机器学习学术速递[7.17]

AI 总结：研究针对超连接（HC）扩展残差流时的性能瓶颈，提出xHC方法，结合时间特征增强与稀疏残差流架构，实现超越N = 4的有效扩展，在MoE模型上有下游改进，还介绍xHC - Flash减少内存流量，让大N残差流扩展用于语言模型预训练更有效实用。

链接：https://arxiv.org/abs/2607.14530

机构：School of AI, Shanghai Jiao Tong University（上海交通大学人工智能学院）； Dots Studio, Xiaohongshu Inc.（小红书公司点点工作室）； University of Science and Technology of China（中国科学技术大学）； School of CS, Peking University（北京大学计算机科学学院）； The Chinese University of Hong Kong（香港中文大学）

作者：Xiangdong Zhang, Xiaohan Qin, Sunan Zou, Tuo Dai, Xiaoming Shi, Huaijin Wu, Yebin Yang, Zhuo Xia, Shaofeng Zhang, Lin Yao, Yuliang Liu, Yu Cheng, Junchi Yan

英文摘要：Hyper-Connections (HC) expand the residual stream of Transformers into $N$ parallel streams, providing a form of memory scaling beyond model width and depth. Manifold-Constrained HC (mHC) stabilizes this formulation at scale. The large gains from $N{=}1$ to $N{=}4$ suggest residual-stream expansion as a promising scaling axis. However, existing HC-family methods typically stop at $N{=}4$. Our experiments reveal why: scaling mHC beyond this point yields diminishing performance gains and rapidly increasing training cost. We attribute this limitation to two bottlenecks: insufficient write-back information for an expanding number of streams and residual-mixing generation whose cost scales cubically with $N$. To address both bottlenecks, we propose xHC (Expanded Hyper-Connections), the first HC-family method to achieve meaningful expansion beyond $N{=}4$. xHC combines temporal feature augmentation for richer write-back with a sparse residual-stream architecture that updates only $k=4$ of the $N=16$ streams while retaining dense access to the full residual state. Across 18B and 28B MoE models, xHC delivers strong and consistent downstream improvements. On an 18B MoE model, xHC improves the average downstream score by 4.0 points over mHC, while adding only modest training FLOPs over the vanilla baseline. Scaling-law experiments show that the vanilla and mHC require $1.50\times$ and $1.19\times$ the compute of xHC, respectively, to reach the same loss. Practical large-$N$ training also requires controlling memory traffic from the expanded residual state. We therefore introduce xHC-Flash, which reduces the per-sublayer memory traffic from $73.5C$ to $40C$, comparable to the $34C$ required by mHC at $N{=}4$, while retaining the gains of full xHC. Together, xHC and xHC-Flash make large-$N$ residual-stream expansion effective and practical for LLM pre-training.

AI 总结：该研究为深度残差架构提出次线性增长原理，通过经典ODE理论和最优控制分析确定\(q \leq 1\)为稳定训练充要条件，阐明架构布局与稳定关系，构建函数空间并给出认证算法，实验证实相关变体训练稳定。

链接：https://arxiv.org/abs/2607.14576

机构：University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）； SRI International（SRI国际公司）

作者：Hyemin Gu, Michael Tyrrell, Tuhin Sahai, Markos A. Katsoulakis

英文摘要：We propose \emph{the sublinear-growth principle} for deep residual architectures -- a sharp stability threshold on the input-magnitude exponent of every residual block's velocity field: $$\|v(x, t)\| \leq c\,\|x\|^q + b, \qquad q \in [0, 1].$$ The threshold $q = 1$ is established via two independent arguments. Classical ODE theory gives a global forward flow on $[0, T]$ at $q \le 1$ and exhibits divergent velocity fields at any $q > 1$. The optimal-control analysis, via the Hamilton-Jacobi-Bellman equation, sharpens this to a selection statement: the training optimum is bang-bang on the boundary of the admissible class, so the optimum at $q > 1$ blows up while the optimum at $q \le 1$ is safe by construction. The exponent criterion $q \le 1$ is thereby a necessary and sufficient condition for stable training. It clarifies architectural placements that ensure the stability of training and inference, explaining, for instance, the stabilizing role of layer normalization. The sublinear-growth velocity fields form \emph{the right function space} on which forward dynamics, adjoint sensitivity, and architectural composition are all well-controlled. An arithmetic of input-magnitude exponents under the five operations that build residual blocks enables efficient certification of $q_k \le 1$ at the level of architectural primitives, in place of ad hoc trial and error in the search for stable neural architectural designs. A parameter-free modification reduces the supercritical Mamba block from $q = 5$ to $q = 1$ without layer normalization, demonstrating this point. Experiments on Mamba and PatchTST confirm that the $q \le 1$ variants train stably: the criterion is the input-magnitude exponent, not the presence of a normalization layer.

AI 总结：研究基于策略内蒸馏，引入新的增量信号作为蒸馏奖励，提出策略内增量蒸馏方法。实验表明该方法能显著改进策略内蒸馏，使推理语言模型在短训练期内表现出色，优于传统方法。

链接：https://arxiv.org/abs/2607.15161

机构：NAVER AI Lab（NAVER人工智能实验室）

作者：Byeongho Heo, Jaehui Hwang, Sangdoo Yun, Dongyoon Han

英文摘要： On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constraints imposed by reward models by providing token-level supervision from a teacher model. Although on-policy distillation has been studied and applied across various settings, its fundamental design remains underexplored. In this paper, we introduce a new distillation reward, termed the delta signal, instead of directly imitating the teacher's output distribution. The delta signal is defined as the difference between the teacher model and its base model prior to instruction tuning for reasoning capability. It therefore captures the changes induced by reasoning tuning and provides a more direct signal for transferring reasoning capabilities. Using extensive empirical evidence, we show that the delta signal substantially improves on-policy distillation and refer to the new distillation method as On-Policy Delta Distillation (OPD$^2$). Experiments across mathematics, science, and code-reasoning benchmarks demonstrate that OPD$^2$ consistently outperforms conventional on-policy distillation, enabling reasoning LLMs to achieve strong performance with only a short post-training period. Code will be available at this https URL

AI 总结：研究针对多模态空间组学整合下游分析常采用单模态管道的问题，提出LATTICE框架，通过构建空间邻域图并训练TransformerConv编码器，在黑色素瘤队列实验中实现多模态整合，提升相关指标，为该领域提供实用框架。

链接：https://arxiv.org/abs/2607.14410

机构：University of Houston（休斯顿大学）； MD Anderson Cancer Center（MD安德森癌症中心）

作者：Jagan Mohan Reddy Dwarampudi, Veena Kochat, Suresh Satpati, Kunal Rai, Tania Banerjee

英文摘要：Spatially resolved omics studies increasingly combine transcriptomic and epigenomic assays, yet downstream analysis is often still performed using single-modality pipelines. We present LATTICE (Latent Alignment of Tissue-level and Transcriptomic Information for Cross-modal Embedding), a graph-based self-supervised framework that learns spot-level representations from harmonized multimodal features. LATTICE integrates five aligned modality blocks per Visium spot: Visium RNA, scMultiome RNA, scMultiome ATAC, spatial ATAC, and spatial CUT\&Tag. These modalities capture spatial transcriptomic measurements, single-cell inferred regulatory activity, and in situ chromatin and histone states within a unified lattice representation. LATTICE constructs a spatial neighborhood graph and trains a TransformerConv encoder using masked reconstruction, cross-modal alignment, and spatial smoothness objectives. On a private 11-sample melanoma cohort from an anonymized clinical collaborator comprising 54{,}912 total spots, LATTICE demonstrated stable optimization behavior, reproducible embeddings across analysis seeds, and complete multimodal integration across all samples. Adding scMultiome RNA to Visium RNA alone substantially improved concordance with Space Ranger clusters across 11 runs (adjusted Rand index [ARI] +0.157, normalized mutual information [NMI] +0.143, and spatial contiguity +0.174). Additional modalities further improved spatial contiguity and multimodal utility score (MUS), although they sometimes reduced agreement with RNA-derived reference labels, likely because the learned embeddings captured chromatin and regulatory structure beyond transcriptomic similarity alone. These results position LATTICE as a practical and empirically grounded framework for multimodal spatial omics integration, while also highlighting the need for stronger supervision and broader external benchmarking.

AI 总结：研究针对长尾心电图心律失常诊断问题，提出角高斯监督对比学习（AG-SCL），集成角高斯对比分支、自适应对数调整和尾部感知增强三个组件，在两个数据集上取得最佳宏观性能，增强对罕见心律失常敏感性并保持特异性。

链接：https://arxiv.org/abs/2607.14613

机构：School of Biomedical Engineering, Shanghai Jiao Tong University（上海交通大学生物医学工程学院）； Department of Neurology and Neurological Rehabilitation, Shanghai Yangzhi Rehabilitation Hospital, School of Medicine, Tongji University（同济大学医学院附属上海养志康复医院神经科与神经康复科）

作者：Jin Dai, Qiuzhen Zhang, Chenyun Dai, Danmei Lan, Can Han

英文摘要：Long-tailed label distributions reduce the reliability of deep learning for electrocardiogram (ECG) arrhythmia diagnosis, particularly for clinically important but rare abnormalities. Existing rebalancing and logit adjustment methods mainly address class frequency while overlooking direction-dependent morphological variability across ECG classes. This study proposes Angular Gaussian Supervised Contrastive Learning (AG-SCL) for long-tailed multi-label ECG diagnosis. AG-SCL integrates three components into a unified framework: an Angular Gaussian contrastive branch that models full-covariance class uncertainty on unit-normalized embeddings, Adaptive Logit Adjustment that learns bounded label-state-specific prior corrections instead of fixed frequency-based margins, and tail-aware augmentation that generates morphology-preserving views while protecting the 7-25 Hz QRS-dominant band. The method was evaluated on the public PTB-XL benchmark and a nocturnal ECG dataset comprising 1317 hours of recordings from 141 subjects. AG-SCL achieved the best macro-level performance on both datasets. On PTB-XL, it obtained a balanced accuracy of 0.838, sensitivity of 0.709, specificity of 0.968, mean average precision of 0.495, and TPR at 5% FPR of 0.778. On Noc-ECG, the corresponding values were 0.918, 0.889, 0.947, 0.488, and 0.900. The largest gains occurred in rare or morphologically unstable rhythm classes, while ablation studies confirmed the contributions of full-covariance modelling, Adaptive Logit Adjustment, and tail-aware augmentation. AG-SCL improves long-tailed ECG diagnosis by combining prior calibration with anisotropic representation learning, enhancing sensitivity to rare arrhythmias while maintaining clinically relevant specificity. Our code is available at: this https URL.

AI 总结：研究针对3D医学成像中假阴性问题，提出多模态语义感知对比学习框架MseaCL，通过纳入放射学报告语义相似性作指导信号，经实验验证该框架用于预训练可提升下游任务表现，如儿科脑肿瘤分子分类AUC至少增22.6%。

链接：https://arxiv.org/abs/2607.14995

机构：University of Toronto（多伦多大学）； The Hospital for Sick Children（病童医院）； Vector Institute（向量研究所）； University Hospital Augsburg（奥格斯堡大学医院）

作者：Sara Ketabi, Matthias W. Wagner, Cynthia Hawkins, Uri Tabori, Birgit Betina Ertl-Wagner, Farzad Khalvati

英文摘要： Multimodal Contrastive Learning (CL) has shown significant performance in aligning representations across various data modalities and improving downstream tasks, especially in healthcare. It works by minimizing the distance between matched (positive) data modalities, while maximizing the distance between mismatched (negative) samples. Traditional CL frameworks typically assume instance-based correspondence within data batches, treating all non-paired samples as negatives. However, this assumption often fails in medical settings, where samples may share high-level semantic attributes, leading to false negatives that degrade representation quality. In this paper, we propose Multimodal Semantic-Aware Contrastive Learning (MseaCL), a CL framework trained on a pediatric cohort of 3D brain magnetic resonance imaging (MRI) scans and radiology reports. The goal of this framework is to mitigate the impact of semantically similar false negative samples by incorporating semantic similarity between radiology reports, as a guiding signal during the learning process. Our results indicate that applying this framework as a pretraining stage can achieve notable improvements in downstream tasks, e.g., at least a 22.6\% increase in the area under the receiver operating characteristic curve (AUC) of pediatric brain tumor molecular classification, demonstrating its potential for more robust and semantically aligned multimodal representations in clinical applications.

AI 总结：研究基于可执行沙盒的大语言模型智能体强化学习，提出分支策略优化（BPO）算法，利用沙盒特性构建新展开拓扑，通过自适应快照、分叉动作等方式计算优势，实验验证该算法能提升成功率、降低方差并减少策略更新。

链接：https://arxiv.org/abs/2607.14171

机构：Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）； McGill Univeristy（麦吉尔大学）； City University of Hong Kong（香港城市大学）

作者：Bowei He, Yankai Chen, Xiaokun Zhang, Xue Liu

英文摘要：Reinforcement learning has emerged as the dominant paradigm for training large language model (LLM) agents that interact with executable sandboxes. State-of-the-art algorithms such as PPO, RLOO, and GRPO inherit their rollout topology from RLHF: for each prompt, N independent trajectories are sampled from the initial state, and an advantage is computed by subtracting a group baseline. This design ignores a defining property of agent sandboxes. They are deterministic, snapshottable, and resumable from any intermediate state. We argue that this property enables a fundamentally different rollout topology: rather than N independent trees of depth T, one can construct a single tree of N leaves whose siblings share prefixes, and therefore share variance. We instantiate this idea as Branching Policy Optimization (BPO), a sandbox-native RL algorithm that (i) adaptively snapshots the sandbox at high-entropy decision points along a backbone trajectory, (ii) forks K alternative actions per branch point and rolls out each to termination, and (iii) computes per-step advantages from sibling returns rather than from independent prompts. We prove this estimator is unbiased and has strictly lower variance than the trajectory-level baseline, with the reduction equal to the prefix-explained portion of return variance. On WebShop, ALFWorld, and SWE-bench Verified with Qwen2.5-7B and Llama-3.1-8B backbones, BPO improves success by 3.6--6.1 absolute points over GRPO and RLOO at matched compute, halves gradient-norm variance, and matches the best baseline using 38% fewer policy updates.

AI 总结：研究针对世界模型在数据覆盖薄弱时易受模型利用问题，提出从人类反馈中学习动力学（DLHF），但朴素DLHF样本效率低，于是引入RENEW利用认知不确定性聚焦微调，经实验评估，RENEW提高样本效率等，为解决离线模型强化学习利用问题提供新途径。

链接：https://arxiv.org/abs/2607.14180

作者：Logan Mondal Bhamidipaty, Mykel Kochenderfer, Subramanian Ramamoorthy

英文摘要：World models are widely used in offline reinforcement learning (RL) to improve sample efficiency and generate experience beyond a fixed dataset. However, they are vulnerable to model exploitation where data coverage is thin. Prior work addresses this either by collecting more expert demonstrations, which is often expensive, unsafe, or unavailable, or by conservative algorithms that avoid uncertain regions, which limits generalization. We propose instead to repair exploitation directly using human preferences over imagined rollouts, leveraging the strong intuitive physics that allows humans to easily spot egregious dynamics hallucinations. We formalize this as Dynamics Learning from Human Feedback (DLHF), a Bradley-Terry preference loss over trajectory log-likelihoods under a learned dynamics model. Unfortunately, naive DLHF is sample inefficient, so we introduce RENEW, which uses epistemic uncertainty to focus finetuning where the model is most exploitable. We evaluate on several Jumanji and classic control environments and find that while naive DLHF requires an outsize preference budget, RENEW makes the framework practical by improving sample efficiency, limiting catastrophic forgetting, and reducing exploitation in pretrained world models. Taken together, our results provide initial evidence that preferences can supervise world model dynamics directly, offering a new approach to addressing exploitation in offline model-based RL.

