiv.org/abs/2608.18008

机构：AI Research and Innovation Nexus for Africa (AIRINA Labs)（非洲AI研究与创新中心（AIRINA实验室））； Sefako Makgatho Health Sciences University (SMU)（塞法科·马加托健康科学大学）； African Center for Advanced Studies (ACAS)（非洲高级研究中心）； African Institute for Mathematical Sciences（非洲数学科学学院）

作者：Christophe D. Hounwanou, John Emeka Eze, Yaé U. Gaba

英文摘要：Combining large language models with reinforcement learning is increasingly explored, yet the theoretical status of LLM-derived reward signals is often left implicit. We formalize the hybrid LLM-planner and RL-controller architecture as a Goal-Augmented Markov Decision Process and show that when the LLM per-state progress score is used as a bounded potential function, the resulting shaping term preserves the optimal policy set even when the LLM scores are inaccurate. This guarantee is stronger than what general LLM-as-reward approaches provide. We verify the result numerically on a small MDP under four potential configurations, including an adversarial one scaled to twenty times the base reward magnitude.

AI 总结：针对因果发现中连续优化方法难以适配样本有限、计算有限场景的问题，提出SURE-Ridge方法，在小样本下结构汉明距离最低且所有样本量下运行时间最短。

链接：https://arxiv.org/abs/2608.17132

机构：University of Southern California（南加州大学）

作者：Sambit Mishra, Urbashi Mitra

英文摘要：Recovering the directed acyclic graph (DAG) of a structural equation model (SEM) from observational data is a central problem in causal discovery. The iterative gradient descent and per-problem hyperparameter tuning of continuous-optimization methods are poorly suited to two practically important regimes: the sample-limited regime, where the number of samples is comparable to or smaller than the number of nodes in the DAG, and the compute-limited regime. This work proposes SURE-Ridge, a non-iterative, closed-form estimator for equal variance linear Gaussian SEM. The method performs parallel node-wise regressions with regularization parameters chosen adaptively by Stein's unbiased risk estimate (SURE), and applies an adaptive thresholding procedure to extract a DAG from the resulting soft adjacency matrix. Numerical results show that SURE-Ridge achieves the lowest structural Hamming distance in the small-sample regime and the lowest run time across all sample sizes tested, compared with NOTEARS, DAGMA, and GBNSL baselines.

AI 总结：本研究针对文本到图像扩散模型开展系统缩放定律研究，提出Abra模型，发现其缩放规律可预测且需更多数据，相关规律可延伸至生成质量等多方面指标。

链接：https://arxiv.org/abs/2608.17286

作者：Kyle Chickering, Wei-An Lin, Swayam Bhanded, Dan Saunders, Akshat Tripathi, Jiaming Song, Shyamal Buch, Xinchen Yan

英文摘要： Compute-optimal scaling laws guide the training of frontier language models yet remain largely unexplored for visual generation. We present a systematic scaling law study for text-to-image diffusion models using Abra, a controlled family of flow-matching transformers trained across three orders of magnitude worth of compute ($10^{19}$ to $10^{22}$ FLOPs), reaching significantly larger compute budgets than previous works. We demonstrate that diffusion models scale just as predictably as language models but require far more data to train optimally: compute optimality occurs at approximately $200$ image tokens per parameter, ten times the Chinchilla compute-optimal prescription for LLMs. We show that unlike language models, diffusion models are robust to overtraining and that practitioners should err on the side of more data rather than a larger model. Finally, we show that this predictability extends beyond training loss to generative quality metrics, optimal CFG settings, representation quality, and even the shape of the training curves, which collapse onto a universal form.

AI 总结：本文提出因果局部状态（CLS）框架，可同时推断动力系统的近似格兰杰因果网络并预测其动力学，在三个基准测试中实现了高保真网络重构与匹配真实网络模型的预测效果，推动了复杂系统的可解释可扩展预测。

链接：https://arxiv.org/abs/2608.17452

机构：Ludwig-Maximilians-Universität München（慕尼黑大学）； Institut für Theoretische Physik, Universität zu Köln（科隆大学理论物理研究所）； Institut für KI-Sicherheit, Deutsches Zentrum für Luft- und Raumfahrt (DLR)（德国航空航天中心人工智能安全研究所）； Entrox Systems（恩特罗克斯系统公司）； Institut für Frontier Materials auf der Erde und im Weltraum, Deutsches Zentrum für Luft- und Raumfahrt (DLR)（德国航空航天中心地球与太空前沿材料研究所）

作者：Jonas Braun, Fabian Fischbach, Daniel Köglmayr, Sebastian Baur, Christoph Räth

英文摘要：Machine learning methods predict many real-world systems with remarkable accuracy, but they are typically treated as black boxes that offer no insight into which interactions drive the dynamics. Causal discovery methods reconstruct the interaction network from observational data, but without regard to whether the inferred structure supports prediction. Existing approaches combining both tasks rely on a single global hyperparameter, such as a causal threshold or a fixed neighborhood size, which cannot recover the structure of heterogeneous systems. Here we introduce causal local states (CLS), a framework that simultaneously infers an approximate Granger-causal interaction network and forecasts the system dynamics. For each node independently, we select the smallest set of neighbors that allows a predictive model to forecast the node near-optimally, and the resulting neighborhoods are then combined for a forecast of the full system. On three benchmarks of increasing difficulty, we achieve reconstruction of the underlying networks with high fidelity and forecasts on par with a model that is supplied with the true network, providing a step toward explainable and scalable forecasting of complex systems.

AI 总结：针对贝叶斯成像逆问题采样成本高的痛点，提出基于近端朗之万动力学与Picard迭代的并行采样框架PiX-MC，实现50倍加速且保持重建质量

链接：https://arxiv.org/abs/2608.17666

机构：Johns Hopkins University（约翰斯·霍普金斯大学）； University of California, Los Angeles（加利福尼亚大学洛杉矶分校）

作者：Deliang Wei, Evan Bell, Wenhan Guo, Yifan Chen, Yu Sun

英文摘要：Bayesian imaging inverse problems often require sampling from high-dimensional posterior distributions. While recent score-based and diffusion models provide expressive Bayesian priors, their sampling procedures remain inherently sequential and computationally expensive for large-scale imaging applications. We propose PiX-MC, a time-parallel posterior sampling framework based on proximal Langevin dynamics and Picard iteration. The proximal-likelihood formulation exploits the fact that many imaging likelihoods admit efficient, problem-specific proximal operators, while Picard refinement exposes parallelism across discretization nodes and naturally supports multi-GPU implementation. To further improve practical scalability and sampling performance, we develop multi-block and annealed variants of the proposed framework. We establish convergence guarantees under transparent assumptions, accommodating non-log-concave posteriors, imperfect learned score models, multi-block implementations, and annealing schedules. Experiments on a diverse collection of imaging inverse problems demonstrate that PiX-MC substantially reduces wall-clock time while preserving reconstruction quality. On a $512\times512\times80$ sparse-view computed tomography (CT) problem, annealed multi-block PiX-MC achieves up to a $50\times$ runtime speedup over the standard Langevin sampler using eight GPUs.

AI 总结：本研究提出带势诱导速度的流匹配模型，生成显式标量能量，实现能量校正生成、OOD检测及反问题后验采样，可降低PDE残差、提升OOD检测精度。

链接：https://arxiv.org/abs/2608.18004

作者：Yixuan Sun, Anirban Samaddar, Sandeep Madireddy

英文摘要： Probabilistic modeling of physical fields benefits from both a data-driven prior and known physical structure such as the governing equations. Energy-based models (EBMs) are a natural fit since energies compose additively, which enables augmenting physics information during inference. However, EBMs have been difficult to train and sample from due to the intractable partition function. We show in this work that flow matching models with a potential-induced velocity yield an explicit scalar energy at all transport times, whose gradient is exactly the converted learned score and which recovers the marginal negative log-density at the population optimum. The time-dependent energy functions are obtained purely from the matching regression objective on an independent linear Gaussian interpolation, without a variational form or additional MCMC steps, and the sampling retains the flow ODE. Access to the energy function from a trained model serves three roles: energy-corrected data generation, energy as a scoring function for out-of-distribution (OOD) detection, and energy compositional posterior sampling for inverse problems. In particular, we show the explicit energy permits general MCMC samplers in the predictor-corrector sampling framework, reducing PDE residual and spectral distance compared to the flow ODE baseline. Furthermore, we demonstrate utilizing the data energy and physics-based energy (e.g., PDE residuals) as complementary mechanisms to improve detection accuracy for OOD tasks. In addition, we explore the connection to MCMC-based inference for inverse problems by composing the energy with a quadratic observational likelihood that yields a posterior energy, used as an explicitly chosen family of inference-time targets.

AI 总结：本文针对反对科学实在论的悲观元归纳论证，通过动摇其归纳步骤提出新挑战，基于频率统计学等领域的认识论，论证普通枚举归纳可处处收敛而元归纳无法，且该情境下无推理方法能实现几乎处处收敛。

链接：https://arxiv.org/abs/2608.17213

机构：University of California, Davis（加利福尼亚大学戴维斯分校）

作者：Hanti Lin

英文摘要：This paper challenges the pessimistic meta-inductive argument against scientific realism by undermining its inductive step rather than its historical premise. Although related challenges already exist, I develop a new one. Drawing on a general epistemology of scientific inference developed in frequentist statistics, machine learning, and formal epistemology, I evaluate induction in terms of convergence to the truth. I argue that ordinary enumerative induction can achieve everywhere convergence, whereas meta-induction fails even to achieve almost everywhere convergence. Indeed, in the problem context where meta-induction arises, the failure is deeper: no inference method whatsoever achieves almost everywhere convergence.

AI 总结：该研究针对带结构损失函数的数据驱动超参数多重调优，利用实代数几何建立紧伪维界，提出多区域下界框架并扩展拓扑框架，解决了现有界宽松及缺乏全面下界的问题。

链接：https://arxiv.org/abs/2608.17343

作者：Anh Tuan Nguyen, Viet Anh Nguyen

英文摘要：Data-driven algorithm design frames hyperparameter tuning as a statistical learning problem, but establishing generalization guarantees remains challenging due to the implicit, non-smooth dependence of model performance on hyperparameters. Existing multi-dimensional bounds under piecewise-polynomial assumptions remain theoretically loose and lack comprehensive lower bounds. We resolve this by establishing tight pseudo-dimension bounds for multi-dimensional data-driven tuning. First, we refine the learning-theoretic upper bound using real algebraic geometry; by analyzing invariant connected sign cells during block elimination rather than isolated sign vectors, we avoid topological over-counting to derive strictly sharper sample complexities. Second, we present a multi-regime lower-bound framework that disentangles combinatorial and algebraic capacities. By constructing shattered problem instances across distinct regimes, we prove our upper bounds are tightly saturated. Finally, we extend our topological framework to accommodate general bi-level validation-loss tuning and broader semi-algebraic applications.

AI 总结：该研究构建了最优传输修正流系统，在威斯康星乳腺癌数据集上实现了无监督恶性评分与归因，发现胸部X光的无标签最优传输热图无法真实定位疾病，仅监督式Grad-CAM表现良好，并贡献了相关方案与基准。

链接：https://arxiv.org/abs/2608.17370

机构：The University of Texas at Austin（德克萨斯大学奥斯汀分校）

作者：Lalit Kumar

英文摘要：Generative models promise a route to explainable clinical AI: rather than probe a classifier, model the distributions of healthy and diseased patients and read explanations off the geometry between them. We build such a system - an optimal-transport rectified flow trained between two clinical distributions - and use it to ask a pointed question the field too rarely tests: do the resulting explanation heatmaps actually localize disease? On tabular tumour biomarkers (Breast Cancer Wisconsin) a single flow yields per-patient counterfactuals, an unsupervised malignancy score (AUROC 0.91; 0.93 +/- 0.01 across five seeds), and a label-free attribution that agrees with a supervised classifier (r ~ 0.5) - a compact, honest interpretability engine, though it never out-predicts logistic regression. Moving to chest X-rays, we show the transport heatmap is a population-level signal, not a localiser; a reconstruction-based, identity-preserving variant does localize synthetic lesions (pointing game 0.52), yet on real RSNA radiologist boxes it collapses to chance while only supervised Grad-CAM stays above it. The central result is a synthetic-to-real gap: label-free heatmaps that look compelling on planted lesions are not evidence of real localisation. We contribute a reusable optimal-transport recipe for generative explanations and a controlled benchmark for stress-testing whether they localize.

