机器学习学术速递[8.10]

AI 总结：本研究提出基于激活工程的虚假信息检测框架，通过对比激活引出潜在空间的虚假信息方向，在多类模型和基准上实现了优于部分基线的检测性能，为可解释性驱动的虚假信息检测提供了新方向。

链接：https://arxiv.org/abs/2608.06417

机构：PUCRS（巴西天主教大学（里约格兰德 do 苏里））； Kunumi Institute（库纳米研究所）

作者：Pedro Barcelos, Otávio Parraga, Marcelo M. Mussi, Lucas M. Fraga, Lucas S. Kupssinskü, Rodrigo C. Barros

英文摘要：The proliferation of misinformation online has driven demand for scalable detection systems. While most existing approaches rely on surface-level linguistic features or external knowledge retrieval, we examine truthfulness as a geometric property of a language model's representation space. We introduce a misinformation detection framework grounded in activation engineering, which leverages the latent geometry of transformer models. Our approach elicits a misinformation direction in the residual stream by contrasting activations from paired truthful and false statements, following the difference-in-means principle of Contrastive Activation Addition (CAA). At inference time, the last-token activation of an unseen claim is projected onto this direction, and the projected representation is fed to an Multilayer Perceptron (MLP) for classification. The procedure requires no fine-tuning of the backbone model, no external evidence retrieval, and no task-specific supervision beyond the contrastive pairs used to estimate the direction. We evaluate the method across 11 models from the Gemma, Llama, and Qwen families, ranging from 270M to 12B parameters, on three fact-checking benchmarks: AVeriTeC, LIAR, and FACTors. The falsehood direction is recoverable across model scales and architectural families, and last-token projection matches or surpasses zero-shot and few-shot prompting baselines on LIAR and FACTors, with the largest gains observed for smaller models. Performance on AVeriTeC is more limited, which we attribute to its evidence-grounded labeling scheme. These findings provide evidence that truthfulness is a structured, linearly separable concept in the latent space of pretrained language models, and point toward interpretability-driven misinformation detection as a practical complement to retrieval-based pipelines. The code is available on this https URL.

AI 总结：本文提出分块混合注意力，将其融入预训练dLLM LLaDA~2.1得到LLaDA-Hybrid，在保持基准性能的同时提升解码吞吐量与并发请求支持能力。

链接：https://arxiv.org/abs/2608.06628

机构：Apple（苹果公司）； Google DeepMind（谷歌DeepMind）； Harvard University（哈佛大学）； MIT（麻省理工学院）

作者：Jinha Kim, Younghun Roh, Jaeyeon Kim

英文摘要：Diffusion language models (dLLMs) offer a promising alternative to autoregressive models by accelerating inference through parallel decoding. Recent dLLMs commonly use blockwise semi-autoregressive decoding, generating blocks autoregressively while denoising tokens within each active block in parallel. However, despite KV caching, each denoising step still attends to all previous blocks, repeatedly incurring prefix-attention cost. Motivated by this bottleneck, we ask whether dLLM inference can be further accelerated by linearizing attention over previous blocks. We introduce block-hybrid attention, which retains exact softmax attention within the active denoising block while applying linear attention over previous blocks. We show that this hybrid attention can be retrofitted into a pretrained dLLM with minimal post-training: LLaDA-Hybrid replaces 6 of the 20 attention layers in LLaDA~2.1, a 16B open-source dLLM, largely following LoLCAT (Zhang et al, 2024). The conversion takes only approximately 60 hours while preserving benchmark performance: 72.0% vs. 75.6% on HumanEval, 63.0% vs. 57.7% on MBPP+, and 86.7% vs. 88.3% on CMATH. With a Triton implementation, LLaDA-Hybrid achieves up to $1.7\times$ higher decoding throughput and supports more concurrent requests before exhausting memory, showing that pretrained dLLMs can be efficiently linearized for faster inference. Our code is available at: this https URL.

AI 总结：本文针对大语言模型剪枝忽略输出差异的问题，提出Wisp、Wisp+、Whisper等差异感知剪枝方法，在Llama系列模型上提升了剪枝效果，可与其他技术结合优化性能。

链接：https://arxiv.org/abs/2608.06630

作者：Linghao Kong, Inimai Subramanian, Micah Adler, Dan Alistarh, Dan Gutfreund, Nir Shavit

英文摘要：Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs. We argue that this overlooks a key computation performed by particularly sparsity-sensitive neurons in the MLP up and gate projections: separating similar inputs into dissimilar outputs. This suggests that effective pruning should preserve not only activations, but also the differences between outputs more broadly. We introduce a family of difference-informed pruning methods built upon this principle. Wisp is a first-order, update-free method that scores weights using input-difference norms, and Wisp+ refines this score neuronwise using the input pairs each neuron separates most strongly. Finally, Whisper is a second-order method that uses a lightly regularized difference Hessian as its reconstruction objective. Across Llama 2 and 3.1 models from 7B to 405B parameters, our second-order variant consistently improves over strong reconstruction-based baselines, while our update-free variants improve over activation-aware baselines, especially in constrained settings. The improvements over Wanda and SparseGPT extend to structured sparsity, downstream evaluations, and other model families. Augmenting stronger techniques such as RIA and ALPS with our difference-informed criteria yields further improvements, shifting the overall accuracy-runtime frontier outward at negligible additional cost. These results suggest that preserving output differences is a broadly useful and composable signal for post-training LLM sparsification.

AI 总结：本研究提出混合三级框架HYMELL，结合分析建模与机器学习，在NVIDIA H100 GPU上对LLaMA 3 8B的预填充、解码阶段误差均低于5%，可实现LLM推理延迟与能耗的精准估计及能效优化。

链接：https://arxiv.org/abs/2608.06723

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

作者：Saeid Shokoufa, Mohammad Erfan Sadeghi, Mehdi Kamal, Massoud Pedram

英文摘要：The rapid scaling of Large Language Models (LLMs) has significantly increased computational cost, energy consumption, and inference latency, making accurate estimation essential for sustainable artificial intelligence deployment and hardware-aware design. In this work, we introduce Hybrid Modeling for Energy and Latency of LLMs (HYMELL), a hybrid three-level framework for estimating LLM inference latency and energy by combining analytical modeling with machine learning (ML). HYMELL models LLM execution through a three-level hierarchy: analytical estimation of primitive operations, ML prediction of higher-level components, and an end-to-end model that captures system-level overheads across both prefill and decode phases. The framework supports diverse architectures, including dense and mixture-of-experts (MoE) feed-forward networks (FFNs), as well as multi-head attention (MHA) and grouped-query attention (GQA) mechanisms. Evaluated on an NVIDIA H100 graphics processing unit (GPU), HYMELL achieves high predictive accuracy; notably, for LLaMA 3 8B, it attains less than 5% error for both prefill and decode phases. By predicting execution costs directly from architectural parameters, it enables fast, hardware-free design space exploration and energy-efficient optimization.

AI 总结：该研究通过分析自注意力模型的查询-键与输出-值回路的参数化，发现更快的查询-键学习可强化注意力、提升可解释性，且预测性能相当。

链接：https://arxiv.org/abs/2608.06776

作者：Rahul Vashisht, Harish G. Ramaswamy

英文摘要：A standard self-attention layer consists of two interacting circuits: the query-key circuit that governs attention allocation, and the output-value circuit that maps attended representations to predictions. Collapsed and factorized parameterizations of the query-key and output-value circuits lead to qualitatively different attention patterns. In particular, some parameterizations give sharper attention to task-relevant tokens, at a similar training loss. We analyze how the parameterizations of these circuits shape the parameter trajectories in single-layer self-attention models trained for next-token prediction. Through gradient-flow analysis, we show that factorization induces implicit rescaling of the two circuits' learning rates. We derive closed-form dynamics showing that output-value and query-key parameters move along a line, with relative speeds determined by their learning rates. Faster query-key learning relative to output-value learning thus produces sharper attention, as the model compensates for slower output-value learning by increasing attention mass on relevant tokens. Experiments show that differences in the relative learning rates of the two circuits govern attention concentration. This improves attention interpretability proxies while maintaining comparable predictive performance.

AI 总结：针对工业科学领域小数据场景，提出FSD-RM范式结合NAS优化模型容量与输入维度，用于制冷机寿命预测，可在降本减复杂度的同时实现有竞争力的预测性能。

链接：https://arxiv.org/abs/2608.06993

机构：Comtrade 360 d.o.o.（康创360有限责任公司）； Comtrade AI GmbH（康创人工智能有限公司）； LE-Tehnika d.o.o.（LE技术有限责任公司）； Alma Mater Studiorum – Università di Bologna（博洛尼亚大学）

作者：Gregor Molan (1), Grafika Jati (1), (4), Francesco Barchi (4), Andrea Acquaviva (4), Aljaž Osterman (3), Martin Molan (2), (1), (4) ((1) Comtrade 360 d.o.o., Letališka cesta 29b, Ljubljana, 1000, Slovenia, (2) Comtrade AI GmbH, Grafenauweg 8, Zug, 6300, Switzerland, (3) LE-Tehnika d.o.o., Šuceva 27, Kranj, 4000, Slovenia, (4) Alma Mater Studiorum - Universita di Bologna, Department of Electrical, Electronic, and Information Engineering (DEI), Viale del Risorgimento 2, Bologna, 40136, Italy)

英文摘要： Large-scale pretrained time-series models achieve strong results through large-scale pretraining and task-agnostic representation learning, but they rely on abundant, diverse data that industrial and scientific domains often lack. We therefore propose the FSD-RM (Family of Small-Data Representation Models) paradigm as a practical alternative for limited, domain-specific telemetry. Rather than relying on large-scale pretraining, we focus on capacity-controlled representation learning using established encoder architectures (CNN1D, LSTM, GRU, Transformer), selected for their suitability in small-data settings and interpretability. These encoders are trained unsupervised on multivariate telemetry data and integrated into a two-stage pipeline for downstream lifetime prediction. To systematically examine architectural trade-offs under data constraints, we employ \textbf{dimension-aware neural architecture search (NAS)} to jointly optimize model capacity and input dimensionality. Experiments on cryocooler telemetry show that the proposed approach achieves competitive predictive performance while reducing training cost and model complexity. The contribution lies in combining established representation learning techniques within a coherent, NAS-driven framework tailored to small-data regimes, with explicitly defined parameter settings and design choices. The results indicate that effective representation learning can be achieved without large-scale pretraining when appropriate inductive bias and capacity control are applied.

AI 总结：该研究对比13种无监督双曲图嵌入器在链接预测与拓扑重构任务的性能，发现最大似然法与表示学习类方法整体表现最优，性能与嵌入范式关联更紧密，还为下游应用的方法选择提供指导。

链接：https://arxiv.org/abs/2608.07029

机构：TU Delft（代尔夫特理工大学）； Indiana University（印第安纳大学）； Institute of Informatics, University of Warsaw（华沙大学信息学院）

作者：Robert Jankowski, Maksim Kitsak, Dorota Celińska-Kopczyńska

英文摘要：Hyperbolic embeddings provide compact geometric representations of complex networks in hyperbolic spaces, but systematic comparisons of methods developed in machine learning, network science, and algorithmics remain rare. We benchmark 13 unsupervised hyperbolic graph embedders under a unified protocol for link prediction and topology reconstruction on synthetic and empirical networks. The protocol captures both missing-link recovery and the preservation of local and global network structure. Maximum-likelihood and representation-learning-based approaches, including hybrid variants, achieve the strongest overall performance, although no method dominates across all tasks and structural regimes. Performance is more strongly associated with embedding paradigm than with disciplinary origin. We identify the network regimes in which different paradigms succeed or fail and provide practical guidance for method selection in downstream applications.

AI 总结：该研究针对现有多模态可穿戴模型的不足，提出OmniDecVAEs框架，在30模态的HAR任务中，提升了识别准确率与数据合成质量，可用于边缘可穿戴与医疗领域。

链接：https://arxiv.org/abs/2608.07385

机构：Khalifa University（哈利法大学）； University of Toronto（多伦多大学）； MIT Media Lab（麻省理工学院媒体实验室）； Aristotle University of Thessaloniki（亚里士多德大学）

作者：Ioannis Ziogas, Ensieh Khazaei, Bilal Taha, Aamna Al Shehhi, Ahsan H. Khandoker, Leontios J. Hadjileontiadis, Dimitrios Hatzinakos

英文摘要：Learning disentangled representations is a key requirement for developing versatile, general-purpose, and sustainable models in multi-modal wearable computing. However, existing approaches do not operate as full-stack wearable processors, i.e., they do not simultaneously address task-specific classification performance, disentangled and interpretable representation learning, fusion, and generative modeling of highly heterogeneous multi-modal time series. To address this gap, we introduce Omni-modal Variational Decomposition Autoencoders (OmniDecVAEs), a framework that efficiently learns multi-purpose representations in a unified and scalable manner from arbitrarily many modalities. OmniDecVAEs extend DecVAEs by learning modality-conditioned time-frequency latent subspaces through a multi-view self-supervised decomposition loss and a shared asymmetric autoencoder (AE) architecture. Results on a challenging omni-modal human activity recognition (HAR) setting with up to thirty modalities, demonstrate the ability of OmniDecVAEs to learn full-stack wearable representations. When compared to transformer-based and VAE-based methods, OmniDecVAEs full-stack disentangled representation properties lead to accuracy improvements of 1.01% and 6.75% in activity and identity recognition, respectively. Furthermore, OmniDecVAEs synthesize realistic omni-modal time-frequency data that manifest with enhanced reconstructions (mean absolute error improves by 76.84%) and distributional similarity between real and synthetic data (maximum mean discrepancy improves by 13.85%). Our results highlight OmniDecVAEs potential as a lightweight model suitable for intelligent edge wearables and clinical healthcare, unifying processing requirements and abilities in a single model, through its enhanced representational capacity, modality-invariant spatial complexity (4.1M parameters), and real-time latency.

AI 总结：本文针对隐藏拜占庭攻击下的多智能体系统在线协同控制问题，分析攻击者信息对模型几何特性的影响，推导安全学习的信息论极限，提出鲁棒学习者并给出遗憾界，为可靠多智能体系统提供理论与算法基础。

链接：https://arxiv.org/abs/2608.06520

作者： Ximing Sun, Yue Wang

英文摘要：We study online cooperative control of a multi-agent system under Byzantine attacks. Namely, an unknown, fixed subset of agents are Byzantine comprised and can stealthily overwrite its own coordinates of the team's planned joint action after observing that plan. The learner observes planned actions, public rewards, and public states, but neither the overwrite nor the executed joint action. Our objective is security: to optimize the team performance against the worst overwrites and achieve the optimal security value. We first show that the attacker's information determines the geometry. An attacker that observes the planned action induces an exact $(s,a)$-rectangular robust Markov decision process (MDP) whose rows are convex hulls of overwrite-induced public-outcome laws, whereas a blind attacker induces an $s$-rectangular model. We then identify the information-theoretic limit of security learning, showing that the security regret decomposes exactly into return regret against the response generating the data and a cumulative response gap $D_K$. Two indistinguishable horizon-one instances force $\Omega(K)$ expected security regret while return regret is zero, showing that dependence on $D_K$ is unavoidable. Finally, we develop a stage-tied robust estimation-to-decisions learner and prove a regret bound of $\widetilde{\mathcal O}\!\left(H^2S\sqrt{AK}\right)+\mathbb E[D_K]$. Our studies thus provide comprehensive theoretical and algorithmic foundations of reliable multi-agent systems under Byzantine attacks.

AI 总结：该研究针对平均报酬准则下的分布鲁棒马尔可夫决策过程，推导了极小极大最优样本复杂度界，并提出两种插件约简学习程序以实现该复杂度。

链接：https://arxiv.org/abs/2608.06545

机构：Yale University（耶鲁大学）； University of Pennsylvania（宾夕法尼亚大学）

作者：Yuepeng Yang, Yuxin Chen, Yuejie Chi

英文摘要：Distributionally robust Markov decision processes provide a principled framework for sequential decision making under model uncertainty. We study how many samples are necessary and sufficient to learn an $\varepsilon$-optimal robust policy under the average-reward criterion. A generative model provides samples from the nominal transition kernel, whereas policy performance is evaluated over $(s,a)$-rectangular total-variation uncertainty sets of radius at most $\sigma$. Let $H_0$ and $H_\sigma$ denote the nominal and robust optimal bias spans, respectively. We identify $\sigma H_0$ as the perturbation scale separating high- and low-tolerance regimes. Our matching upper and lower bounds show that, up to logarithmic factors, the minimax total sample complexity is $$ NSA \asymp \frac{SA}{\varepsilon^2}\begin{cases} \min\{H_0,H_\sigma\}, & \varepsilon\gtrsim\sigma H_0,\\ \min\{H_0,H_\sigma\}+\sigma H_\sigma^2, & \varepsilon\lesssim\sigma H_0. \end{cases} $$ Here $S$ and $A$ are the numbers of states and actions, and $N$ is the number of samples per state-action pair. The sample complexity consists of a linear-span term that resembles the nominal AMDP results and a robustness-specific term that appears only in the low-tolerance regime. We attain these rates using reduction-based plug-in procedures that select the reduction---nominal or robust---and its discount factor: a span-informed procedure that makes these choices using known span parameters, and a span-agnostic procedure that calibrates both choices from data.