AI 总结：研究闭环知识系统饱和及逃逸问题，引入三级操作框架，利用李雅普诺夫漂移条件等刻画系统动态，通过案例展示反馈影响，建立了稳定性工具、干预效果与跨域诊断间的操作联系。

链接：https://arxiv.org/abs/2607.14185

机构：Pfizer（辉瑞公司）； Institute of Humanities and Social Science Data, Fudan University（复旦大学人文社会科学数据研究所）

作者：Xuening Wu, Shan Yu, Shenqin Yin

英文摘要： Feedback-driven loops support iterative improvement in large language models, reinforcement learning, and autonomous discovery, yet their gains often diminish under repeated internal feedback. We study why closed-loop knowledge systems saturate and what external information can move them beyond their current attractors. We introduce a three-level operational framework in which knowledge states $x_t$ evolve through transition kernels $K_{\theta}$ indexed by a structural parameter $\theta$. The governing structure is defined as the observational equivalence class of $\theta$ induced by these kernels, while attractors and basins are properties of the fixed-$\theta$ dynamics. A structural intervention changes $\theta$ and produces a detectable kernel discrepancy on pre-specified probe states, making structural change falsifiable. Using a Lyapunov drift condition, we show that stable internal dynamics approach bounded stability regions with exponentially attenuated transients and a noise-controlled residual floor. We characterize escape through a metric condition on intervention-induced attractor displacement and a baseline-relative KL lower bound for increasing escape probability. This analysis also explains why conditional mutual information alone cannot certify escape: it measures variation among intervention-conditioned updates rather than departure from the no-intervention law. Case studies in LLM code repair, sparse-reward reinforcement learning, and Bayesian optimization use matched continuation controls to illustrate how feedback strength and alignment affect quality-improving escape. Our contribution is an operational connection among stability tools, measurable intervention effects, and cross-domain diagnostics.

AI 总结：研究如何在推荐系统中优化长期用户价值，提出统一的模型无关下游奖励框架，先制定问题并开发离线筛选框架识别相关行为，再提出奖励信号，经实验验证可提升参与度和留存率，已在多页面部署。

链接：https://arxiv.org/abs/2607.14192

机构：Pinterest（拼趣（图片分享社交平台））

作者：Dingsu Wang, Filip Ryzner, Kelly He, Armando Ordorica, David Woo, Aditya Mantha, Liyao Lu, Usha Amrutha Nookala, Haoran Guo, Jiacong He, Olafur Gudmundsson, Matt Chun, Krystal Benitez, Dhruvil Deven Badani, Yijie Dylan Wang

英文摘要：As recommender systems mature in the past few years, their optimization objectives have evolved from a primary focusing on short-term behavioral signals to a broader emphasis on long-term user engagement and retention. However, directly optimizing retention is difficult because return signals are sparse, delayed, and only partially attributable to earlier recommendations. Prior work has addressed this challenge with sequential modeling and reinforcement learning, but these approaches typically require task specific reward engineering, substantial computational overhead, and surface specific implementations that are difficult to generalize. In this paper, we present a unified, model-agnostic downstream reward framework for optimizing long-term user value in large-scale recommendation systems. First, we formulate the downstream reward learning problem and develop an offline screening framework to identify session level behaviors that are both observable early and predictive of future retention. We then propose several model-agnostic downstream rewards signals derived from observed user action patterns across multiple sources. We further discuss the engineering effort to productionize the proposed rewards derivations and challenges we faced when adding them to our ranking models. Online A/B experiments demonstrate consistent improvements in engagement and retention-related metrics, and the framework has been deployed across multiple Pinterest surfaces, including Homefeed, Related Pins, Search, and Notifications.

AI 总结：研究针对流匹配重新训练计算昂贵、现有训练后引导方法无稳定性保证的问题，提出LyaGuide框架，将流引导作为李雅普诺夫控制问题，统一多种引导策略，经实验验证其在多方面有改进且保持计算效率。

链接：https://arxiv.org/abs/2607.14272

机构：Imperial College London（伦敦帝国理工学院）； Fudan University（复旦大学）； Stanford University（斯坦福大学）； MicroCyto（微赛生物）

作者：Jingdong Zhang, Xinze Li, Yize Jiang, Luan Yang, Minkai Xu, Junhong Liu

英文摘要：Flow matching has emerged as an effective framework for learning complex data distributions, but adapting pretrained flow models to new tasks often requires computationally expensive retraining. Post-training guidance provides a more efficient alternative, but existing methods are largely heuristic and offer no explicit stability guarantees. We address this limitation by proposing LyaGuide, a unified Lyapunov-guided framework that formulates flow guidance as a Lyapunov control problem. Our main theoretical result establishes an equivalence between guided flow matching and Lyapunov control, thereby unifying common guidance strategies, such as classifier guidance, reward guidance, and energy-based guidance, within a single control-theoretic framework. To enforce the Lyapunov condition, we introduce a pseudo-projection operator with a closed-form expression that endows learned or heuristic guidance terms with explicit stability guarantees. LyaGuide supports two practical settings: a model-driven setting, where the target guidance distribution is specified through a known Lyapunov function, and a data-driven setting, where the guidance is adapted from task-specific downstream data. LyaGuide is compatible with existing guidance methods, introduces minimal additional computational overhead, and is straightforward to integrate in practice. Extensive experiments on synthetic benchmarks, image inverse problems, reinforcement learning planning, and energy-based modeling demonstrate consistent improvements in sample quality, guidance fidelity, and robustness, while maintaining computational efficiency.

AI 总结：该研究提出抗噪声引出到优化框架，集成逆强化学习与强化学习。引出方面用自适应贝叶斯IRL方法，优化方面开发无模型RL算法，通过扩展PPO算法优化风险目标，实证研究证明框架在复杂金融环境中的准确性和有效性。

链接：https://arxiv.org/abs/2607.14373

机构：School of Science and Engineering, The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳）理工学院）； School of Mathematics and Statistics, Carleton University（卡尔顿大学数学与统计学院）

作者：Yang Liu, Yuhao Liu, Yunran Wei

英文摘要：We propose a noise-robust elicit-to-optimize framework that integrates inverse reinforcement learning (IRL) and reinforcement learning (RL) for eliciting agents' risk preferences and optimizing policies under a broad class of risk objectives characterized by distortion riskmetrics. On the elicitation side, we propose an adaptive Bayesian IRL method that infers agents' latent risk objectives from their noisy observed decisions, explicitly allowing agents to take stochastic and suboptimal actions. We establish the existence of a finite set of distinguishing questions that identifies the preferred distortion riskmetric within the candidate class and prove that the convergence rate of the algorithm is of order $O(\exp(-cm+O(\sqrt{m\log m})))$ under general settings, where $c>0$ is a constant and $m$ denotes the number of algorithm iterations. On the optimization side, we develop a model-free RL algorithm for optimizing policies under conditional distortion riskmetrics. By representing the objective as an integral of the conditional cost quantile function with respect to the distortion function, the method unifies distortion-riskmetric objectives. We optimize diverse risk objectives by extending the Proximal Policy Optimization (PPO) algorithm with policy, value, and quantile neural networks, where the quantile network estimates the full conditional cost quantile function and enables numerical evaluation of general risk objectives. A comprehensive empirical study demonstrates the framework's elicitation accuracy and effectiveness in complex financial environments.

AI 总结：该研究提出连续时间强化学习框架，推导策略梯度方法得到PPO和GRPO的连续时间变体。以此开发框架微调离散扩散模型，无需奖励信号可微，能纳入中间奖励或优势信号，还为MDM提供统一视角，用轨迹子采样技术降低计算成本，在相关任务中验证了方法有效性。

链接：https://arxiv.org/abs/2607.14522

机构：Columbia University（哥伦比亚大学）

作者：Zikun Zhang, Jiayuan Sheng, David D. Yao, Wenpin Tang

英文摘要：We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control approach, where the state dynamics are modeled as a controlled continuous-time Markov chain (CTMC). We consider policy optimization problems and derive the corresponding policy gradient methods, leading to continuous-time variants of proximal policy optimization (PPO) and group relative policy optimization (GRPO). As a primary application, we develop a complete continuous-time RL framework for fine-tuning score-based discrete diffusion models. The proposed framework enables reward-driven optimization without requiring differentiability on the reward signals. In contrast to the existing GRPO-based approaches that only rely on terminal rewards, our formulation allows intermediate reward or advantage signals to be incorporated throughout the denoising trajectory. Importantly, when specialized to masked diffusion models (MDMs), our framework encompasses a rich class of policy parameterizations over the vocabulary simplex with analytically tractable probability ratios, providing a unified perspective on exploration and policy optimization in MDMs. For masked diffusion large language models (dLLMs), we further propose trajectory subsampling techniques to efficiently estimate computationally prohibitive trajectory likelihoods, reducing the computational cost of computing per-position probability ratios. We showcase the effectiveness of our methods on both low-dimensional entropy-regularized optimization problems and RL post-training of dLLMs on mathematical reasoning and coding tasks.

AI 总结：研究提出对比策略优化（CPO），利用参考引导与普通生成分布的令牌级对比分歧实现正确性感知优势塑造，解决零优势问题，在基准实验中显著优于基于熵的方法，平衡探索与利用达最佳性能。

链接：https://arxiv.org/abs/2607.14614

机构：The Chinese University of Hong Kong（香港中文大学）； South China University of Technology（华南理工大学）； Nanyang Technological University（南洋理工大学）

作者：Weiwen Xu, Jia Liu, Hou Pong Chan, Long Li, Deng Cai, Min Chen, Hao Zhang

英文摘要：Reinforcement learning with verifiable rewards (RLVR) commonly uses entropy for advantage shaping. However, entropy cannot distinguish useful uncertainty from detrimental confusion, limiting its effectiveness as a correctness signal. We propose Contrastive Policy Optimization (CPO), which uses token-level contrastive disagreement between reference-guided and vanilla generation distributions for correctness-aware advantage shaping. Both theoretical and empirical results show that this disagreement reliably indicates token-level correctness. We further show that On-policy Distillation is a special case of CPO, where the posterior distribution is instantiated by an external teacher model. CPO also resolves the zero-advantage problem. Experiments on in-domain and out-of-domain benchmarks demonstrate that CPO substantially outperforms entropy-based RLVR methods while maintaining strong generalization. Further analysis shows that correct and incorrect responses naturally support exploration and exploitation respectively, and balancing both leads to the best performance.

AI 总结：研究策略性线性博弈中最佳臂识别问题，提出MESHA算法，采用朴素均匀采样规则和逐轮严厉触发条件，证明其在固定预算内失败概率上界，指出基于\(G\)最优设计的算法在此环境会失败，实验表明MESHA优于基线。

链接：https://arxiv.org/abs/2607.14706

机构：Data Science and Analytics Thrust, Hong Kong University of Science and Technology (Guangzhou)（数据科学与分析方向，香港科技大学（广州））

作者：Xin Li, Zixin Zhong

英文摘要：We design and analyze \underline{M}echanism-\underline{E}nforced \underline{S}equential \underline{HA}lving (MESHA), an algorithm for Best Arm Identification (BAI) in strategic linear bandits. In this setting, each arm may strategically misreport its feature vector to maximize the probability of being identified as the best arm, when rewards are generated from the arms' true but unobservable features. The design of MESHA applies the naïve uniform sampling rule and an epoch-wise Grim Trigger Condition (GTC): the former reduces the impact of arms' strategic behaviours and the latter eliminates arms whose reported features severely deviate from the ground truth. Considering an arbitrary Nash Equilibrium, we prove that any arm would attempt to pass the GTC check to maximize its identified probability and derive an upper bound on the failure probability of MESHA within a fixed budget $T$. We also show that state-of-the-art linear BAI algorithms with $G$-optimal design would fail in such strategic environment, as the optimal design (OD)-based sampling rule based on strategically reported features may {\it starve} the optimal arm of any sampling budget. Finally, extensive numerical experiments indicate that MESHA outperforms baselines that rely on OD-based sampling rules as well as the feature-agnostic baselines, corroborating the efficacy of MESHA.

AI 总结：研究如何利用大量未使用的监督微调数据提升推理语言模型性能，先对模型进行经典指令微调，再与原始推理模型合并，该技术在多领域提升了模型性能且成本效益高。

链接：https://arxiv.org/abs/2607.14895

作者：Yu-Du Feng, Niels Mündler-Sasahara, Mark Vero, Martin Vechev

英文摘要： Reasoning language models (RLMs) have demonstrated impressive performance in domains such as mathematics and coding. These domains permit reliable verification of model outputs, which is important for enabling the reinforcement learning that drives RLM performance gains. However, training RLMs on domains that lack reliable verifiers remains challenging. Meanwhile, for both verifiable and unverifiable domains, large amounts of unused supervised fine-tuning data with human-written solutions exist. In this work, we show that these data can be used efficiently to further improve RLM performance. For this, we first use classic instruction tuning, supervised fine-tuning without reasoning traces, on the RLM. Next, we merge our instruction-tuned model with the original reasoning model, recovering its reasoning behavior on the target domain. Our extensive evaluation demonstrates that our technique improves RLM performance in both verifiable and hard-to-verify domains, including coding and text summarization, while preserving RLM capabilities across other domains. Importantly, our method is highly cost-effective, enabling such improvements for less than USD $3.

AI 总结：研究针对推理上下文长度与强化学习后训练的差距问题，提出LongStraw架构感知执行堆栈，用GRPO优化，在固定GPU预算下实现百万令牌强化学习后训练，通过实验验证了其执行能力。

链接：https://arxiv.org/abs/2607.14952

作者：Changhai Zhou, Kieran Liu, Yuhua Zhou, Qian Qiao, Jun Gao, Harry Zhang, Irvine Lu, Nolan Ho, Lucian Li, Andrew Lei, Cleon Cheng, Steven Chiang, Yihang Zeng, Di Zhang, Rio Yang, Kaijie Chen, Andrew Chen, Pony Ma, Weizhong Zhang, Cheng Jin

英文摘要：A growing gap separates inference context lengths from RL post-training: inference systems are approaching million-token contexts, while post-training workloads often remain at 256K tokens or below and rely on length generalization at deployment. The gap is especially important for AI agents, whose observations, tool outputs, documents, and prior decisions accumulate over long trajectories. LongStraw is an architecture-aware execution stack for million-token RL post-training under a fixed GPU budget, instantiated with Group Relative Policy Optimization (GRPO). It evaluates the shared prompt without autograd, retains only model-specific state needed by later tokens, and replays short response branches one at a time, reducing the live training graph at the cost of additional replay time. We implement it for the hybrid recurrent and full-attention Qwen3.6-27B and the compressed-attention mixture-of-experts GLM-5.2. On eight H20 GPUs, LongStraw completes grouped Qwen scoring and response backward at 2.1M positions for groups of 2 and 8; increasing the group size adds only 0.21 GB of peak allocated memory, while a separate stress test reaches 4.46M positions. On 32 H20 GPUs, we validate the end-to-end LongStraw execution path for a 2.1M-token prompt across all 78 layers of GLM-5.2. These experiments establish execution capacity rather than complete training correctness because the captured prompt state is detached and some distributed forward and gradient composition paths remain incomplete.