AI 总结：本研究针对极端干旱年份2012年的县级玉米产量预测问题，对比非深度学习与深度学习模型，采用样本加权和特征选择改进非深度学习模型，发现VITA模型表现最优。

链接：https://arxiv.org/abs/2608.17971

机构：Boston College（波士顿学院）

作者：Shrey Gupta, Yi Ming, George Mohler

英文摘要：The impact of climate variability on food production has led to the creation of various forecasting models that uses machine learning (ML), numerical weather predictors (NWP) or a hybrid of ML-NWP models to identify structural and physical relationships between meteorological drivers and crop growth, in order to predict crop yield. Droughts, for example the 2012 Midwestern US (Corn Belt) drought, are extreme events that affect crop production and test the limits of these forecasting models. Using 16 meteorological drivers as predictors, we compare ML (non-deep learning) and deep learning forecasting models to predict the county-level corn yield for the extreme drought year, 2012. This forecasting problem is characterized by a dissimilarity between the feature distributions of the training and test data, where the meteorological conditions of the extreme drought year fall outside the range of historically observed values. Additionally, the dataset consists of spatial and temporal irregularities where counties with missing yields introduce spatial sparsity and the use of only a subset of daily values per year introduce temporal sparsity. To overcome this, we use sample weighting and feature selection as modifications to improve our forecasting models. These modifications lead to an improvement for ML models; however, the deep learning model VITA shows little to no improvement. While VITA outperforms the ML models with or without modifications, our current study sheds light on the effect of dissimilarity between train and test feature distributions on forecasting models, compares deep learning versus non-deep learning models, and introduces modifications that are effective for non-deep learning models.

AI 总结：本研究提出OYS方法，将扩散模型采样的时间步长选择作为黑盒优化问题，用贝叶斯优化直接优化目标指标，可提升多类图像生成任务性能，大幅降低推理成本且无需额外训练。

链接：https://arxiv.org/abs/2608.18040

机构：Cornell University（康奈尔大学）

作者：Travis Zhang, Christian Belardi, Justin Lovelace, Jin Peng Zhou, Saebyeol Shin, Carla P. Gomes, Kilian Q. Weinberger

英文摘要：Sampling from a diffusion model typically requires many forward passes through a large neural network, making generation computationally expensive. While much work has focused on efficient solvers and samplers, comparatively little attention has been paid to selecting the sampling timesteps themselves. A recent line of work optimizes theoretically derived surrogates for sample quality rather than the quality metric itself. We propose Optimizing Your Sampling (OYS), which instead treats timestep selection as a black-box optimization problem, optimizing the target metric directly with Bayesian optimization. OYS outperforms both the default schedules and those of Align Your Steps on text-to-image generation, and improves over the default schedules on inpainting and other image tasks, in both quantitative and human evaluations. OYS requires no additional training, is applicable even to distilled models, and improves both simple and sophisticated samplers such as Euler and DPM-Solver++. A 5-step OYS schedule retains 89%-94% of the quality of a 50-step schedule while reducing inference cost by 10x.

AI 总结：该研究提出一种两人零和重复博弈，其值恒等式关联贝叶斯更新与指数权重遗憾，分解出三类遗憾项，且多类学习方法均为其特例。

链接：https://arxiv.org/abs/2608.18061

作者：Akshay Balsubramani

英文摘要：We give a two-player zero-sum repeated game between a learner and nature whose value identity generates Bayesian updating and an exact accounting of exponential-weights regret at once, and supplies the comparator-class variational form that a wide class of concentration phenomena share. The terminal payoff is the most a comparator can gain at fixed relative entropy from the prior, and the one-step constraint is an information budget on nature's move under the learner's mixed action. With the learner's move otherwise unrestricted, Gibbs/Bayes weights emerge as its unique Bellman equalizer -- the mixed action that makes the per-round loss independent of which direction nature moves -- with log-partition functions playing the role of value functions. The regret decomposes exactly into three parts: a per-round information loss reflecting the variation in observed outcomes, an additive retempering drift that accounts exactly for any change of measurement scale between rounds, and the information the comparator carries relative to the prior. The variance and bounded-range proxies that drive standard regret bounds are looser relaxations of this decomposition, which holds generally and governs them all. Both players' strategies are read off from the decomposition term by term, and repeated play yields an information-theoretic ledger of self-play in place of the usual quadratic-variation surrogate. The same comparator-class geometry accounts for the classical large-deviation bounds, and methods across bandits, posterior sampling, aggregation, and boosting are specializations of the one regret decomposition.

AI 总结：本文针对时间压力下两轮车碰撞风险评估问题，提出基于学习到的时间重要性的边缘AI架构MotoSafety，在多数据集验证下性能优于基线模型，适合低成本边缘部署，还具备跨领域迁移能力。

链接：https://arxiv.org/abs/2608.17823

机构：Indian Institute of Technology Indore（印度理工学院印多尔分校）； Texas State University（德克萨斯州立大学）

作者：Sumit S. Shevtekar, Chandresh K. Maurya, Gourab Sil, Subasish Das

英文摘要： Powered two-wheeler riders face critical safety challenges in low- and middle-income countries, yet limited studies exist on how cognitive stressors such as Time Pressure influence collision risk. To address this gap, we introduce a large-scale dataset of over 129,000 labeled multivariate time-series sequences from 153 simulator rides by 51 participants under No, Low, and High TP, capturing 64 features across vehicle dynamics, control inputs, proximity, and behavioral violations. Building on this dataset, we propose MotoSafety, a novel edge-AI architecture grounded in the Learned Temporal Importance principle. MotoSafety achieves 94.97% accuracy and 99.33% ROC AUC, outperforming ten baselines, including TimesNet and LLM4TS, and achieves 0.039 MSE and 0.094 MAE for forecasting (4.4x lower error than Time-LLM and iTransformer). With only 1.15M parameters and 0.135 ms latency, it is suitable for edge deployment on low-cost CPU hardware. Using ground truth TP as an inductive bias improves accuracy from 94.09% to 94.97%, while predicted TP achieves 94.82%. Using only 21 IMU+GPS features, it achieves 93.91% accuracy, indicating practical deployment. Beyond PTW safety, the architecture shows better transferability to human activity (97.66%) and clinical (99.65%) domains. This lightweight framework advances PTW collision risk assessment, supporting the Safe System Approach for Intelligent Transportation Systems.

AI 总结：

链接：https://arxiv.org/abs/2608.17849

机构：the University of Hong Kong（香港大学）

作者：Wei Wei, Xianhao Chen

英文摘要：Split federated learning (SFL) has emerged as a powerful paradigm for model training at the edge. However, SFL inherently involves discrete decision variables for model splitting and resource allocation, resulting in a challenging mixed-integer problem. Consequently, prior optimization schemes for SFL are either \textit{heuristic} or \textit{computationally inefficient}, which cannot handle large-scale user populations. To address this limitation, this work establishes an efficient optimization framework for SFL under resource-constrained networks. Our framework jointly optimizes model splitting and resource allocation to minimize training cost, which is defined as the weighted sum of latency and energy costs. We first study the model splitting problem and develop a polynomial-time algorithm that achieves the global optimum. Then, we extend the approach to the joint model splitting and resource allocation problem. In this case, we formulate it as a two-dimensional master problem and develop an efficient approximation method with a $(1+\epsilon)$-approximation guarantee. Extensive experiments show that the proposed approach provides efficient solutions to strike the optimal energy--latency tradeoff.

AI 总结：本文针对公开编码器与私有下游模型场景，提出无查询的任务感知攻击框架SW-ProxyCE，实验表明其生成的对抗样本可有效迁移至下游模型，且性能优于任务无关攻击。

链接：https://arxiv.org/abs/2608.16931

作者：Linhua Cong, Dingkun Liu, Dongrui Wu

英文摘要：Electroencephalography (EEG) foundation models have recently emerged as a promising paradigm for EEG decoding by learning reusable representations from large-scale heterogeneous neural recordings. However, the open release of EEG foundation encoders, while facilitating downstream developments, also introduces a previously unexplored security risk: publicly available representations may make private downstream models vulnerable. This paper investigates adversarial transfer attacks in EEG foundation model deployment in a public-encoder and private-downstream setting, where attackers have white-box access to a released encoder and a small task-matched labeled reference set, but no access or query to victim parameters, outputs, or gradients. We propose Shrinkage-Whitened Proxy Cross-Entropy (SW-ProxyCE), a query-free task-aware attack framework that recovers task-level decision geometry from a small labeled reference set through shrinkage-whitened class prototypes, enabling transferable adversarial generation without training an additional surrogate classifier. We evaluated SW-ProxyCE across three EEG tasks using three general-purpose foundation encoders and a paradigm-specific pre-trained encoder, covering both linear-probing and full-fine-tuning downstream models in cross-subject and within-subject scenarios. Results demonstrated that adversarial examples generated from the public encoder and limited labeled references can effectively transfer to inaccessible downstream models. SW-ProxyCE consistently outperformed task-agnostic representation-shift attacks, revealing that the strong transferability of EEG foundation models does not necessarily lead to adversarial robustness. Our code will be available on GitHub.

AI 总结：该研究针对经济预测的分布偏移问题，提出动态机制感知共形预测（DRACP），经验证其校准可靠性最优，在通胀激增等场景表现突出，为预测区间的校准与效率提供了权衡方案。

链接：https://arxiv.org/abs/2608.17079

机构：University of Bucharest（布加勒斯特大学）； National Institute of Research and Development for Biological Sciences（国家生物科学研究与发展研究所）

作者：Bogdan Oancea

英文摘要： Conformal prediction provides distribution-free prediction intervals but relies on exchangeability, an assumption often violated in economic forecasting because of covariate shift, concept drift, local heterogeneity and latent regimes. We propose Dynamic Regime-Aware Conformal Prediction (DRACP), which combines density-ratio, localized kernel and probabilistic regime-aware weighting with a self-tuning online significance controller in a unified weighted conformal calibration framework. We distinguish three theoretical results: finite-sample validity under oracle importance weights, a coverage-gap bound for estimated weights with rates in effective sample size, and deterministic or regret guarantees for the online controller. We evaluate DRACP against six baselines on 48 real forecasting series covering euro-area and EU-27 HICP inflation, US macroeconomic and energy indicators, and daily financial series. Recent online methods (FACI, strongly-adaptive online conformal prediction and conformal PID) were verified against the authors' implementations. DRACP is not the most efficient method: strongly-adaptive online conformal prediction achieves the best interval score and intervals about 20% narrower. Instead, DRACP provides the most reliable calibration, achieving coverage closest to the nominal 0.90 (0.890), never falling below 0.80 on any series, maintaining the best coverage at all forecast horizons, and performing best during the 2021-2023 inflation surge. The strongly-adaptive method undercovers on 20 of 48 series versus 10 for DRACP. DRACP therefore offers a principled trade-off between calibration and efficiency, favoring reliable coverage when prediction intervals must satisfy coverage standards. An ablation study shows that the online controller and conditional-scale normalization provide most of the performance gain, whereas the weighting components make a smaller contribution.