AI 总结：该研究提出 BC-ICL 方法，将预训练表格基础模型转化为在线决策随机策略，通过 Bootstrap 重采样与臂-上下文架构优化，在上下文多臂老虎机任务上取得优于基准的遗憾性能。

链接：https://arxiv.org/abs/2608.06559

作者：Devansh Gupta, Shiv Tavker, Dmitry Efimov, Suchitra Sathyanarayana, Gitanjali Bhutani, Boris N. Oreshkin

英文摘要：Contextual bandits offer a natural framework for sample-efficient personalization, but practical deployment remains difficult under sparse, biased interaction data, unreliable uncertainty estimates, and severe cold starts. We study whether pre-trained tabular foundation models with in-context learning can be turned into randomized policies for online decision making. We propose BC-ICL (Bootstrap-conditioned action selection using ICL), which at each round draws a bootstrap resample of the interaction history, conditions a frozen pre-trained ICL model on that resample, scores all actions, and selects the action with the highest sampled score. We further introduce an arm-context conditioning architecture that promotes shared statistical strength across actions and helps avoid common bootstrap failure modes of isolated-arm bandits. Empirically, this policy delivers strong early-round regret and regret performance on standard contextual bandit suites, outperforming established baselines under a strict online protocol.

AI 总结：该研究提出CrystalGRPO框架，通过强化学习后训练优化基于流模型的晶体结构预测，两种模式在多数据集骨干组合中提升了恢复性能与覆盖率。

链接：https://arxiv.org/abs/2608.06582

机构：University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）； North Carolina Battery Complexity, Autonomous Vehicle and Electrification (BATT CAVE) Research Center（北卡罗来纳州电池复杂性、自动驾驶与电气化（BATT CAVE）研究中心）

作者：Kaixiang Su, Hongfei Xue, Qiang Zhu

英文摘要： Flow-based generative models can efficiently produce candidate structures for crystal structure prediction (CSP), but their pretrained objectives do not directly optimize downstream target recovery. Reinforcement-learning post-training offers a flexible solution, yet existing approaches rely primarily on energy rewards and coordinate-only stochastic policies. Predicted energy does not identify the reference polymorph, while reward-driven concentration can reduce the candidate coverage required for Top-N recovery. We introduce CrystalGRPO, a CSP-aligned post-training framework that extends existing ODE-to-SDE policy constructions to the joint coordinate--lattice state. CrystalGRPO combines MACE-predicted energy with a StructureMatcher-based recovery score and provides two operating modes: CrystalGRPO-Q, which prioritizes single-draw recovery, and CrystalGRPO-C, which combines full-trajectory reference regularization with a coverage-aware group advantage to preserve finite-budget target recovery. Across MP-20 and MPTS-52 with PXRDGen and OMatG backbones, both variants reduce one- and twenty-sample RMSE relative to coordinate-only reinforcement in all four backbone--dataset settings. CrystalGRPO-Q consistently improves Top-1, whereas CrystalGRPO-C achieves a higher Top-20 across all settings.

AI 总结：该研究提出一种基于神经ODE的正则化方法，将其集成到Actor-Critic算法中，在A2C的Atari基准和PPO的网格世界环境中显著提升了强化学习智能体的性能。

链接：https://arxiv.org/abs/2608.06595

机构：CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）； Technical University of Munich（慕尼黑工业大学）

作者：Mohamed Ghanem, Bernd Finkbeiner

英文摘要：Neural networks applied to sequential decision-making tasks typically rely on latent representations of environment states. While environment dynamics dictate how semantic states evolve, the corresponding latent transitions are usually left implicit, creating a potential misalignment between the two. We propose to model latent dynamics explicitly by drawing an analogy between Markov decision process (MDP) trajectories and ordinary differential equation (ODE) flows: in both cases, the current state fully determines its successors. Building on this view, we introduce a neural ODE-based regularization method that enforces latent embeddings to follow consistent ODE flows, thereby aligning representation learning with environment dynamics. Although broadly applicable to deep learning agents, we demonstrate its effectiveness in reinforcement learning by integrating it into Actor-Critic algorithms. Our approach yields major performance gains across various standard Atari benchmarks for A2C and gridworld environments for PPO.

AI 总结：该研究针对MDP提出带证书的次二次双模拟度量方法，通过近似最近邻索引与单调上下界实现，在基准测试中比基线更高效，且在网格世界任务中性能提升28.6%。

链接：https://arxiv.org/abs/2608.06762

作者：Ibne Farabi Shihab, Joyanta Jyoti Mondal

英文摘要：Bisimulation metrics quantify behavioral similarity in Markov decision processes, but their Wasserstein fixed-point operator updates every state pair and incurs quadratic pairwise work. We give a certificate-carrying sub-quadratic method for MDPs with bounded transition support and a useful low-dimensional indexing representation: an approximate-nearest-neighbor index selects the pairs updated by the exact restricted operator, while monotone lower and upper runs enclose the exact metric at every sweep. The main analytical result is a coverage-augmented anytime bound: local index quality alone cannot control global error, because uncovered pairs retain their initialization gap. The limiting error is at most $\max(\rho,\eop/(1-\gamma))$, and with exact covered backups the lower arm satisfies $\|\dann-d\|_\infty=\rho$. Because $\rho$ depends on the unknown exact metric, the algorithm returns the observable sandwich width instead; agreement of the induced lower and upper clusterings certifies exact recovery of the covered aggregation. A reward-oblivious lower bound shows sub-quadratic index-first coverage cannot remove the coverage term, while a separate adaptive lower bound requires $\Omega(|\Scal|)$ pair evaluations. Exact-operator experiments verify the identity and enclosure in every seeded run, and timing experiments recover quadratic versus sub-quadratic scaling under both cheap and full Wasserstein backups. On the grouped $|\Scal|=64$ benchmark, exact restricted refinement reaches the exact-metric skyline once retrieval covers roughly half of all pairs, while independently trained MICo and DBC baselines stay $22$-$33\times$ above that skyline at every retrieval budget. Taxi shows the certificate abstaining under an uninformative embedding, while a $2500$-state gridworld improves over a reward-only metric by $28.6\%$ using $12.8\%$ of one quadratic sweep.

AI 总结：该研究针对强化学习组件孤立问题，提出协调模型表示等三个维度的ROSER框架，在连续控制基准上性能优于基线及单纯堆叠方法，为样本高效智能体开发提供了整体设计思路。

链接：https://arxiv.org/abs/2608.07086

机构：Tsinghua University（清华大学）； Nanyang Technological University（南洋理工大学）； Mila - Quebec Artificial Intelligence Institute（米拉-魁北克人工智能研究所）； University of Oxford（牛津大学）

作者：Qi Zhao, Guozheng Ma, Yilun Kong, Lu Li, Haoyu Wang, Zilin Wang, Tiantian Zhang, Yuxing Wang, Jian Sha, Yongzhe Chang, Xueqian Wang, Dacheng Tao

英文摘要：Reinforcement learning systems are significantly more complex than other machine learning paradigms due to inherent properties, causing RL system design to jointly account for many tightly coupled factors. Despite advances in individual algorithmic components, their functional interdependencies remain underexplored: do they exhibit mutual synergy or counterproductive interference? To bridge this gap, we conduct a systematic investigation and find that the efficacy of different components exhibits significant task-dependency, and naively stacking state-of-the-art techniques does not necessarily yield performance gains; instead, it often triggers emergent challenges, such as compounded non-stationarity. Building upon these findings, we distill a suite of actionable insights into the principled coordination of these components. Guided by these insights, we propose ROSER, an RL framework that coordinates three critical dimensions: Model-based Representation, Optimization Stability, and Experience Replay. Across diverse continuous-control benchmarks, ROSER consistently outperforms vanilla baselines and achieves 17.60% gains over naive stack. Our findings underscore the necessity of a holistic perspective in RL system design and paves the way for developing sample-efficient agents.

AI 总结：该研究提出一种结合决策树剪枝的可解释强化学习方法，通过定义结构感知与使用感知算子简化策略，在经典控制及MuJoCo基准上验证其可保持高性能并提升可解释性。

链接：https://arxiv.org/abs/2608.07151

机构：Ludwig-Maximilians-University Munich（慕尼黑大学）； Siemens AG（西门子公司）

作者：Mark Leon Ringer, Michel Tokic

英文摘要：Reinforcement learning policies are difficult to inspect, but interpreting them is a prerequisite for trustworthiness. Converting a trained policy into explicit decision-tree rules improves transparency and the resulting artifacts often remain too complex for human understanding. We present a pruning process that simplifies such rule-based policies while preserving task performance and making edits to the policy auditable. The process defines a small set of structural and usage-aware operators and evaluates candidate edits by re-executing the policy to measure return and interpretability proxies. This exposes an transformation process from complex to compact policy structures. We investigate this approach on classic control and MuJoCo benchmarks, where pruning traces reveal consistent interpretability improvements while maintaining high performance.

AI 总结：本文提出Momba，将观测与特征归一化等三项神经网络设计进展与熵正则化MORL算法结合，在标准连续控制基准上大幅提升了MORL算法生成解集的质量。

链接：https://arxiv.org/abs/2608.07180

作者：Adam Štafa, Santeri Heiskanen, Petr Novotný, Joni Pajarinen

英文摘要：Recent advances in deep reinforcement learning (RL) have shown that improving neural network architectures can yield substantial gains in sample efficiency and asymptotic performance without altering the underlying algorithms. In contrast, work on multi-objective reinforcement learning (MORL), which aims to discover a set of policies that balance trade-offs among conflicting objectives, has predominantly focused on algorithmic innovations, leaving the area of architectures underexplored. While the optimal policies and value functions can differ significantly depending on the trade-offs, MORL algorithms commonly represent them with simple feedforward networks conditioned on the trade-off. This raises the question of whether the performance of the algorithms could be improved with more expressive function approximators. In this paper, we integrate recent advances in neural network design: (i) observation and feature normalization, (ii) weight normalization, and (iii) modeling of distributional returns with an entropy-regularized MORL algorithm. The empirical results across standard continuous control benchmarks demonstrate that these changes substantially improve the quality of the produced solution sets without requiring major changes to the underlying algorithm.

AI 总结：该研究通过闭式分析发现，部分可观测强化学习中学习偏差是性能差的主因，调整演员-评论家的前瞻步数可解决问题，提供了理论依据且经实验验证。

链接：https://arxiv.org/abs/2608.07228

机构：University College London（伦敦大学学院）

作者：Idil Gözel (University College London)

英文摘要：When a reinforcement learning agent cannot observe the full state, we usually blame its policies: it cannot see enough to represent a good one. We show that in a solvable case the bigger problem lies elsewhere. Even when a good policy is available and the agent's value function is expressive enough to describe it exactly, learning still ends up somewhere far worse. We study a partially observed linear-quadratic problem in which a standard actor-critic learner can be solved in closed form. At our default setting the best policy the agent can represent is already close to optimal, costing 10.4% more than the ideal controller that observes everything. Learning does not find it. The algorithm instead comes to rest at a policy that is 35% worse than the best one available to it, and we can say exactly where and why. The cause is a bias in what the critic learns rather than a limit on what the actor can express. Because the agent cannot attribute what it sees to the part of the state it cannot observe, the critic misreads that unexplained variation as sharp curvature in its own value estimates, and the actor follows that error away from the optimum. We derive closed-form expressions for the resulting policy, for its cost, and for the one design choice that removes the problem, which is how far the learner looks ahead before trusting its own value estimates. Deep reinforcement learning experiments follow these predictions closely. Notably, giving the agent memory of past observations does not help, while changing how far it looks ahead does.

AI 总结：该研究探讨折扣马尔可夫决策过程中仅从最优动作可恢复的转移概率信息，明确了不同形式奖励对转移核可识别性的影响，证明了转移核的可识别条件及相关维度特性。

链接：https://arxiv.org/abs/2608.07301

作者：Neal Batra

英文摘要： We study what can be recovered about the transition probabilities of a Markov decision process from optimal actions alone. This is closely related to the inverse problem considered by Letcher et al., who ask when the dynamics can be recovered from numerical \(Q\)-values. Here the numerical values themselves are not observed; only the optimal actions are known, for every reward in a given class. For state-action rewards \(r(s,a)\), knowing the optimal actions for every reward also tells us how much better one action is than another when each is followed by the same fixed policy. This is still not enough to determine the transition probabilities uniquely. We prove that two kernels give the same optimal actions for every reward exactly when \[ Q_{s,a} = \Bigl(P_{s,a}+\tfrac1\gamma e_s^{\mathsf T}(L-I)\Bigr)L^{-1} \] for one invertible matrix \(L\) satisfying \(L\mathbf 1=\mathbf 1\). Near a kernel with strictly positive entries, there is an \(n(n-1)\)-dimensional family of different kernels with this property. The result is unchanged if we consider only rewards having a unique optimal action at every state. We then compare this with rewards of the forms \(r(s)\) and \(r(s,a,s')\). Rewards that depend on the next state can usually recover the transition kernel itself: every row at a state with at least two actions is determined, and we describe exactly when a row at a state with one action can remain hidden. State rewards reveal less: two kernels give the same optimal actions exactly when every deterministic policy is optimal for the same set of rewards. The results show how the form of the reward affects what can be learned about the dynamics from optimal actions alone.

AI 总结：本研究针对并行Q网络，设计评估8种CNN拓扑并集成多种Q学习扩展，提出复合架构Aftab，在Atari-57与Procgen Hard基准上均优于基线，已开源。

链接：https://arxiv.org/abs/2608.07335

机构：University of Padua（帕多瓦大学）

作者：Taha Shieenavaz, Shabnam Zareshahraki, Loris Nanni

英文摘要：Recent advancements in deep reinforcement learning have increasingly favored simplified, highly parallelized paradigms. Notably, the Parallelized Q-Network (PQN) algorithm achieves stable off-policy learning without relying on computationally expensive replay buffers or target networks. However, the representational capacity and parameter efficiency of visual encoders operating in these buffer-free settings remain underexplored. In this work, we systematically investigate the architectural design space of Convolutional Neural Networks for PQN. We design and rigorously evaluate eight distinct CNN topologies, optimizing for sample efficiency under strict parameter constraints. Furthermore, we study the impact of representation and value estimation enhancements by integrating the Hadamax encoding paradigm and advanced Q-learning extensions, including distributional, ensemble, and dueling heads. Extensive experiments on the Atari-57 benchmark demonstrate that our proposed composite architecture, Aftab, achieves an Interquartile Mean (IQM) Human-Normalized Score of 6.479, establishing a 0.86 Probability of Improvement over the standard PQN baseline. Additionally, structural resilience evaluations on the highly non-stationary Procgen Hard benchmark confirm out-of-distribution generalization, with Aftab yielding an IQM Procgen Normalized Score of 0.418 compared to the baseline's 0.382. Ultimately, this work establishes an efficient, probabilistically superior structural reference for model-free reinforcement learning, all while preserving the simplicity and memory efficiency of unbuffered, parallelized optimization. The complete Aftab framework, including all model definitions, training configurations, and raw experimental logs, is open-sourced and available on our GitHub repository: this https URL

AI 总结：针对智能体强化学习中事后信号分配不清的问题，提出TRIAL框架，通过轨迹相对步分配优化监督信号，在WebShop、ALFWorld等任务上优于GRPO及多数基线方法，提升了任务性能。

链接：https://arxiv.org/abs/2608.07371

机构：Zhejiang University（浙江大学）； Shanghai AI Laboratory（上海人工智能实验室）； Tencent（腾讯）

作者：Haoyu Zheng, Yun Zhu, Qing Wang, Wenqiao Zhang

英文摘要：Recent agentic reinforcement learning methods use hindsight to complement sparse outcome rewards. However, a completed rollout can yield many such signals, leaving their appropriate allocation across turns unclear. We introduce TRIAL, a trajectory-relative hindsight distillation framework with a unified turn-aligned scoring protocol. For each decision turn, TRIAL extracts an outcome view of that decision's realized consequence and evaluates the same response under ordinary and hindsight-conditioned contexts. The signed log-probability gap determines the direction and local strength of token-level supervision, while turn-level magnitudes are normalized jointly over the realized trajectory. The resulting allocation multipliers have an eligible-token-weighted mean of one, redistributing dense supervision across turns while fixing its average multiplier. Experiments on WebShop and ALFWorld with different backbones show that TRIAL outperforms GRPO across all eight combinations of backbone, environment, and evaluation metric, while achieving the best or tied-best performance among six methods on six of them. On WebShop with Qwen3-1.7B, TRIAL improves the success rate from 56.4% to 75.2% and the task score from 78.7% to 85.7%. Controlled ablations further show that trajectory-relative turn allocation provides substantial gains beyond those of dense hindsight distillation alone.