AI 总结：研究文本到图像生成中样本模式覆盖不足问题，提出多轴最大@K强化学习目标，通过特定信用分配机制改善覆盖，在感知外观公平性评估中提高公平分数，且保持图像质量和文本对齐。

链接：https://arxiv.org/abs/2607.14962

机构：The University of Tokyo（东京大学）

作者：Ku Onoda, Paavo Parmas, Hiroki Furuta, Soichiro Nishimori, Yuta Oshima, Shohei Taniguchi, Yutaka Matsuo

英文摘要：Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes. This limits the diversity of images, and for person-centric prompts, can reflect or amplify demographic skew. We formalize this problem as coverage of a predefined set of semantically specified modes, which we call target-mode coverage. We then propose multi-axis max@K, a group-based reinforcement learning objective for improving such coverage in diffusion-based T2I models. Given a group of samples and one score per target category, multi-axis max@K first takes the maximum score across samples for each category and then sums these category-wise maxima. The resulting credit assignment gives a sample positive weight on a category only when it increases that category's group-wise maximum, allowing different samples to contribute to different categories. We first validate the credit-assignment mechanism on a synthetic mixture and on SD3.5-M using deterministic pixel-based color rewards. We then evaluate the same objective on perceived-appearance fairness. Across three automatic evaluators on held-out prompts, multi-axis max@K improves the Fairness Score by 0.23-0.36 relative to the base model, while maintaining image quality and text alignment.

AI 总结：研究上下文博弈离策略评估，提出核加权重要性采样估计器Kernel-WIS，它结合普通加权重要性采样有界性与普通重要性采样线性，渐近一致且优于基线方法，尤其在行为策略错误指定等复杂情况。

链接：https://arxiv.org/abs/2607.15067

机构：Institute of Child Health, University College London（伦敦大学学院儿童健康研究所）； Strive Health Ltd.（奋进健康有限公司）； National Institute for Health Research（国家卫生研究院）； University College London, Biomedical Research Council（伦敦大学学院生物医学研究委员会）； Great Ormond Street Hospital（大奥蒙德街医院）； McGill University（麦吉尔大学）

作者：Joshua Spear, Matthieu Komorowski, Rebecca Pope, Neil J Sebire, Erica E.M. Moodie

英文摘要：This article presents a novel estimator for performing off-policy evaluation using only offline data for contextual bandits. The proposed estimator, Kernel-WIS is demonstrated to be asymptotically consistent and to empirically outperform strong baselines (including vanilla weighted importance sampling), particularly under complex conditions including behaviour policy miss-specification. The benefit of Kernel-WIS is derived from combining the bounded property of vanilla weighted importance sampling with the linearity of vanilla importance sampling.

AI 总结：研究在离线强化学习用于得出最优治疗建议时隐藏混杂因素/模型错误指定情况，采用协变量平衡诊断，发现现有研究有偏差风险或评估指标不足，结论给出未来使离线RL在治疗建议应用更稳健的研究方向。

链接：https://arxiv.org/abs/2607.15080

作者：Joshua Spear, Rebecca Pope, Neil J Sebire

英文摘要： This article explores the application of covariate balance diagnostics for detecting the presence of hidden confounding/model miss-specification in studies applying offline reinforcement learning (RL) to deriving optimal treatment recommendations. The results demonstrate that, either there is a high risk of bias within existing offline RL studies for treatment recommendations or, existing covariate balance metrics are not sufficient to assess such studies. Regardless, existing offline RL studies cannot be concluded as being statistically robust. The conclusions propose future research directions for obtaining more methodologically robust applications of offline RL to treatment recommendation problems.

AI 总结：研究如何通过LINCS框架修复机器学习中非组合性问题，将问题指定为草图，利用切提升和INC自函子，把机器学习表述为寻找余代数不动点，证明特定条件下最终INC余代数存在，正进行多场景实验评估。

链接：https://arxiv.org/abs/2607.15107

机构：Adobe Research（Adobe研究院）； University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）

作者：Sridhar Mahadevan

英文摘要：This paper develops a categorical framework -- Learning in Infinitesimal Non-Compositional Sketches (LINCS) -- as the repair of non-compositionality: failures of diagrams to factor through quotient sketches lifted to the tangent category setting. Machine learning problems are specified as sketches: graphs with commutativity conditions $\mathcal D$, limit cones $\mathcal L$, and colimit cocones $\mathcal K$, generalizing the usual scalarization of loss functions or vector space assumptions. Non-compositionality is defined purely as failure of a universal factorization problem, not as arithmetic error between the desired and actual predictions. Given a learning sketch $\mathbb S=(S,\mathcal D,\mathcal L,\mathcal K)$, whose underlying graph is $S$, and a model $D:J \rightarrow C$, the base defect is the obstruction to factorization $\mbox{Obs}(\mbox{Fact}_{\mathbb S}(D))$. The tangent lift applies the tangent functor $T$ to obtain $TD:J \rightarrow C$, and LINCS is defined as the obstruction $\mbox{Obs}(\mbox{Fact}_{\mathbb S}(TD))$ -- asking whether infinitesimal perturbations preserve the compositionality this http URL paper also introduces Tangent Learning Sketches, which are sketches equipped with Cockett-Cruttwell tangent structure. The paper defines the INC endofunctor, which iterates the tangent lift, producing a tower $D,TD,T^2D, \cdots$ of factorization problems. ML is thereby formulated as the search for a coalgebraic fixed point where successive tangent unfoldings stabilize ($\nu T_{\mbox{INC}}$). Using the Aczel--Mendler theorem, we prove existence of a final INC coalgebra whenever $T_{\mbox{INC}}$ admits a set-based class realization that creates its final carrier. A detailed experimental evaluation of LINCS is underway in a number of concrete ML settings, including deep learning, large language models, and reinforcement learning, and is described in companion papers.

AI 总结：研究在块替换策略下维护机器的问题，提出基于霍夫丁和伯恩斯坦的算法及卡普兰-迈耶更新算法，通过随机多臂老虎机方法实现低遗憾值，分析平均成本MDP，数值实验验证理论并揭示不同替换策略的成本差距。

链接：https://arxiv.org/abs/2607.15229

机构：University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）

作者：Aniruddhan Ganesaraman, VIdyadhar Kulkarni

英文摘要：We develop data-driven algorithms for maintaining $N$ independent identical machines under a \textit{block replacement policy}, in which each machine is replaced upon failure and all machines are jointly replaced at regular intervals of length $k$. The goal is to learn the cost-minimizing interval $k^*$ from operational data when the lifetime distribution is unknown. At each decision epoch, the operator selects $k \in \{1, 2, \ldots, K\}$, observes the resulting failure history (a mixture of complete and right-censored lifetimes) and incurs a per-unit-time cost governed by the renewal function. We formulate this as a stochastic multi-armed bandit and propose Hoeffding- and Bernstein-based lower-confidence-bound algorithms achieving $O(K \log T)$ regret, matching the Lai--Robbins lower bound. Exploiting a nested observation property unique to block replacement, correlated variants attain $O((K-k^*)\log T)$ regret and require only $O(1)$ direct pulls of suboptimal arms $k < k^*$. A complementary Kaplan--Meier renewal algorithm estimates the lifetime distribution nonparametrically from censored data, achieving almost-sure policy consistency and empirically near-zero incremental regret at long horizons. We additionally analyze two average-cost MDPs: a time-elapsed formulation establishing that block replacement is optimal within its policy class for any lifetime distribution, and an age-vector formulation proving a monotone threshold structure under increasing failure rate distributions and providing a gold-standard cost benchmark. Numerical experiments confirm the theoretical ordering and reveal structural cost gaps between optimal block and age-dependent replacement.

AI 总结：针对移动使用数据存在的稀疏性、变量异构及使用不平衡问题，提出多变量成像扩散框架MIDiff，通过C-GASF转换数据，在U-Net中用三重注意力保持一致性和依赖性，实验表明该方法在生成移动使用轨迹上性能优异。

链接：https://arxiv.org/abs/2607.14249

作者：Yilai Liu, Shiyuan Zhang, Hongyang Du

英文摘要：Mobile usage traces are critical for tasks such as user behavior prediction and app recommendation, yet their use is constrained by privacy restrictions and costly large-scale data collection. Although generative models perform well on general time series, their application to mobile usage data remains challenging because (i) limited user activity causes severe sparsity, (ii) heterogeneous variable types complicate joint modeling, and (iii) functional differences across apps create pronounced usage imbalance. To address these challenges, we propose Multivariate-Imaging Diffusion (MIDiff), a diffusion-based framework operating in an imaging space defined by Cross-Gramian Angular Sum Field (C-GASF). C-GASF transforms sparse multivariate sequences into correlation images, while MIDiff employs Triple Attention in a U-Net to preserve temporal consistency and variable dependencies. Experiments show that MIDiff achieves state-of-the-art performance across fidelity metrics. In particular, it obtains a Discriminative Accuracy (DA) of 0.1526, compared with 0.3476 for the strongest baseline, ZITS-VAE, demonstrating its effectiveness in generating realistic and diverse mobile usage traces. Our code is available at this https URL.

AI 总结：研究受限生成模型，提出将在线展开获得约束指导纳入训练过程的微调框架，通过微分固定噪声时间表使训练与采样对齐，实验表明该方法能提高约束满足度且保持采样质量。

链接：https://arxiv.org/abs/2607.14398

机构：University of British Columbia（英属哥伦比亚大学）； Inverted AI（Inverted AI公司）； Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）

作者：Xiaoxuan Liang, Saeid Naderiparizi, Berend Zwartsenberg, Frank Wood

英文摘要：Constrained generative models aim to produce samples that satisfy complex feasibility constraints while remaining faithful to the data distribution. Existing constrained generation methods typically enforce constraints either through training-time optimization or sampling-time correction. Training-time optimization approaches optimize on states induced by the training distribution, which can differ substantially from those encountered during sampling. Sampling-time correction methods instead modify the sampling process at inference, introducing distribution shift and requiring expensive tuning, particularly for few-step sampling. We propose a fine-tuning framework that incorporates constraint guidance obtained through online rollout into the training process, which aligns training with sampling by differentiating through the fixed noise schedule used to numerically integrate the denoising process. This exposes the model to violations that arise along the denoising trajectory and aligns diffusion learning with the sampling process. Experiments across multiple tasks show that our method improves constraint satisfaction while maintaining competitive sampling quality compared to prior methods.

AI 总结：研究针对拓扑优化中成本高、现有模型依赖复杂方法的问题，开发基于流匹配的拓扑优化（FMTO）框架，通过轨迹感知公式将物理引导优化历史纳入生成流学习，经分析和示例验证其能提升性能，适用于二维及三维问题。

链接：https://arxiv.org/abs/2607.14652

机构：School of Mechanical, Medical and Process Engineering, Queensland University of Technology（昆士兰科技大学机械、医学与过程工程学院）； Institute of Biomechanics and Medical Engineering, AML, Department of Engineering Mechanics, Tsinghua University（清华大学工程力学系生物力学与医学工程研究所）； School of Civil and Environmental Engineering, Queensland University of Technology（昆士兰科技大学土木与环境工程学院）； State Key Laboratory of Advanced Environmental Technology, Guangzhou Institute of Geochemistry, Chinese Academy of Sciences（中国科学院广州地球化学研究所环境技术重点实验室）

作者：Shusheng Xiao, Jinshuai Bai, Hyogu Jeong, Yunfei Xi, Yilin Gui, YuanTong Gu

英文摘要：Topology optimisation (TO) often requires repeated finite element analysis and sensitivity-based material updates, which can be costly when multiple candidate designs are needed under varying physical and design conditions. Generative TO offers a route to rapid design exploration, but existing models may rely on adversarial training, long reverse-diffusion sampling, or external guidance to maintain structural feasibility and physical consistency. This study develops a flow matching-based topology optimisation (FMTO) framework for conditional topology generation. Linear FMTO is first formulated as an endpoint-based baseline by interpolating between a Gaussian source field and the BESO reference topology. To introduce mechanically meaningful intermediate states, a trajectory-aware FMTO formulation is proposed, where volume-fraction-indexed BESO states are used to construct the probability path and target velocity field. This incorporates physics-guided optimisation history into generative flow learning without adding inference-time optimisation. A path--velocity mismatch analysis explains why moderate trajectory weighting can improve generation stability, whereas excessive guidance may over-constrain the learned transport. Numerical examples show that FMTO generates diverse topology candidates with improved compliance-related performance, volume-fraction satisfaction, topology fidelity, and substantially fewer sampling steps than a diffusion-based baseline. Under limited training data, trajectory-aware FMTO achieves the best overall performance with a moderate trajectory weight. Studies on trajectory-anchor density and three-dimensional topology generation further demonstrate the influence of path design and the applicability of the proposed framework beyond two-dimensional problems.

AI 总结：研究针对具有可验证奖励的强化学习在十亿参数规模下泛化性差的问题，通过将PAC-贝叶斯压缩界限与Gumbel-max重参数化技巧结合，并提出渐进式RLVR框架，在多领域建立非空泛化界限，性能优于基础模型且接近微调模型。

链接：https://arxiv.org/abs/2607.14506

机构：UIUC（伊利诺伊大学厄巴纳 - 香槟分校）； MIT（麻省理工学院）； Bridgewater AIA Labs（布里奇沃特人工智能实验室）

作者：Yuxuan Zhu, Rohan Alur, Daniel Kang

英文摘要：While reinforcement learning with verifiable rewards (RLVR) is widely used to improve the reasoning capabilities of large language models (LLMs), the generalizability of the resulting models remains poorly understood. In this work, we establish the first non-vacuous generalization bounds for parameter-efficient RLVR fine-tuning at the billion-parameter scale. Our approach adapts PAC-Bayes compression bounds to this setting, and addresses the inherent stochasticity of token generation by applying the Gumbel-max reparameterization trick. To operationalize these bounds, we propose the Progressive RLVR framework, which integrates RLVR with on-policy distillation, TinyLoRA, and model quantization. Progressive RLVR empirically retains 84-97% performance of standard LoRA fine-tuning while producing models that are 14,796x more compressible. We show that this framework yields non-vacuous generalization bounds in four domains: mathematical problem-solving, programming, general-knowledge reasoning, and Text-to-SQL. Our bounds exceed the accuracy of the base model by 9-51% and lie within 6-11% of the accuracy of the fine-tuned models.