AI 总结：本研究提出OraclePhys，一种面向结构力学的大语言模型微调系统框架，含自动评分基准、多形式监督数据集及对照训练研究，发现标签答案形式而非比特数决定微调效果，训练所得8B模型达空间结构响应任务数据精度前沿。

链接：https://arxiv.org/abs/2608.17162

机构：University of Houston（休斯顿大学）； Tsinghua University（清华大学）

作者：Mingyu Li, Guorui Song, Jing Lin, Haoqian Wang

英文摘要：What a language model internalizes from fine-tuning is usually diagnosed after the fact. We make it an experimental variable. OraclePhys is a systematic fine-tuning framework with three components: OraclePhys-Bench, an exactly-graded structural-mechanics benchmark whose finite-element oracle scores every answer and counterfactual edit -- no human labels, no LLM judging; OraclePhys-30K, a supervision dataset of seven answer forms over byte-identical structure descriptions; and a controlled training study across the seven forms and three verifier roles. The study yields two findings. First, the label's answer form -- not its bit count -- causally determines what fine-tuning teaches: a ranking objective installs an out-of-distribution forward model where the untrained base sits at the guessing prior, a scalar objective at best a partial one, a boolean nothing detectable; the vector-scalar gulf survives a second physics domain, a second model family, and a paraphrased evaluation surface. Second, written or score-filtered answers install this capability, while advantage-weighted scores (GRPO) raise reward yet leave the model statistically equivalent to its start on held-out physics -- within the recipes and budgets tested -- sufficing only for routing. The trained 8B -- the first LLM on spatial structural response -- reaches the task's data-precision frontier: above a frontier LLM at zero- and 32-shot, at a specialist's level. What the label spells out about the target computation is what fine-tuning teaches; what you train on is what you route.

AI 总结：针对脑电图机器学习在高风险环境中易受分布偏移影响的问题，引入EEG OOD检测基准，评估相关方法并结合互补方法构建稳健安全网。

链接：https://arxiv.org/abs/2608.17620

机构：School of Informatics, University of Edinburgh（爱丁堡大学信息学院）

作者：Philipp Bomatter, Henry Gouk

英文摘要：Machine learning models for electroencephalography (EEG) analysis show great promise across a wide range of applications, but their deployment in high-risk domains is hindered by their vulnerability to distribution shifts. Encountering out-of-distribution (OOD) data can lead to catastrophic, overconfident predictive failures. While OOD detection methods can mitigate these risks, they remain heavily under-explored for EEG. Moreover, evaluations in the broader literature typically evaluate OOD detection performance in isolation, ignoring their practical impact on downstream applications. To bridge this gap, we introduce a benchmark for EEG OOD detection, evaluate a broad range of methods, and furthermore evaluate their value in two clinical downstream prediction task. Our results disentangle OOD detection and model uncertainty estimation capabilities, which are frequently conflated in the literature, provide actionable insights about the current state of the art for EEG OOD detection and model uncertainty estimation, and demonstrate how complementary methods for both aspects can be combined to form a robust safety net for the deployment of EEG-based machine learning models in real-world applications.

AI 总结：针对药物开发中分子性质预测的分布偏移与传统点预测指导有限的问题，提出标签偏移下的共形预测框架，无需重训练即可生成严谨预测区间，提升AI预测可信度与决策可靠性。

链接：https://arxiv.org/abs/2608.17678

机构：Mogam Institute for Biomedical Research（慕庵生物医学研究院）； Intellicode（智码公司）

作者：Hyeonsu Lee, Juyeon Kim, Erkhembayar Jadamba, Seungjin Choi, Hyunjin Shin

英文摘要： Drug discovery and development underpins healthcare but remains costly and failure-prone. A critical bottleneck lies in predicting molecular properties such as solubility, potency, and toxicity, which directly determine whether a candidate can advance from preclinical to clinical trials. Artificial Intelligence (AI) has accelerated this process, yet its reliability is often undermined by distribution shift, as experimental conditions frequently diverge from training data. In addition, conventional point predictions provide only single-value estimates, offering limited guidance for high-stakes experimental design. We address these challenges with a conformal prediction framework tailored to label shift. By weighting conformal scores using marginal label probability ratios, our method produces statistically rigorous prediction intervals without retraining. This enables robust uncertainty quantification even when property distributions drift, directly tackling one of the most pervasive obstacles to applying AI in real-world drug development. By moving beyond accuracy alone to provide actionable confidence measures, our approach enhances the trustworthiness of AI-driven predictions. This further aligns predictive modeling with regulatory demands for transparency and uncertainty reporting and ultimately supports more reliable decision-making in billion-dollar development pipelines.

AI 总结：针对基于语言模型的日志异常检测器置信度校准差的问题，提出轻量级事后校准框架LoRD，经实验验证其可提升置信度可靠性并减少过度自信异常相关错误且不牺牲检测性能。

链接：https://arxiv.org/abs/2608.17965

机构：Beijing Jiaotong University（北京交通大学）； University of Florida（佛罗里达大学）

作者：Bin Li, Dongdong Wang, Siyang Lu

英文摘要：Online log anomaly detection is critical for maintaining the reliability of large-scale computing systems. Although recent language model-based log anomaly detectors achieve strong detection performance, their confidence estimates remain poorly calibrated. We show that these detectors frequently assign excessive confidence to incorrect predictions, particularly for anomalous logs under severe class imbalance. Moreover, confidence on erroneous predictions remains persistently high even when conventional calibration metrics indicate good calibration, creating a critical reliability gap for operational monitoring systems. To address this issue, we propose Log Reconstruction and Distance (LoRD), a lightweight post-hoc calibration framework for reliable log anomaly detection. LoRD learns prediction-route-specific reliability models from latent representations of correctly classified validation samples and estimates prediction reliability through route-wise reconstruction distances. Based on the estimated reliability, LoRD selectively recalibrates high-risk predictions to suppress overconfident errors while preserving reliable predictions. Extensive experiments on four large-scale log benchmark datasets and multiple language model-based detectors demonstrate that LoRD consistently improves confidence reliability and substantially reduces overconfident anomaly-related errors without sacrificing anomaly detection performance.

AI 总结：本研究针对SGC节点分类任务，提出以最小溯因解释为中间表示的逻辑框架，可提取紧凑且高保真的全局逻辑规则。

链接：https://arxiv.org/abs/2608.17103

作者：Bryan Lima Cavalcante, Thiago Alves Rocha

英文摘要：Graph Neural Networks (GNNs) have achieved remarkable performance in node classification tasks, motivating growing interest in methods capable of explaining their predictions. Recent logic-based approaches, such as LogicXGNN, derive global logical rules for Graph Neural Networks (GNNs) from collections of explanatory subgraphs. While informative, these subgraphs may contain redundant structural information that is specific to individual nodes, potentially limiting the generality of the extracted rules. In this work, we propose a logic-based framework for node classification in Simple Graph Convolution (SGC) networks that uses minimal abductive explanations as an intermediate representation for rule extraction. For each node, we compute a minimal set of node-feature pairs sufficient to preserve the predicted class. These explanations are then used to train decision trees from which global logical rules are extracted. Experiments on benchmark datasets show that the proposed framework produces compact global rules while maintaining high fidelity to the original SGC model.

AI 总结：本研究提出一种时空预测框架，通过融合通用知识图谱与传感器网络数据，提升GNN的交通预测精度，且验证了外部知识对预测效果的普遍增益作用。

链接：https://arxiv.org/abs/2608.17440

机构：Kiel University（基尔大学）； GEOMAR Helmholtz Centre for Ocean Research Kiel（基尔亥姆霍兹海洋研究中心）； ZBW – Leibniz Information Centre for Economics（莱布尼茨经济信息中心（ZBW））

作者：Mattis thor Straten, Yannick Wolker, Steffen Strohm, Prathvish Mithare, Ralf Krestel, Matthias Renz

英文摘要：Although Graph Neural Networks (GNNs) have made significant advances in spatio-temporal traffic forecasting, their performance is limited when they rely solely on sensor proximity or road-network topology. This paper presents a spatio-temporal prediction framework, developed to incorporate knowledge in various forms. This framework aims to improve sensor-level, contextual understanding of the environment. A general-purpose knowledge graph (e.g., Wikidata) is used to create semantic subgraphs around traffic sensors and generate knowledge graph embeddings that capture meaningful relationships, such as nearby points of interest, administrative hierarchies, and the functional roles of locations. These embeddings are then fused with conventional traffic sensor graphs to provide additional adjacency matrices informed by semantics. This allows GNNs to learn the semantic context beyond physical connectivity. This study differs from previous research in two key ways. Firstly, rather than proposing a novel GNN architecture, it demonstrates the general impact of external knowledge on prediction accuracy. Secondly, experiments with well-established traffic forecasting approaches show that external knowledge provides additional information that street network data alone cannot convey. The results show that integrating data from general-purpose knowledge graphs and sensor networks through data fusion can enhance the prediction accuracy of traffic forecasting models, and offers a potential pathway toward improved interpretability.

AI 总结：该研究针对后训练导致的灾难性遗忘问题，提出让智能体在轨迹中途切换专用LoRA适配器的SLAaaT方法，实验显示其可解决新问题、自主切换策略且能力损耗低，在任务能力和token使用上优于生成子智能体的方法。

链接：https://arxiv.org/abs/2608.17034

作者：Kenneth Ge

英文摘要：Post-training can unlock new capabilities and improve performance on specialized tasks, but sometimes at the cost of catastrophic forgetting in other domains. This poses a problem in long agent trajectories that compose different capabilities. We reject this tradeoff by giving an agent a tool to switch between specialized LoRA adapters mid-trace. To test its effectiveness, we compose two synthetic coding tasks that are logically simple but require specialization. We find that this allows the model to solve problems it previously could not, that the model is able to switch autonomously (and find a new strategy that beats our human heuristic baseline on one task), and that this incurs an up to an 18x reduction in capability tax compared to an agent using only one specialized adapter. Our approach also substantially outperforms spawning subagents in both task capabilities and token usage.

AI 总结：本研究建立了跨境电价预测的可复现评估框架，对比了六种深度学习模型在低数据场景下的表现，发现N-HiTS和NBEATSx在有限数据中表现具竞争力，Transformer模型需更多调优。

链接：https://arxiv.org/abs/2608.17091

机构：Institute for Automation and Applied Informatics, Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院自动化与应用信息研究所）； Department of Computer Science, Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院计算机科学系）

作者：Hadeer Elashhab, Sai Srijan Papineni, Marvin Dorn, Veit Hagenmeyer, Benjamin Schäfer

英文摘要：While publicly available electricity market data presents a valuable resource for forecasting research, the field lacks established benchmark datasets for standardized comparison. As a result, many studies have relied on different datasets and metrics to evaluate methods in isolated settings, making it difficult to assess progress and compare state-of-the-art approaches consistently. In this work, we use public data to evaluate deep learning models for electricity price forecasting (EPF) across multiple market settings. Our goal is to establish a reproducible framework that enables a consistent evaluation of forecasting models. Although deep learning has been explored for day-ahead EPF, many prior studies are limited to single-market settings, narrow feature sets, or fixed training regimes. This work presents a comparative evaluation of six deep learning models--covering state-space, MLP, RNN, and Transformer-based architectures--emphasizing generalization across markets. We simulate low-data target-market conditions using zero-shot, one-shot, and few-shot learning. Our test set focuses on the Germany-Luxembourg (DE-LU) bidding zone in 2024 using a standardized dataset with calendar, historical price, and market-derived features. Our findings suggest that N-HiTS and NBEATSx perform competitively in limited-data scenarios, while transformer-based models can reach comparable accuracy but tend to require more adaptation and tuning. Model performance also benefits from careful feature selection and hyperparameter tuning, and we note that the differences between the strongest models are often small.