AI 总结：本文针对生成模型可能编码错误因果结构的问题，提出对抗性因果干预证伪（ACIF）博弈，证明其理论性质并给出线性高斯示例，搭建了因果生成建模等领域的桥梁。

链接：https://arxiv.org/abs/2608.06427

机构：University of Calgary（卡尔加里大学）

作者：Mojtaba Eslami

英文摘要： Generative models can reproduce an observational distribution while encoding an incorrect causal structure. We study a sequential game in which a structural causal generator proposes observational and interventional distributions, while an adversarial experimentalist selects interventions intended to maximally falsify the generator. The discriminator is therefore not merely a real-versus-synthetic classifier: it is indexed by an intervention and tests whether the generator reproduces the corresponding post-intervention law. We introduce Adversarial Causal Intervention Falsification (ACIF), formulate oracle and implementable versions of the game, and distinguish three objects that are often conflated: observational fit, interventional equivalence over an admissible query class, and point identification of a structural causal model. For finite model and intervention classes, we prove: (i) an exact reduction of the adversarial objective to a worst-intervention integral probability metric; (ii) identification up to interventional equivalence, with point identification under a separating intervention family; (iii) existence of mixed-strategy equilibria; (iv) finite-sample uniform convergence and margin-based model-selection guarantees; and (v) a logarithmic elimination guarantee for a disagreement-driven sequential design under a balanced-separation condition. We also give a complete linear-Gaussian example in which two observationally indistinguishable causal directions are separated by a single well-chosen intervention. The framework clarifies what an adversarial causal discriminator can and cannot certify, and provides a principled bridge between causal generative modeling, active causal discovery, and experimental design.

AI 总结：FUSE是一种用于混合类型表格流匹配的方法，通过分离特征处理与跨列交互，在8个表格数据集上实现了分布保真度和下游效用的强劲一致性能。

链接：https://arxiv.org/abs/2608.07294

作者：Suman Cha, Seongchan Lee, Dohyun Ko, Hyunjoong Kim

英文摘要：Generating mixed-type tabular data requires jointly modeling diverse feature distributions and their complex cross-column dependencies. Variational flow matching handles distinct endpoints via factorized distributions, yet leaves feature-specific processing and cross-column interactions implicit within a shared backbone. We introduce Feature-wise Unified Specialization with cross-column Exchange (FUSE) to explicitly separate these roles. FUSE applies separate adaptive mixture modules to numerical and categorical features, allowing each feature to combine shared specialized subnetworks, while joint attention preserves information exchange across all columns. We also characterize the excess population risk from restricted conditioning contexts and bound the continuous Wasserstein generation error by endpoint-prediction risk. Comprehensive experiments on eight tabular datasets demonstrate that FUSE achieves strong and consistent performance across distributional fidelity and downstream utility metrics.

AI 总结：该研究在高斯教师-学生模型中发现，初始预测器不可见的隐藏尺度参数可控制ReLU网络中神经元的特征所有权，实现确定性的特征选择与冗余神经元剪枝。

链接：https://arxiv.org/abs/2608.06766

机构：School of Future Technology Southeast University（东南大学未来技术学院）

作者：Tongxi Wang

英文摘要：Training changes a network's predictions while allocating task-relevant structure across its internal units. In an overparameterized ReLU network, several neurons can begin with exactly the same functional role, yet one may acquire a teacher feature while the others become redundant. We call the identity of that neuron feature ownership and ask whether it can be controlled by a parameter choice invisible to the initial predictor. In a tractable Gaussian teacher--student model, we fix the complete initial function and vary only a positive-homogeneous scaling gauge. Opposite gauges produce distinct feature trajectories and a sharp $\Theta(D^2)$ separation in specialization time that no global change of clock can explain. Among any fixed number of initially duplicate students, assigning the favorable gauge to one neuron deterministically selects it as the owner and drives the remaining functional contribution to zero. An exact reaction--transport decomposition attributes the effect to different mobilities for changing a feature's coefficient and direction. We prove global selection and functional pruning, extend finite-time selection to visible perturbations and small-step full-batch gradient descent, and verify the predicted loss, alignment, pruning, and dissipation trajectories in population and finite-sample training. The initial predictor therefore determines neither when the feature is learned nor which neuron learns it.

AI 总结：针对不可知PAC学习，研究直接和$C^r$的学习曲线与单实例学习曲线的依赖关系，证明单实例学习速率不决定直接和速率，并给出两类函数的不可知学习曲线阶数结果。

链接：https://arxiv.org/abs/2608.06951

机构：Truth Audit Labs

作者：Mihir More, Aritra Das, Debayan Gupta

英文摘要：Hanneke, Moran, and Waknine \cite{HannekeMoranWaknine2024} asked how the agnostic PAC learning curve of the direct sum $C^r$ depends on the single-instance learning curve $\epsagn(n\mid C)$ and on $r$. We show that the single-instance learning rate does not determine the direct-sum rate. Let $\F$ be the class of the two constant binary functions and let $\G$ consist of the zero function and the identity function. Both classes have agnostic learning curve of order $n^{-1/2}$.

AI 总结：

链接：https://arxiv.org/abs/2608.07224

机构：MIT（麻省理工学院）； The Hebrew University（希伯来大学）

作者：Ilan Doron-Arad, Idan Mehalel, Elchanan Mossel

英文摘要： Motivated by LLMs, which generate outputs by iteratively sampling from next-token distributions, we introduce a PAC-learning model for binary stochastic autoregressive learning. This generalizes the deterministic autoregressive learning framework of Joshi et al., COLT 2025. In our model, one fixed generator assigns a Bernoulli next-token distribution to every prompt string. Starting from an input prompt, a token is sampled and appended to the prompt; the same generator is then applied again to this expanded prompt; this procedure is repeated for $M$ steps. Three forms of supervision are considered: base one-step samples, chain-of-thought (CoT) samples that reveal full random trajectories of length $M$, and end-to-end (e2e) samples that reveal only the final token of length $M$ trajectories. For a generator class, we study the minimum number of samples $m_{base}(\varepsilon),m_{CoT}(\varepsilon), m_{e2e}(\varepsilon)$, resp., required to learn the one-step probabilities in the base model, and the final-token probability in the CoT and e2e models, under squared loss error~$\varepsilon$. We show that stochastic autoregressive learning fundamentally differs from the deterministic theory. At scale $\varepsilon$, there is no universal comparison between the three learning tasks: both $m_{CoT}/m_{base}$ and $m_{e2e}/m_{CoT}$ can be made simultaneously arbitrarily larger than $M/\varepsilon$, the natural analogue for the existing deterministic results. Nevertheless, after altering scales, for every class, CoT learning at scale $\varepsilon$ is upper-bounded by base learning at scale $\varepsilon/M^2$, whereas e2e learning at scale $\varepsilon$ is upper-bounded, up to logarithmic factors, by $(M/\varepsilon) m_{CoT}(\Theta(\varepsilon))$. These dependencies and scales are essentially tight. We complement these bounds by studying dimension $d$ logistic functions in our model.

AI 总结：MiCoPro是面向边缘AI的混合精度硬件/软件协同设计框架，通过硬件感知代理模型实现延迟约束下的最优量化配置，在两类硬件上达成最高40%延迟降低、精度下降不足3%的效果。

链接：https://arxiv.org/abs/2608.06916

机构：Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））

作者：Zijun Jiang, Yangdi Lyu

英文摘要：Quantized Neural Networks~(QNN) with low-bitwidth data have proven promising in efficient storage and computation on edge devices. To mitigate accuracy degradation while maximizing speedup, layer-wise mixed-precision quantization~(MPQ) becomes a popular solution. However, existing algorithms for exploring MPQ schemes are limited in flexibility and efficiency. Comprehending the complex impacts of different MPQ schemes on post-training quantization and quantization-aware training results is a challenge for conventional methods. Furthermore, an end-to-end framework for the optimization and deployment of MPQ models is missing in existing work. To address these challenges, we propose the MiCo framework, a holistic MPQ exploration and deployment framework for edge AI applications. The framework adopts a novel optimization algorithm to search for accuracy-optimal quantization configurations under strict latency constraints. We further extended the framework to MiCoPro, which introduces a robust Hardware-Aware Proxy (HAP) model to enhance prediction accuracy and hardware versatility. By leveraging target-specific latency modeling, MiCoPro enables rapid exploration and direct deployment from PyTorch models to bare-metal C code. We demonstrate the versatility of our framework on both the BitFusion accelerator and SIMD-extended RISC-V processors, achieving up to 40\% of latency reduction with less than 3\% of accuracy drop.

AI 总结：针对LLM长上下文处理的KV缓存瓶颈，提出无需额外训练的GraceKV方法，通过全局资源分配平衡缓存的分辨率与覆盖范围，在32项实验设置中24项排名第一，128倍压缩仍稳健。

链接：https://arxiv.org/abs/2608.07001

作者：Haolin Tian, Yuzhe Liu, Tonghan Wang

英文摘要：As large language models (LLMs) process increasingly long contexts, KV cache storage and repeated access have become a major bottleneck. Existing KV cache compression methods rely on predefined, fixed compression rules and are typically developed around either token eviction or merging. As a result, cache resources can neither flow freely across layers, heads, and context slots, nor be jointly allocated to balance local resolution and information coverage. Therefore, we propose GraceKV, a global approach for the allocation of resolution and coverage in KV cache compression, and formulate the compression process as a global resource allocation problem under a fixed cache budget. GraceKV treats each layer-KV head-slot combination as an atomic unit and builds a prototype tree. Leaf nodes correspond to token-level KV entries, while each internal node uses a single prototype to compress the KV space covered by its children. A set of non-overlapping nodes in the tree forms the representation of an atomic unit. Adding the root of a new tree expands information coverage, whereas splitting a selected node improves local resolution. All candidate actions compete globally for a shared cache budget. Finally, the nodes retained across all trees form the compressed KV cache. This process adaptively determines the allocation of cache resources among atomic units globally and the balance between resolution and coverage. GraceKV requires no additional training, and the entire compression and inference process is performed on the GPU. Systematic experiments across diverse long-context tasks and compression ratios show that GraceKV ranks first in 24 of 32 settings and remains robust up to 128-fold compression. These results validate the effectiveness of global budget allocation in coordinating information coverage and local resolution.

AI 总结：MAUPITI传感器集成16×16 TMOS阵列与RISC-V微控制器，采用原型NCM分类器，在低内存功耗约束下实现红外传感器设备端学习，准确率与传统分类器相当，延迟开销可忽略，支持在线自适应。

链接：https://arxiv.org/abs/2608.07192

机构： Politecnico di Torino（都灵理工大学）； STMicroelectronics（意法半导体）

作者：Beatrice Alessandra Motetti, Tanguy Dugas du Villard, Matteo Risso, Alessio Burrello, Francesco Daghero, Enrico Macii, Massimo Poncino, Marco Castellano, Alfio Basile, Daniele Jahier Pagliari

英文摘要：Low-resolution infrared (IR) array sensors represent an interesting solution for privacy-preserving human sensing in embedded systems. In this letter, we describe a smart multi-pixel IR sensor integrating a 16$\times$16 thermal MOSFET (TMOS) array and a RISC-V microcontroller extended with low-precision SIMD instructions, capable of on-device learning and continual adaptation for pose and gesture recognition tasks under tight memory and power constraints ($

AI 总结：本论文针对分布式与联邦优化的七大瓶颈，提出ProxSkip等算法，建立通信高效、鲁棒优化的理论框架，经实验验证其有效性。

链接：https://arxiv.org/abs/2608.06563

作者：Grigory Malinovsky

英文摘要：Machine learning and optimization have advanced together, with practical demands motivating new theory and theoretical breakthroughs enabling new applications. Modern large-scale training relies on classical optimization principles, but the constraints of distributed systems require these foundations to be reconsidered. This thesis addresses seven challenges at the intersection of theory and practice, focusing on key bottlenecks in federated learning and distributed optimization. First, we introduce ProxSkip and prove that local gradient steps can accelerate communication, providing a theoretical foundation for this widely used heuristic. Second, we develop Variance Reduced ProxSkip, which eliminates the neighborhood error of stochastic local updates while balancing communication and local computation. Third, we show that local steps retain their communication acceleration under partial client participation. Fourth, we prove that server-side stepsizes and sampling without replacement improve convergence in heterogeneous settings. Fifth, for Random Reshuffling, we demonstrate that compressing gradient differences rather than gradients yields better theoretical and practical performance. Sixth, we establish that Byzantine robustness and partial participation can be achieved simultaneously using gradient-difference clipping. Finally, we develop the first theoretical framework for low-rank adaptation based on randomized asymmetric chains, providing new insights into fine-tuning large models. Across these contributions, we introduce novel algorithmic frameworks, establish sharp guarantees under realistic assumptions, and support the theory with numerical experiments.

AI 总结：本文提出Krum-Proxy攻击，通过两阶段优化等技术绕过联邦学习的Krum等基于距离的鲁棒聚合，在保持干净准确率的同时提升了攻击成功率，暴露了此类聚合方法的脆弱性。

链接：https://arxiv.org/abs/2608.06637

作者：Srinivasan Subramanian, Md. Abdullah Al Hafiz Khan, Kazi Aminul Islam

英文摘要：Robust aggregation methods are widely used in federated learning to mitigate the impact of adversarial client behavior. Distance-based aggregation rules, such as Krum and Multi-Krum, select updates that are closest to the majority under the assumption that benign updates form a compact cluster. However, these methods rely on geometric properties that can be exploited by adaptive adversaries. We introduce the Krum-Proxy attack, a selection-aware backdoor injection strategy that consistently bypasses Byzantine-robust aggregation. Rather than relying on naive scaling or constraining, our method actively optimizes malicious updates to infiltrate the dense core of the benign distribution. The proposed method constructs adversarial updates that are not only similar to benign updates but are also optimized to lie in regions of the update space that are favored during aggregation. This is achieved through a two-stage optimization procedure that separates task-specific attack objectives from geometry-aware refinement, using a nearest-neighbor proxy, stochastic reference modeling, and anchor-guided alignment. To maintain stealth, we introduce a projection mechanism that constrains adversarial updates within realistic norm and variance bounds. Experiments on standard federated learning benchmarks show that Krum-Proxy achieves higher attack success while preserving clean accuracy, highlighting the vulnerability of distance-based aggregation to selection-aware adversaries.

AI 总结：该研究以HAS-FL为案例，发现自适应子模型联邦学习中更新差异估计受容量混淆影响，自适应分配存在失效模式，且其收益源于容量预算与覆盖，而非分配智能。

链接：https://arxiv.org/abs/2608.07157

作者：Alireza Moayedikia, Alicia Troncoso Lora

英文摘要： Sub-model federated learning lets resource-constrained clients train width-reduced versions of a global model, but existing methods allocate capacity by device resources alone. A natural next step, allocating capacity by each client's data heterogeneity as estimated from the updates the server already observes, has been repeatedly suggested. We ask whether that step is possible, using HAS-FL, an adaptive capacity-allocation framework, as a test case. Our findings are threefold. First, validated against ground-truth label-distribution divergence on reproducible partitions, update-divergence estimates of client heterogeneity are dominated by capacity rather than data: across two corrected estimators, multiple datasets, and all seeds, the estimates correlate strongly and negatively with device capacity, and no data signal remains once capacity is controlled for. This previously undocumented confound affects any method estimating client statistics from sub-model updates. Second, adaptive allocation has a hidden failure mode: when every client is capped below full width, the uncovered parameters stay at random initialization and progressively corrupt the global model. A simple coverage guarantee removes the failure and explains why uniform allocation collapses. Third, a matched-budget control settles what adaptivity contributes: random allocation to the same average budget performs no differently on both image benchmarks, and on the naturally partitioned text benchmark the adaptive policy is the weakest of the three strategies while consuming the most capacity. Sub-model training remains valuable because it admits constrained clients at quadratically reduced cost, but what protects accuracy is parameter coverage rather than allocation intelligence. Its apparent benefits come from capacity budgeting and coverage, and future designs need heterogeneity signals separable from capacity effects.

AI 总结：针对分裂式联邦学习的投毒攻击，本文提出TOFD框架，通过目标推理、样本净化、解耦优化三阶段防御，在五个数据集上优于现有最优防御，鲁棒性高且开销低，适用于实际部署。

链接：https://arxiv.org/abs/2608.07274

机构：Shanghai University of Finance and Economics（上海财经大学）

作者：Yuhan Xie, Jingrong Huang, Chen Lyu

英文摘要：Split Federated Learning (SFL) facilitates privacy-preserving collaborative training with reduced client-side overhead. However, its split architecture introduces unique attack surfaces, rendering it vulnerable to diverse poisoning attacks. Most existing defenses fail to exploit the split paradigm, limiting their ability to detect and contain malicious behaviors at an early stage. To bridge this gap, we propose Target-Oriented Feature Decoupling (TOFD), a unified framework that jointly enables proactive detection and robust optimization against a wide range of poisoning attacks. TOFD operates in three stages: (1) Target Inference, which identifies potential attack targets by refining class-wise safe zones via class-specific Margin Perturbation (MP); (2) Sample Purification, which adaptively filters poisoned smashed data using thresholds calibrated through cross-class min-max normalization of MP; and (3) Decoupling Optimization, which leverages an adversarial guidance model to capture attack-induced patterns and decouple their influence during optimization, thereby suppressing residual adversarial effects. We provide theoretical guarantees for the convergence of TOFD. Extensive experiments on five datasets demonstrate that TOFD consistently outperforms state-of-the-art defenses under diverse attack scenarios, achieving superior robustness with low computational overhead suitable for practical deployment.