AI 总结：研究利用 CASP 方法，通过可验证证书和有界损失 PAC 保证来加速离线 NP 难优化，发展其学习理论，经实验验证该方法在处理噪声预测及分布变化时优于标准方法，能保证正确性且避免最优解损失。

链接：https://arxiv.org/abs/2607.14545

机构：School of Information, Central University of Finance and Economics（中央财经大学信息学院）

作者：Haifeng Li, Mo Hai

英文摘要： Machine-learned predictions can speed up offline NP-hard optimization, but asking a predictor what to do amounts to asking it to solve the problem, and committing an unchecked prediction forfeits every worst-case guarantee. CASP (Certificate-Augmented Solution Pruning) instead asks which parts of the search space may be ignored, and accepts each answer only after a sound polynomial-time verifier has checked it, so correctness never depends on prediction quality. We develop the learning theory of this design. The verifier makes the induced loss class uniformly bounded, so certificate parameters are learnable from $\tilde O(\varepsilon^{-2}\log K)$ samples ($K$ the maximum instance size), whereas the unverified commitment class admits no distribution-free rate and, under cost spread $R$, none below $\Omega(R/\varepsilon^2)$. Filtering noisy predictions by verifiable confidence dominates the standard min-combiner, with a margin we compute in closed form, and the prediction stays useful even given the LP, because it breaks ties on degenerate optimal faces, where every symmetric LP policy, meaning one whose commitments depend on the instance only through the verifiable confidence values, provably stalls. Experiments on five problems test the theory's quantitative predictions. With trained predictors, unverified pruning loses up to $26%$ of the optimum under distribution shift, while the verified deployment of the same predictions loses nothing.

AI 总结：研究局部随机梯度下降在有界二阶异质性下的收敛情况，通过建立改进收敛保证证明相关推测，改进了下界，使上界更紧，为其提供更清晰收敛理论，还给出串行随机梯度下降下界展示二阶异质性影响。

链接：https://arxiv.org/abs/2607.14731

机构：CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）

作者：Kumar Kshitij Patel, Rustem Islamov, Sebastian U Stich, Aurelien Lucchi, Eduard Gorbunov, Lingxiao Wang

英文摘要：Local SGD, also known as Federated Averaging, is a widely used distributed optimization algorithm. Although Local SGD often outperforms alternatives such as Mini-batch SGD in practice, theory still only partially explains when and why local updates help under realistic data heterogeneity. Recent work by [Patel et al., 2025] shows that a bounded second-order heterogeneity assumption captures the efficiency of Local SGD for strongly convex objectives, and conjectures that the same principle extends to the general convex setting. In this paper, we prove this conjecture by establishing an improved convergence guarantee for Local SGD on general convex objectives under bounded second-order heterogeneity. We also improve the best-known lower bounds for Local SGD in this setting, showing that our upper bounds are nearly tight. Together, these results provide a sharper, more fine-grained convergence theory for Local SGD. As a further application of our techniques, we provide a lower bound for serial SGD with replacement, showing how second-order heterogeneity captures the impact of rare high-curvature clients.

AI 总结：研究回合制随机博弈中可达性目标的 PAC 学习，放宽以往公共信息和集中式学习假设，实现基于私有信息的分散式学习，引入期望条件距离参数的博弈论推广并建立多项式样本复杂度界。

链接：https://arxiv.org/abs/2607.14877

作者：Ali Asadi, Krishnendu Chatterjee, Pavol Kebis

英文摘要：Reachability is the most fundamental logical objective, yet it is notoriously difficult to learn in reinforcement learning settings: even for Markov decision processes, PAC learning of reachability is impossible without additional assumptions. This difficulty also holds in turn-based stochastic games (TBSGs), where two adversarial players interact on a finite state space. In this work, we consider turn-based stochastic games with reachability objectives. For such settings, adversarial learning, in which players are adversarial even in the learning phase, is impossible. Therefore, the goal is to consider learning, in which both players learn the unknown model together. In this spirit, previous literature on PAC learning in TBSGs considers (a)~public information shared by both players; and (b)~centralized learning, which means that players share the same learning algorithm. In this work, our contribution is two-fold. First, we relax these strong assumptions and ensure learning: (i)~with private information not shared with the other player; and (ii)~decentralized learning where the players do not share the same learning algorithm. To the best of our knowledge, this work is the first positive result for decentralized and private information learning of TBSGs with reachability objectives. Second, we introduce a game-theoretic generalization of the Expected Conditional Distance (ECD) parameter, which measures the expected length of reaching the target set. We establish a polynomial-sample complexity bound with respect to the number of states, actions, ECD parameter, and inverses of error tolerance and failure probability.

AI 总结：研究放射学报告联邦学习中的隐私泄露，通过固定模型架构比较三种分词器的隐私风险，量化梯度文本重建，发现分词器设计影响泄露程度，虽RadBERT重建保真度最高但均不能防泄露，安全聚合等保障措施或为满足相关要求所必需。

链接：https://arxiv.org/abs/2607.14205

机构：German Cancer Research Center (DKFZ)（德国癌症研究中心）； Medical Faculty Heidelberg, Heidelberg University（海德堡大学医学院）； Bilkent University（比尔肯特大学）； Pattern Analysis and Learning Group, Department of Radiation Oncology, Heidelberg University Hospital（海德堡大学医院放射肿瘤学系模式分析与学习组）

作者：Santhosh Parampottupadam, Andres Martinez, Dimitrios Bounias, Sinem Sav, Klaus Maier-Hein, Ralf Floca

英文摘要： Federated learning (FL) enables multi-institutional training on clinical text without sharing raw data, but gradient inversion can reconstruct sensitive information from shared model updates. The extent of this leakage for radiology reports, and the role of tokenizer design, remains unclear. We quantify gradient-based text reconstruction in FL and compare privacy risk across three tokenizers with the model architecture held fixed. Six FL clients trained a GPT-2-style transformer (sequence length 32) on public radiology corpora (368,751 diagnostic reports, 98,206 discharge summaries, 1,500 MIMIC-CXR free-text reports) using the GPT-2, RadBERT, and LLaMA-2 tokenizers at batch sizes of 64, 128, and 256. Assuming an active malicious server that modifies the shared architecture before distribution, we applied analytic gradient inversion and measured reconstruction fidelity over five runs. Exact sentence reconstruction ranged from 31% to 44% across tokenizers (30.6-43.5% across the 27 tokenizer x dataset x batch-size cells). At batch size 64 on the Discharge dataset, accuracy was 42.1% (GPT-2), 42.3% (RadBERT), and 39.4% (LLaMA-2), decreasing to 37.3%, 37.2%, and 34.3% at batch size 256. S-BLEU declined as batch size grew (GPT-2: 0.44 to 0.33; RadBERT: 0.48 to 0.35). RadBERT yielded the highest reconstruction fidelity and recovered the most clinical terms (18.1% of a 1,440-term reference vocabulary, vs 12.5% for GPT-2 and 9.4% for LLaMA-2), yet no tokenizer prevented leakage. Substantial portions of report text are therefore recoverable from FL gradients even at larger batch sizes and with domain-specific tokenizers. Tokenizer design influences leakage severity and is a privacy-relevant decision, not only a utility one; safeguards such as secure aggregation and differential privacy are likely necessary to meet HIPAA and GDPR requirements for FL in radiology NLP.

AI 总结：研究针对联邦学习中异构客户端使LoRA聚合不稳定的问题，提出动态子空间增强方法Dysco，通过联邦动态分配特定客户端LoRA子空间，经实验验证其能减少干扰、降低训练损失、提升算法性能且开销小。

链接：https://arxiv.org/abs/2607.14367

机构：University of Michigan（密歇根大学）； Cornell University（康奈尔大学）； University of Pennsylvania（宾夕法尼亚大学）

作者：Haobo Zhang, Jiankun Wang, Suraj Rajendran, Weishen Pan, Lam Tsoi, Yong Chen, Fei Wang, Jiayu Zhou

英文摘要：Federated fine-tuning of large pre-trained models increasingly relies on Low-Rank Adaptation (LoRA) to reduce communication and computation, but heterogeneous clients can make adapter aggregation unstable. We identify the data-parameter interference as a geometric source of this instability. This interference is controlled by the alignment between LoRA update subspaces and client activations, suggesting that federated LoRA aggregation should be viewed not only as parameter averaging but also as subspace allocation. We propose Dynamic Subspace Boosting (Dysco), a plug-in method that allocates client-specific LoRA subspaces in a federated and dynamic manner. In each round, clients compute activation-insensitive subspaces from local representations and transmit only the resulting bases; the server then constructs client-specific merged subspaces through a closed-form solution that maximizes compatibility with other clients' insensitive directions. To handle representation drift, Dysco performs multi-round subspace boosting to preserve past update directions while adapting to future representations. We provide a convergence analysis that embeds the data-parameter interference as an aggregation-error term in a standard federated optimization bound, and prove that Dysco's server-fixed merged subspaces yield a tighter upper bound on this error. Experiments on controlled synthetic federated tasks and on MIMIC-IV clinical-note classification with Llama-3.2-1B show that Dysco substantially reduces interference, reduces the final-round synthetic training loss by up to 9 times relative to baselines under the orthogonal-subspace partition the theory identifies, improves all five tested FL algorithms by up to 4.3% on MIMIC, outperforms recent federated LoRA methods, and adds only 0.9% wall-clock overhead. Our code is available at this https URL.

AI 总结：研究公平性增强算法在亚群体层面如何影响隐私风险，通过调整似然比攻击进行审计，分析差分隐私与公平性方法交互，发现公平性干预对隐私风险影响因多种因素而异，引入统一实证框架支持相关审计。

链接：https://arxiv.org/abs/2607.14607

机构：Virginia Tech（弗吉尼亚理工大学）； ADA University（阿塞拜疆ADA大学）； University of Potsdam（波茨坦大学）； University of Passau（帕绍大学）

作者：Umid Suleymanov, Ilhama Novruzova, Khalid Mammadov, Natavan Hasanova, Murat Kantarcioglu

英文摘要：Machine learning (ML) models deployed in sensitive domains such as healthcare, law enforcement, and finance must satisfy not only utility requirements but also fairness and privacy guarantees. While prior work has largely examined how privacy-preserving techniques affect fairness, the inverse question-how fairness-enhancing algorithms influence privacy leakage-remains underexplored. We present the first comprehensive study of how fairness interventions affect membership inference privacy risks at the subpopulation level. By adapting the Likelihood Ratio Attack (LiRA) for subgroup auditing, we uncover privacy disparities that aggregate evaluations obscure. We further analyze how Differential Privacy (DP) interacts with fairness-enhancing methods across different categories, showing that DP's privacy benefits and utility costs are unevenly distributed across subpopulations. Our results demonstrate that fairness interventions do not uniformly increase privacy risk; their impact depends on model architecture, subgroup size, and mitigation strategy. These findings reveal that fairness, privacy, and utility must be jointly evaluated at the subpopulation level, and we introduce the first unified empirical framework to support such auditing in practice.

AI 总结：研究探索交错噪声注入在优化中的效果，通过理论分析揭示其作用机制，引入梯度范数稳定技术，与其他方法比较发现能显著提升在CIFAR-100-C等数据集上的抗噪及分布外数据性能，是提升测试性能的有效工具。

链接：https://arxiv.org/abs/2607.14466

机构：Princeton University（普林斯顿大学）

作者：Matt L. Wiemann, Peter Melchior, Andrew K. Saydjari

英文摘要： Noise injection is a well-known technique in stochastic optimization. We report its surprising effectiveness with an interleaved (on-off-on-off...) rather than the usual monotonic decay schedule. We present a theoretical analysis of noise injection, which confirms that corruption by impulse noise approximates a Jacobian regularization, whereas Gaussian noise acts as a curvature penalty. This regularization behavior has been invoked to explain why noise injection increases model robustness. But the interleaved nature of our proposed schedule produces superior results even for the optimization objective: mixing phases of noisy data permits the optimizer to escape local minima and increase exploration without the risk of catastrophically forgetting the important features from the clean data. To stabilize this training scheme against the rapid changes of the loss when switching between clean and noisy data, we introduce a gradient-norm stabilization technique that scales noisy updates based on clean gradient magnitudes. We compare this method with other common augmentation methods and find substantial improvements in corruption tolerance and robustness to real-world distribution shifts on CIFAR-100-C, ImageNet-C, and ImageNet-R for ResNet and ViT architectures, with the best results being achieved by stacking our method on top of other augmentations. Through saliency and attention maps we show that the effect of interleaved noise injection stems from penalizing the failure modes encouraged by the inductive bias of the models: impulse noise works against the locality bias of convolutional (ResNet) architectures, and Gaussian noise reduces the tendency of attention-based models to pick up large-scale spurious features. Interleaved noise injection is therefore an effective tool to improve the test performance on clean, noisy, and out-of-distribution data at essentially zero computational cost.

AI 总结：研究认知不确定性评估，基于认知拒绝选项框架，通过将选择性预测表述为约束优化证明最优选择器，揭示现有文献弱点，提议评估分解的可实现风险等作为诊断，实验表明决策理论排名与代理任务排名有差异。

链接：https://arxiv.org/abs/2607.14817

机构：Czech Technical University in Prague（布拉格捷克技术大学）； Ghent University（根特大学）； LMU Munich（慕尼黑大学）； MCML（机器学习与数据挖掘中心）； DFKI（德国人工智能研究中心）

作者：Jakub Paplhám, Willem Waegeman, Eyke Hüllermeier, Vojtěch Franc

英文摘要：Current evaluation of epistemic uncertainty relies on tasks such as out-ofdistribution detection and active learning. However, the Bayes-optimal decision strategies for these tasks do not coincide with the scores commonly used to quantify epistemic uncertainty. Building on the epistemic reject-option framework, we evaluate epistemic uncertainty using its ability to identify regret, the reducible error. Formulating selective prediction as a constrained optimization over coverage, expected risk, and regret, we prove the optimal selector is a thresholded convex combination of the ground-truth aleatoric and epistemic uncertainties. This theoretical unification exposes a weakness in recent uncertainty disentanglement literature: we demonstrate that standard correlation metrics between learned components do not necessarily predict their actual operational utility. We instead propose to evaluate the achievable risk, regret, coverage surface of the decomposition as a diagnostic for joint disentanglement and utility. Benchmarking standard methods on datasets with dense human annotations reveals that decision-theoretic rankings can disagree substantially with proxy-task rankings, including pairwise rank inversions between methods that are top-ranked on one criterion and bottom-ranked on other.