AI 总结：该研究通过在6个虚拟分子库上对4种分子语言模型进行基准测试，发现显式领域适配可提升分子表示性能，适配后的编码器在基准任务中表现最佳，为虚拟筛选等领域提供了样本高效的自适应决策策略。

链接：https://arxiv.org/abs/2608.17567

作者：Henrik Wille, Luis-Finley Schütz, Felix Strieth-Kalthoff

英文摘要：Pretrained molecular language models are increasingly used as molecular encoders for learning structure-property relationships. However, their practical suitability for molecular discovery within and beyond their pretraining domain remains unclear. Herein, we systematically benchmark four molecular language models across six virtual molecular libraries spanning drug discovery, organic materials, and catalysis. Native molecular language model embeddings show substantial variation in discovery performance across libraries, whereas molecular fingerprints provide a consistently strong and robust baseline. Consistent with a potential domain-representation mismatch, we show that explicit domain adaptation substantially improves representation performance. Fine-tuning molecular language model encoders on structures from the target virtual library consistently improves sample efficiency, with several adapted encoders emerging as the top-performing representations across the benchmark tasks. These results show that molecular representation quality depends strongly on the target domain and that explicit adaptation can improve the practical utility of molecular foundation models. More broadly, our findings establish domain-adapted molecular representations as a promising strategy for sample-efficient adaptive decision making in virtual screening and self-driving laboratories.

AI 总结：该研究针对文档敏感性分类的标签泄漏问题，构建了含16000份外交电报的Strategic 16K基准语料库，测试发现BERT性能最优、TF-IDF结合逻辑回归性价比最高，成果为该领域提供了首个可复现的泄漏控制基准。

链接：https://arxiv.org/abs/2608.16928

作者：Aleesha Zainab, Muhammad Ahmed Khalid, Faheem Ullah Khan, Asifullah Khan

英文摘要：Automatic sensitivity classification of organizational documents is a critical yet underserved problem, where the consequences of misclassification range from regulatory violations to security breaches. While AI-based approaches offer a scalable alternative to manual review, their reliability depends fundamentally on the integrity of training data. A pervasive but underreported problem in this domain is label leakage: residual classification markers embedded within document bodies that allow models to exploit surface shortcuts rather than learning genuine content-based sensitivity signals, producing performance estimates that are inflated and unreliable. This paper addresses this problem by introducing Strategic 16K, a carefully constructed, leakage-controlled corpus of 16,000 diplomatic cables sourced from the WikiLeaks Public Library of US Diplomacy (PlusD), and presents a systematic benchmark evaluating six model architectures spanning classical machine learning and transformer-based approaches. We document an extended leakage removal protocol that identifies and eliminates three categories of residual classification markers embedded within document bodies. On the clean benchmark, BERT achieves the strongest performance (Accuracy = 89.14%, F1 = 89.33%), followed by ELECTRA (Accuracy = 88.57%, F1 = 88.90%). Among classical models, TF-IDF with Logistic Regression achieves the strongest performance at significantly lower computational cost. These results constitute the first fully reproducible sensitivity classification benchmark constructed under explicit leakage-controlled conditions from WikiLeaks PlusD.

AI 总结：该研究针对现有多模态时间序列预测方法上下文影响难解释控制的问题，提出SCENARIODIFF分层框架，通过三类智能体生成结构化信号引导多模态扩散Transformer，锚点混合采样优化轨迹，在Time-MMD基准的事件驱动领域表现优异。

链接：https://arxiv.org/abs/2608.17164

机构：VinUniversity； FPT Software AI Center, FPT Corporation（FPT软件AI中心，FPT集团）； VNU University of Engineering and Technology（VNU工程技术大学）； Aalborg University（奥尔堡大学）

作者：Tuan-Binh Tran, Dat Nguyen Cong, Duc-Trong Le, Thanh Trung Huynh, Tung Kieu

英文摘要：Textual context such as news, reports, and logs can provide valuable signals for time series forecasting, especially when future dynamics are driven by external events that are not yet visible in historical values. Existing multimodal forecasting methods often either ask large language models (LLMs) to predict numerical values directly or fuse text and time series implicitly, making contextual influence difficult to interpret and control. We propose SCENARIODIFF, a hierarchical contextual reasoning framework for multimodal time series forecasting under noisy and weakly aligned documents. SCENARIODIFF organizes contextual information into three levels: a Historical Context Agent extracts stepwise evidence from raw documents, a Scenario Agent produces a qualitative scenario description for the forecast horizon, and an Anchor Guidance Agent generates sparse anchor points for event-relevant future regions. These structured signals condition a Multimodal Diffusion Transformer, while Anchor Blended Sampling locally refines generated trajectories without retraining. Experiments on the Time-MMD benchmark show that SCENARIODIFF is especially effective in event-driven domains, demonstrating the value of explicit hierarchical scenario guidance for multimodal time series forecasting. Our full implementation is available at this https URL

AI 总结：针对非规则时间序列预测的渐近偏差与基函数适应性问题，提出DNBNet模型，通过去偏机制、多尺度分解等设计提升预测效果，实验验证其有效性与泛化性。

链接：https://arxiv.org/abs/2608.17284

机构：College of Computer Science and Electronic Engineering, Hunan University（湖南大学计算机与电子工程学院）

作者：Rongwen Li, Changjian Chen

英文摘要：Irregular time series forecasting is crucial in many domains, such as healthcare and meteorological observation. However, due to the inherent characteristics of irregular time series, including sparse observations and non-uniform sampling, accurately predicting future dynamics remains challenging. In light of these two characteristics, many existing methods aggregate irregular observations into fixed-dimensional estimated response coefficients through predefined basis functions and use these coefficients as sequence representations. Nevertheless, this modeling paradigm still suffers from two key limitations: (i) a potential non-vanishing asymptotic bias caused by ignoring the sampling density of timestamps; and (ii) the limited adaptability of predefined basis functions to diverse temporal patterns. In this study, we propose a Debiased Neural Basis-Function Network (DNBNet) to address these challenges. Its core is a debiased neural basis-function response mechanism, which corrects asymptotic bias through importance sampling while parameterizing basis functions with neural networks to adapt to diverse temporal patterns. In addition, considering the sparsity of irregular data, we design a novel multi-scale decomposition module based on average pooling, together with a mass-aware fusion mechanism, to obtain richer representations. Finally, a dual-branch decoder is employed for forecasting. Extensive experiments on multiple real-world datasets demonstrate the effectiveness of DNBNet and its strong generalizability across diverse irregular time series scenarios. Our code can be obtained at this https URL.

AI 总结：本文针对不规则时间序列预测中MSE评估存在偏差的问题，提出CSE指标并构建多类型数据集基准，验证其能更准确评估模型连续时间预测性能。

链接：https://arxiv.org/abs/2608.17293

机构：College of Computer Science and Electronic Engineering, Hunan University（湖南大学计算机与通信学院）

作者：Rongwen Li, Haixin Xie, Xiao Wang, Changjian Chen

英文摘要：Existing research on irregular time-series forecasting has primarily focused on model design, while evaluation metrics remain insufficiently studied. Existing benchmarks typically use mean squared error (MSE) as the evaluation metric. We show that, in irregular forecasting, MSE is determined not only by the model prediction but also by the sample-specific timestamp sampling distributions, leading to a biased assessment of the models' continuous-time predictive performance. To address this issue, we propose the Continuous-time Squared Error (CSE), which employs importance weighting to eliminate the influence of the timestamp sampling distributions. We further theoretically prove that CSE's asymptotic estimation error with respect to continuous-time risk is no greater than that of MSE. Finally, we construct a systematic benchmark covering synthetic, semi-synthetic, and eight real-world datasets to validate the effectiveness of CSE and systematically evaluate models' continuous-time predictive performance. Experiments show that CSE can recover continuous-time risk more accurately than MSE, while relying solely on MSE may not fully reflect models' continuous-time predictive performance in real-world scenarios. Our code can be obtained at this https URL.

AI 总结：该研究针对加密货币预测难题，提出结合FNO的MoFE框架，经比特币数据集实验，在T+1、T+5预测中达SOTA，缓解相位滞后，获更优DA、IC及高夏普比率的超额收益。

链接：https://arxiv.org/abs/2608.17342

机构：School of Art and Science University of Rochester（罗切斯特大学艺术与科学学院）； AGI Lab Beijing Institute of Mathematical Sciences and Applications（北京数学科学与应用研究院AGI实验室）

作者：Bowen Liu, Mingming Sun

英文摘要：Forecasting cryptocurrency prices remains a formidable challenge due to inherent non-stationarity, abrupt regime shifts, and multi-scale stochastic dependencies. Conventional deep learning models often struggle to capture complex underlying dynamics, frequently resulting in persistent phase-lagged predictions. To address these limitations, we propose MoFE, a novel deep learning framework that integrates Fourier Neural Operators (FNOs) within a Mixture-of-Experts (MoE) architecture. Rooted in the theoretical framework of stochastic differential equations, MoFE conceptualizes cryptocurrency volatility as a superposition of multi-frequency components, which includes user network based fundamental growth, mining costs and halving mechanism caused seasonal volatility, and market sentiment-induced chaos. Specifically, specialized adaptive FNO (AFNO) and Convolution dual-domain experts learn continuous function-to-function mappings to encapsulate global spectral trends, cyclical adjustments and microstructures, while a dynamic gating based MoE mechanism enables adaptive strategy switching across diverse market regimes. Extensive experiments on Bitcoin datasets spanning January 2020 to December 2025 demonstrate that MoFE achieves state-of-the-art (SOTA) performance in both T+1 and T+5 forecasting horizons. Notably, the model effectively mitigates the phase-lag effect, delivering superior Directional Accuracy (DA) and Information Coefficient (IC). In high-fidelity simulated trading environments, these predictive gains transfer into significant excess returns and robust risk-adjusted performance, characterized by a high Sharpe ratio.

AI 总结：该研究提出无需训练的人机协作异常检测框架，通过专家修正PatchCore检测器的记忆库，仅用少量黄金样本结合修正，可改进MVTec AD多数类别异常检测效果，成本低于全面审查。

链接：https://arxiv.org/abs/2608.17775

机构：School of Engineering, Newcastle University（纽卡斯尔大学工程学院）

作者：Ayusha Abbas, Saram Abbas, Kabita Adhikari

英文摘要：Anomaly detectors are hardest to deploy exactly where training data is scarcest: a newly commissioned production line has a handful of verified "golden" samples and no machine-learning engineer on the factory floor. We present a training-free human-in-the-loop framework in which a domain expert corrects a PatchCore detector by direct memory bank editing: no retraining, no gradients, no original training data. A false-positive correction inserts the reviewed image's normal patches through a self-calibrating novelty gate admitting only those beyond the median pool-normal nearest-neighbour distance. From a bank built on only ten golden samples, operator corrections close a median 66% of the gap to an uncorrected fully trained bank (mean 80%, raised by three categories that overshoot parity), significantly improving 12 of 15 MVTec AD categories and harming none: ten samples plus corrections outperform hundreds of samples without them. On already-trained banks the headroom is smaller and concentrated where the bank undersamples normal appearance (gated: toothbrush +0.10, metal nut +0.09, zipper +0.05, screw +0.05), and no category except grid is significantly harmed. Evaluation uses a held-out protocol (20 splits per category, Holm-corrected Wilcoxon), because corrected images entering the bank inflate naive evaluation toward AUROC 1.0 by memorisation. Passive and active querying are statistically indistinguishable; a matched-label-budget control attributes gains to deployment-time label production at 43% of exhaustive-review cost; a defect-memory extension fails decisively. Feedback is simulated from ground truth; live expert trials, where mislabelling is costliest on small banks, remain future work.