AI 总结：FedDOSE是分解站点效应的联邦学习框架，通过模块化引导Tucker分解等技术处理多站点fMRI的动态功能连接，在ASD和ADHD检测中性能优于现有方法。

链接：https://arxiv.org/abs/2608.07393

机构：Nanyang Technological University（南洋理工大学）； Shanghai Jiao Tong University（上海交通大学）； Indian Institute of Technology Ropar（罗帕尔印度理工学院）

作者：Deepank Girish, Yi Hao Chan, Yubin Zheng, Sukrit Gupta, Jagath C. Rajapakse

英文摘要：Functional Magnetic Resonance Imaging ( fMRI ) data are often pooled into collaborative multi-site consortia, as deep learning models for analyses require large datasets to generalize well. While Federated Learning (FL) offers a privacy-preserving paradigm for collaborative training, standard approaches continue to struggle with statistical heterogeneity. In particular, site differences pose a key challenge in multi-site data settings. Additionally, existing FL approaches for fMRI rely on static Functional Connectivity ( FC), omitting dynamic information in brain networks. To address this, we propose FedDOSE, a novel framework that explicitly decomposes site differences for analysis of dynamic FC (dFC). FedDOSE introduces a Modularity-Guided Tucker Decomposition block to encode high-dimensional dFC tensors and capture modular-level spatio-temporal patterns efficiently. Class-specific prototypes are generated across all sites and subsequently aligned at the global level by using a combination of Optimal Transport (OT) barycenter formulation and Procrustes analysis. Extensive experiments for diagnosing Autism Spectrum Disorder (ASD) and Attention-Deficit Hyperactivity Disorder (ADHD) on three multi-site resting-state fMRI datasets: ABIDE-I, ABIDE-II, and ADHD-200, demonstrate that FedDOSE outperforms state-of-the-art methods in ASD and ADHD detection. Our results highlight its effectiveness in learning robust representations from multi-site datasets for reliable analysis.

AI 总结：针对感知噪声下智能体决策问题，该研究构建人工生命捕食者-猎物觅食模型，发现不确定性感知策略可提升智能体存活率，揭示了行为随不确定性的状态转变，为含噪声标签的鲁棒学习提供类比。

链接：https://arxiv.org/abs/2608.06420

机构：University of Waterloo（滑铁卢大学）

作者：David Szczecina

英文摘要：Perception in biological systems is inherently noisy, requiring organisms to make decisions under uncertainty where misclassification can be costly or fatal. We present an Artificial Life predator-prey model of foraging under noisy perception, and compare agent performance when using various policies that take into account their noisy predictions. Through controlled experiments under both symmetric and asymmetric perceptual noise, we show that blindly trusting perceptual labels leads to catastrophic failure as noise increases, while uncertainty-aware strategies significantly improve survival and reduce fatal errors. We further observe qualitative regime shifts in behaviour, with agents transitioning from exploratory to conservative strategies as uncertainty increases. Our model links risk-sensitive foraging, ecological information use, and Artificial Life by showing that explicit information gathering can improve robustness when perception is unreliable. These results highlight the importance of uncertainty-aware decision-making and provide an interpretable artificial life analogue to robust learning with noisy labels.

AI 总结：该研究发现大型语言模型的量化损伤是乘法性的，而非加法性的，提出边际收缩概念，拟合关系可准确预测决策翻转率，增加1位是修复损伤最廉价的方式。

链接：https://arxiv.org/abs/2608.06564

机构：Holistic AI（霍利斯提克人工智能公司）； University College London（伦敦大学学院）

作者：Zekun Wu, Swati Dhiman, Adriano Koshiyama

英文摘要：Quantization is how large language models are actually deployed, and below four bits it is known to hurt. What nobody can say is which of the model's decisions will change at a given bit-width. The damage is silent: a compressed agent stops calling its tools, then loses half its safety refusals, yet benchmark scores barely move. Prior work assumes quantization adds noise of a roughly fixed size, which would make confident decisions safe. We measure the decision itself instead. The margin of a two-way decision is the model's score for the option it picks minus the score of its best alternative; we track it before and after quantization across 16 models from 8 model families, three quantization methods, and bit-widths from 8 down to 2. Quantization does not add fixed-size noise to the margin. It multiplies the margin by a factor that collapses with bit-width (median 0.86 at 4 bits, 0.33 at 3, 0.00 at 2); we call this margin shrinkage. This contraction reduces the protection a large margin affords; the model's own small biases pick the direction of failure: at 3 bits the decision to call a tool collapses toward inaction while the choice of which tool is untouched. In fitted statistical comparison, additive-noise accounts never win on the damaged tool and safety decisions. The fitted relation predicts flip rates within a median of 1.8 percentage points on held-out decisions, though no flip was used in the fit; per decision, the predicted flip probabilities are calibrated uncertainty estimates (expected calibration error 0.004 over 131,758 predictions). The same form holds in every model we measure, but the constants are each model's own and do not transfer. A small paired margin set, measured per model and bit-width, estimates which decisions break without full generative evaluation; under our cost-matched tests, nothing repairs damage more cheaply than one more bit.

AI 总结：针对超越反馈的在线共形预测场景，本文提出OCPQ方法，将标签高效预测器适配到该设置，实现了低查询率下的高覆盖率，且在真实数据集上验证了其有效性。

链接：https://arxiv.org/abs/2608.07139

作者：Joar Skalse, Edoardo Pona, Osvaldo Simeone, Nicola Paoletti

英文摘要：Uncertainty quantification is essential when deploying machine learning models in safety-critical applications. Online conformal prediction (OCP) provides theoretically principled uncertainty quantification for arbitrary black-box classifiers and non-i.i.d. data streams by constructing prediction sets that are guaranteed to contain the true label at a user-specified frequency. OCP usually updates prediction sets using feedback from previously deployed predictions. We instead study an OCP setting beyond feedback: on each round, the learner can either output a prediction set or query the correct label, but not both. Thus, no deployed prediction is ever evaluated directly. We reduce this problem to a partial monitoring game in which prediction actions return no observation and a separate query action reveals the label. The reward function is constructed in a way that encourages the learner to output small prediction sets while ensuring that the correct label is covered with a sufficiently high probability. To solve this game, we develop OCP with queries (OCPQ) by adapting the label efficient forecaster of Cesa-Bianchi, Lugosi, and Stoltz (2004) to our setting. For any black box classifier and any (non-i.i.d.) oblivious data stream of length $T$, OCPQ has $O(T^{2/3})$ expected regret and expected coverage at least $\beta-O(T^{-1/3})$ for a user-defined $\beta$, while querying only an expected $T^{-1/3}$ fraction of rounds. This provides coverage comparable to bandit-based OCP methods while requiring no feedback from deployed prediction sets. Experiments on real-world datasets further demonstrate the effectiveness of our approach.

AI 总结：MiGHT-EHR是针对异构时序EHR的多任务图变换器，在MIMIC-III/IV数据集上的四项临床预测任务中优于现有最优方法，且表示具有临床可解释性。

链接：https://arxiv.org/abs/2608.06430

作者：Anirudh Rayas, Yuan Wang, Pavan Turaga

英文摘要：Learning from Electronic Health Records (EHRs) has gained significant attention due to its potential to improve clinical prediction. However, effective learning remains challenging because EHRs encode heterogeneous, temporally ordered clinical interactions. In particular, EHRs contain: (i) heterogeneous clinical entities, including patients, visits, diagnoses, prescriptions, and procedures, together with their heterogeneous interactions, (ii) longitudinal patient trajectories across hospital visits and (iii) shared statistical dependencies across related clinical prediction tasks. Existing EHR learning methods capture only a subset of these properties. To bridge this gap, we propose Multi-task Graph transformer for Heterogeneous Temporal EHRs (MiGHT-EHR), which jointly models all three within a unified representation learning method. MiGHT-EHR constructs a heterogeneous graph from EHRs in which nodes represent clinical entities and edges connect statistically associated entities identified via normalized point-wise mutual information. Across MIMIC-III and MIMIC-IV datasets, MiGHT-EHR outperforms state-of-the-art methods on average across four tasks: drug recommendation, prediction of length-of-stay, mortality, and readmission, with particularly strong improvements in mortality and readmission prediction. Furthermore, a post-hoc analysis of the learned representations reveals that patient neighborhoods are organized by clinical outcomes, salient medical concepts are recoverable as linear directions in the representation space, and task probabilities are well calibrated. Collectively, these findings demonstrate that MiGHT-EHR representations support diverse prediction tasks while preserving clinically interpretable structure.

AI 总结：SNI-GNN是借助SmartNIC的全图GNN训练系统，通过网络内嵌入预测减少通信，在保持精度的同时实现21%-45%通信量降低，1.3-3.6倍加速，可高效扩展至16个GPU。

链接：https://arxiv.org/abs/2608.06441

作者：Guofan Yu, Sitian Chen, Zhenheng Tang, Xiaowen Chu, Amelie Chi Zhou

英文摘要：Full-graph GNN training delivers high accuracy but scales poorly on multi-server clusters due to heavy, irregular inter-node embedding exchanges. We present SNI-GNN, a SmartNIC-assisted full-graph training system that reduces communication while preserving accuracy by predicting remote embeddings in-network. SNI-GNN deploys a lightweight linear-trend predictor on SmartNICs to refine cached historical embeddings, coupled with an importance-based boundary-node sampling policy and an asynchronous DPU--GPU data pipeline with intermediate-result reuse. We provide error and convergence bounds showing that predictor bias remains controlled under bounded second-order dynamics and yields standard non-convex convergence with inexact gradients. Implemented on NVIDIA BlueField-3, SNI-GNN integrates with state-of-the-art full-graph systems, cuts communication by 21--45\%, achieves 1.3--3.6$\times$ end-to-end speedups over BNS-GCN and up to 1.29$\times$ over baseline SANCUS, with accuracy loss $\leq 0.01$, and scales efficiently to 16 GPUs on graphs with up to tens of millions of edges. These results indicate SmartNIC-based in-network prediction is a practical complement to partitioning and compression techniques for communication-efficient full-graph GNN training at scale.

AI 总结：提出Accounting Graph Transformer模型，针对小企业短历史数据完成13项财务KPI的12个月联合预测，在多组测试集上均优于LightGBM等基准模型，为企业财务分析提供集成预测层。

链接：https://arxiv.org/abs/2608.07037

机构：Foresight-AI, Intuit（富睿特远见人工智能实验室，Intuit公司）

作者：Shrutendra Harsola, Vignesh Subrahmaniam

英文摘要：Small businesses often have only 12-24 months of accounting history, yet planning and risk workflows require coordinated forecasts across financial statements. We study joint 12-month forecasting of 13 income-statement, balance-sheet, cash-flow, and working-capital key performance indicators (KPIs) from 71 monthly ledger series. We introduce the Accounting Graph Transformer (AGT), which represents each ledger series as a masked token, exchanges information through typed attention on a fixed accounting-relation graph, pools target-specific context, and fuses it with a gated three-month recency path. Across 11,993 forecast origins from 1,060 unseen companies, AGT achieves sample-weighted KPI-macro mean absolute error (MAE) $0.6990 \pm 0.0013$ over three independent seeds, compared with $0.7378 \pm 0.0014$ for the strongest baseline, LightGBM. At the pre-specified seed 42, a paired company-clustered bootstrap gives a LightGBM-minus-AGT difference of 0.0395 with 95% confidence interval (CI) $[0.0350,0.0439]$. AGT is best on all 13 KPIs against LightGBM, TimeMixer, and SOFTS in the matched seed-42 comparison, while final-architecture ablations show that relational attention, accounting topology, and the recency path each improve validation and test accuracy. On 7,094 additional unseen companies with origins sampled from January-May 2025, AGT obtains 0.7548 MAE versus 0.7694 for SOFTS. A single 5.3M-parameter model produces 156 aligned forecasts without company-specific fitting, providing one forecasting layer for integrated planning, liquidity, and working-capital analysis.

AI 总结：Fluid-DiT是一种无图扩散Transformer，以注意力去噪替代图消息传递，通过隐空间公式解耦几何保真度与分布学习，在流体流动模拟的基准测试中优于图扩散基线，且泛化性与可扩展性强。

链接：https://arxiv.org/abs/2608.07161

机构：CMU（卡内基梅隆大学）； DP Tech（德璞科技）

作者：Shentong Mo, Guolin Ke

英文摘要：Simulating complex fluid flows requires capturing full equilibrium distributions rather than just mean trajectories, yet high-fidelity solvers remain computationally prohibitive. Recent advances, such as Diffusion Graph Networks (DGNs), have combined diffusion models with graph neural networks to sample equilibrium states directly from unstructured meshes, enabling distributional accuracy even from short simulations. However, graph-based diffusion approaches suffer from hand-crafted architectural constraints, limited receptive fields in message passing, and costly multi-scale designs, which restrict scalability to larger and more complex domains. We propose Fluid-DiT, a Graph-Free Diffusion Transformer that replaces graph message passing with attention-based denoising, eliminating explicit graph design while preserving the ability to model distributions of chaotic flows. Our framework introduces a latent-space formulation that disentangles geometric fidelity from distributional learning, reducing high-frequency artifacts and accelerating sampling. By leveraging the transformer's global receptive field, Fluid-DiT naturally captures both local flow structures and long-range correlations without requiring hierarchical graph coarsening. On canonical benchmarks including laminar cylinder wakes, ellipse-flow systems, and turbulent 3D wing experiments, Fluid-DiT consistently outperforms graph-based diffusion baselines in both sample quality and distributional accuracy, achieving higher $R^2$ correlations and lower Wasserstein distances. Moreover, it generalizes robustly from short, incomplete trajectories to unseen Reynolds numbers and geometries, demonstrating strong scalability.

AI 总结：本研究提出时间相关性波动性（TCV）指标，发现高TCV下GNN等模型泛化差，进而提出GLIDE层，在合成与真实基准上使平均性能最高提升45.6%。

链接： https://arxiv.org/abs/2608.07333

机构：Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）； The Hong Kong University of Science and Technology（香港科技大学）； East China Normal University（华东师范大学）； University of Michigan（密歇根大学）

作者：Chen Shao, Yue Wang, Zhenyi Zhu, Zhanbo Huang, Tobias Käfer, Zonghan Wu, Danai Koutra

英文摘要：Modeling multivariate time series by representing them as graphs, where individual series act as nodes and pairwise temporal corre- lations serve as edges, has gained significant traction. Recent advances in Graph Neural Networks (GNNs) have demonstrated strong perfor- mance by assuming a static graph topology and aggregating information from neighboring series. In this work, we investigate the representa- tional power of GNNs for forecasting under both static and dynamic settings (i.e., when pairwise correlations evolve drastically over time) and identify critical limitations in current architectures. To formalize this, we first propose Temporal Correlation Volatility (TCV), a model- agnostic metric designed to quantify the distributional evolution of these latent structures. We establish a clear connection between TCV and performance degradation, demonstrating that many popular models, including Transformers, generalize poorly in high-TCV settings and are often outperformed by simple structure-agnostic baselines. To address these limitations, we propose Graph Layer for Inference in Dynamic En- vironments (GLIDE), a novel GNN layer enhanced by two theoretically grounded design mechanisms: (D1) Path-based Message Passing, which captures path-based neighborhoods and (D2) Static and Dynamic Propagation Separation, which identifies optimal dynamics via local static approximation. These components significantly improve learning under dynamic topology while preserving robustness in static scenarios. Ex- tensive experiments on synthetic and real-world benchmarks show that GLIDE improves average performance by up to 45.6% across static and dynamic settings, with the largest gain reaching 85.7%. The source code is available at this https URL.

AI 总结：针对LLM偏好对齐导致的过度自信与校准问题，提出基于双层优化的校准方法，通过最大化预测分布熵实现，在多项选择与开放式问答任务中提升了校准效果与域外泛化能力。

链接：https://arxiv.org/abs/2608.07419

机构：Dartmouth College（达特茅斯学院）； University of Pennsylvania（宾夕法尼亚大学）； National University of Singapore（新加坡国立大学）

作者：Ruochen Jin, Zhanliang Wang, Zongyu Dai, Jiancong Xiao, Bojian Hou

英文摘要：Preference alignment often makes large language models (LLMs) overconfident and poorly calibrated. Traditional post-hoc temperature scaling is inherently domain-dependent: a temperature fitted on one domain does not generalize across domains. This motivates us to modify model parameters during training to improve calibration. We propose maximizing the entropy of predictive distributions as the calibration objective, which directly targets overconfidence by discouraging overly concentrated predictions. Inspired by temperature scaling, we realize this through a bilevel optimization formulation, where the lower level trains the model under a parametric loss and the upper level selects loss hyperparameters to maximize entropy. To make the framework practical at LLM scale, we adopt an efficient first-order approximation that avoids explicit second-order computation. Across both multiple-choice and open-ended generative question answering, experiments demonstrate that our method yields well-calibrated LLMs with particular advantages in out-of-domain generalization.