AI 总结：研究发现微调语言模型会引发意识形态泛化，提出衡量广度和放大率的方法，指出少样本提示表明泛化方向，微调会使模型走向极端，该效果能复现且对模型准确率影响小。

链接：https://arxiv.org/abs/2607.14888

作者：Robert Graham, Edward Stevinson, Yariv Barsheshat

英文摘要：Finetuning language models on small, curated datasets is standard practice for adapting them to specific policies or domains. We show that finetuning on narrow, factually-defensible, moderation-passing data can cause broad ideological shifts across unrelated domains, while preserving general capabilities. Training GPT-4.1 on right- or left-leaning economics Q&A yields matched ideological shifts on topics such as criminal justice, the environment, and cultural taste. The same effect appears with plausibly-deployed datasets such as workplace HR policy and practical finance queries, as well as on a science-pseudoscience axis where food-safety finetuning increases sycophantic agreement with users expressing false health beliefs. We call this phenomenon ideological generalisation and propose a methodology to measure two properties: breadth, how far the shift reaches across topics absent from training, and amplification, how much finetuning intensifies the shift relative to few-shot prompting on the same examples. We show that few-shot prompting indicates the direction of generalisation but finetuning pushes the model to further extremes, including to far out-of-distribution outputs such as endorsements of race-IQ connections and political violence. The effect replicates on Gemma-3, holds under judge-free evaluations and external benchmarks, survives mixing with generic data, and leaves GSM8K accuracy within $\pm 1$pp of the baseline.

AI 总结：研究针对世界-动作模型（WAMs）提出BadWAM框架，用于建模和评估世界-动作漂移攻击，包括仅动作攻击和保持想象攻击，通过不同标准刻画攻击面，评估结果显示能大幅降低任务成功率，揭示WAM漏洞。

链接：https://arxiv.org/abs/2607.15207

机构：National University of Singapore（新加坡国立大学）； The Hong Kong Polytechnic University（香港理工大学）

作者：Qi Li, Xingyi Yang, Xinchao Wang

英文摘要：World-action models (WAMs) are emerging as a promising foundation for embodied control: rather than predicting actions alone, they learn representations that couple action generation with future world prediction. This coupling is often viewed as a source of robustness, interpretability, and safety, as a robot's action can in principle be checked against its imagined future. In this paper, we show that this assumption is fragile. We introduce BadWAM, a unified framework for modeling and evaluating World-Action Drift Attacks: a new class of WAM-specific adversarial attacks that use small visual perturbations to break the alignment between what a WAM imagines and what it executes. BadWAM characterizes this attack surface along two natural criteria: attack strength and stealthiness. When the adversary prioritizes disruption, BadWAM instantiates an action-only adversarial attack, which directly drives the model toward task-failing actions. When the adversary additionally prioritizes stealth, BadWAM instantiates an imagination-preserving adversarial attack, which seeks to induce harmful action shifts while keeping the model's predicted future close to its clean imagination. Together, these two attacks capture a spectrum of WAM-specific failures: from overt action hijacking to stealthier cases where the model appears to imagine a plausible future but executes a desynchronized action. We evaluate BadWAM across different variants of WAMs. Results show that our attacks substantially reduce task success rates under closed-loop execution. For example, our action-only attack reduces the model performance from 96.5% to 43.1% success. The results of our imagination-preserving attack further exposes a WAM-specific vulnerability: moderate future-preserving regularization can maintain strong attack performance while reducing future imagination drift.

AI 总结：研究针对脑电图癫痫诊断难题，提出NeuroGRIP框架，结合外部医学知识校准脑电图图。通过构建知识库、利用大语言模型提取知识图，经对齐感知查询和相似性搜索检索关系证据，提升诊断准确性与可解释性，为临床诊断提供新框架。

链接：https://arxiv.org/abs/2607.14314

作者：Lincan Li, Zheng Chen, Yushun Dong

英文摘要：Seizure diagnosis from EEG signals is a critical yet persistently challenging task, due to the complicated neural dynamics and the spurious connections in inter-channel modeling. While spatial-temporal graph neural networks (STGNNs) have advanced EEG brain network representation learning, the resulting graph structures suffer from low clinical plausibility and limited interpretability due to their purely data-driven nature. To this end, we introduce NeuroGRIP, a retrieval-augmented graph refinement framework that incorporates external medical knowledge to calibrate noisy EEG graphs. We first construct a large-scale, domain-specific knowledge base derived from authoritative clinical guidelines. Leveraging large language models, we extract structured biomedical entities and relations to form a textual knowledge graph (KG), which serves as external knowledge source of clinical priors. Our framework performs alignment-aware query construction by projecting STGNN-generated EEG node embeddings into the semantic space of KG. Semantic queries are then executed via FAISS-based similarity search over knowledge triplets to retrieve relation evidence. Each predicted edge is assigned a confidence score based on retrieved similarity, relation type, and source reliability, enabling us to prune medically implausible edges from the originally predicted graph. Extensive experiments on TUSZ and CHB-MIT demonstrate that NeuroGRIP not only improves seizure detection accuracy but also enhances interpretability by grounding each prediction in clinically validated knowledge. This work provides the first unified framework that tightly couples brain dynamics with external medical expertise via retrieval-augmented reasoning, paving the way for knowledge-enhanced, explainable clinical diagnosis. The code is available at: this https URL.

AI 总结：研究无人口统计信息的图公平性问题，提出基于梯度分布的GradDist度量偏差，进而提出梯度引导的Grad2Fair方法，直接利用梯度去偏并消除人口统计预测，实验验证该方法在多数情况下性能优于基线。

链接：https://arxiv.org/abs/2607.14705

机构：School of Computer Science and Engineering, Sun Yat-Sen University（中山大学计算机科学与工程学院）； School of Software Engineering, Sun Yat-sen University（中山大学软件工程学院）； Institute of Artificial Intelligence, Xiamen University（厦门大学人工智能研究所）

作者：Yuchang Zhu, Zezhong Xie, Huizhe Zhang, Huazhen Zhong, Jintang Li, Liang Chen, Zibin Zheng

英文摘要：Graph neural networks (GNNs) frequently encounter group fairness issues, often yielding biased predictions against specific demographic groups defined by sensitive attributes such as gender or race. While this challenge has motivated extensive research, most existing solutions rely on the strong assumption that demographics are fully available. To bypass this strict requirement, a few recent studies have attempted to use predicted demographics as proxies to enforce fairness constraints. However, predicted demographics may be inaccurate, resulting in the failure to improve fairness. In this work, we investigate the problem of graph fairness without demographic information and avoid the utilization of predicted demographics. Motivated by our observation that the gradient distributions of misclassified nodes implicitly encode demographic information, we first propose GradDist, a gradient-based metric that quantifies bias by measuring the distance between local modes within these distributions. To mitigate this bias, we propose Gradient-to-Fairness (Grad2Fair), a gradient-guided approach for group fairness without demographics. Due to the potential demographics in gradients, Grad2Fair directly leverages gradients to debias and eliminates demographic prediction, thereby enabling stable fairness performance. Experiments on several real-world datasets demonstrate the effectiveness of Grad2Fair, as evidenced by superior performance over baselines in most cases. Our code is available at this https URL.

AI 总结：研究提出门零增长这一用于持续学习的函数保持算子，通过零初始化门添加残差块，在横截性条件下实现秩分离。实验表明其能控制函数漂移和雅可比矩阵泄漏，在变压器模型上旧域遗忘近零，优于非FP控制，还涵盖多种结构确立其为规范实例。

链接：https://arxiv.org/abs/2607.14571

机构：Votee AI（Votee人工智能公司）； Beever AI（Beever人工智能公司）

作者：Dante Lok

英文摘要：We introduce \emph{gate-zero growth}, a function-preserving (FP) operator for continual learning that adds new residual blocks through a zero-initialised gate. Under a transversality condition, gate-zero growth induces \emph{rank separation} in the functional Jacobian: old directions are unchanged, new-weight directions are exactly flat at the growth point, and new gate directions are the only first-order source of new functional variation. As gates open during continual learning, function drift is $O(\|\boldsymbol{\alpha}\|^2)$ and Jacobian leakage $O(\|\boldsymbol{\alpha}\|_\infty)$, giving a controlled departure from the FP locus. On a $300\mathrm{M}\to857\mathrm{M}$ Transformer adapted from WikiText-103 to BookCorpus, gate-zero growth reaches near-zero old-domain forgetting ($\Delta_A < 0.1$) under both exact-preservation (Isolation) and joint-frontier (Freeze-Nothing) operating points, while a non-FP control ($G_{\text{stack}}$) suffers an order-of-magnitude larger forgetting under the same recipe. The same geometric analysis covers LoRA, ReZero, and zero-init adapter constructions, establishing gate-zero growth as the canonical instance of a shared local geometry that governs safe capacity activation in CL.

AI 总结：研究针对动态系统零样本重建基础模型缺乏预测机制洞察的问题，将DynaMix简化为DynaBase，其通过简单线性混合预测，参数负载低，表现出色，还得出映射族及不同训练策略效果，揭示最小机制并协调文献观察。

链接：https://arxiv.org/abs/2607.14937

机构： Central Institute of Mental Health, Mannheim, Germany（德国曼海姆中央精神卫生研究所）； Interdisciplinary Center for Scientific Computing (IWR), Heidelberg, Germany（德国海德堡跨学科科学计算中心 (IWR)）； Faculty of Physics and Astronomy, Heidelberg University, Heidelberg, Germany（德国海德堡大学物理与天文学系）

作者：Christoph Jürgen Hemmer, Florian Plaswig, Daniel Durstewitz

英文摘要：Recent foundation models (FMs) for zero-shot reconstruction of dynamical systems (DS) achieve strong out-of-domain generalization but provide little insight into the mechanisms that underlie their forecasts. Such an understanding could help to strip down overladen FM architectures to their bare essence and expose the minimal requirements for in-context learning in the DS domain. Toward this goal, here we iteratively reduce a recent powerful SOTA model for DS reconstruction, DynaMix (Hemmer & Durstewitz, 2025), to a minimal interpretable two-parameter form, which we call DynaBase. DynaBase produces forecasts through a linear blend of the current latent state and the nearest in-context neighbor and its temporal successor. Surprisingly, despite its extreme simplicity, DynaBase produces highly competitive zero-shot DS reconstructions across chaotic and cyclic systems, with a negligible parameter load, many orders of magnitude below that of other FMs. Even more, this extreme simplicity permits direct model optimization on DS reconstruction measures, as well as closed-form one-step analytical solutions on prediction MSE. Theoretical and empirical analysis of DynaBase further leads to a 1-parameter family of maps, with the context-parroting algorithm of (Zhang & Gilpin, 2026) recovered at one end, and chaotic (divergent but bounded) behavior at the other. We further show how different training strategies lead to models either optimal for short-term prediction or for DS reconstruction. Thus, DynaBase not only exposes the minimal mechanisms required for producing zero-shot DS reconstruction, but also reconciles within an accessible mathematical frame divergent observations in the literature.

AI 总结：研究针对ALS预测临床有意义事件的挑战，开发受数字孪生启发的事件发生时间框架，整合多源数据，经聚类、建模等确定功能域及预测因素，构建TTE模型，能生成个性化生存曲线，为ALS相关决策支持提供可行方法。

链接：https://arxiv.org/abs/2607.14190

机构：Harrison College of Pharmacy, Auburn University（奥本大学哈里森药学院）； Fisk University（菲斯克大学）； Lewis Katz School of Medicine, Temple University（天普大学刘易斯·卡茨医学院）； Emory University（埃默里大学）； Barnett College of Public Health, Temple University（天普大学巴尼特公共卫生学院）

作者：Zongliang Yue, Qi Li, Terry Heiman-Patterson, Frank Bearoff, Zhaohui Qin, Huanmei Wu

英文摘要：Amyotrophic lateral sclerosis (ALS) is a progressive and heterogeneous neurodegenerative disease in which predicting clinically meaningful milestones, such as assistive device use, remains challenging. We developed a time-to-event, digital-twin-inspired framework that integrates longitudinal ALS Functional Rating Scale-Revised (ALSFRS-R) trajectories with survival modeling to support individualized prediction of functional decline and assistive device utilization. We constructed a harmonized longitudinal dataset by integrating diagnosis records, ALSFRS-R assessments, activities of daily living, and demographic information, followed by preprocessing to ensure data quality, temporal alignment, and cohort consistency. Correlation-based clustering identified coherent functional domains spanning bulbar, upper limb, axial, lower limb, and respiratory systems. Generalized additive mixed models characterized nonlinear, domain-specific functional decline across all domains. In addition, a temporal machine learning model was developed to predict longitudinal functional decline and capture stage-dependent disease progression. Cox proportional hazards modeling further identified lower limb function, particularly walking and stair climbing, as the strongest predictors of earlier wheelchair access. Building on these results, we implemented a digital twin-inspired temporal machine learning-based time-to-event (TTE) model that generates individualized survival curves and dynamically predicts wheelchair-free survival. This framework provides a scalable, interpretable, and clinically actionable approach for linking ALS progression with personalized decision support, with applications in proactive care planning, clinical trial stratification, and precision medicine.

AI 总结：研究赞助搜索市场广告加载设计权衡，通过安卓应用商店实验发现增加广告加载量对收入、转化率和参与度的影响及异质性，设计并部署自适应算法e-LAAL，在生产部署中改善收益与转化率权衡，优于静态基准。

链接：https://arxiv.org/abs/2607.14418

机构：University of Washington（华盛顿大学）

作者：Mohammad Rashid, Hema Yoganarasimhan

英文摘要：Ad-load design is a central supply-side decision in sponsored search: more sponsored slots can raise revenue, but may crowd out organic results and degrade user outcomes. We study this trade-off using a large-scale randomized field experiment on an Android app store, where over five million users are exposed to one through six sponsored slots. Increasing ad load raises revenue by up to 43%, but reduces total search conversions by up to 5% and daily engagement by up to 2.2%. These average effects mask substantial heterogeneity: additional slots generate large revenue gains for high-ad-conversion queries, but little or negative marginal revenue for low-conversion queries. The trade-off also shifts within query as advertiser composition changes, such as brand-advertiser presence. Motivated by these findings, we design and deploy a novel adaptive algorithm -- exploration-augmented Locally Adaptive Ad Load (e-LAAL). e-LAAL combines LAAL, a model-free query-level decision rule that updates ad-load recommendations using recent outcomes, with static exploration arms that maintain support and provide fixed-policy counterfactual benchmarks. We provide a finite-time dynamic-regret guarantee for the e-LAAL architecture. In a platform-level production deployment serving 22.3 million users and 77.6 million searches, e-LAAL improves the empirical revenue--conversion trade-off relative to deployed static benchmarks and outperforms uniform and historical query-dependent static benchmarks.

AI 总结：HyperShadow是用于检测高维空间对象3D投影的基准测试，通过190k参数点网络及零参数刚性见证进行检测，能在不同损坏层级达到高准确率和泛化率，为研究三维解释不兼容性提供工具，数据等已公开。

链接：https://arxiv.org/abs/2607.14419

作者：Akshay Sasi

英文摘要： Machine-learning datasets labelled "4D" universally denote three spatial dimensions plus time. We introduce HyperShadow, the first public benchmark in which the fourth, fifth, and sixth dimensions are spatial: the task is to decide whether a 3D point cloud is a native three-dimensional shape or the projection, the "shadow", of a rigid object living in R^N (N = 4-6). We show this task is fundamentally distinct from intrinsic-dimension estimation: a shadow is still at-most-3-dimensional data, and standard estimators (TwoNN, Levina-Bickel MLE) reach only 71-73% accuracy. Detection instead requires projection signatures, density folds, filled volumes with characteristic radial profiles, and topology changes, which a 190k-parameter point network recovers at 96.6% accuracy across four corruption tiers, generalizing at 79-91% to object families never seen in training. On a temporal track of rigidly rotating objects we introduce a zero-parameter rigidity witness: the residual of the optimal rigid 3D alignment (Kabsch) between consecutive frames, which must vanish for any rigid 3D motion but cannot vanish for the shadow of a rigid rotation in R^N. This single interpretable statistic separates the classes at AUROC 0.982. All data are generated reproducibly from seeds; the dataset, models, and code are released publicly. HyperShadow makes no claim about physical reality; it is a controlled instrument for studying which observable statistics can certify incompatibility with a purely three-dimensional explanation.