AI 总结：该研究利用澳大利亚大悉尼网联车辆数据，量化危险驾驶并构建时空热图，对比多种模型预测险些发生的危险驾驶事件，发现ARIMA表现最优，识别出悉尼内城和西部高风险区域，为主动道路安全干预提供支持。

链接：https://arxiv.org/abs/2608.16913

机构：Data Science Institute, University of Technology Sydney (UTS)（悉尼科技大学数据科学研究所）； COMPASS IOT PTY LTD（COMPASS IOT私人有限公司）

作者：Adriana-Simona Mihăiţă, Clarence Cheung, Artur Grigorev, Tuo Mao, David Lillo-Trynes

英文摘要：Road safety monitoring has historically been reactive, relying on crash-record analysis after fatalities and injuries have already occurred. Proactive identification of high-risk locations and dangerous driving behaviour before incidents occur is a critical but underexplored challenge. This paper addresses this gap using connected vehicle telemetry data from Greater Sydney, Australia, to detect and forecast near-miss risky driving events at the Local Government Area (LGA) level. Risky driving is quantified through g-force thresholds (hard braking >0.6g, harsh cornering >0.47g, harsh acceleration >0.5g), and spatio-temporal heatmaps are constructed to identify high-risk zones. Eight predictive models are benchmarked across three families: ensemble learning (Random Forests, XGBoost, LightGBM), deep learning (LSTM, N-BEATS), and classical time-series methods (ARIMA, Exponential Smoothing, Prophet). ARIMA achieves the lowest mean absolute error (MAE: 162.21), performing comparably to LSTM (MAE: 163.92) and outperforming all ensemble methods, with N-BEATS reaching an MAE of 180.75. These results demonstrate that parsimonious time-series models are competitive with deep learning approaches when training data volume is limited. The study highlights the potential of IoT-based connected vehicle data to support proactive road safety interventions, with Sydney's inner and western LGAs (CBD, Parramatta, Bankstown) identified as persistent high-risk zones warranting targeted policy action.

AI 总结：该研究针对现有多任务学习方法容量变化受限的问题，提出优化驱动的EMAN框架，通过潜在相对相位实现路径涌现，在多数据集实验中以竞争力的计算成本提升了性能。

链接：https://arxiv.org/abs/2608.16930

作者：Chenlei Fang, Jingchen Li, Hongzong LI, Qingyao Li, Yixuan Zhang, Huarui Wu, Haobin Shi, Chunjiang Zhao

英文摘要：Existing multi-task learning methods rely on hard sharing, multiple paths or experts, adaptive sharing, and dynamic expansion. However, their capacity changes are usually constrained by predefined structures or triggered by task boundaries and conflict signals. This raises a fundamental question: can a network start from exact single-path computation and grow a new independent path only when persistent optimization evidence appears? We propose the Emergent Modular Atomic Network (EMAN), an optimization-driven framework for exposing an antisymmetric growth direction through latent relative phases without instantiating a second path, and for monitoring multiple decision signals during training to transform local optimization evidence into a structural decision. EMAN materializes two equal-capacity independent paths only after certification. EMAN adaptively allocates shared and task-specific representation capacity to accommodate varying task requirements. Extensive experiments on controlled rank settings, PASCAL-Context, and NYUv2 validate its effectiveness, achieving improved performance at a competitive computational cost.

AI 总结：本研究针对多层知识编辑方法存在的传播衰减问题，提出无锚点的DOW-KE方法，联合优化所有编辑层权重更新，在多数模型-数据集设置中取得最优性能。

链接：https://arxiv.org/abs/2608.16932

作者：Ran Chen, Junbo Zhang, Qianli Zhou, Xinyang Deng, Wen Jiang

英文摘要：Multi-layer locate-then-edit methods for knowledge editing first optimize target residual-stream activations (anchors) at selected layers, then realize them layer by layer as weight updates. This pipeline optimizes an intermediate representation but deploys multi-layer weight updates whose joint effect through the true forward pass is never itself optimized: regardless of how anchors are set or propagated, each update comes from a local solve, so propagation-induced attenuation and distortion go uncorrected, leaving a closure gap between anchor targets and realized edits. We propose DOW-KE, an anchor-free method built on a single principle: what is optimized must be exactly what is deployed. DOW-KE backpropagates the final editing objective through the complete model, jointly optimizing the updates of all edited layers so cross-layer propagation and coupling enter every gradient step. The same principle dictates where preservation resides: embedding the preservation projection in the update parameterization, inside the computation graph, makes every gradient act on the deployed update; post-hoc constraints would reopen the gap, and the constrained search keeps edits clear of protected knowledge. In large-scale sequential editing on two datasets and three models, DOW-KE achieves the highest overall Score and neighborhood Specificity in five of six model-dataset settings among the evaluated baselines.

AI 总结：该研究基于EdNet-KT3数据聚类出8种学习策略簇，发现其可预测学习者后期参与度但与知识掌握程度关联微弱，说明聚类追踪的是参与度而非掌握程度。

链接：https://arxiv.org/abs/2608.16963

作者：Qingchuan Lyu, Yingxin Li, Albert Yang

英文摘要： Learning analytics often treats unsupervised clusters of intelligent tutoring system (ITS) logs as learner types that should predict learning. We test that assumption on EdNet-KT3. Clustering study-strategy features (resource use, revision, video, problem practice) for 5{,}000 active learners yields a silhouette-selected parent cut ($k=5$) with 4 contrast poles (reading-focused, video-heavy, revision-heavy, and problem-first) plus a large near-mean residual ($\sim$64.9\%). Reclustering that residual adds four finer styles, giving a bootstrap-stable hierarchy of 8 named strategies. We split each learner's timeline by respond count so clusters use only the early half and outcomes only the late half. Early clusters predict later engagement (continuing to practice and finishing late sessions, especially persistence, $\eta^{2}\approx 0.106$; completion $\eta^{2}\approx 0.021$) but not later unassisted accuracy (correctness on late first-attempts without help; $p_{\mathrm{adj}}\approx 0.093$). Volume rises with some styles, yet volume-only clustering barely matches strategy labels (ARI$=0.064$). A knowledge-tracing model (SAKT) on the seven TOEIC exam sections predicts next correctness only modestly better than a baseline that knows only how hard each section usually is (AUC lift $+0.051$; CI $[+0.045,+0.058]$), and that mastery signal is nearly independent of behavior styles (ARI$=0.007$). Behavioral clustering here describes study styles and engagement, not knowledge gains.

AI 总结：针对类别不平衡与噪声数据问题，提出RoBell-RVFL模型，采用双策略样本级加权机制，在UCI、KEEL数据集及40%标签噪声下表现优于现有RVFL变体。

链接：https://arxiv.org/abs/2608.16965

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

作者：A. Rahaman, A. Quadir, M. Tanveer

英文摘要：The dominance of majority classes in real-world datasets poses a fundamental challenge to randomized neural networks, often biasing decision boundaries and overlooking critical minority samples. Existing remedies, such as synthetic minority over-sampling (SMOTE) and class-weighted loss functions, primarily address class proportions while neglecting intra-class distribution, making them vulnerable to label noise and outliers. In this paper, we propose \textbf{RoBell-RVFL}, a robust and lightweight \emph{quality-aware} generalized bell random vector functional link network that redefines how randomized models handle class imbalance and noisy data. RoBell-RVFL employs a dual-strategy, sample-level weighting mechanism that strictly preserves minority class information using unit weights, while adaptively regulating the influence of majority class samples through a probability-weighted generalized bell (gbell) membership function in a kernel-induced feature space. This design effectively suppresses noisy, boundary, and outlier samples within the majority class, enabling the network to learn from informative samples rather than merely abundant ones. By explicitly incorporating local class probability and class distribution information into the learning process, RoBell-RVFL achieves adaptive control over sample contributions without sacrificing the closed-form learning efficiency of RVFL networks. Extensive evaluations on UCI and KEEL benchmark datasets, along with robustness tests under up to 40\% label noise, demonstrate that RoBell-RVFL consistently and significantly outperforms recent state-of-the-art RVFL variants. The results indicate that adaptive, quality-aware sample weighting is essential for robust RVFL learning, rendering conventional global weighting schemes ineffective in noisy and imbalanced environments.

AI 总结：本文指出生成式模型的公平性失效源于评估问题，提出Fairness Cards工具明确评估选择以提升公平性评估的可复现性与可比性，推动评估标准的范式转变。

链接：https://arxiv.org/abs/2608.16974

机构：Criteo AI Lab（Criteo人工智能实验室）； FairPlay joint team（FairPlay联合团队）

作者：Mariia Vladimirova, Jean-Yves Franceschi, Thibaut Issenhuth

英文摘要：Despite groundbreaking advancements in generative models during the last decade, concerns about their lack of fairness, reinforcing societal inequalities and harming marginalized groups, remain under-addressed and difficult to act upon. This position paper argues that fairness failures in generative models, albeit driven by multiple factors, are ultimately stemming from an evaluation problem: fairness findings are rarely comparable across papers or actionable for deployment decisions. This paper diagnoses recurring empirical and conceptual failure modes in current practice and motivates a shift from ad-hoc bias checks to standardized, generative-specific evaluation. We propose Fairness Cards as a minimal reporting artifact that makes evaluation choices explicit (prompt families, counterfactual protocols, metrics, and refusal handling) enabling reproducibility, comparability, and accountability. We conclude with additional recommendations towards a paradigm shift in evaluation standards. Our project page can be found at this https URL.

AI 总结：J-Miner可从微调后的语言模型分类器中挖掘隐含的决策知识，生成可执行规则，规则复现源分类器决策精度高、保真度优，还能迁移至轻量级模型并保留高准确率。

链接：https://arxiv.org/abs/2608.17063

机构：Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University（同济大学上海智能自主系统研究院）； Shanghai Key Laboratory of Data Science, College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机与人工智能学院上海市数据科学重点实验室）； Meituan（美团）； College of Design and Innovation, Tongji University（同济大学设计创意学院）

作者：Yunfan Gao, Xinyi Huang, Tao Sheng, Haorui Song, Yun Xiong, Haofen Wang

英文摘要： Large language models can be fine-tuned into specialized classifiers that perform well across diverse text tasks and make complex judgments, but they typically expose only final labels, leaving the decision knowledge acquired through fine-tuning implicit within the model. We study how to mine this internal decision knowledge from a fine-tuned classifier and encode it in an executable representation that can be inspected, validated, and reused beyond the source classifier. We introduce J-Miner, which mines text-level named concepts by aggregating vocabulary-aligned internal signals across layers and token positions, and uses the classifier's own predictions to learn executable decision rules over them. This process distills local internal readouts into an explicit classifier-level knowledge representation. Across multiple classification tasks, J-Miner rules reproduce up to 98.3\% of source-classifier decisions and achieve 6.0--29.5 percentage points higher behavioral fidelity than equally compact rules learned from input words. Further analysis shows that the named concepts reflect internal semantic evidence associated with task decisions, while the learned rules consolidate these distributed signals into inspectable decision structures. The resulting decision knowledge also transfers to lightweight standalone students: using about 1/24 as many parameters as the source classifiers, they reconstruct and execute the representation from raw text while retaining 99.8\% of the source classifiers' mean task accuracy. These findings show that task-specific decision knowledge can be faithfully represented in an explicit, executable form and reused beyond the classifier in which it was learned.

AI 总结：提出基于零知识证明的PANDA系统，可在不泄露神经网络私有参数的情况下高效证明其鲁棒性与公平性，支持参数超290万的网络，规模远超同类方案且开销更低。

链接：https://arxiv.org/abs/2608.17070

机构：Yale University（耶鲁大学）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

作者：Youwei Zhong, Ben Merbaum, Timos Antonopoulos, Ning Luo, Charalampos Papamanthou, Katerina Sotiraki, Ruzica Piskac

英文摘要：With the growing deployment of machine learning models, formal guarantees of the robustness and fairness of these models have become increasingly important in safety-critical and legal-compliance settings. However, model parameters are often commercial secrets that cannot be disclosed to auditors or end users. To this end, we present PANDA, a scalable system that uses zero-knowledge proofs (ZKPs) to prove the robustness and fairness properties of a model without revealing its private parameters. PANDA is built on top of CROWN, an efficient robustness certification framework that is used in many state-of-the-art formal verification tools for neural networks. The core contribution of PANDA is a novel algorithm for proving linear relaxation bounds for non-linear activation layers, yielding simple, lightweight proofs. Remarkably, our system can generate proofs of local robustness for neural networks with more than 2.9M parameters in 5 minutes, and can verify them in 10 seconds. Prior ZKP-based robustness system rely on exponential-time algorithms that cannot scale to nontrivial networks. In contrast, PANDA scales polynomially in the number of neurons in a network, allowing us to support neural networks 4 orders of magnitude larger than previous approaches with significantly reduced prover overhead.