AI 总结：该研究提出ED-CSP框架，结合关系集编码器等模块，基于化学成分等预测晶体结构，在ED-CS数据集上训练后，其MR@5指标优于现有模型，具备生成式预测能力，为相关研究建立了基准。

链接：https://arxiv.org/abs/2608.06448

作者：Germain Poloudenny, Yaël Frégier, Arnaud Demortière

英文摘要：Recovering a periodic 3D crystal structure from sparse, unindexed electron diffraction (ED) observations is a challenging generative inverse problem. Existing ED-based learning methods mainly predict crystallographic labels, reconstruct structures from indexed reflections, or retrieve candidates from finite structure libraries. Here, we introduce ED-CSP, a machine learning framework that predicts crystal structures from chemical composition, atom count, and multiple detector-plane ED spot sets. ED-CSP combines a relational set encoder, permutation-invariant multi-view aggregation, and a periodic flow generator to jointly predict lattice parameters and fractional atomic coordinates. To train the model, we construct ED-CS, a dataset of 4.85 million simulated multi-view ED crystal structures, deduplicated across seven materials repositories and filtered to exclude CHILI-100K overlaps. On 2,075 held-out CHILI-100K materials, ED-CSP trained only on CHILI achieves a structural match rate of 57.49% MR@5, outperforming PXRDGen (52.92%), a state-of-the-art crystal structure prediction model conditioned on powder X-ray diffraction. Scaling training data further improves performance: initializing from a one-million-structure precursor raises MR@5 to 66.27%. On 1,024 compositions absent from the training retrieval library, the model still achieves 53.52% MR@5, demonstrating true generative capability beyond exact-formula retrieval. Replacing target ED observations with diffraction from non-isomorphic structures of identical composition decreases MR@5 by 22.09 percentage points, confirming that predictions depend on the input diffraction patterns rather than composition alone. ED-CSP and ED-CS establish a benchmark for generative crystal structure prediction from sparse ED observations and provide a foundation for future transfer to experimental data.

AI 总结：该研究提出NS-RIS算法学习隐量子马尔可夫模型，使其在非量子生成序列数据上优于经典HMM，在多基准任务中提升性能并降低运行时间，推动HQMM成为实用序列数据模型。

链接：https://arxiv.org/abs/2608.06554

机构：Texas A&M University（德克萨斯农工大学）

作者：Ning Ning

英文摘要：Hidden Markov models (HMMs) are widely used probabilistic models for discrete sequential data but can be limited when hidden dynamics are complex. Hidden quantum Markov models (HQMMs) generalize HMMs by replacing probability vectors with density matrices and stochastic transitions with quantum operations, enabling richer latent representations. However, existing HQMM learning methods have not consistently outperformed Expectation--Maximization (EM)-trained HMMs on data not generated by quantum processes, limiting their practical applicability. We introduce NS-RIS, Newton--Schulz Retraction-based Inference on the Stiefel manifold, a scalable algorithm for learning trace-preserving HQMMs. NS-RIS uses Newton--Schulz orthogonalization to compute a polar-factor search direction while preserving Stiefel-manifold feasibility, avoiding costly matrix decompositions. We further establish a finite-time stationarity guarantee under standard assumptions on smoothness, stochastic gradients, and finite Newton--Schulz accuracy. Empirically, NS-RIS provides the first benchmark evidence that an HQMM can significantly outperform an EM-trained HMM on data not generated by a quantum model. On synthetic HMM-generated benchmarks, NS-RIS outperforms both EM and the state-of-the-art HQMM method COSM, improving the evaluation metric by an average of 38.5% and by up to 50.6%. On a synthetic HQMM benchmark, it improves the test metric over COSM by 18.9% while reducing runtime by 12.0%. On the real-world Splice classification benchmark, NS-RIS also surpasses both EM and COSM in higher-dimensional latent regimes, reducing mean classification error by 17.9% for latent dimension 6 and 14.9% for latent dimension 8 relative to COSM. These results move HQMMs beyond a theoretical generalization of HMMs and establish them as practical and expressive models for scientific sequence data.

AI 总结：研究提出ArchEGraph大规模图数据集，定义两个基准任务并开展泛化实验，为建筑能源建模的几何-拓扑-物理耦合研究提供统一测试平台，支持替代模型开发评估。

链接：https://arxiv.org/abs/2608.06772

机构：Tsinghua University（清华大学）； UC Berkeley（加州大学伯克利分校）； MIT（麻省理工学院）

作者：Yihui Li, Yihui Chen, Kaidi Zha, Xiaoyue Yan, Zhexuan Yu, Shiqi Dai, Jun Xiao, Jun Yin, Ramon Elias Weber, Borong Lin

英文摘要：Accurate estimation of building energy use is essential for achieving carbon neutral and sustainable buildings. To better understand the influence of design decisions on building energy use and calibrate machine learning models that can give architects and engineers rapid design feedback, large-scale datasets are needed that explicitly map building geometry to performance. We present ArchEGraph, a large-scale benchmark dataset that represents buildings as heterogeneous graphs with aligned geometry, topology, weather, and zone-level thermal loads. The dataset contains 5,481 buildings and 49,326 validated building-weather simulation cases. In total, it includes over 133,000 space nodes and 1.44 million face nodes, reflecting substantial geometric and topological complexity. Based on ArchEGraph, we define two benchmark tasks: (i) graph reconstruction from polygonal meshes, aiming to recover topological structure from geometric representations; and (ii) topology-informed load prediction, which leverages graph structure and temporal weather conditions to forecast zone-level response time series. We further introduce standardized evaluation protocols for both tasks and conduct cross-building and cross-climate generalization experiments to assess model robustness. ArchEGraph provides a unified testbed for studying geometry-topology-physics coupling in building energy modeling, enabling the development and evaluation of scalable and generalizable surrogate models.

AI 总结：该研究构建含29870条评分的步行性数据集，提出用户条件多模态深度学习框架，发现人行道图像评分更高，模型一致性提升65%，助力构建更包容的行人环境评估模型。

链接：https://arxiv.org/abs/2608.06934

机构：School of Civil and Environmental Engineering, University of New South Wales (UNSW)（新南威尔士大学土木与环境工程学院）； Research Centre for Integrated Transport Innovation (rCITI)（综合交通创新研究中心）

作者：Moloud Damandeh, Meead Saberi

英文摘要：Visual perception of walkability varies substantially across individuals, reflecting differences in personal characteristics, experiences, and preferences. Existing studies, however, often reduce these diverse judgements to aggregated scores, implicitly assuming uniform perception, and commonly rely on vehicle-mounted street-view imagery that does not reflect the pedestrian's visual experience. This paper introduces a dataset of 29,870 walkability ratings from 1,196 respondents, linking sidewalk-view imagery across urban, suburban, and regional Australian environments with individual rater attributes, and proposes the first user-conditioned multimodal deep learning framework for walkability perception, fusing visual features with respondent-level representations. A viewpoint-comparison study shows that sidewalk-view images receive significantly higher walkability ratings than matched street-view images, indicating that imagery source is a substantive design decision in perception surveys. The user-conditioned model improves rank agreement with observed ratings by 65% over an image-only baseline (quadratic weighted kappa 0.47 vs. 0.29), demonstrating that who is evaluating an environment carries predictive indication beyond image content alone. These findings support moving from aggregated, observer-independent walkability scores toward models that represent diverse users, enabling more inclusive assessment of pedestrian environments.

AI 总结：本文针对三维深度学习框架在边缘设备部署的瓶颈，提出适配树莓派5的硬件受限工作流，通过合成LiDAR数据集和特征驱动的CPL层，实现边缘端50 FPS推理与88.36%分类准确率，验证了边缘实时三维感知的可行性。

链接：https://arxiv.org/abs/2608.07106

机构：Chemnitz University of Technology（开姆尼茨工业大学）

作者：Niclas Meyer, Stefan Reitmann

英文摘要：Deploying three-dimensional deep learning frameworks to low-power embedded processors is bottlenecked by the unstructured nature of spatial data and the resource-intensive distance sorting algorithms often used before neural network inference. To address this gap, this paper presents a hardware-constrained workflow optimized for native execution on the Raspberry Pi 5. To account for the reality gap between noiseless, clean computer-aided design (CAD) datasets and real-world sensor data, we use physics-based simulation to construct a synthetic LiDAR dataset. Cross-dataset evaluations demonstrate a substantial drop in classification accuracy when networks trained on clean CAD data are evaluated on synthetic LiDAR sensor data, highlighting the critical need for sensor-aware training. To address the latency bottleneck of traditional geometric preprocessing on edge CPUs, we integrate an isolated, feature-driven Critical Points Layer (CPL) as a frontend filter. Our results show that the pretrained CPL deterministically compresses raw 1024-point clouds to a subset of 40 to 60 unique coordinates. When profiled on the ARM Cortex-A76 processor, the complete pipeline achieves an inference throughput of approximately 50 FPS while maintaining an instance classification accuracy of 88.36%, demonstrating the viability of deterministic real-time 3D perception at the edge.

AI 总结：本研究针对动态图学习中大规模时序图计算挑战，提出TRicci框架，通过时序Forman-Ricci曲率实现边稀疏化，可在保持预测性能的同时缩短训练推理时间。

链接：https://arxiv.org/abs/2608.07158

机构：University of Manitoba（曼尼托巴大学）； University of Central Florida（中佛罗里达大学）

作者：Poupak Azad, Cuneyt Gurcan Akcora, Kiarash Shamsi

英文摘要：Temporal graph learning has become essential for analyzing real-world systems whose interactions continuously evolve over time, including financial transaction networks, communication systems, and online social platforms. However, learning from large-scale temporal graphs remains computationally challenging when networks are dense and rapidly changing. To address this limitation, we propose a network-curvature-inspired edge sparsification framework for dynamic graph learning. Our proposed method, TRicci, extends classical Forman-Ricci curvature to directed weighted temporal graphs by capturing structural support, temporal recency, and local interaction competition. Experiments on 9 transaction networks and 3 temporal graph benchmark datasets demonstrate that the proposed framework preserves predictive performance across multiple graph-level prediction tasks. The results show that TRicci sparsifies temporal graphs by approximately 80% while reducing end-to-end downstream training and inference time by an average of 55.94%, without substantial degradation in predictive performance. Our findings suggest that temporal curvature can serve as a principled basis for scalable temporal graph learning by preserving predictive temporal-structural information under substantial sparsification.

AI 总结：本文提出固定与自适应拓扑DeepONet，将点样本替换为Hausdorff局部凸空间对偶的连续线性泛函，在多算子任务上验证其性能，为非可赋范空间提供紧凑可移植的函数坐标。

链接：https://arxiv.org/abs/2608.06428

机构：Division of Applied Mathematics, Brown University（布朗大学应用数学系）

作者：Khemraj Shukla, George Em Karniadakis

英文摘要：Deep Operator Networks (DeepONets; arXiv:1910.03193 ) typically encode an input function through point values on a fixed discretization. Building on the Topological DeepONet framework of Ismailov ( arXiv:2603.11972 ), we replace point samples by continuous linear functionals drawn from the continuous dual of a Hausdorff locally convex space $({V},\{p_\alpha\}_{\alpha\in A})$, whose topology is generated by a point-separating family of seminorms rather than a single norm, and develop fixed and adaptive functional measurement systems. Measurements are combined with the coefficient-space Two-Step procedure of Lee and Shin ( arXiv:2309.01020 ), while a training-only decoder and regularization stabilize the adaptive coordinates. We derive a discrete error decomposition separating measurement, output-basis, and neural-approximation errors, together with a Barron-rate refinement. The framework is evaluated on the antiderivative operator, a non-normable locally convex input space, heterogeneous Darcy flow, a controlled operator, and fixed-time and time-evolving Navier-Stokes vorticity operators. In the heterogeneous Darcy problem, the functional models retain nearly resolution-independent errors of 5.5-5.6% on unseen grids, while in the controlled problem adaptive measurements reduce the mean error below 1.2%. For the fixed-time Navier-Stokes problem, the Adaptive Topological DeepONet is the most accurate DeepONet-based model, attaining a mean relative $L^2$ error of 1.685% +/- 0.017% using 128 functional coordinates. A comparably sized Fourier neural operator (FNO; arXiv:2010.08895 ) achieves the lower error 0.832% +/- 0.172%, but requires the full 64x64 input field, twice the training time, and 10.7x greater peak GPU memory. The formulation provides compact, interpretable, and discretization-portable coordinates in the continuous dual $V'$, including for non-normable input spaces.

AI 总结： 该研究提出EpiFlow框架，通过处理污水数据、分析其与疾病负担指标的关系，结合随时间变化的预测模型，在预测弗吉尼亚州COVID-19住院人数时，提升了预测准确性与覆盖率。

链接：https://arxiv.org/abs/2608.06671

机构：Biocomplexity Institute, University of Virginia（弗吉尼亚大学生物复杂性研究所）； Virginia Department of Health（弗吉尼亚州卫生部门）； US Department of Defense, Pentagon（美国国防部五角大楼）； Old Dominion University（奥多明尼昂大学）

作者：Aniruddha Adiga, Jingyuan Chou, Gursharn Kaur, Andrew Warren, Srinivasan Venkatramanan, Baltazar Espinoza, Bryan Lewis, Justin Crow, Alexandra Lorentz, Rekha Singh, Madhav Marathe

英文摘要：Wastewater-based surveillance is an effective tool for disease monitoring and can provide early warning of outbreaks. Although wastewater viral loads (WVL) correlate with disease burden, their utility for improving real-time forecasting remains under investigation. During the early phases of an epidemic, many indicators can effectively monitor disease spread, but their reliability may decline because of reporting fatigue and low prevalence. Hospital burden can vary substantially even during low-prevalence periods, making accurate forecasting of burden indicators essential for minimizing disease impacts. In this paper, we present principled approaches for processing wastewater data, characterizing its relationship with burden indicators, and generating real-time forecasts. We assess the predictability of WVL using entropy measures. We analyze the relationship between WVL and burden indicators using causality tests that capture temporal dynamics and the leading-indicator behavior of WVL. We incorporate these insights into a time-varying forecasting model that accounts for the evolving relationship between the signals. We also evaluate the effects of delays in WVL reporting through simulations. We test the utility of our methods by forecasting COVID-19 hospital admissions across Virginia and its health regions during periods of varying disease prevalence. Incorporating WVL improves forecast accuracy relative to baseline models, particularly during critical epidemic phases, and results in a 20 percentage point improvement in forecast coverage. Our results demonstrate that WVL signals can improve infectious disease forecasting even under conditions of low prevalence or delayed reporting.

AI 总结：KReF是一种无训练检索框架，将历史未来作为查询的局部经验预测分布，在多数LTSF基准上取得了优于或匹配训练基线的预测性能，确立了检索作为LTSF的有效归纳偏置的价值。

链接：https://arxiv.org/abs/2608.06748

作者：Yang Zhang, Rui Su

英文摘要：Probabilistic long-term time-series forecasting commonly relies on trained models. Training-free conformal methods typically construct intervals around a pre-existing point forecaster and do not natively represent a complete predictive distribution; sequential variants additionally suffer from increasingly delayed feedback at long horizons. We propose KReF, a training-free retrieval framework that treats retrieved historical futures as a querylocal empirical predictive distribution. After robust preprocessing, KReF embeds each lookback using handcrafted statistics or frozen random Fourier features and retrieves similar historical lookback-future pairs. Their similarity weights directly define predictive masses, quantiles, CRPS, and a weighted-mean point forecast. KReF further uses the observed query lookback to construct a probability-integral-transform map and applies validation-selected expansion and shrinkage rates to adapt interval boundaries. Across six LTSF benchmarks and four horizons, KReF obtains the lowest CRPS in all 12 dataset-embedding settings and the lowest IS90 in 9 settings. Without gradient-based fitting, its point forecasts also match or surpass trained baselines on two of six datasets. An archive-oracle analysis further reveals substantial headroom under finer horizon- and channel-wise routing. These results establish retrieval as a useful and underexplored inductive bias for LTSF.