AI 总结：研究时态知识图谱问题生成，提出ChronoQG框架，通过整合多种方法构建有时态表现力和跳数限制的基准数据集，评估多种设置下的相关方法，揭示静态KGQG与TKGQG差距，为时态忠实问题生成提供测试平台。

链接：https://arxiv.org/abs/2607.14770

机构：Nankai University（南开大学）； Peking University（北京大学）； University of Electronic Science and Technology of China（电子科技大学）； Shanghai University of Finance and Economics（上海财经大学）

作者：Xuemeng Liu, Zhengpin Li, Wanpeng Tang, Haotong Xie, Wentao Zhang

英文摘要：Knowledge graph question generation (KGQG) aims to generate natural-language questions from structured graph evidence. Existing KGQG benchmarks, however, are mostly built on static knowledge graphs and do not encode the temporal scopes of graph facts. As a result, they cannot evaluate whether generated questions faithfully preserve temporal validity, event ordering, and answer-determining temporal constraints. In this paper, we study temporal knowledge graph question generation (TKGQG), where a generated question must be faithful to both the support subgraph and the temporal constraints required to identify the target answer. We propose ChronoQG, the first temporally expressive and hop-bounded benchmark construction framework for TKGQG. ChronoQG integrates a comprehensive temporal-constraint taxonomy, topology-temporal subgraph sampling, and trace-grounded question generation to construct temporally faithful questions. The framework produces four benchmark datasets from heterogeneous temporal knowledge graphs, totaling 16,011 verified questions. We evaluate representative LLM-based KGQG methods and prompting baselines across diverse TKGQG settings, including temporal-constraint counts, topological templates, and temporal-constraint types. The results show that existing methods struggle to preserve temporal constraints, especially under multi-constraint settings and harder temporal-constraint types. These findings reveal a clear gap between static KGQG and TKGQG, and establish ChronoQG as a challenging testbed for temporally faithful question generation.

AI 总结：介绍工程应用中非线性动力学稀疏识别（SINDy）方法，通过对候选非线性项库稀疏回归解决代理建模局限性，教程介绍该方法及扩展，经案例研究表明其易实现且灵活，是工程应用有价值的识别工具。

链接：https://arxiv.org/abs/2607.15077

机构：Department of Aeronautics, Imperial College London（伦敦帝国理工学院航空系）； Department of Mechanical Engineering, University of Washington（华盛顿大学机械工程系）； NSF AI Institute in Dynamic Systems, University of Washington（华盛顿大学动态系统领域美国国家科学基金会人工智能研究所）

作者：Yao Cheng Li, Ana Larrañaga, Steven L. Brunton, Urban Fasel

英文摘要：Many engineering problems involve phenomena whose governing equations are poorly characterized or only partially known. Surrogate modeling techniques such as neural networks can capture the behavior of these systems, but they typically demand large training datasets that are difficult to obtain in engineering contexts and yield models with limited physical interpretability. The Sparse Identification of Nonlinear Dynamics (SINDy) method addresses both limitations by performing sparse regression over libraries of candidate nonlinear terms, recovering interpretable governing equations from comparatively small datasets. Although SINDy has been demonstrated extensively on canonical benchmark systems, its application to practical engineering problems is less widely documented. This tutorial introduces the SINDy method and progressively builds toward its main extensions, from noise-robust weak-form and ensembling-based variants to constrained and parametrizable formulations. The paper and the accompanying tutorial (available at this https URL ) is organized in three parts: the first introduces the standard SINDy algorithm and progressively extends it, inviting readers without prior knowledge to follow each step and adapt the methods to their own problems; the remaining two parts present detailed case studies on (1) the system identification of an unmanned aerial vehicle and (2) a chaotic thermosyphon heat exchanger. Through these examples, we aim to demonstrate that SINDy is simple to implement yet flexible enough to serve as a valuable identification tool for advanced engineering applications.

AI 总结：研究针对物理信息神经网络（PINNs）收敛失败问题，提出通过门控逐层优化进行学习初始化的框架LIGO-PINN。经多领域严格评估，该方法性能优于现有方法，能有效缓解收敛失败，还可推广到3D非结构化领域，并分析了训练动态。

链接：https://arxiv.org/abs/2607.14233

机构：Stevens Institute of Technology（史蒂文斯理工学院）； Wageningen University & Research（瓦赫宁根大学及研究中心）

作者：Nilay Anurag, Shital Adhikari, Taniya Kapoor, Nikhil Muralidhar

英文摘要： Physics-informed neural networks (PINNs) have had a broad research impact in modeling domains governed by partial differential equations (PDE). However, PINNs have been shown to perform poorly, sometimes even converging to trivial solutions, in challenging PDE domains, or when generalizing to unseen but related PDE domains. Previously proposed solutions detail hyperparameter tuning to reduce loss imbalance between data-driven and physics guided losses, curriculum learning based training strategies, or dynamic re-sampling of hard collocation points. These methods face certain pitfalls: hyperparameter tuning is expensive, designing a training curriculum is ambiguous in multi-parameter PDE settings, and dynamic resampling still fails in complex PDE settings. Complementary to this line of thinking, we believe the initial PINN network weights also play a crucial role in the emergence of catastrophic failures during training, yet the effect of PINN weight initialization has been surprisingly under-investigated. To this end, we propose a framework for Learned Initialization via Gated Layerwise Optimization (LIGO-PINN) to overcome PINN convergence failures. Through rigorous evaluation on 1D and 2D PDE domains, including a challenging 2D fluid dynamics setting, we demonstrate that our methodology outperforms state-of-the-art methods designed to alleviate PINN failures, achieving a 91.5% average performance improvement across six baselines and 81% over the strongest baseline. We also verify that LIGO-PINN generalizes to 3D unstructured domains. Finally, we analyze training dynamics across all three PDE domains to explain both LIGO-PINN's improvement and the convergence failure of traditional PINNs. Code: this https URL Keywords: Machine Learning, Physics-Informed Neural Networks, Deep Learning, PDE Modeling

AI 总结：针对从低分辨率和噪声位移数据估计非均匀弹性特性的不适定问题，提出PIE - PINN框架，结合B样条引导位移网络与分层半柯西模型，用交替最大似然训练策略，能稳健估计杨氏模量和泊松比，案例研究验证了其稳健性。

链接：https://arxiv.org/abs/2607.14563

机构：Texas A&M University（德克萨斯A&M大学）

作者：Tatthapong Srikitrungruang, Jaesung Lee

英文摘要：Estimating spatially heterogeneous elastic properties from low-resolution displacement measurements is a severely ill-posed inverse elasticity problem because low resolution obscures spatial details needed to distinguish heterogeneous property variations, and small measurement perturbations or fitting errors are amplified through inverse estimation. Existing inverse methods often rely on high-fidelity observations and manually prespecified loss weights, limiting their adaptability and making them sensitive to noise and resolution degradation. We propose a Probabilistic Inverse Elasticity Physics-Informed Neural Network (PIE-PINN) framework for robust estimation of Young's modulus and Poisson's ratio from noisy, low-resolution displacement data. PIE-PINN models displacement observation, strain-discrepancy, and equilibrium residuals using Laplace distributions within a unified probabilistic model. To improve robustness, the framework combines a B-spline-guided displacement network with a hierarchical half-Cauchy model for displacement residual scales. The B-spline provides a smooth global representation of the displacement field, while the neural network correction captures local variations. The hierarchical scale model adaptively downweights severe displacement fitting errors, enabling more robust recovery of the latent mean displacement field. An alternating maximum-likelihood training strategy updates the mean through weighted residual minimization and updates the scales to adjust the loss weights. Systematic case studies across varying noise levels and observation resolutions demonstrate the robustness of PIE-PINN.

AI 总结：研究在线控制实验中A/B测试方差大成本高问题，提出利用策略重叠加速实验的新协议，将随机处理分配机制视为元策略，用Δ-离策略估计方法获无偏估计，理论和实证证明该方法可提升效率，有望用于多种系统评估。

链接：https://arxiv.org/abs/2607.14604

作者：Olivier Jeunen

英文摘要：Online controlled experiments are the gold standard for hypothesis testing in online platforms. Notwithstanding their ubiquity, they are notoriously expensive to run, and issues of variance hamper statistical power in assessing treatment effects. While standard variance reduction techniques leverage model-based control variates to reduce outcome noise, they remain agnostic to potential structural relationships between competing policies. In this work, we identify a critical inefficiency in the standard A/B-testing protocol: when a treatment and control policy agree on an action, the resulting outcome contributes noise but no signal regarding the treatment effect -- unnecessarily inflating confidence intervals. We propose a novel experimental protocol that exploits this policy overlap to accelerate experimentation. The key insight is to frame the randomised treatment assignment mechanism as a meta-policy, and leverage $\Delta$-Off-Policy Estimation methods to obtain unbiased estimates for average treatment effects. We prove analytically that our approach recovers standard A/B-testing practices in the general case, but that its variance scales with the divergence between policies rather than raw outcome variance. Hence, we dominate the standard Difference-in-Means estimator whenever policies have common support, and the improvement is strict whenever the overlap region contributes non-zero residual variance. Empirical results corroborate these theoretical insights -- holding promise for significant impact on the real-world evaluation of recommender systems, information retrieval pipelines, and large language model interfaces.

AI 总结：针对时间序列预测中预测不足风险高且多数方法忽视峰值预测的问题，提出非对称峰值感知损失APAL，增加对预测不足惩罚及峰值区域训练权重，经评估其能提升尾部准确性和峰值预测质量，平衡总体误差，是实用解决方案。

链接：https://arxiv.org/abs/2607.14871

机构：Department of Transport and Planning, Faculty of Civil Engineering and Geosciences（交通与规划系，土木与地球科学学院）； Mobility Innovation Centre Delft University of Technology（代尔夫特理工大学移动创新中心）； Delft University of Technology（代尔夫特理工大学）

作者：Theivaprakasham Hari, Yanan Xin, Winnie Daamen, Serge Paul Hoogendoorn, Sascha Hoogendoorn-Lanser

英文摘要： In many operational time-series forecasting applications, such as crowd demand forecasting, the risk related to under-prediction is substantially higher than that of over-prediction. Accurate prediction of rare demand spikes plays a critical role in downstream tasks. Yet most time-series forecasters are trained with symmetric objectives (e.g., MSE, MAE) and evaluated primarily on aggregate error, which can mask failures in extreme-values and peak-timing predictions. We introduce Asymmetric Peak-Aware Loss (APAL), a simple, model-agnostic objective that (i) penalizes under-predictions more heavily and (ii) increases the training weight of peak regions within each forecast window. We further propose a peak-critical evaluation protocol that complements MAE/MSE with channel-wise tail error (Top-10% and Top-1%) and peak metrics (precision, recall, F1 under timing tolerance, and peak timing error). We evaluate APAL on long-horizon multivariate forecasting across five state-of-the-art backbones, with a focus on pedestrian demand forecasting using (i) a production-ready subset of the City of Melbourne pedestrian hourly count dataset and (ii) a beach visitor count dataset. The generality of the loss function for time-series forecasting is tested on additional benchmarks. Across peak-critical datasets and settings, APAL improves tail accuracy and peak-prediction quality while exposing a controllable trade-off with aggregate error, making it a practical solution when peak-prediction failures are the dominant operational concern.

AI 总结：该论文指出可解释人工智能技术虽多但未有效影响实际工作流程，原因是存在基础缺陷。主张机器学习社区从临时方法转向解决基础和结构挑战，通过分析论文和调查从业者揭示问题，最后给出清单推动XAI走向以人为本、行动导向范式。

链接：https://arxiv.org/abs/2607.14123

作者：Michal Moshkovitz, Suraj Srinivas, Lesia Semenova, Nave Frost, Cyrus Rashtchian, Valentyn Boreiko, Shichang Zhang, Himabindu Lakkaraju, Cynthia Rudin, Jennifer Wortman Vaughan

英文摘要：Despite the proliferation of Explainable AI (XAI) techniques -- from feature attributions to sparse autoencoders -- explanations rarely influence real-world workflows. In practice, they are often generated and discarded without guiding meaningful action. This gap reflects foundational shortcomings: research has not yet established methodologies for integrating explanations into end-to-end, human-in-the-loop systems. This position paper argues that the machine learning community must pivot from ad-hoc XAI methods toward addressing foundational & structural challenges, including unclear problem formulations, underspecified evaluation objectives, and the absence of pipelines for explanation-driven feedback. We support this claim through an analysis of recent ICML, NeurIPS, and ICLR papers and a survey of XAI practitioners, revealing recurring issues that limit cumulative progress. We conclude by outlining a practical checklist designed to shift XAI toward a more human-centered, action-oriented paradigm. By emphasizing foundational clarity over the development of ad-hoc methods, we hope to provide a roadmap for integrating explanations into actionable, feedback-driven AI systems.

AI 总结：研究针对预训练视觉语言模型零样本图像分类中提示与类独立性假设不成立的问题，提出类感知零样本提示重加权方法CARPRT，通过无训练方式量化提示与类的相关性并调整权重，实验表明该方法优于现有方法。

链接：https://arxiv.org/abs/2607.14125

机构：University of Melbourne（墨尔本大学）； Southeast University（东南大学）； RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）； The University of Tokyo（东京大学）

作者：Ruijiang Dong, Zesheng Ye, Jianzhong Qi, Lei Feng, Feng Liu, Gang Niu, Masashi Sugiyama

英文摘要：Pre-trained vision-language models (VLMs) enable zero-shot image classification by computing the similarity score between an image and textual descriptions, typically formed by inserting a class label (e.g., "cat") into a prompt (e.g., "a photo of a"). Since the score for a given image-class pair is sensitive to the choice of prompt, existing studies ensemble multiple prompts using a weighting vector to aggregate scores across different prompts. Yet, in current strategies, the weighting vector assigned to each prompt is shared across all classes, implicitly assuming that prompts are conditionally independent of classes, which often does not hold in practice, as a prompt like "an aerial view of" might be apt for "airport" but ill-suited for "apple". To address this, we propose class-aware zero-shot prompt reweighting (CARPRT). This scoring scheme adjusts the weighting vector for each class label by capturing the class-specific relevance of different prompts in a training-free manner. For each class label and every available prompt, we quantify their class-specific relevance by averaging image-text relevance scores over images predicted to that class under the given prompt. These estimates are then normalized to derive class-specific weights. Evaluations on standard image classification benchmarks show that CARPRT outperforms existing class-independent reweighting methods, confirming that modeling prompt-class dependencies is crucial for effective zero-shot prediction and even broader VLM-based application settings that rely on prompt ensembling. Our code is available at this https URL.