AI 总结：针对线性时序逻辑可微语义的浅层嵌入困境，提出代数通用且支持求导的评估引擎，实现多种代数并审计其行为，成果属于PyTorch库telos。

链接：https://arxiv.org/abs/2608.17087

作者：Konstantinos Kogkalidis

英文摘要：Linear temporal logic is a modal extension of propositional logic that allows one to state how a system should behave over time. Its canonical domain is the booleans, but discretely-valued judgements are of little use in steering softly-valued systems (neural policies, adaptive controllers, sequence models, etc). In such cases, the goal formula's (dis)satisfaction becomes a training signal, and differentiability becomes a prime concern. Candidate differentiable semantics abound, but navigating them is tricky. Implementations, where available, are shallow embeddings, demanding an upfront commitment to a single semantic algebra and its (usually implicit) conduct. The paper casts the reader as a functional programmer asked to come to terms with this predicament, and refusing. Out of that refusal comes an evaluation engine that is algebra-generic and amenable to differentiation, together with an executable specification of the algebras it can accept. Various algebras are implemented and audited for their behavior, both forward and backward. Each algebra turns out to be a choice of which direction to disappoint, and how. Everything described (and more) is part of the PyTorch library telos, to be found at this https URL.

AI 总结：本文提出迭代张量网络变换（ITNTs）框架，可在压缩域中对张量列编码的数据执行初等与滤波函数的逐元素评估，能高效处理大规模数据，在三维流场计算与Max-SAT问题求解中展现出应用价值。

链接：https://arxiv.org/abs/2608.17135

机构：Clarendon Laboratory, University of Oxford（牛津大学克拉伦登实验室）； The Hamburg Centre for Ultrafast Imaging（汉堡超快成像中心）； Institute for Quantum Physics, University of Hamburg（汉堡大学量子物理研究所）； Institute of Software Methods for Product Virtualization, German Aerospace Center (DLR)（德国航空航天中心产品虚拟化软件方法研究所）

作者：Xiao Wang, Tomohiro Hashizume, Pia Siegl, Dieter Jaksch

英文摘要：Tensor networks are powerful formats for compressing large-scale data. However, their application to general data processing has been limited by the difficulty of performing nonlinear operations. Here, we introduce iterative tensor network transformations (ITNTs), a general algorithmic framework for the element-wise evaluation of elementary and nonlinear filtering functions on data encoded as tensor trains (TTs), a class of tensor networks. Our approach operates entirely in the compressed domain, enabling efficient computation on exponentially large datasets while maintaining a controlled computational cost. We demonstrate its power in two key areas: (I) evaluating highly nonlinear elementary and filtering functions on a 3D reactive flow field, enabling high-fidelity reaction rate computation and region filtering, and (II) finding extrema in complex optimization problems, such as solving Max-SAT instances on spaces up to $2^{70}$ configurations. These results establish ITNT as a foundational tool that provides tensor network methods with the capability for general-purpose data science and large-scale optimization.

AI 总结：本研究结合大规模人群健康调查数据与定制堆叠集成机器学习模型，识别出定期体检、年龄等CKD关键预测因子，为CKD风险分层提供了可解释框架。

链接：https://arxiv.org/abs/2608.17174

作者：Md. Atik Shams, David Eisenberg, Sumaiya Fatema, Asma Sultana, D. M Hasibul Islam, Junnatul Mawa, Anindita Datta, Nafiya Ahmed, Danastan Tasaouf Mridula, SK. Sazid Mahmud, Simon Bin Akter, Tanjila Helaly, Jorge Fresneda Fernandez, Humayera Islam, Tanmoy Sarkar Pias

英文摘要：Chronic kidney disease (CKD) progresses silently and severely undermines quality of life, making early detection critical for improving patient outcomes. We present a two-part study that combines large-scale telehealth data with advanced machine learning to both classify self-reported CKD status and identify key drivers of disease. Using selected features from the Behavioral Risk Factor Surveillance System (BRFSS 2021: 438,693 samples; BRFSS 2019: 418,268 samples) and the National Health Interview Survey (NHIS 2021: 29,482 samples; NHIS 2020: 31,568 samples), we addressed missing data with nine state-of-the-art imputation methods and mitigated class imbalance via sampling strategies. Our customized stacked ensemble model achieved balanced accuracy of 72.56-76.12%, with corresponding AUROC scores of 79.59-82.29%. SHapley Additive exPlanations (SHAP) analysis, followed by clinical review, highlighted critical predictors, including regular medical check-ups, age, blood pressure, and indicators of mental health stress. These findings deliver a robust and interpretable framework for CKD risk stratification and provide actionable insights into its associated factors.

AI 总结：本研究针对t-SNE的亲和矩阵，提出逐行幂变换方法，发现锐化可提升最近邻保持、平滑可提升中局部邻域保持，为优化t-SNE邻域保持提供了新视角。

链接：https://arxiv.org/abs/2608.17190

机构：Ghent University（根特大学）

作者：Shirin Mohebi, Guillaume Bied, Jefrey Lijffijt

英文摘要：Dimensionality reduction methods are instrumental to visualize high-dimensional data, and t-SNE stands as one of the most widely used methods due to its emphasis on local neighborhood preservation. A central component of t-SNE is the affinity matrix, which expresses pairwise similarities in the form of symmetrized probabilities, over which the optimization problem of t-SNE is defined. We study how the sharpness of this probability distribution affects neighborhood preservation at different scales. We introduce a row-wise power transform controlled by a parameter gamma that can smooth or sharpen each row of the affinity matrix while preserving sparsity and rank order. We show that this transform is equivalent to rescaling the Gaussian bandwidth and thus to changing the perplexity. However, as the sharpness of the probability distribution varies per point, a fixed gamma leads to point-dependent effective perplexities, making it distinct from changing the global perplexity. Empirically, we find that sharpening improves preservation of the very nearest neighbors, while smoothing improves preservation of broader local neighborhoods, outperforming alternative affinity constructions including multiscale methods in the mid-local range.

AI 总结：该研究针对熔融沉积建模零件的结合质量与孔隙率预测问题，提出三类物理信息混合机器学习策略并探索其八种组合，验证了多策略组合在有限实验数据下可构建准确的物理一致性预测模型。

链接：https://arxiv.org/abs/2608.17246

机构：Vanderbilt University（范德堡大学）

作者：Berkcan Kapusuzoglu, Sankaran Mahadevan

英文摘要：This article investigates several physics-informed and hybrid machine learning strategies that incorporate physics knowledge in experimental data-driven deep-learning models for predicting the bond quality and porosity of fused filament fabrication (FFF) parts. Three types of strategies are explored to incorporate physics constraints and multi-physics FFF simulation results into a deep neural network (DNN), thus ensuring consistency with physical laws: (1) incorporate physics constraints within the loss function of the DNN, (2) use physics model outputs as additional inputs to the DNN model, and (3) pre-train a DNN model with physics model input-output and then update it with experimental data. These strategies help to enforce a physically consistent relationship between bond quality and tensile strength, thus making porosity predictions physically meaningful. Eight different combinations of the above strategies are investigated. The results show how the combination of multiple strategies produces accurate machine learning models even with limited experimental data.

AI 总结：本文通过分析不同课程调度的优化动力学，提出衡量跨难度知识迁移的Relative Transfer指标，据此推导TDCS方法，经多推理基准实验证明其性能优于代表性调度策略，为课程学习提供统一优化解释。

链接：https://arxiv.org/abs/2608.17268

机构：Fudan University（复旦大学）

作者：Zhikai Ding, Ziyi Ye

英文摘要： Curriculum learning has been widely adopted in the post-training of large language models by organizing training data from easy to hard. However, its effectiveness varies substantially across reasoning tasks, suggesting that no single curriculum is universally optimal and raising a fundamental question: what determines when curriculum learning works? In this paper, we answer this question by analyzing the optimization dynamics induced by different curriculum schedules. We show that the transfer relationship between different difficulty levels characterizes the optimization dynamics induced by curriculum learning, which in turn explains the effectiveness of different curriculum schedules, and formalize this relationship as Relative Transfer, a principled measure of cross-difficulty knowledge transfer. Based on this measurement, we derive Transfer-aware Dynamic Curriculum Sampling (TDCS), which dynamically adjusts the sampling distribution according to the estimated transfer relationship throughout training. Extensive experiments on multiple reasoning benchmarks demonstrate that TDCS consistently outperforms representative scheduling strategies across different tasks, model scales, and training paradigms. More importantly, our work provides a unified optimization-based explanation of curriculum learning through cross-difficulty transfer.

AI 总结：CORAM通过将目标矩阵划分为行切片并在流形上合并任务因子，结合放大系数、扩散切片与残差通路，在多套件中较OrthoMerge提升0.25-1.35点，性能匹配或超越最强权重空间基线。

链接：https://arxiv.org/abs/2608.17366

作者：Xinyi Sui, Ziran Liu, Nam Ling, Wei Wang, Wei Jiang

英文摘要：Merging finetuned models combines specialized capabilities without joint training or access to the original data. Most methods operate by linear arithmetic in Euclidean weight space, which cannot carry the geometry of the update. Orthogonal Model Merging (OrthoMerge) uses a single orthogonal transform for each weight matrix, but such a transform cannot change singular values. We propose CORAM, which partitions each target matrix into row slices, represents every expert slice by its singular value decomposition in the corresponding base-model SVD frame, and merges the task-specific factors on their corresponding manifolds. Because manifold averaging contracts the merged update, CORAM applies an amplification coefficient $\lambda=\kappa\hat{c}$. The scale c_hat is estimated from the expert and merged update norms and is approximately $\sqrt{N}$ for $N$ experts with comparable update magnitudes. The restoration strength kappa is selected from the dispersion of expert updates without evaluating candidate merged models. This rule remains within 0.72 points of the best swept value on all evaluated suites. CORAM also includes spread slicing to distribute highly updated rows across slices and a residual pathway for non-target layers. Across four suites covering three model families, 3B to 9B scales, and language and vision-language experts, CORAM improves over OrthoMerge by 0.25 to 1.35 points and matches or exceeds the strongest weight-space baselines.

AI 总结：针对GRPO中组梯度冲突导致策略更新效果差的问题，提出GUPO方法，通过贝叶斯框架建模组梯度并结合狄利克雷公式校准梯度贡献，经多基准实验验证其有效性。

链接：https://arxiv.org/abs/2608.17411

作者：Peizheng Guo, Jianqi Zhang, Xingyu Zhang, Yun Fan, Jiahuan Zhou, Changwen Zheng, Wenwen Qiang

英文摘要：Group Relative Policy Optimization (GRPO) has become a widely used approach for post-training Large Language Models (LLMs) for reasoning. In GRPO, the group gradients induced by different queries within the same mini-batch are directly averaged to form the policy update. However, these group gradients can point in conflicting directions. Our empirical analysis suggests that group-gradient conflicts tend to be associated with less effective policy updates, motivating the need for a reliable aggregated update direction under such conflicts. Standard GRPO aggregation treats the realized group gradients as deterministic contributions and does not account for differences in their reliability during aggregation. To address this issue, we propose Gradient Uncertainty-Aware Policy Optimization (GUPO), which models each group gradient as a random variable under a Bayesian formulation and estimates its probability distribution. GUPO then derives gradient uncertainty using a Dirichlet-based formulation and uses it to calibrate the contribution of each group gradient during aggregation. Extensive experiments on multiple benchmarks demonstrate the effectiveness of GUPO.