AI 总结：该研究针对LLM监督中裁决数量增加导致一致性下降的问题，提出分片方法，可提升监督一致性、抵御对抗攻击，且分片后较弱裁判可超越更强的整体裁判。

链接：https://arxiv.org/abs/2608.06422

作者：Victor Akinwande, J. Zico Kolter, Aran Nayebi

英文摘要：Giving an LLM judge more compute does not necessarily make it check more requirements. When one call must return many verdicts, some decisions become weakly grounded in the evidence, even when that call receives the same token or tool budget as a panel of separate calls. Across expert-graded research replications, legal work, and clinical-trial assessments, agreement with experts falls as the number of verdicts per call grows. We identify sharding as the intervention that mitigates this failure in model-based oversight. Sharding partitions the requirements into smaller groups, assigns each group to a separate call, and aggregates the verdicts. Against a single call with the panel's full budget, sharding improves agreement while holding the model, evidence, total budget, and per-decision budget fixed. Overall, we find that a sharded weaker judge can outperform a more capable holistic judge and match that judge even when the latter receives the panel's full budget. Additionally, we find that sharding exhibits robustness against adversaries. A best-of-N adversary can hold the underlying work fixed, vary only its presentation, and increase an overloaded judge's acceptance of genuinely unmet criteria severalfold. Wherever sharding reduces baseline error, it removes this adversarial advantage, keeping over-acceptance low even as the adversary's search widens. Sharding does not address attacks that persuade the judge separately on each criterion rather than exploiting overload. In that setting, we find that debate-style opposition on top of sharding withstands such adaptive re-optimization.

AI 总结： 该研究针对BiomeGPT式微生物组Transformer的注意力权重局限，提出符号化集成梯度归因方法，结合二阶集成海森矩阵，可区分致病与保护性微生物信号，揭示群落相互作用规则，提升模型可解释性

链接：https://arxiv.org/abs/2608.06486

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

作者：Oren Nelson

英文摘要：In a feature-tokenized transformer ( arXiv:2106.11959 ) such as BiomeGPT (doi: https://doi.org/10.64898/2026.01.05.697599 ), each input token is built by fusing a fixed identity with a sample-specific measurement: a fixed species and a variable abundance, T = S + A. To interpret downstream classification in such models, prior work inspects the attention weights of the special [CLS] token ( arXiv:2106.11959, arXiv:1810.04805, BiomeGPT) to rank sample tokens by importance. These weights have two critical limitations: they are nonnegative, so they cannot separate disease-supporting from health-supporting evidence ( arXiv:2201.12114 ), and they act after token fusion, obscuring how the input sources S and A each affect the output. To address this we use Integrated Gradients ( arXiv:1703.01365 ), a signed, fusion-aware attribution method, and propose a source-derived baseline T' = S + A_0 for feature-tokenized models such as BiomeGPT, which preserves species identity as a fixed biological coordinate while isolating the effect of abundance variation. Applied to a disease-versus-health decision margin, it yields polarity that explicitly separates pathogenic from protective microbial signals. We show that this gradient-based approach uncovers species-abundance directional relationships and sensitivity diagnostics entirely obscured by unsigned [CLS] attention weights. We further recommend second-order Integrated Hessians ( arXiv:2002.04138 ) to expose microbiome community interaction rules: how a perturbation in one member alters the model's sensitivity to another, and which other species drive ambiguous cases toward disease or health at a given abundance level. This provides a principled approach to explainability in BiomeGPT that generalizes to other smooth and differentiable feature-tokenized transformers. Code is available at this https URL

AI 总结：该研究针对长 horizon 智能体上下文压缩的执行不稳定性问题，提出了验证器引导框架 TRACE，在 AppWorld 上的实验显示其在任务性能等指标上优于现有基线，为可靠上下文压缩提供了新方向。

链接：https://arxiv.org/abs/2608.06503

机构：University of Virginia（弗吉尼亚大学）； Nokia（诺基亚公司）

作者：Guanghui Min, Liang Wu, Mayank Darbari, Chen Chen, Liangjie Hong

英文摘要：Recurrent context compression controls context growth in long-horizon agents, but its behavioral effects remain poorly understood. In this preliminary empirical study, we show that compression can weaken the influence of recent interactions, increasing blocked actions, repeated exploration, and instability across runs. Motivated by these observations, we introduce TRACE, a verifier-guided framework that evaluates individual compaction events through paired closed-loop continuations from the same environment state and uses summary preferences to optimize a natural-language compression prompt while keeping all models frozen. Initial results on AppWorld show improvements over existing compression baselines in task performance, multi-run reliability, and context--execution efficiency. These findings provide early evidence for boundary-local evaluation as a promising direction for reliable agent context compression.

AI 总结：该研究针对自适应数据清洗中存在的移除预算混杂问题，提出匹配操作点评估框架，经 CIFAR-10、ImageNet-100 实验验证，可消除虚假性能提升，确保结果反映真实损坏区分能力。

链接：https://arxiv.org/abs/2608.06511

作者：Wei-Hsiang Chen, Pin-Hsuan Yu, Chen-Hsuan Fang, Jung-Hua Wang

英文摘要：Adaptive data-cleaning methods replace manual filtering thresholds with data-driven partitions. However, changing the partition granularity, the number of groups used to segment samples by estimated corruption risk, can implicitly shift the decision boundary and alter the overall number of removed samples. This creates a bias known as removal-budget confounding, where apparent gains in metrics like precision or false-positive rate reflect a smaller removal budget rather than superior corruption discrimination. To address this evaluation bias, we introduce an operating-point-aware evaluation framework that evaluates methods using matched-budget and matched-recall controls alongside threshold-independent metrics (AUROC and AUPRC). We test this framework on a multi-cue adaptive cleaner redesign featuring a reweighted learning-difficulty cue, an auxiliary Euclidean-distance cue, and increased partition granularity intended to isolate clean-but-difficult samples. While naive evaluations (assessing configurations at their own induced operating points) suggest substantial performance improvements for the redesign, these gains disappear once operating points are equalized. False-positive decomposition reveals that clean-but-difficult samples primarily drive error counts at low corruption rates, become threshold-dependent at moderate corruption, and contribute negligibly under severe corruption. Experiments on CIFAR-10 and ImageNet-100 demonstrate that most performance differences observed in naive evaluation shrink or vanish at low-to-moderate corruption when operating points are matched. True ranking advantages only remain in specific low-prevalence settings and in high-recall regions under severe corruption. These findings highlight that adaptive cleaning methods must be benchmarked at matched operating points to ensure performance gains reflect genuine corruption discrimination.

AI 总结：该研究针对分布偏移下异质性处理效应的实验设计问题，提出TWNA方法，通过两阶段分层设计平衡部署重要性与统计难度，在兼具部署重要性与测量难度的组上收益最大。

链接：https://arxiv.org/abs/2608.06512

机构：University of New South Wales（新南威尔士大学）； Florida Atlantic University（佛罗里达大西洋大学）

作者：Hoang Dang, Luan Pham, Minh Nguyen

英文摘要：Randomized experiments are often run in one population to guide decisions in another. Allocating by experimental proportions wastes budget on groups that rarely appear in deployment, whereas allocating by deployment proportions under-samples groups that are hard to measure precisely. We propose \textbf{TWNA} (Target-Weighted Neyman Allocation), a two-stage stratified design that uses pilot estimates of group--arm outcome variances to allocate final-stage sample sizes and treatment probabilities for target-weighted group average treatment effect (GATE) precision. The oracle rule has a closed form and balances deployment importance with statistical difficulty; the plug-in rule recovers it as pilot variance estimates stabilize. We also extend TWNA to handle uncertainty about deployment composition, remaining robust whether the target mix is roughly known or entirely unknown. Finally, we distinguish this weight robustness from a pilot-robust variant for skewed, rare-event, or contaminated outcomes. Simulations and real-covariate benchmarks show the largest gains when groups are both deployment-important and difficult to measure.

AI 总结：该研究提出CertBind多尺度理论，解决多模态编码器组合后的检索决策可验证问题，通过多尺度设计实现误差控制与恢复，在实验中验证了其对原生检索能力的可控性与无损害性。

链接：https://arxiv.org/abs/2608.06516

作者：Shuheng Cao, Zhenhao Zhang, Ruiqi Chen, Renjie Cao, Weijia Zhang, Siyu Zhang, Jiaxin Liu, Xiangyu Zeng, Haotian Geng, Fan Gu

英文摘要：Lightweight connectors make frozen multimodal encoders composable at the representation level. Deployment exposes a second problem at the level of task decisions. A connected route can expand cross-modal reach while changing an established native retrieval capability. We introduce CertBind, a multiscale theory of certifiable composition for frozen multimodal connector graphs. At the node scale, native anchors establish the exact task identification boundary under the stated chart model. At the edge scale, contract-aware conformal ranks provide graph-wide family-wise error control. At the path scale, an overlap-aware budget and clean calibration yield a finite-sample recovery radius under declared conditions. At the query scale, this radius yields a covered top-k candidate set that becomes a point certificate when its size equals k. CertBind therefore retains supported routes as Direct, sends only flagged routes to recovery, returns Certified for decisive recovery, and returns Abstain for unresolved queries. The evaluated C-MCR shared route reduced native CLIP R@1 from 0.524 to 0.290. The production fallback recovered 0.963 +- 0.002 of clean retrieval, while the passing branch recorded a no-harm value of 1.000. CertBind extends multimodal composability from connected representations to certifiable task decisions.

AI 总结：该研究针对现有密码分析提取方法无法恢复现代语言模型的无偏GLU前馈块的问题，提出多阶段前向查询恢复原语，在多种模型上实现亚百分位或低误差，且明确其非端到端攻击的性质。

链接：https://arxiv.org/abs/2608.06631

作者：Chunhui Shi, Xinwen Fu

英文摘要：Cryptanalytic extraction has been demonstrated for ReLU networks, for networks using componentwise activations such as GELU or SiLU, and for a Transformer's final projection matrix. These methods do not recover the bias-free Gated Linear Unit (GLU) feed-forward blocks used in many modern language models. Such a block multiplies an activated linear projection by a second learned linear projection within each hidden unit, a two-branch structure absent from the network classes and final-layer setting addressed by those methods. We give a constructive, multi-stage forward-query recovery primitive for isolated bias-free GLU blocks. Finite-difference curvature supplies gate-direction candidates, and paired observations at x and -x separate gate magnitude, orientation, and value-branch coupling. Across high-precision targets, six Qwen layers, an 8,192-unit Llama subproblem, and a full-dimensional Gemma block all reach sub-percent median validation error. Four finite-precision configurations remain below 5 percent median error, but none reproduces every stored weight. These isolated-block experiments are not an end-to-end model-API attack: deriving the required internal block responses from final model outputs remains unsolved.

AI 总结：本研究提出狄利克雷逐次学习器算法，解决了多类别U校准中预测器的悔策率差距问题，得到的算法对有界和光滑真损失均达到最优悔策率。

链接：https://arxiv.org/abs/2608.06656

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

作者：Pahan Dewasurendra

英文摘要：Can one forecaster attain the optimal regret rate for every bounded proper loss and also adapt to every smooth proper loss? Recent work answered this up to a dimension gap. Its self-concordant perturbation gives roughly $K^{5/4}\sqrt{T}$ worst-case regret and incurs an additional $\beta\sqrt{K}\log K$ for $\beta$-smooth losses. We close both gaps with a one-line forecaster. After observing class counts $c_{t-1}$, draw the next prediction from $\operatorname{Dir}(c_{t-1})$, on the face of classes seen so far. This is a fresh Bayesian bootstrap of the outcomes. The analysis rests on an exact identity: averaging any bounded proper loss under $\operatorname{Dir}(\alpha)$ equals a discrete derivative of its Dirichlet-averaged Bayes risk. The identity makes the be-the-perturbed-leader term telescope to a nonpositive Jensen gap. A one-count likelihood ratio then bounds stability by the inverse square root of that class's count. The resulting single, horizon-free algorithm satisfies $\sup_{\ell}\mathbb{E}\operatorname{Reg}_{\ell}\leq 4\sqrt{S_T T}\leq 4\sqrt{K T}$ and $\mathbb{E}\operatorname{Reg}_{\ell}\leq \frac{5}{2}\beta(1+\log T)$ for every $\beta$-smooth proper loss. Here $S_T$ is the number of observed classes. Known lower bounds show that both rates are optimal in their nontrivial regimes. The proof covers nondifferentiable losses and changes of the active simplex face.

AI 总结：本文针对异构设备罕见故障预测难题，提出可迁移自 logistic 模型，在含27台模拟冰箱的合成数据集上验证了模型的故障概率估计能力，为预测性维护提供支持。

链接：https://arxiv.org/abs/2608.06695

机构：Université de Sherbrooke（谢布鲁克大学）

作者：Islam Benamirouche, Djemel Ziou, Feriel Fass

英文摘要：Predicting failures before they occur remains a major challenge in predictive maintenance, particularly when failures are rare, when equipment of the same family differ in sensor configurations, and when the goal is anticipation rather than diagnosis of an already observed fault. This paper proposes a common-to-target probabilistic model that learns shared failure-related patterns across a family of heterogeneous equipment and adapts parsimoniously to target equipment. The model explicitly accounts for sensor heterogeneity, operating context, and degradation dynamics to produce calibrated failureprobability estimates suitable for maintenance planning. Its performance is evaluated on a synthetic refrigerator dataset comprising 27 simulated refrigerators with varying sensor configurations, operating conditions, and failure types, providing a controlle

AI 总结：该研究提出对决世界模型，通过在潜在动态中减去动作预测的平均效应来抑制共模干扰项，无需额外机制，在多个任务中可恢复智能体自身效应，适用于各类动作条件世界模型。

链接：https://arxiv.org/abs/2608.06706

作者：Jiazhuo Li, Yiming Fei, Zhiruo Zhou, Heikichi Hayashi

英文摘要：Latent world models plan by predicting future states from an action, but when a scene contains motion the agent does not control, they quietly go action-blind: predictions for different actions become indistinguishable even as the training loss keeps improving. Existing remedies suppress this distraction with reconstruction, task reward, or auxiliary objectives, each adding machinery or assumptions. We show that a minimal alternative suffices, borrowed from the dueling decomposition of value into a state baseline and an action advantage: in latent dynamics, subtracting a prediction's mean effect over actions cancels whatever the actions share--the action-independent variation where distractors live--leaving a clean, controllable channel, with no reward, no reconstruction, and no distractor-specific auxiliary loss. Because this is only a subtraction at readout time, it applies unchanged to any action-conditioned world model, including frozen pretrained ones. Across a gridworld, synthetic generators with known factors, distracting continuous control, and natural-pixel Atari, the isolated channel recovers the agent's own effect where entangled predictors fail, with nuisance leak indistinguishable from zero; applied post hoc it surfaces an action channel in off-the-shelf models that their raw readouts miss, and it converts into goal-reaching control in the gridworld. We prove the cancellation is exact in finite samples for both discrete and sampled action sets, and we state its measured boundary--distractors whose motion tracks the action--together with the remaining limitations in the appendix.

AI 总结：本研究提出混合策略决策树（MDT），用求解器输出引导LLM在博弈中的均衡推理，在无限制德州扑克8种LLM配置下，将与均衡的L1距离降低52.6%，且策略可移植性良好。

链接：https://arxiv.org/abs/2608.06741

机构：Shanghai Jiao Tong University（上海交通大学）； GTO Wizard； Tsinghua University（清华大学）； The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））； Vector Institute（向量研究所）

作者：Han Wang, Philippe Beardsell, Boning Li, Aaron Sasmita, Shuai Li, Hongyuan Zha, Baoxiang Wang

英文摘要：Reasoning in large language models (LLMs) is often grounded in human text, human demonstrations, and human-generated rationales. For equilibrium reasoning in complex games, however, relying on human data can be suboptimal. In fact, human play is often guided by intuition and heuristics and can deviate substantially from game equilibrium. This discrepancy is amplified in games with mixed-strategy equilibria, where human data is heavily biased toward pure strategies. Consequently, conditioning LLMs on this data yields weak game strategies. To grant LLMs the reasoning capacity in games, in this work, we study how to elicit equilibrium play using solver output. We propose Mixed-Strategy Decision Tree (MDT), which articulates the silent optimality of the equilibrium into sparse strategic rules that both humans and LLMs could understand. Using solver output rather than human annotation allows us to extend the input to arbitrarily new states and continuations. We instantiate this study on No-Limit Texas Hold'em by querying a solver oracle for over \textbf{250 million mixed-strategy decisions}; MDT together with other techniques \textbf{reduces the $\ell_1$ distance to the equilibrium by $52.6\%$} across $8$ different LLM configurations. A Route-only ablation tests the incremental contribution of the shadow-based contrast, while complete River-endgame and Liar's Dice experiments evaluate strategic fidelity and portability beyond the original NLH communication setting.