AI 总结：研究利用激光雷达衍生地形智能预测卫星地面站选址的代表性杂波高度，提出可解释机器学习框架，用多种数据训练，选LightGBM，模型误差降低超60%，评估相关标准，SHAP识别关键预测因子，证明开放数据可改善杂波建模。

链接：https://arxiv.org/abs/2607.14127

机构：U.S. Geological Survey（美国地质调查局）

作者：Shohini Sarkar, Smithi Mahendran, Rishi Chudasama, Varun Mannam, Arav Luthra, Yuvraj Rekhi, Vivek Nadig, Arsh Goenka

英文摘要：Representative clutter height (RCH) is a key parameter in radio propagation and interference analysis because it captures the dominant height of local obstructions that drive terminal clutter loss. Current practice often relies on fixed clutter heights assigned to land use classes in Recommendation ITU-R P.452-18, but this misses within class variation and can lead to conservative exclusion zones and poor site ranking for low Earth orbit ground station siting and spectrum coordination. We present an interpretable, globally deployable machine learning framework for predicting RCH from open geospatial data. The model is trained using LiDAR derived labels from the U.S. Geological Survey 3D Elevation Program and inference time features from global land-cover, terrain, demographic, thermal, and optical remote sensing products. We define RCH using a robust 75th percentile clutter height statistic, evaluate multiple regressors, and select LightGBM for its accuracy, efficiency, and compatibility with feature attribution analysis. The final model achieves a mean absolute error of 1.79m and an R^2=0.765, reducing absolute error by more than 60% relative to the ITU baseline. Beyond aggregate fit, we evaluate domain facing criteria relevant to RF planning, including meter scale error, tolerance band accuracy, over and under estimation tails, agreement with ITU clutter height regimes, and SHAP-based physical plausibility. SHAP identifies tree canopy cover, land-cover semantics, and spectral reflectance as the most influential predictors. Studies on segmentation derived features, non-forest ablations, and land-cover matched international validation show that open geospatial data can improve clutter modeling at scale without sacrificing interpretability or deployability.

AI 总结：针对多域检索中错误域证据及污染控制问题，提出C3R控制层。基于风险控制预测集构建双分割方案，认证污染预算。通过实验验证其稳定性及有效性，能减少错误权威基础，且与冻结堆栈和重排器无关。

链接：https://arxiv.org/abs/2607.14157

机构：Electric Power Research Institute (EPRI)（电力研究协会）

作者：Jayakumar Manoharan

英文摘要：Retrieval over corpora that mix several domains often returns relevant but wrong-domain evidence that ranking metrics miss and that conformal risk control bounds only marginally, under-covering the worst domains. This work introduces C3R, a drop-in control layer that, from an inferred domain posterior and no query-time label, certifies a per-domain contamination budget where feasible and otherwise abstains rather than silently violating; on the hardest domains it guarantees a reduction, not a tight bound. The core is a two-split scheme built on risk-controlling prediction sets, whose finite-sample transfer bound crosses from the inferred to the true domain with fully estimable slack, supports heterogeneous budgets, and inverts for deployment. Population validity rests on this bound and a controlled simulation; across a thousand resampled calibrations the certificate never violates (a stability result) while marginal control violates the most-contaminated domain in every draw, and soft demotion retains more recall than the strongest calibrated cascade at equal certified contamination. The method replicates across open testbeds including an independent one from public federal regulations, and an LLM-judged downstream probe indicates wrong-authority grounding rises with contamination and falls under control. The layer is frozen-stack and reranker-agnostic.

AI 总结：研究针对卫星图像野火分割难题，基于 U 型网络构建量子混合模型，在瓶颈部分注入变分量子电路，对比经典 FPN 等方法。实验表明量子增强方法及数据混合有优势，验证了架构对野火检测的有效性和通用性。

链接：https://arxiv.org/abs/2607.14160

机构：IonQ Team, App Dev Club, University of Maryland, College Park（离子量子团队、应用开发俱乐部、马里兰大学帕克分校）

作者：Jaiman Munshi, Tanvi Tewary, Sawyer Bloom, Aidan Chu, Chetan Maviti, Kyon Winston-Bey, Harshit Badjatia, Farhan Kittur, Vardhan Madhavarapu, Varun Kota, Joshua Kwon, Nazia Rangwala-Vohra, Franz Klein (IonQ Team, App Dev Club, University of Maryland, College Park)

英文摘要：Wildfire detection from satellite imagery is a semantic image segmentation problem that has proven to be difficult due to challenges such as class imbalance, feature complexity, and atmospheric interference. In this paper, we build on the foundational U-Net image segmentation model to develop a quantum-hybrid solution in hopes of more effectively modeling the high-dimensional spectral feature space of the Sen2Fire dataset. We inject a variational quantum circuit in the bottleneck portion of U-Net, specifically the QuFeX and QB-Net ansatzes. We test a classical Feature Pyramid Network (FPN) for further comparative analysis of the model, and we also explore classical improvements to the U-Net model and its training process, including a compression of parameters, alternative loss functions, and uniform mixing of input data. Our primary finding is that under matched conditions, both QB-Net (with an $F_1$ score of 31.18) and QuFeX ($F_1 = 30.79$) outperformed the classical U-Net baseline results ($F_1 = 28.71$). Additionally, the classical FPN achieved a comparable score of 31.13. A crucial finding was that data mixing removed a significant domain shift between the geographically-separated train and test sets, which boosted the classical FPN $F_1$ score to 39.76. We validate the architecture's robustness and generalizability to the wildfire detection problem via cross-dataset transfer on the California Burned Areas (CaBuAr) dataset. Overall, we find that quantum machine learning has potential to provide an advantage in the problem of wildfire image segmentation, and further experiments will continue to validate and expand upon this finding.

AI 总结：研究探讨10-K文件中全文与风险因素情绪的聚合相关价值，将监督词典学习方法扩展到10-K文件及其风险因素部分，在多级别训练情绪分数，评估指标表现，发现不同聚合级别表现差异及词典基线问题，确立后续系统的情绪生成方法。

链接：https://arxiv.org/abs/2607.14174

作者：Sanggyu Sean Choi

英文摘要：Financial sentiment extraction has largely relied on news text and supervised extraction against return labels alone, leaving 10-K filings -- and volatility, the target risk disclosure is arguably best suited to informing -- comparatively unexplored. We extend a supervised lexicon-learning approach to 10-K filings and their Item 1A risk-factor sections, training sentiment scores against both return and volatility labels at three levels of aggregation: sector, portfolio, and individual firm. Across 1,383 filings from 94 Nasdaq-100 technology constituents (2006--2023), we evaluate the resulting twelve sentiment metrics on classification accuracy, correlation with realised market outcomes, and qualitative lexical content. Full-filing text produces more accurate sentiment at the sector and portfolio level for both targets, but this reverses at the individual-firm level, where the narrower Item 1A section performs better -- an effect we attribute to the interaction between document volume and the amount of independent training signal available at each level of aggregation. A Loughran-McDonald dictionary baseline is consistently, strongly negatively correlated with price at every level tested, underscoring the value of a supervised approach for regulatory disclosure text. These findings, and the design choices they motivate, establish the sentiment-generation methodology underlying a subsequent, larger-scale, multi-source system.

AI 总结：研究NR-V2X车辆通信低延迟中继选择问题，提出基于带边特征的图同构网络的边缘感知学习优化框架，通过离线MILP预言机监督GINE，还提出GP-MILP策略，实验证明该方法能紧密匹配MILP决策且降低延迟。

链接：https://arxiv.org/abs/2607.14176

作者：Giambattista Amati, Federica Mangiatordi, Emiliano Pallotti, Simone Angelini, Pierpaolo Salvo, Paola Vocca

英文摘要： Reliable, low-latency uplink connectivity is a key requirement for C-V2X networks in dense urban environments, where fast channel variations and blockages often degrade direct vehicle-to-infrastructure links. Multi-hop relaying can restore coverage, but relay-link activation under radio, capacity, and routing constraints results in an NP-hard optimisation problem, typically solved via Mixed-Integer Linear Programming (MILP), whose runtime scales poorly with graph size. This paper introduces an edge-aware Learning-to-Optimise framework for real-time relay selection. Each V2X snapshot is modelled as a directed graph: node features encode vehicle state and traffic demand, while edge features capture radio-link capacity. An offline MILP oracle generates optimal relay configurations that supervise a Graph Isomorphism Network with Edge Features (GINE), enabling edge-level relay activation through a single forward pass, with tightly bounded inference latency. To bridge learning and exact optimisation, we also propose a hybrid GINE-Pruned MILP (GP-MILP) strategy in which GINE predictions prune the MILP search space. Experiments on a large-scale dataset generated via an OSM-SUMO-GEMV$^2$ pipeline show that GINE closely matches MILP decisions at the link level (accuracy 0.9589), F1-score (0.9544) on validation) and yields consistent end-to-end connectivity gains over a 1-hop MILP baseline (up to 9.2% with four RSUs and 12% with two RSUs). Inference latency remains tightly bounded, with all evaluated instances completing within 5~ms. Moreover, GP-MILP preserves MILP-equivalent solutions (same objective value) while achieving solver runtimes below 30~ms for more than 98%) of the graph instances, making MILP-grade optimisation compatible with stringent NR-V2X latency budgets.

AI 总结：研究利用儿科电子健康记录训练TEDDY模型，对纵向诊断轨迹和就诊时间建模，在疾病发病预测任务中表现出色，能支持广泛、罕见疾病和长期风险预测，无需大规模人口数据或数十亿参数模型。

链接：https://arxiv.org/abs/2607.14191

机构：Baylor College of Medicine（贝勒医学院）

作者：Matthew Brady Neeley, Jorge Botas, Johnathan Jia, Lin Yao, Daniel Palacios, Benjamin Choi, Zhandong Liu, Hyun-Hwan Jeong

英文摘要：Pediatric electronic health records capture developmentally structured clinical trajectories, yet their potential for generative healthcare foundation models remains largely unexplored. Here we present TEDDY (Temporal Event Decoder for Disease in Youth), a 1.84-million-parameter decoder transformer trained on approximately 73 million ICD-10 diagnoses from 1.6 million children at a single pediatric institution. TEDDY models longitudinal diagnosis trajectories and visit timing. Predictions were made before visit codes were revealed, limited to first occurrences, and evaluated against sex- and age-matched controls. Across 797 disease-onset prediction tasks spanning 16 ICD-10 chapters, TEDDY achieved a median AUC of 72.0%, outperforming same-data DenseNet (50.0%), CNN (57.2%), RNN (60.1%), and LSTM (62.7%) baselines on 96-99% of tasks. Performance held across sex and age and was strongest among lower-prevalence diagnoses; 202 of the 225 rarest conditions (90%) had 95% confidence intervals above chance. Predictive signal remained detectable more than two years before first recorded diagnosis, with median AUCs of 59.7% in the unrestricted analysis and 64.4% in a fixed-cohort sensitivity analysis. In asthma and attention-deficit/hyperactivity disorder benchmarks, AUCs were 79.3% and 84.7%, compared with 62.7% and 71.7% for the strongest comparators, including a general-purpose language model three orders of magnitude larger. Visit-timing predictions had a 3.0-day mean absolute restricted mean survival-time error over 365 days, although median and long-tail return intervals remained miscalibrated. Together, these results establish pediatric diagnostic histories as a substrate for compact generative models supporting broad, rare-disease, and long-horizon risk forecasting without population-scale data or billion-parameter models.

AI 总结：研究针对流式视频游戏中模仿学习面临的挑战，提出流式增强方法，基于预测逆动力学模型，在现代3D游戏三个任务中评估其效果，结果显示该增强方法能有效提升代理性能，是训练鲁棒高效游戏代理的有力工具。

链接：https://arxiv.org/abs/2607.14200

作者：Somjit Nath, Abdelhak Lemkhenter, Pallavi Choudhury, Chris Lovett, Katja Hofmann, Sergio Valcarcel Macua, Lukas Schäfer

英文摘要：Imitation learning is an appealing way to scale game-playing agents to complex 3D environments by training policies to map visual observations to actions from human demonstrations. However, these demonstrations are expensive to collect and modern game-playing is often done through streaming in which network delay and compression introduce spatiotemporally correlated visual artifacts that can cause a covariance shift at test time. To address these challenges, we propose streaming augmentations that mimic four types of artifacts commonly encountered during streaming with low-bandwidth network connection: pixelated blocks and scrubs, global blur, and ghosting. We instantiate our approach on top of predictive inverse dynamics models (PIDM), which combine future-state conditioning with an inverse dynamics policy in a learned latent space, and evaluate the impact of our augmentations across three tasks in modern 3D video games. Under stable streaming conditions, agents trained with spatiotemporal augmentations achieve up to 41% higher evaluation performance compared to agents trained without augmentations under an identical data budget. When network lag is introduced, agents trained with augmentations degrade by only 7.45% vs 49.82% of the original performance for agents trained only with the original data. These results clearly indicate that spatiotemporal augmentations tailored for the streaming setting are a simple yet powerful tool to train robust and efficient game-playing agents.

AI 总结：该研究围绕五个规范选择组织多种局部加法特征归因方法，通过公理矩阵比较，将常见失败模式与假设关联，为使用局部加法归因的研究提出十项报告清单，强调归因结果依数学假设而定且假设应报告

链接：https://arxiv.org/abs/2607.14271

作者：Rebecca Afriyie Sarpong, Daniel Commey

英文摘要： Feature-attribution methods are central to explainable artificial intelligence. Their assumptions are expressed in several mathematical languages: cooperative-game values, path integrals, gradient operators, perturbation distributions, and backpropagation rules. This survey proposes a common framework for local additive feature attribution. It organizes Shapley, path-based, gradient/backpropagation, perturbation, and CAM-style methods around five specification choices: value function, reference, path, perturbation distribution, and conservation rule. It then compares these methods through an axiom-by-method matrix and links common failure modes, including baseline sensitivity, off-manifold perturbations, sanity-check failures, adversarial manipulation, and method disagreement, to the assumptions that produce them. Finally, the survey proposes a ten-item reporting checklist for studies that use local additive attributions. The central message is that attribution results are meaningful only relative to the mathematical assumptions under which they are defined, and that those assumptions should be reported.