AI 总结：该研究提出AC-MTM，用对比逆动力学替代JEPA世界模型的高斯型抗坍塌机制，在多目标视觉任务上性能优于SIGReg，且训练稳定无额外复杂组件

链接：https://arxiv.org/abs/2608.17542

机构：Quantexa（昆泰克萨公司）

作者：Jack Boylan, Chris Hokamp

英文摘要：Joint-Embedding Predictive Architectures (JEPAs) learn world models by predicting future embeddings, but the objective admits a trivial solution of a constant encoder, so every practical system adds an anti-collapse mechanism (LeCun, 2022; Assran et al., 2023; Bardes et al., 2022; 2024). LeWorldModel (LeWM) prevents collapse with SIGReg, a regularizer that forces the latent distribution to match an isotropic Gaussian: the representation is stabilized by prescribing what it must look like, independently of the environment it models. We argue that the anti-collapse pressure can instead come from the transition data itself. Action-Contrastive Masked Transition Modeling (AC-MTM) keeps LeWM's forward latent-prediction objective and adds a training-only inverse-dynamics head trained with Action-NCE: each latent transition must identify the action that produced it among the other actions in the batch, a discrimination task that a collapsed encoder provably fails. The inverse branch is discarded after training, leaving test-time encoding, forward prediction, planning, and compute identical to LeWM. On four standard pixel-control tasks under a matched planning protocol, AC-MTM trains stably from scratch and matches SIGReg on average. On the harder multi-object OGBench Visual Scene task, results are consistent with the prescribed geometry becoming a bottleneck: AC-MTM reaches 80.0$\pm$2.0% success versus 58.0$\pm$2.0% for SIGReg, improving by 20-24 points in each training seed. A single 50-episode random-policy run gives a 52% baseline estimate. Contrastive inverse dynamics thus provides a distribution-free anti-collapse signal that requires no target network, stop-gradient, pretrained encoder, or reconstruction objective, and we characterize the action-space and observability assumptions under which it holds. We make our code available at this https URL

AI 总结：本专著提出消元几何（EG）框架，用于研究局部最优对象的共享部署规则实现问题，整合多学科工具，其应用涵盖模型选择、预测等领域，可指导架构修复。

链接：https://arxiv.org/abs/2608.17646

作者：Mian Huang, Xueqin Wang

英文摘要：This monograph develops elimination geometry (EG), a typed, native-loss, audit-oriented framework for studying when locally optimal objects can be realized by a shared deployment rule. Elimination and compression may erase distinctions required by prediction, inference, control, or representation. EG asks which distinctions are lost, whether the induced defect is visible to the declared task, and whether changing information, architecture, action space, or deployment domain can repair it. EG separates local solvability, global realizability, and finite-sample certifiability. It derives native defects from the original objective and distinguishes architecture obstruction from model approximation, generalization, and implementation error. The monograph synthesizes tools from geometry, optimization, information theory, statistics, and machine learning into interfaces for integrability, representation admissibility, resource constraints, observational overlap, and common deployment. Formal results address regular, coordination, singular, compositional, and resource-limited mechanisms with explicit antecedents and claim boundaries. Applications include sparse model selection, distribution-free prediction, observational treatment policies, routed expert and retrieval systems, and learned score fields. Obstruction-Aware Learning and Inference links structural diagnosis to finite-data authorization, mechanism-matched intervention, and independent validation. Reproducible synthetic and real-data studies illustrate how certificates can guide architecture repair while recording failed gates and unresolved cases. The framework requires the deployment contract, native endpoint, competing explanations, information and compute budgets, and validation rule to be fixed before a persistent performance floor is attributed to architecture.

AI 总结：该研究指出跨视图对应是测量干预，开发含双面验证等的有效性理论，发现对应分歧会影响智能体评估，需声明验证跨视图对应以支持可靠结论。

链接：https://arxiv.org/abs/2608.17713

机构：School of Computation, Information and Technology（计算、信息与技术学院）； Technical University of Munich（慕尼黑工业大学）

作者：Zhen Zhang, Ahmad Hafez, Amr Alanwar

英文摘要：Agent evaluations and trace-based learning often compare outputs across transformed views through a post-response correspondence treated as neutral preprocessing. We show that this correspondence is a measurement intervention: omitting it can manufacture sensitivity, an over-aggressive map can manufacture invariance, and multiple optimal correspondences can leave mechanism labels and signed learning credit unidentified. We develop a validity theory and audit with three components: two-sided validation of nuisance removal and response preservation, all-optima identification of downstream conclusions, and uncertainty propagation after validity is established. We characterize the linear feasibility boundary for response-preserving nuisance removal, compute sharp ranges over exact-optimum correspondence sets, and give a distribution-free certificate that retains a credit coordinate only when all exact optima agree on its nonzero sign. Across public code and SQL pipelines, two deterministic optimal tracebacks disagree on temporal localization for 55.9% of 1,586 nonzero trajectory pairs; two frozen 800-rollout tool-use audits, including a task-and-seed-disjoint replication, expose exact-optimum reversals of intended turn-level credit, although a clean public quick-start subset shows none. A pre-registered transport gate failed on natural responses; frozen corrected and held-out controls then show that a map calibrated only on benign examples erases every retained harmful response, while two-sided validation selects response-preserving alternatives. Cross-view correspondence must therefore be declared, validated, and propagated into uncertainty before agent evaluation or credit assignment supports a point conclusion.

AI 总结：本文提出MAGPIE-Net，通过嵌入地理自适应可微格点到站点映射模块，基于FY-4A AGRI观测数据预测站点邻域短时强降雨，在2023年华东华中暖季测试中，其检测率与提前时长均显著优于格点输出基线模型。

链接：https://arxiv.org/abs/2608.17753

机构：College of Meteorology and Oceanography, National University of Defense Technology（国防科技大学气象海洋学院）； Key Laboratory of High Impact Weather (Special), China Meteorological Administration（中国气象局高影响天气重点实验室（专项））； Hunan Key Laboratory of Meteorological Disaster Prevention and Reduction（湖南省气象灾害防御与减重点实验室）； Institute of Meteorological Science of Hunan Province（湖南省气象科学研究所）

作者：Xiang Lin, Yunying Li, Chengzhi Ye, Zitong Chen, Jing Sun

英文摘要：Short-duration heavy-rainfall warning determines whether 1 h rainfall will exceed a threshold within a target-station neighborhood over the next few hours. Multitemporal infrared and water-vapor observations from the Fengyun-4A Advanced Geostationary Radiation Imager (FY-4A AGRI) capture cloud-top cooling, moisture evolution, and cloud expansion before substantial surface rainfall develops. However, most deep-learning nowcasting methods convert these signals into local warnings by post-processing gridded precipitation predictions, preventing station-neighborhood event targets from directly supervising the satellite-to-station learning pathway. We propose MAGPIE-Net, which embeds a geographically adaptive, differentiable grid-to-station mapping in a pathway combining convection-initiation features, multiscale encoding, and auxiliary gridded precipitation diagnosis. Station-neighborhood event losses thereby constrain the satellite representation and its mapping to irregular station locations for 0-3 h event prediction. In independent 2023 warm-season tests over central and eastern China, critical success index (CSI) values under the primary 40 km/20 mm h-1 definition were 0.371, 0.304, and 0.238 at 0-1, 1-2, and 2-3 h. Across episodes, MAGPIE-Net achieved a detection rate of 65.1% and a mean lead time of 64.6 min, compared with 23.6% and 18.3 min for the best gridded-output baseline, and remained superior for smaller neighborhoods and the 50 mm h-1 threshold. During the critical early-warning stage, when antecedent 1 h rainfall within 40 km remained below 1 mm, MAGPIE-Net detected 51.9% of episodes with a mean lead time of 38.5 min. These results show that event-oriented satellite-to-station modeling converts multitemporal geostationary cloud and moisture observations into local heavy-rainfall warnings more effectively than gridded-precipitation modeling.

AI 总结：该论文研究拉德马赫和的四阶矩几何，结合矩包络与凸性阈值论证得到高斯稳定性不等式，解决相关猜想并证明p=3时的二次稳定性估计，所得边界可应用于拉德马赫随机投影等领域。

链接：https://arxiv.org/abs/2608.17802

机构：The University of Hong Kong（香港大学）

作者：Peigan Gao, Jian Qian

英文摘要：Let $\varepsilon_1,\ldots,\varepsilon_n$ be independent Rademacher signs and let $a=(a_1,\ldots,a_n)\in\R^n$ satisfy the normalization below. For the normalized Rademacher sum, we determine how its higher moments depend on the fourth-order mass. Combining a sharp fixed-q moment envelope with a separate argument below the convexity threshold gives the Gaussian stability inequality for the full range $p\geq4$ of this linear-in-q bound. The same fourth-order framework determines the sharp finite dimensional $L_p/L_4$ Khintchine constant for $p\geq5$, with the flat coefficient vector as the extremizer. These results settle the conjectures of Jakimiuk and of Barański, Murawski, Nayar, and Oleszkiewicz stated below. We also prove Jakimiuk's conjectured quadratic stability estimate at $p=3$. The resulting bounds retain information about sparsity and effective dimension, with applications to Rademacher random projections and randomly signed errors; those applications are not developed further here. Their Laplace-transform form also gives coefficient-sensitive tail bounds. The proofs are discovered with substantial assistance from ChatGPT 5.6 Sol.

AI 总结：该研究针对LLMs，提出结合关联上下文检索的知识编辑白盒攻击，提升攻击有效性且不严重损害模型整体性能。

链接：https://arxiv.org/abs/2608.17836

作者：Roman Maksimov, Vladimir Aletov, Vladimir Solodkin, Dmitry Bylinkin, Daniil Medyakov, Aleksandr Beznosikov

英文摘要：As large language models (LLMs) are granted increasing autonomy, it is essential to investigate methods that can induce unsafe behavior. We propose a novel white-box attack inspired by locate-then-edit approaches from the field of Knowledge Editing. Our choice is motivated by the observation that models edited with such schemes tend to assign unusually high prediction probabilities to the edit target, a property that is particularly advantageous when designing attacks. We modify the editing framework by incorporating as- sociative knowledge retrieved from the model, thereby extending constraint removal to an entire thematic category rather than being limited to prompts from a predefined dataset. Experiments with various archi- tectures demonstrate improved attack effectiveness over competing methods without dealing critical damage to general model performance.

AI 总结：该研究提出动态压缩方法，允许循环模型选择性重访过去标记以修正固定状态，在少样本函数复用任务中，其所需循环状态更小、扩展性更优，实现了计算与内存的有效权衡。

链接：https://arxiv.org/abs/2608.17896

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

作者：Jyothish Pari, Ryan Bahlous-Boldi, Pulkit Agrawal

英文摘要：Recurrent models process long contexts efficiently by compressing their history into a fixed-size state, but modern architectures typically do so in a single causal pass over the sequence. Each input must therefore be compressed before the model knows how it will later be used, forcing a limited state to compromise across possible future demands. We introduce dynamic compression, which allows a recurrent model to selectively revisit past tokens and revise its fixed-size state through additional recurrent updates. The model need not preserve every part of the history at uniformly high fidelity in its recurrent state, because lower-fidelity information can be revisited from the retained raw sequence when it becomes relevant. We study this in a controlled setting where the model first learns multiple functions in-context and, later in the same sequence, encounters a series of few-shot tasks that each require it to identify and reuse one of those functions. A single-pass model must preserve every function at sufficient fidelity for any future task, whereas selective re-scanning allows the model to revisit and refine only the function currently needed. We find that dynamic compression substantially reduces the recurrent state required for accurate reuse and scales more favorably as the number of stored functions grows. These results demonstrate a computation--memory tradeoff in which recurrent models can spend more computation revisiting their history to make more effective use of a fixed-size state.