AI 总结：研究针对LLM推理的权重量化问题，提出CubicQuant参数化非均匀标量格式，其在不同分布下的重构误差优于现有方案，且具备高效GPU执行潜力。

链接：https://arxiv.org/abs/2608.06763

作者：Xuetian Gao

英文摘要：Weight quantization for large-language-model inference must balance adaptive reconstruction levels with representations regular enough for efficient GPU execution. Uniform integers constrain each group to a linear grid. Low-bit floating-point formats use a fixed exponent-mantissa structure, while learned codebooks gain flexibility at the cost of irregular decoding and additional metadata. We introduce CubicQuant, a parametric non-uniform scalar format that preserves a dense integer code stream while adapting reconstruction levels within each weight group. A monotonic cubic curve, specified by two shape parameters and one scale, maps uniformly spaced magnitude codes to non-uniform levels. The family spans 1-8-bit weight payloads, contains symmetric uniform integer quantization as an exact special case, and has effective width B + 64/G bits per weight for payload width B and group size G. We derive population distortion under Uniform, Gaussian, and Laplace distributions, formulate continuous and Dynamic-A8-carrier-aware fitting objectives, and describe direct packed-weight GPU execution. For finite groups of G=128 with 15,360 samples per distribution, W4 CubicQuant reduced reconstruction RMSE relative to optimally clipped four-bit uniform integer quantization by 3.90% on Uniform, 13.49% on Gaussian, and 28.14% on Laplace samples. Relative to the best enumerated four-bit finite floating-point format, the reductions were 3.90%, 9.44%, and 6.27%. Preliminary H200 kernel measurements show a workload-dependent crossover: model-dtype execution is faster for narrow GEMV, while Dynamic A8 becomes favorable as row count grows. The results establish the format's representational promise and direct executability; downstream model quality and cross-device end-to-end performance remain open evaluation questions.

AI 总结：该研究提出统一几何框架，整合多种可微嵌入诊断方法，证明积分视角不可约，实验验证其能准确估计单细胞嵌入可信性并区分不同类型嵌入。

链接：https://arxiv.org/abs/2608.06809

机构：Stony Brook University（石溪大学）

作者：Xinyu Zhang, Klaus Mueller

英文摘要：How can an analyst decide whether a nonlinear dimensionality reduction embedding can be trusted? Existing diagnostics provide only partial answers: projection glyphs characterize local sensitivity, map-continuity scores measure local conditioning, and transport-based analyses reveal path-dependent inconsistencies. However, these methods appear unrelated and provide no common framework for understanding when they agree or not. We show that they are all derived from a single geometric object induced by every differentiable embedding, whether defined implicitly through optimization or explicitly by a learned mapping. This framework provides two complementary geometric views of an embedding. The differential view explains local behavior: its first-order term recovers projection glyphs, while its second-order curvature quantifies how far their linear approximation remains reliable. The integral view follows the same geometry along high dimensional paths and determines whether an embedding depends only on the current state or also on the path taken to reach it. We further show that map-continuity is a prerequisite for the other analyses. The framework is theoretically complete for diagnostics derived from the embedding geometry, and we prove the integral view irreducible: no amount of local measurement at any number of points, to any order of derivative, reproduces what it detects. Classical rank-based metrics form a complementary class based on finite-scale neighborhood relationships. Experiments on synthetic and real datasets validate theoretical predictions, demonstrate accurate curvature-based trust estimates on single-cell embeddings, and show that the integral analysis distinguishes single-valued embeddings from path-dependent optimization-based embeddings in ways that existing pointwise diagnostics cannot.

AI 总结：该研究针对从正确示范学习的问题，提出多尺度奖励对冲方法，获首个无时间范围的多项式有限界，在上下文推荐等任务中取得良好效果，且计算效率在特定场景下可优化。

链接：https://arxiv.org/abs/2608.06825

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

作者：Pahan Dewasurendra

英文摘要：Learning from correct demonstrations is harder than supervised learning when many answers are correct: after predicting, the learner sees one valid answer but not whether its own answer was valid, nor any reward. Existing reward-hedging guarantees consequently assume a finite reward class. We give the first horizon-free guarantee for continuous classes. The key is to hedge in one shared vote over tolerant optimality tests at every accuracy scale. A target reward has one surviving proxy per scale, and a prediction with gap above that scale doubles the proxy. This yields the simultaneous tail bound $|\{t:\ell_t>2^{-j}\}|\leq \log_2\mathcal N(\mathcal G,2^{-j-1})+j$, where $\mathcal G$ is the class of optimality-gap functions. Integrating the tails gives cumulative hidden gap bounded by a metric-entropy integral, independently of the number of rounds. Polynomial entropy $(A/\epsilon)^d$ gives $O(d\log A)$ total gap and a fast $O(d/m)$ statistical rate. For bounded linear contextual recommendation, the result is $O(d)$ regret for arbitrary compact menus. This is the first polynomial finite bound without structural restrictions on the menus, at the price of improper prediction. Although the general vote can be expensive, it is exactly polynomial-time for one-dimensional Lipschitz parameter curves. Fixed-radius rank-two recommendation takes $O(KT^2)$ time for menus of size $K$. We also prove an $\Omega(d)$ lower bound, low-rank and bounded ReLU-network corollaries, and a robust theorem that adds only the demonstrator's cumulative suboptimality. A reproducible adaptive stress test illustrates the predicted scale adaptation. After factorization, an exact MovieLens audit runs in 1.7 CPU seconds across ten users and improves mean latent gap over both a demonstrated-rating policy and a proper online baseline. The learner uses only action demonstrations and never observes a reward or a loss.

AI 总结：该研究提出Graph Machine架构，含边增强注意力与以边为中心的引用两种边机制，在数独任务上优于Transformer基线，证明显式边机制是有前景的架构设计。

链接：https://arxiv.org/abs/2608.06834

作者：Lintai Hou

英文摘要：Transformers provide a powerful architecture for global content-based matching, but reasoning problems may benefit from a stronger inductive bias toward iterative traversal of latent relations. We introduce Graph Machine, an architecture with two explicit edge-based mechanisms: Edge-augmented attention, in which edges modulate attention between nodes, and edge-centric referral, in which nodes exchange addresses to update their edges. Conceptually, this enables the model to dynamically and differentiably construct and revise relational graphs across layers. We study this inductive bias using Sudoku under controlled settings and find that Graph Machine outperforms Transformer baselines, with ablation studies and mechanistic analysis attributing the gains to the edge mechanisms. Surprisingly, we found that the model discovers a compact edge-based construction for Sudoku geometry. Our results support explicit edge mechanisms as a promising architectural design, motivating broader evaluation.

AI 总结：本文研究ANN符号模式涌现的数学原理，证明其推理逻辑可表述为稀疏符号交互，相关准则使符号模式涌现，为ANN符号解释奠基，还凸显交际学习潜力。

链接：https://arxiv.org/abs/2608.06839

作者：Quanshi Zhang, Qihan Ren, Siyu Lou

英文摘要：Artificial Neural networks (ANNs) are often treated as black-box models, making explainability a central challenge in deep learning. Many engineering methods have been proposed to approximately explain the ANN from various perspectives, such as feature attribution and visualization. However, it remains a long-standing open question whether the complex inference logic of an ANN can be explained exhaustively and concisely as sparse symbolic patterns. This raises a deeper inquiry: does the emergence of symbolic patterns reflect a natural law rather than chance? Here, we show that across a broad class of ANNs trained on diverse tasks, their inference logic can indeed be reformulated as sparse symbolic interactions. We further prove that two common mathematical criteria, which are implicitly required across tasks, lead to the emergence of such sparse symbolic interactions. Empirical evidence confirms that the two criteria hold for the majority of input samples in diverse models. Furthermore, the faithfulness of these interactions is also demonstrated by their strong sample-to-sample and model-to-model transferability, as well as their ability to explain the overall generalization power of ANNs. Our theoretical analysis and extensive experiments provide a solid foundation for symbolic explanations of ANNs, and offer novel insights into the ANN's generalization power. Our findings also highlight the potential of communicative learning, a paradigm in which the inference logic of an ANN can be directly inspected and tuned at the level of symbolic patterns, thus complementing traditional end-to-end learning paradigm. Finally, the observed emergence of symbolic patterns in ANNs suggests that similar symbolic representations may also emerge in other types of black-box systems under certain conditions, because our proof does not depend on any specific ANN architecture.

AI 总结：本研究提出基于Nyström方法的NysHD方法，将半正定相似函数引入超维计算（HDC），在图和字符串数据集上分类准确率平均提升11%和17%，扩展了HDC可解决的问题类型。

链接：https://arxiv.org/abs/2608.06860

作者：Quanling Zhao, Anthony Hitchcock Thomas, Ari Brin, Xiaofan Yu, Tajana Rosing

英文摘要：Hyperdimensional computing (HDC) is an approach from the cognitive science literature for solving information processing tasks using data represented as high-dimensional random vectors. The technique has a rigorous mathematical backing, and is easy to implement in energy-efficient and highly parallel hardware like FPGAs and "processing-in-memory" architectures. The effectiveness of HDC in machine learning largely depends on how raw data is mapped to high-dimensional space. In this work, we propose NysHD, a new method for constructing this mapping that is based on the Nyström method from the literature on kernel approximation. Our approach provides a simple recipe to turn any user-defined positive-semidefinite similarity function into an equivalent mapping in HDC. There is a vast literature on the design of such functions for learning problems. Our approach provides a mechanism to import them into the HDC setting, expanding the types of problems that can be tackled using HDC. Empirical evaluation against existing HDC encoding methods shows that NysHD can achieve, on average, 11% and 17% better classification accuracy on graph and string datasets respectively.

AI 总结：SkillAligner是无训练的执行时技能适配框架，将检索技能视为可调整草稿，经联合适配整合为执行指南，在多基准实验中提升任务性能、降低退化与推理成本。

链接：https://arxiv.org/abs/2608.06880

机构：Zhejiang University（浙江大学）

作者：Qinfeng Li, Dalin He, Yuntai Bao, Ying Yang, Ruoxi Chen, Xinyan Yu, Lizhou Liang, Ge Su, Wenqi Zhang, Xuhong Zhang

英文摘要：General-purpose skills promise reusable procedural knowledge for language agents, yet semantic relevance does not guarantee execution utility: a retrieved skill may encode assumptions that conflict with the current task, execution environment, or other retrieved skills. We formalize this problem as the skill--execution misfit. To address it, we propose SkillAligner, a training-free execution-time skill adaptation framework that treats retrieved skills as adaptable drafts rather than fixed instructions. Before execution, SkillAligner performs a one-time joint adaptation that specializes useful skill fragments to task requirements, aligns their procedural assumptions with the available execution interface, and composes the resulting guidance by resolving dependencies, conflicts, and redundancy across skills. The adapted content is consolidated into a compact execution guide and reused throughout the subsequent trajectory. Extensive experiments across diverse agent benchmarks and model backbones show that SkillAligner substantially improves task performance over existing skill-use baselines, reduces skill-induced regressions at the instance level, and lowers total inference cost.

AI 总结：本研究提出PRISM理论，为薛定谔桥模型设计可处理的高斯参考，推导有限步数下的最优参考闭式解，通过实验验证其有效性并揭示真实图像对该理论的打破机制。

链接：https://arxiv.org/abs/2608.06893

机构：Arizona State University（亚利桑那州立大学）

作者：Forouzan Fallah, Yezhou Yang

英文摘要：Schrödinger bridge models restore a clean signal from a degraded observation by following the conditional bridges of a reference process, yet this reference is chosen heuristically, typically white noise with a hand-tuned schedule. We develop PRISM, a theory of bridge reference design. We characterize the time-varying Gaussian references that remain exactly tractable with per-mode schedules: precisely those whose instantaneous covariances commute. We then prove an invisibility principle: with the exact drift and unlimited solver steps, every admissible reference recovers the true posterior. The choice of reference therefore matters only under finite computational resources. For a fixed step budget, we derive the finite-step objective in closed form and prove that every optimal noise spectrum is proportional to Pk, the spectrum of information destroyed by the sensor, with a mode-independent constant x*(T) = (2 ln T)^-1/2 (1 + o(1)). The analysis shows that noise color and temporal scheduling are interchangeable, and regularization provably shifts the optimal reference toward white noise. Experiments in Gaussian settings confirm the predicted orderings and the closed-form loss floors. On FFHQ, the distortion-- perception trade-off and spectral localization transfer, but white noise outperforms the matched reference; a pre-registered study that changes the training regime refutes ridge whitening as the explanation. A 2x2 mechanism study then traces the inversion to the non-Gaussian per-mode statistics of real images. PRISM turns reference design from a hyperparameter sweep into a calculation in the Gaussian regime, and locates exactly where real images break it.

AI 总结：该文针对弱监督学习领域的实际需求，提出置信度差异分类的解决方法、更宽松假设下的互补标签学习方案，并给出部分标签学习的公平评估框架，推动了该领域的发展。

链接：https://arxiv.org/abs/2608.06896

作者：Wei Wang, Gang Niu, Masashi Sugiyama

英文摘要：Deep learning has achieved great success in recent years thanks to the availability of high-quality, well-annotated training data. However, this requirement is often not met in real-world applications. Weakly supervised learning aims to train an accurate model with incomplete, inexact, or inaccurate supervision. In this chapter, we will discuss recent advances in this field, including new supervision paradigms, relaxed assumptions, and practical solutions. First, we introduce a new weakly supervised binary classification problem called confidence-difference classification and propose consistent approaches to solve it. Next, we investigate complementary-label learning, a weakly supervised multi-class classification problem. Our proposed approaches are based on more relaxed assumptions about the data generation process than existing consistent approaches. Lastly, we present an evaluation framework for partial-label learning, another popular multi-class weakly supervised learning problem, in order to promote fair and realistic evaluation of algorithms in this field.

AI 总结：本文提出基于极限学习机（ELM）的星载图像压缩框架ELMZip，通过凸最小二乘问题拟合与非对称传输协议，在高重建保真下实现高效压缩，提升小型卫星下行传输效率，助力实时地球观测。

链接：https://arxiv.org/abs/2608.06942

作者：Woojin Cho, Junghwan Park, Sangcheol Sim, Steve Andreas Immanuel, Junhyuk Heo, Darongsae Kwon

英文摘要：The acquisition of multispectral imagery via small satellites (e.g., CubeSats) presents significant data downlink challenges due to high data volumes and restricted communication windows. While onboard image compression is critical to address this bottleneck, traditional methods often struggle to adapt to the nonlinear statistics of multi-band, multi-resolution data. To overcome these limitations, we propose ELMZip, a novel framework based on Extreme Learning Machines (ELM) and domain decomposition strategies for efficient, resolution-free onboard neural representation. ELMZip formulates the fitting process as a convex least-squares problem using random-feature single-layer networks, thereby eliminating the need for computationally expensive backpropagation. By adopting an asymmetric transmission protocol that sends only the compact output weights, the proposed method significantly reduces the downlink payload. Unlike previous neural representation approaches that rely on iterative optimization and require transmitting full network parameters, ELMZip achieves significant compression efficiency while maintaining high reconstruction fidelity. This capability enables immediate image reconstruction for analysis, allowing resource-constrained platforms to maximize data return and advancing real-time AI-powered Earth observation.

AI 总结：该研究通过明确分子身份并将其通过生成过程拉回，揭示了三种分子生成架构的内部储备呈分段常数区域，其组织受多种因素影响，需先表征内部组织才能将生成空间视为可化学导航。

链接：https://arxiv.org/abs/2608.06956

机构：Toyota Research Institute（丰田研究所）； Technical University of Denmark（丹麦技术大学）； CAPeX Pioneer Center for Accelerating P2X Materials Discovery（CAPeX P2X材料发现加速先锋中心）； University of Toronto（多伦多大学）； Vector Institute for Artificial Intelligence（向量人工智能研究所）； NVIDIA（英伟达）； Massachusetts Institute of Technology（麻省理工学院）； Acceleration Consortium（加速联盟）

作者：Raul Ortega-Ochoa, Tejs Vegge, Jens S. Bakander, Luis Mantilla Calderon, Alan Aspuru-Guzik, Tonio Buonassisi

英文摘要：Generative models for matter are often evaluated as samplers over output representations, and their latent spaces are commonly used as proxies for navigating chemical space. Much less is known about how these models internally arrange discrete chemical identities within those representations. We study this arrangement by making molecular identity explicit and pulling it back through the generative process. Through these pullbacks we probe the regions that generate the same object, exposing the trained model's internal repertoire: a fixed partition that determines which objects (novel or not) the model can produce. Across three molecular generative architectures, we find that this repertoire is arranged into piecewise-constant regions separated by recurring coarse-to-fine boundaries. Its organization depends on the representation probed, the identity convention, decoder stochasticity, and the metric used to compare coordinates. During training, local chemical organization stabilizes while the number of distinct molecular identities represented within each neighborhood continues to change. Internal organization must therefore be characterized, rather than assumed, before a generative space can be treated as chemically navigable.

AI 总结：本文提出DHC-ECS方法，整合三类聚类技术，引入新型相似度度量，在异构基准数据集上较基线方法表现更优，可减少人工参数调整依赖。

链接：https://arxiv.org/abs/2608.06990

机构：Tongji University（同济大学）； RadioSky (Shanghai) Communication Technology Co., Ltd（天睿（上海）通信技术有限公司）

作者：Yuning Yu, José Rodríguez-Piñeiro, Xuefeng Yin, Bin Feng

英文摘要：Clustering is a fundamental data mining technique for pattern recognition through unsupervised learning. Among various clustering methods, hierarchical clustering, density-based clustering, and graph clustering stand out as representative approaches. For hierarchical clustering, it can be categorized into agglomerative and divisive modes to construct clusters in a recursive manner. The key aspect of both modes is the calculation of inter-cluster similarity, which determines whether to merge the sub-clusters into one cluster or divide a current cluster into sub-clusters. Traditionally, the similarity is derived from pairwise distances, often overlooking density variations and structural connectivity in graphs. To address this, we propose a density-aware hierarchical clustering method based on element-categorized connection subgraphs (DHC-ECS), which effectively integrates the hierarchical clustering, density-based clustering, and graph clustering. Particularly, a novel inter-cluster similarity metric is introduced that considers not only distances but also the element categorization in the KNN connection subgraphs, kernel density estimation, and local connectivity within sub-clusters. Extensive evaluations on heterogeneous benchmark datasets demonstrate that DHC-ECS exhibits superior overall performance in terms of clustering accuracy and parameter robustness compared with the baseline methods (including AChameleon, RNN-DBSCAN, McDPC, and G-RMS). The work indicates the great potential of the proposed clustering algorithm for low-dimensional datasets by leveraging local density and graph-structured connectivity (i.e., the duality of vertices and edges), as well as the possibility to determine an intrinsic threshold, reducing the reliance on manual parameter tuning.

AI 总结：该研究提出Modular TTT框架，将TTT各组件设为显式设计维度，通过消融实验明确关键组件对性能的影响，训练的大参数模型性能可与Gated DeltaNet媲美。

链接：https://arxiv.org/abs/2608.07110

机构：Shanghai Jiao Tong University（上海交通大学）； Shanghai Innovation Institute（上海创新研究院）； ByteDance Seed（字节跳动Seed）

作者：Bohao Tang, Zhen Qin, Yuqi Pan, Zheng Li, Pengfei Liu, Ya Zhang

英文摘要：Test-time training (TTT) views sequence modeling as an online learning problem in which fast weights are updated by an internal learning rule. Despite the growing number of TTT variants, existing approaches typically hard-code each variant separately, which makes it difficult to design new TTT methods and to isolate the role of each component. To address this, we propose Modular TTT, a framework that represents the inner learner as a directed acyclic graph and exposes the fast-weight network, loss function, learning rate, weight decay, and normalization as explicit design dimensions. Modular TTT automatically composes primitive-level train-view forward, train-view backward, and causal query-view rules into the full graph-level TTT computation, including the fast-weight state transition. Using Modular TTT, we systematically ablate the components of TTT and find that small learning-rate initialization, weight decay, and a single-layer nonlinearity improve performance, while MSE and inner-product losses perform similarly. Deeper fast-weight networks and normalization tend to hurt performance because they induce excessively large activations, while residual connections and gating provide little measurable benefit. Guided by these findings, we train the best resulting variant as 410M- and 1.45B-parameter models on 100B tokens, and observe training loss and benchmark performance comparable to Gated DeltaNet.

AI 总结：本研究针对超高分辨率PET的晶间散射难题，提出前馈神经网络优化晶间散射恢复，在保持亚毫米空间分辨率的同时提升灵敏度，可缩短扫描时间并降低辐射剂量。

链接：https://arxiv.org/abs/2608.07155

机构： Université de Sherbrooke（谢布鲁克大学）； Interdisciplinary Institute for Technological Innovation（跨学科技术创新研究所）； Sherbrooke Molecular Imaging Center of CRCHUS（CRCHUS谢布鲁克分子成像中心）； Institut Fresnel（弗雷内尔研究所）； Aix Marseille Univ（艾克斯-马赛大学）； Centrale Med（中央医学院）； Imaging Research & Technology (IR&T) Inc.（成像研究与技术公司）

作者：Alexandre Bernier, Roger Lecomte, Jean-Baptiste Michaud

英文摘要：Inter-crystal scatter (ICS) events pose a significant challenge in ultrahigh- resolution positron emission tomography (UHR-PET), especially as detector crystals become smaller and their readouts increasingly segmented. Current approaches either reject these events, reducing sensitivity, or accept them with suboptimal positioning algorithms, degrading image resolution. We present a feed forward neural network to optimize ICS event recovery by inferring the line-of-response belonging to the first Compton interaction. Our approach was validated using both Monte Carlo simulations and experimental data from the fully pixelated LabPET-IIbased preclinical and brain UHR-PET this http URL demonstrate a 70% to 106% increase in sensitivity while preserving sub-millimeter spatial resolvability (down to 1.6 mm) compared to conventional methods. This ICS recovery approach is an effective solution that compensates for the lower detection efficiency of small, pixelated detectors in UHR-PET, enabling reduced scan times and lower radiation doses while largely preserving image quality.

AI 总结：本文提出MCCF架构，解决缺失模态下的多模态融合问题，该架构兼具模态缺失鲁棒性与校准不确定性，在多基准测试中表现出良好的覆盖率与精度性能。

链接：https://arxiv.org/abs/2608.07183

机构：Swinburne University of Technology（斯威本科技大学）

作者：Alireza Moayedikia

英文摘要：Multimodal fusion architectures typically assume all modalities are available at inference, yet sensor failures, acquisition variability, and cost constraints routinely produce incomplete observations. Existing work treats modality absence as a prediction-accuracy problem, leaving a more basic question unanswered: whether a model's confidence estimates remain calibrated when an entire input stream is removed. We argue that missing-modality robustness and calibrated uncertainty are a single coupled property, and introduce Modality-Conditioned Conformal Fusion (MCCF), an architecture that addresses both at once. MCCF combines a multimodal bottleneck fusion backbone trained with modality dropout, per-modality evidential heads producing modality-decomposed Dirichlet distributions, and a Dempster-Shafer combination rule that fuses the per-modality evidence into a joint predictive distribution; an absent modality contributes vacuous evidence that is structurally ignored, so the fused uncertainty automatically reflects the reduced information without test-time imputation. A Mondrian conformal calibration module keyed on the modality-presence mask then provides finite-sample group-conditional coverage for every non-empty modality subset. MCCF is, to our knowledge, the first method with formal coverage guarantees under arbitrary modality availability through architectural integration rather than post-hoc recalibration, and the evidential decomposition yields per-modality vacuity scores that localise uncertainty to the absent modality responsible. Across a synthetic problem and three real multimodal benchmarks, MCCF holds its target coverage on every modality-presence subset, substantially narrows the coverage gap between full and partial modalities relative to a marginal split-conformal baseline, and imposes no measurable accuracy cost relative to temperature-scaled and evidential baselines.

AI 总结：本研究提出AutoPrune框架，通过TPDSL让LLM自动设计视觉令牌剪枝策略，在14个多模态基准和3个MLLM主干上，剪枝94.4%视觉令牌仍保留超99%性能，大幅降低推理成本。

链接：https://arxiv.org/abs/2608.07193

作者：Zhen Liu, Wenli Huang, Wei Song, Yuhan Liu, Zhiqin Yang, Jingwen Fu

英文摘要：Visual-token pruning can substantially reduce the inference cost of multimodal large language models (MLLMs), yet existing methods largely rely on fixed, handcrafted heuristics and costly expert trial and error. As pruning objectives, budgets, and model architectures diversify, manually navigating the expanding design space becomes increasingly difficult. This paper aims to build an AI4AI framework for visual-token pruning by addressing a natural question: Can large language models automatically design effective visual-token reduction algorithms? Although LLMs possess broad algorithmic knowledge and strong reasoning capabilities, translating such general knowledge into effective solutions for a specialized task remains nontrivial. We argue that the key lies in designing an appropriate search-state representation that connects the internal knowledge of LLMs with the structural requirements and constraints of visual-token pruning. Based on this insight, we propose AutoPrune, a training-free framework for LLM-driven visual-token pruning policy design. At its core, AutoPrune introduces a Token Pruning Domain-Specific Language (TPDSL) comprising 131 reusable atoms for budget control, token scoring, selection constraints, and token reassembly. A key property of TPDSL is that it represents each search state as a residual modification of a strong base policy. This residual formulation narrows the search space and directs the LLM's attention toward the policy components that are most consequential for performance. Experiments on 14 multimodal benchmarks and three MLLM backbones demonstrate the effectiveness, efficiency, and transferability of AutoPrune. Even when removing 94.4% of visual tokens, AutoPrune preserves more than 99% of full-token performance while reducing FLOPs by 9.9x and prefill latency by 6.4x.

AI 总结：本研究采用基础模型NeuroSTORM对rs-fMRI数据编码微调，在189次扫描的儿童数据中，其头痛分类性能优于FC矩阵模型，可区分慢性偏头痛，为儿童头痛预测提供了概念验证。

链接：https://arxiv.org/abs/2608.07287

机构：Boston Children’s Hospital（波士顿儿童医院）； Harvard Medical School（哈佛医学院）

作者：Guilherme S. Imai Aldeia, Clara Moon, Julie Shulman, Navil Sethna, Allison Smith, Alyssa Lebel, William G. La Cava, Scott Holmes

英文摘要： Headache is the most common neurological disorder in children and substantially affects quality of life. We investigated whether resting-state functional MRI (rs-fMRI) can support pediatric headache classification using machine learning. We encoded rs-fMRI data using NeuroSTORM, a recent foundation model, and fine-tuned it to distinguish healthy controls from children with headache and subsequently classify headache subtypes. We compared NeuroSTORM with a standard neuroscience approach using functional-connectivity (FC) matrices derived from brain activity as predictors. Using 189 rs-fMRI scans from 110 individuals collected across two visits (prevalence of any headache: 74%), NeuroSTORM achieved an area under the receiver operating characteristic curve (AUROC) of 0.82 (95% CI, 0.82-0.82) and an area under the precision-recall curve (AUPRC) of 0.93 (95% CI, 0.93-0.94) for discriminating headache from non-headache. In contrast, models trained on FC matrices showed lower performance (AUROC, 0.67 [95% CI, 0.67-0.67]; AUPRC, 0.85 [95% CI, 0.85-0.85]). In multiclass classification of healthy controls, chronic migraine, and non-chronic headaches (e.g., post-viral headache, new daily persistent headache, post-traumatic headache), NeuroSTORM achieved a macro-AUROC of 0.69 (95% CI, 0.68-0.69). Results suggest that the approach can distinguish chronic migraine but has difficulty differentiating other headache subtypes from chronic migraine. Overall, under limited-data conditions, NeuroSTORM appears to capture latent rs-fMRI representations that transfer to headache-related tasks without relying on FC features. These findings provide proof of concept for fMRI-based prediction of pediatric headache and highlight potential future utility for subtype identification and individualized treatment strategies.

AI 总结：该研究针对仅解码器的语言模型FFN，通过对比实验发现，源自忆阻分支几何的MemGLU在相近损失下无需SwiGLU的开放正尾即可表现良好，表明模型会适应预训练的门控几何。

链接：https://arxiv.org/abs/2608.07323

机构：City University of Hong Kong（香港城市大学）； Beihang University（北京航空航天大学）； National University of Singapore（新加坡国立大学）

作者：Yuting Ge, Pengju Yang, Mingkai Nie

英文摘要：We test whether decoder-only language-model FFNs require SwiGLU's open positive tail. We introduce MemGLU as a closed-tail comparator derived from a memristive branch geometry. Across paired 9M and 30M pretraining runs with three seeds, MemGLU remains within about 0.1% of SwiGLU in validation NLL. Trained SwiGLU checkpoints are sensitive to positive-tail suppression, while mechanism diagnostics show that the two models use their gates differently despite similar losses. These results suggest that models adapt to the gate geometry available during pretraining. At the tested scales, SwiGLU's open positive tail is not necessary for decoder-only language-model FFNs.

AI 总结：该研究提出用于保留表示学习的残差代数，通过Fold、FPRC-PQ等实现，在A股数据上显著提升投资收益与夏普比率，增益源于残差所有权与组合的显式建模。

链接：https://arxiv.org/abs/2608.07349

作者：Yao Wu

英文摘要：Learning from heterogeneous representations is usually reduced to feature concatenation, which erases which representation produced an error. We instead algebraize the residual: a representation is a typed object that owns both a coordinate system and the residual it leaves unresolved, and learning is an ordered composition of operators that preserve or deliberately erase that type. Fold realizes the objects as point-in-time conditional-mean fields on 10x10 rank grids. FPRC-PQ realizes the algebra as relax-aggregate-close: each field is relaxed by a correction fitted to its own residual in its own coordinates; corrected fields meet at a fixed mean that is the sole identity-erasure boundary; and a shared learner closes only the aggregate's fresh residual. The composition telescopes exactly into representation, local residual estimate, and residual-of-residual estimate. Its aggregate is a learned control-variate interface with population variance reduction, while refitting the closer along perturbations of the backbone yields first-order coupled-path mean orthogonality. As an analytical extension, a reflective rumination operator reads the displacement of a global reconstruction from the aggregate anchor, reflects it, and fixes its gain by a unique orthogonal projection rather than return-tuned grid search. On 3.67M Chinese A-share stock-day observations (2023-2026) under a frozen point-in-time protocol, the evaluated base algebra raises net-of-cost return from 13.52% to 19.10% and Sharpe from 1.42 to 2.09. Matched-capacity, unified-residual, identity-free two-stage, and pairwise-only controls all trail it. The gain is therefore not explained by more features or more trees, but by making residual ownership and composition explicit while representation identity is still available.

AI 总结：该研究针对世界模型训练中局部与长视目标不匹配的问题，提出DPWM非递归架构，采用端到端长视终点目标训练，显著提升了连续控制等基准的长时预测性能。

链接：https://arxiv.org/abs/2608.07420

机构：University of California, Davis（加州大学戴维斯分校）

作者：Xinyi Li, Zaishuo Xia, Chenjie Hao, Yubei Chen

英文摘要： World models are expected to support imagination over extended temporal horizons, yet most are still trained through local few-step prediction objectives and deployed by recursively rolling out their own predictions. This creates a fundamental mismatch: few-step losses optimize local transition fidelity, while long-horizon prediction depends on how errors and gradients propagate through the entire trajectory. As a result, transitions with different downstream influence on the endpoint are treated uniformly during training, and small local errors are amplified through recursive inference. We argue that long-horizon accuracy is better achieved by optimizing directly, through an end-to-end endpoint prediction objective. To instantiate this paradigm, we introduce the Direct Prediction World Model (DPWM), a non-recursive architecture that compresses an action sequence of arbitrary length into a single embedding and predicts the endpoint observation in a single forward pass. This design avoids recurrent rollout in both prediction and gradient propagation, making long-horizon end-to-end training practical at horizons where unrolled autoregressive training becomes unstable. Empirically, DPWM substantially improves long-horizon endpoint prediction over recursive world-model baselines on continuous-control and pixel-based benchmarks, with larger gains as the prediction horizon increases. We further show that recurrent baselines benefit similarly when retrained with the same long-horizon endpoint objective, supporting our central claim that the training objective, rather than the particular backbone choice, is the main driver of long-horizon prediction accuracy. Our results suggest that world models can benefit from being trained and evaluated at the temporal scales where they are ultimately used, shifting the focus from local transition modeling toward long-horizon predictive accuracy.

AI 总结：本研究揭示扩散大语言模型（DLLMs）的安全机制漏洞，提出SN-Guided Diffusion黑盒越狱框架，实现高迁移攻击成功率且生成成本远低于现有方法。

链接：https://arxiv.org/abs/2608.07430

作者：Elena Dumitrescu, Gert Lek, Lydia Y. Chen, Jérémie Decouchant

英文摘要：Diffusion Large Language Models (DLLMs) replace autoregressive next-token prediction with iterative parallel denoising, yet their internal safety mechanisms remain poorly understood. In this work, we investigate DLLMs both as targets and as adversaries, exposing mechanistic vulnerabilities in diffusion-based alignment. We first show that safety alignment in DLLMs remains sparse and transferable across architectures. DLLMs initialized from autoregressive predecessors inherit the same mechanistic safety footprint as their source models, enabling transfer attacks via direct safety neuron mapping and pruning. Self-pruning increases attack success rates (ASR) from 2.6% to 73.8% on LLaDA and from 1.9% to 86.6% on Dream, while transfer pruning from Qwen2.5 increases ASR from 1.9% to 73.2% on Dream and from 7.0% to 86.3% on Fast-dLLM. Building on these findings, we introduce SN-Guided Diffusion, a fully offline black-box jailbreak framework that steers the diffusion process away from safety-triggering regions using a weighted safety neuron loss, which achieves near-perfect prompt separability (AUROC = 1.0 for benign-vs-jailbreak discrimination). Across multiple open and proprietary targets, our method achieves a transfer ASR of up to 77.1% on Llama-3-8B-Instruct, 86.9% on Qwen2.5-7B-Instruct, and 74.3% against Gemini-2.5-Flash-Lite, while requiring only 20 generation episodes per prompt. Compared to prior jailbreaking frameworks, our method achieves competitive transferability with orders-of-magnitude lower generation cost. Our codebase is available at this https URL.