AI 总结：本研究针对开源IC设计预布线延迟估计难题，提出结合决策树与线性回归的混合轻量级ML方法，其误差较OpenLane降低80%，兼具高准确率、小体积、快速度与高可解释性。

链接：https://arxiv.org/abs/2608.17914

机构：Universidad de Costa Rica（哥斯达黎加大学）

作者：Marvin Castro Castro, Erick Carvajal Barboza

英文摘要： Static Timing Analysis (STA) is a critical step in the design flow of digital integrated circuits, however, obtaining accurate delay estimations can represent a challenge when limited information regarding physical design is available. In response, this work presents a hybrid and light-weight machine learning (ML) based approach that combines a decision tree with linear regression to improve pre-routing delay estimations generated by the open-source RTL-to-GDSII tool OpenLane. The proposed model achieves an 80\% reduction in error compared to OpenLane's estimates, demonstrates a 71\% improvement even without utilizing OpenLane-specific parameters. Overall, this method offers an alternative to traditional delay propagation techniques and more complex machine learning models that is not only accurate, but is also over 300 times smaller, 2 times faster and offers a higher explainability.

AI 总结：针对无元数据场景下LLM-AutoFE的轨迹问题，提出SIGMA框架，利用SHAP值和EXIT方法，降低特征重复率并提升效率，实现与SOTA相当的性能。

链接：https://arxiv.org/abs/2608.17948

机构：Yokohama National University（横滨国立大学）

作者：Xuan Zheng, Kento Uchida, Shinichi Shirakawa

英文摘要：Recent research has leveraged Large Language Models (LLMs) to enhance Automated Feature Engineering (AutoFE) through semantic descriptions and trajectory-based prompting. However, there exist two challenges that limit their applicability and scalability in long-horizon optimization: (1) semantic metadata is unavailable in many practical settings, and (2) trajectory accumulation increases the risk of exceeding the context window, while without it, the generation process can become unstable, leading to becoming stuck in the local optima and a high duplicate rate of generated features. To this end, we propose a SHAP-enhanced Implicit-trajectory Generation for Metadata-free AutoFE (SIGMA), a scalable constant-context optimization framework. SIGMA leverages SHAP values to provide task-aware signals for guiding group feature generation instead of semantic information. In addition, we adopt an EXposed-feature Implicit Trajectory (EXIT) approach, where the exposed features in the prompt implicitly represent the trajectory. Empirical results demonstrate that SIGMA achieves performance comparable to the state-of-the-art (SOTA) LLM baselines with a nearly constant prompt length. Notably, EXIT significantly reduces the duplicate ratio of generated features from 37.2% to 6.8%. At the same time, SIGMA matches traditional SOTA performance with only 5.4 features on average, demonstrating substantial efficiency gains in feature utilization.

AI 总结：该研究揭示连续代码世界模型中采样-验证机制的危险，通过理论分析与实验发现，LLM合成的模式盲模型易被利用，接受仅能证明样本一致性，无法保证连续控制任务的性能。

链接：https://arxiv.org/abs/2608.17956

机构：AGILabs

作者：Javier Aguilar Martín

英文摘要：In the Code World Model paradigm an LLM synthesizes an executable world model that a classical planner searches, and the model is accepted when it reproduces sampled transitions. We ask what that acceptance certifies in continuous control. We define the pipeline's danger as an expected risk and isolate its exact factor: the probability that N i.i.d. gate rollouts all miss a critical event of probability r is exactly (1-r)^N; an independent acceptance sample adds its budget to the exponent. On three hybrid instruments the accepted mode-blind model is exploited: the planner is pinned at the mode boundary at a regret of nearly the whole attainable return. We prove a localization budget, valid at boundary points: models with Lipschitz constant at most L differing by eta at a point disagree above tolerance eps on a region of volume at least kappa((eta-eps)/L)^(d+m); the discontinuous reset modes studied pay no such budget. With real LLM synthesis, GPT-5.x repairs an omitted 1D clamp in 105 of 111 mode-containing draws -- every attempt exact on 50 of 56 instrument-stream blocks (95% CI [0.781, 0.960]). On 2D regions no artifact recovers the rule (0/156); eight targeted interventions leave the failure in place, and positive controls locate it: a located rule is not induced, while given form and location the constants follow exactly. A version-space certificate proves identification is class-relative: at the widest dose the declared fit succeeds in 20/20 blocks and every sample-consistent circle is within tolerance in 18/20. We prove a class of entry rules exactly consistent with every sample yet harmless at play, so identifiability is a measurable property of the instrument. Re-scoring all 1034 artifacts on independent samples confirms acceptance certifies sample consistency and no more: where the gate is provably informative it covers about two percent of the exploited planner's queries.

AI 总结：该研究揭示仅在单个真实表格上预训练的TFMs有强迁移性，提出以任务为中心、基于检索的新视角，为TFMs的模型与语料库设计提供了新框架。

链接：https://arxiv.org/abs/2608.17957

机构：Polytechnique Montréal（蒙特利尔理工学院）； Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）； Chandar Research Lab（钱达尔研究实验室）； University of Toronto（多伦多大学）； Layer 6 AI（第六层人工智能公司）； Prior Labs（普里奥实验室）； ELLIS Institute Tübingen（埃利斯研究所图宾根分部）； University of Freiburg（弗赖堡大学）； Cohere（科here公司）

作者：Nour Shaheen, Junwei Ma, Alex Labach, Frank Hutter, Valentin Thomas, Anthony L. Caterini

英文摘要： Tabular Foundation Models (TFMs) increasingly rely on in-context learning, where a model receives labelled examples at inference time and predicts labels for new inputs without updating its weights. Existing TFMs are typically trained on either massive synthetic corpora or very large collections of real datasets. In contrast, we show that surprisingly strong transfer can emerge from self-supervised pre-training on just a single real table. In this setting, we also find that tables tend to be either broadly useful or broadly poor regardless of downstream prediction task, and that the strongest predictor of usefulness is the number of features rather than the number of instances. This leads to a task-centric interpretation of tabular pre-training: the number and the quality of tasks are essential for the pre-training of TFMs. We show that the same task-centric perspective can help corpus design at scale: fine-grained column-level pre-processing consistently improves downstream performance, while no improvements are observed when we filter or deduplicate at the dataset level. Finally, we offer a new perspective for how TFMs generalize: we believe that tabular in-context generalization is largely retrieval-based, and good models are those that learn to identify relevant examples in the provided context and aggregate them well. The mechanics of TFMs have been relatively understudied; our task-centric, retrieval-based perspective offers a new framework to guide future model and corpus design.

AI 总结：该研究提出推理时架构增强技术“再循环”及其自适应变体，无需额外训练，可显著降低Gemma3系列模型的困惑度、提升推理任务准确率，为架构演进提供新方向。

链接：https://arxiv.org/abs/2608.17981

机构：Google DeepMind（谷歌DeepMind）； University of Texas, Austin（德克萨斯大学奥斯汀分校）

作者：Michael C. Mozer, Shoaib Ahmed Siddiqui, Danny Sawyer, Sunny Sanyal, Rosanne Liu

英文摘要：We describe an inference-time architectural enhancement for off-the-shelf foundation models that markedly reduces perplexity and boosts accuracy across generation and reasoning tasks. Our approach incurs essentially no additional latency during generation, though it requires serial processing in the prefill phase. Motivated by the fundamental limitation that state updates in feedforward transformers are bounded by model depth, our technique, recirculation, introduces a specific form of recurrence that allows the model to act as a dynamical system and track belief states. We distinguish this technique from chain-of-thought computation---which is better reserved for complex inferences rather than basic state tracking---as well as from popular depth-recurrence techniques (looping) and the costly training of recurrent transformers. We also propose and evaluate an adaptive variant of recirculation which requires only light tuning of hyperparameters while freezing the original model weights. Relative to the off-the-shelf baseline, adaptive recirculation achieves remarkable gains on the Gemma3 family, including a 23% reduction in perplexity on a suite of datasets, a 21% increase in accuracy on GSM8k, and reliable improvements in accuracy on other downstream tasks. Our training-free approach succeeds by leveraging the model itself to inform architectural modifications, suggesting a route to architectural evolution guided by a trained network's properties rather than forced, arbitrary design choices.

AI 总结：本研究复现了WEASEL 2.0，分析其四项设计选择的敏感性，发现最大集成规模规则对长序列数据集配置过度，提出自适应规则后可减少内存和时间消耗且准确率影响极小。

链接：https://arxiv.org/abs/2608.18021

机构：University College Dublin（都柏林大学学院）

作者：Cian Higgins, Gerard Carrigan, Pinar Sungu Isiacik, Georgiana Ifrim

英文摘要：WEASEL 2.0 is a dictionary-based time series classifier that combines dilated sliding windows with a randomised hyperparameter ensemble and a fixed-size dense feature representation. Two of its hyperparameter choices, the maximum ensemble size and the maximum window size, are specified by simple thresholding rules whose chosen thresholds are not empirically justified in the original paper. In this work we reproduce WEASEL 2.0 on 114 UCR datasets, achieving a mean accuracy of 0.865 and median of 0.928, closely matching the published values (Wilcoxon signed-rank, p = 0.655). We then test the sensitivity of four design choices: the downstream classifier, the absence of feature weighting, the maximum window-size rule, and the maximum ensemble-size rule. The first three are robust to perturbation. The fourth is over-provisioned for long-series datasets, motivating an adaptive rule that sets the maximum ensemble size from series length and number of classes. Evaluated on fixed-length datasets, the adaptive rule reduces peak fit memory by a median of 37 MB (mean 395 MB) and fit time by a median of 0.4 s (mean 4 s), with a median accuracy change of 0% (mean -0.11%). Memory and time savings concentrate on long-series datasets where the original rule allocates the largest ensemble size.

AI 总结：该研究针对GPT风格模型无法直接迁移到符号音乐的问题，提出有效性-无损性框架，通过构建预测有效且关系无损的坐标系优化标记化，实验验证了相关边界，揭示了跨模态迁移的关键在于标记化接口而非架构。

链接：https://arxiv.org/abs/2608.18025

机构：Tsinghua University（清华大学）

作者：Yi Wang

英文摘要：GPT-style models achieve strong performance by representing language with finite vocabularies of reusable discrete tokens. This success has motivated symbolic music tokenizations to treat recurring musical structures, such as chords, motifs, and phrases, as reusable units analogous to linguistic tokens. However, tokenization derives its advantage not from reusable combinations alone, but from compression: effective compression requires coordinates in which recurring regularities form stable and predictable conditional distributions. The key problem is therefore not to find larger musical combinations, but to discover the coordinate system in which musical facts become predictively compressible. We formulate the Effectiveness--Losslessness Framework and define tokenization as the construction of a predictively effective and relationally lossless coordinate system. The Predictive Effectiveness Principle defines the Fact--Token Boundary: decoupling and denesting construct coordinate interfaces that expose predictive regularities. The Relational Losslessness Principle defines the Token--State Boundary: tokenization stops before context-dependent relations are fixed, leaving their computation to model states. Controlled symbolic-music experiments validate these boundaries. Effective coordinate construction improves predictive compressibility, while fixed relational projections constrain contextual modeling. Sequence compaction alone does not guarantee predictive compression, while preserving contextual freedom allows higher-order musical organization to emerge without explicit structural labels. These results reveal why GPT-style models do not transfer directly across modalities: architectures transfer, but tokenization interfaces do not. Tokenization must discover effective representations while preserving the relational freedom from which contextual structure can emerge.