AI 总结：本文提出全面框架评估多种XAI方法在多数据集和模型上的可解释性，侧重保真度、简单性和稳定性，利用基准实验构建知识库以估计未见数据集和模型的可解释性分数，为评估比较XAI方法提供工具，助力可信AI系统发展。

链接：https://arxiv.org/abs/2607.14315

作者：Georgios Makridis, Georgios Fatouros, Athanasios Kiourtis, Dimitrios Kotios, Vasileios Koukos, Dimosthenis Kyriazis, Jonh Soldatos

英文摘要：In this paper, we present a comprehensive framework for assessing the explainability of various XAI methods, such as LIME and SHAP, across multiple datasets and machine learning models, with the ultimate goal of creating a unified multidimensional explainability score. Our methodology focuses on three key aspects of explainability: fidelity, simplicity, and stability. We leverage benchmarking experiments to systematically evaluate these aspects and use the insights gained to construct an offline knowledge base. This knowledge base captures the explainability scores for each registered model and serves as a valuable resource for context-dependent evaluation of explainability. By analyzing the complementary characteristics and metadata of AI models, datasets, and XAI methods, the knowledge base will enable the estimation of explainability scores for previously unseen datasets and models. Properties like fidelity, simplicity, and stability may vary significantly based on the dataset, underlying model, and domain expertise of the end user. We demonstrate our framework by applying it to three open-source datasets, discussing the implications of the obtained results in relation to the characteristics of the datasets. Our work contributes to the growing field of XAI by providing a robust and versatile tool for evaluating and comparing the explainability of various XAI methods, ultimately supporting the development of more transparent and trustworthy AI systems.

AI 总结：研究从观测数据学习可解释规范性策略的问题，核心方法是结合反事实结果估计与大规模混合整数优化的COAT框架，主要贡献是应用于航空公司辅助定价提升收入，推动扩大采用及相关决策举措。

链接：https://arxiv.org/abs/2607.14318

机构：IBM Research（IBM研究院）

作者：Youssef Drissi, Markus Ettl, Shivaram Subramanian, Wei Sun, Zack Xue

英文摘要：We introduce COAT (Counterfactual Optimal Action Tree), a framework for learning interpretable prescriptive policies from observational data. COAT combines counterfactual outcome estimation with large-scale mixed-integer optimization, using column generation to translate causal predictions into feasible, transparent decisions under business and regulatory constraints. We apply COAT to airline ancillary pricing, a setting characterized by complex business rules and limited experimental flexibility. In a 17-week field pilot with a major global airline, COAT increased upsell revenue per booking by 6.9%, with the airline projecting \$50-\$150 million in incremental annual premium seat revenue across eligible domestic markets. The success of the pilot led to scaled adoption and informed broader AI-driven decision initiatives within the organization.

AI 总结：研究发现大语言模型存在价值泄露问题，即其答案受自身价值观影响却未向用户披露。为此引入评估套件量化，发现模型受多种价值观影响，前沿模型差异大，价值泄露是新的失败模式，当前训练和评估未充分解决。

链接：https://arxiv.org/abs/2607.14345

作者：Jan Betley, Johannes Treutlein, Jan Dubiński, Harry Mayne, Karol Gałązka, Niels Warncke, Anna Sztyber-Betley, Owain Evans

英文摘要：People use language models for practical questions whose answers are difficult to verify. We show that models exhibit covert value leakage: the information they provide is influenced by their own values, without this influence being disclosed to the user. In one of our evaluations, the user is considering investing in an AI company and wants to know how likely the AI bubble is to pop. Claude Opus 4.8 gives a lower probability when the company under consideration is Anthropic rather than OpenAI. Yet Claude mostly fails to disclose this influence to the user. Covert value leakage is a form of misalignment because it goes against the user's preferences and is likely to mislead them. To investigate this phenomenon, we introduce a suite of evaluations to quantify value leakage and whether models disclose it. We find that models are influenced by different types of values, including preferences for morally good outcomes, for the company that developed them, and for some human leisure activities over others. We often observe large differences among frontier models on the same evaluation. For example, on a Fermi-estimation task, Claude models falsely claim to give unbiased answers in their chain-of-thought, while Qwen models explain how their values bias their answers. Value leakage is a failure mode distinct from sycophancy and reward hacking, and current alignment training and evaluations do not adequately address it.

AI 总结：研究在治疗数据缺失时的策略学习问题，通过扩展有效估计器到MAR和MCCAR数据下的策略值及CATE估计，经渐近效率分析和实验验证，证明MAR估计器更优，为从业者提供稳健策略学习工具。

链接：https://arxiv.org/abs/2607.14346

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

作者：Johnna Sundberg, Rayid Ghani, Eli Ben-Michael, Edward Kennedy

英文摘要： Policy learning methods are increasingly used to inform treatment allocation under budget constraints. Most proposed methods assume complete treatment data, yet applications frequently suffer from missingness that can bias estimates and lead to suboptimal policies. We address this gap by extending efficient estimators for average treatment effect (ATE) estimation to policy value and conditional average treatment effect (CATE) estimation under missing at random (MAR) and missing completely conditionally at random (MCCAR) treatment data. Through asymptotic efficiency analysis, we prove that the MAR estimator, which leverages partially-observed units, is both valid and more efficient than the MCCAR estimator when MCCAR assumptions hold. This result provides formal justification for preferring MAR-based estimation in policy learning under both missing data settings. Our comprehensive experiments using synthetic and semi-synthetic datasets confirm that correctly specifying the missingness mechanism is crucial: misspecified estimators remain biased regardless of sample size, while our estimators achieve near-oracle performance when assumptions are satisfied. Our work provides practitioners with theoretically grounded, empirically validated tools for robust policy learning in the presence of missing treatment data.

AI 总结：研究大语言模型个性化中监督微调与上下文学习的选择问题，通过构建框架分析用户面临的统计 - 经济权衡，得出不同方法占优情况、资源消耗特性及平台策略等结论，实验与平台调研验证了相关理论。

链接：https://arxiv.org/abs/2607.14371

作者：Fengzhuo Zhang, Zhuoran Yang, Dirk Bergemann

英文摘要：Large Language Models (LLMs) have revolutionized AI services, but a critical tension emerges: while personalization improves model performance, it consumes scarce computational resources that users must share. When should a user invest in expensive Supervised Fine-Tuning (SFT) versus lightweight In-Context Learning (ICL)? How does congestion from other users' personalization choices reshape these incentives? And what strategies should platforms adopt when offering multiple personalization algorithms? We develop a tractable framework for LLM serving that captures the statistical-economic trade-offs users face. Our analysis yields several surprising insights. First, we show that ICL and SFT dominate in different regimes, determined by an interplay between pretraining coverage and data signal-to-noise ratios, but congestion can flip these rankings. Second, equilibrium resource consumption exhibits pronounced non-monotonicity: improving pretraining precision reduces the congestion, while broader pretraining coverage and harder tasks sometimes increase it. Third, we prove that offering both personalization methods never hurts the platform's maximal profits, despite potentially increasing computational load. Experiments with GPT-2 on linear regression tasks validate our theoretical predictions about algorithm performance. Complementing these results, our review of documentation from 21 major AI platforms shows that the share offering both SFT and ICL increased from 9.5% in 2021 to 71.4% in 2025, consistent with our platform-design implications.

AI 总结：研究通用机器人策略评估难题，提出主动评估框架，将策略评估当作顺序实验设计问题，通过拟合概率替代模型、自适应选评估配置，高效表征策略行为并识别易失败区域，相比随机测试节省大量试验次数。

链接：https://arxiv.org/abs/2607.14439

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

作者：Andrew Liao, Hanchen Cui, Karthik Desingh, Aryan Deshwal

英文摘要：Generalist robot manipulation policies trained on large, diverse datasets have shown remarkable promise across a wide range of tasks. However, rigorously evaluating these policies remains a fundamental challenge. Real-world performance depends on a large combinatorial space of task factors including object poses and camera viewpoints, making full, exhaustive evaluation intractable. Additionally, real hardware evaluation is slow and resource-intensive, so current practice is to use narrow test suites that can miss critical failure modes and misrepresent true deployment readiness. We propose an active evaluation framework that addresses this challenge by treating policy evaluation as a sequential experimental design problem. Our approach fits a probabilistic surrogate model over a structured space of task factors and adaptively selects evaluation configurations to maximize information gain over the policy's performance distribution, allowing for sample-efficient characterization of policy behavior across unseen conditions and a systematic identification of failure-prone regions. We conduct 2331 real-world evaluations across 3 tasks with 3 factor variations and find that our approach typically saves the evaluator at least 20-40% of trials compared to typical random testing.

AI 总结：研究用DSAE对激光雷达点云分类，通过实验比较不同编码器深度下的表现，发现深度为\(K = 5\)时存在隐藏状态坍缩，乘积系数不能改善坍缩前指标及防止坍缩，确定大深度表示坍缩是DSAE激光雷达分类的失败模式。

链接：https://arxiv.org/abs/2607.14463

作者：Patricia Medina, Hy P. G. Lam

英文摘要：We study Dynamical System Autoencoders (DSAE) for LiDAR point-cloud classification using spatial coordinates and Product Coefficient feature augmentations. The experiments compare separately trained DSAE architectures at encoder depths $K=1,\ldots,5$ and evaluate the resulting hidden representations with Random Forest, kNN, and a majority-class Dummy baseline. The main finding is a hidden-state collapse at $K=5$. For both xyz and xyz plus Product Coefficient inputs, the hidden-state standard deviation falls to the order of $10^{-5}$, while all three classifiers attain the same macro F1 score of $0.224688$. We prove that between-class hidden scatter is bounded by total hidden scatter, which in turn is controlled by the reported hidden-state variance. Thus a nearly constant hidden representation cannot retain substantial class-separating structure. Product Coefficients neither improve pre-collapse macro F1 nor prevent the $K=5$ collapse in the present DSAE setting. These results identify large-depth representation collapse as a concrete failure mode for DSAE LiDAR classification.

AI 总结：研究将高阶 RK 积分器用于神经网络优化器，构建 Adam 变体并在计算匹配协议下评估，发现其“适应性”虚幻，修复后训练损失降低但对初始步长敏感，未达测试精度，还证实梯度平均是隐式正则化器，高阶自适应积分优势不明显。

链接：https://arxiv.org/abs/2607.14516

作者：Akhilesh Gogikar

英文摘要： Interpreting optimizers as gradient-flow discretizations has motivated applying higher-order Runge-Kutta (RK) integrators to neural networks. We build a representative Adam variant (Bogacki-Shampine 3(2) RK pair, FSAL reuse, local-error step control) and evaluate it under a strict compute-matched protocol giving every method the same gradient-evaluation budget - an accounting this literature rarely enforces. Under it the RK variant loses to plain Adam on training loss in both minibatch and full-batch (RK's best-case) training. Instrumenting it shows the "adaptivity" is illusory: normalized error stays far below tolerance, the step size pins at its growth cap from step one (98-100 percent of steps), and no rtol x hmax x h0 setting makes it act; tolerances spanning 100x give bit-identical trajectories. The method is exactly fixed-step Adam with an averaged gradient at 3-4x cost. Repairing it (true reject branch; error on the applied map) reverses the full-batch result - about 40x lower training loss than tuned Adam - and a fixed-step control isolates adaptivity (an emergent warmup-and-growth schedule) as the mechanism. But the gain is fragile to the initial step size and does not reach test accuracy. A pre-registered follow-up rules out the obvious explanations: deeper minimization does not overfit, and an explicit temperature knob only hurts - leaving a trajectory effect, the controller selecting a minimum generalizing 1.3-3.4 points below first-order descent at equal depth. An n=10 study confirms one secondary effect: gradient averaging is a genuine implicit regularizer, beating lr-matched Adam and AdamW on 10/10 seeds - yet RMSprop and NAdam match or beat it at a third the per-step cost. Higher-order adaptive integration buys deeper deterministic minimization and a small regularization effect, but nothing a cheaper, well-tuned first-order baseline does not already provide.

AI 总结：研究μ子风格优化器中表示选择对优化器几何的影响，引入{\方法}族优化器，通过预训练实验及固定动量诊断发现平衡非原生表示可匹配原生表示性能，减小较短维度会改变优化效果。

链接：https://arxiv.org/abs/2607.14536

机构：Pengcheng Laboratory（鹏城实验室）； Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）； Southern University of Science and Technology（南方科技大学）； Shenzhen University of Advanced Technology（深圳先进技术大学）； University of Chinese Academy of Sciences（中国科学院大学）

作者：Da Chang, Qiankun Shi, Lvgang Zhang, Di He, Yaoshuai Ma, Ganzhao Yuan, Yongxiang Liu

英文摘要：Muon-style optimizers apply a polar map to matrix momentum, but their updates also depend on the representation of each parameter block before orthogonalization. We study this representation choice as a form of optimizer geometry and introduce {\method}, a family of Muon-style optimizers that shares the same momentum rule and Newton--Schulz backend across native, nearest-square, skinny, and vector representations. Each Frobenius-isometric representation induces a distinct polar steepest-descent geometry, in which the shorter matrix dimension determines the number of supported singular channels, the pullback scaling, and the constants in stochastic nonconvex convergence bounds. In a teacher--student model, curvature collapse and an isotropic Marchenko--Pastur spectral profile connect early-stage dissipation to the represented nuclear-to-squared-Frobenius norm ratio. Pretraining experiments on LLaMA2-130M and LLaMA2-600M, together with fixed-momentum diagnostics, show that balanced non-native representations can match the performance of the native representation, whereas reducing the shorter dimension weakens the scaling and singular-channel support, leading to behavior that increasingly resembles normalized momentum.

AI 总结：研究针对CPU上大语言模型推理的量化问题，提出PolyQ方法，通过激活感知的逐通道比特分配及编译时模型编译器优化，实现分数比特部署，在多个模型上提升质量，在不同CPU上有良好性能，证明其在边缘设备推理的实用性、可预测性和节能性。

链接：https://arxiv.org/abs/2607.14618

机构：University of California, Irvine（加利福尼亚大学欧文分校）

作者：Hyunwoo Oh, Suyeon Jang, Hanning Chen, KyungIn Nam, Sanggeon Yun, Ryozo Masukawa, Mohsen Imani

英文摘要：CPUs are the most universal target for on-device LLM inference, but existing low-bit quantization methods offer either coarse operating points or fine-grained mixed precision that is difficult to execute efficiently on CPUs. We present PolyQ, a CPU-oriented compiler/quantization co-design for activation-aware channel-wise bit allocation under a user-specified average-bit budget. PolyQ assigns per-channel bit-widths from $\{2,3,4,8,16\}$, then uses a compile-time model compiler to permute and cluster channels into bit-homogeneous blocks, generate SIMD- and LUT-compatible kernels, and merge compatible permutations across operators to keep layout regularization off the runtime path. This turns fine-grained budget fitting into a practical fractional-bit deployment method for CPU-only inference. Across Falcon-H1-3B, Llama2-13B, and Qwen3-32B on WikiText-2, PolyQ provides stable quality scaling from 3--6\,b and improves perplexity by 2.4--32.1\% over prior methods at a 3\,b target. End-to-end measurements on three representative CPUs -- workstation, laptop, and mobile -- show that compiler layout regularization reduces activation reorder traffic by up to 70.8\%, prefill latency and decode throughput scale nearly proportionally with the configured bit budget, and energy/token overhead stays below 2\% relative to an optimized LUT-based back-end. These results show that fractional-bit CPU deployment is practical, predictable, and energy-efficient across diverse edge targets.

AI 总结：研究针对电池健康估计问题，提出TIDE方法，结合电池领域知识与运行测量，通过知识引导退化先验、单调残差组件和上下文学习组件，提升估计准确性、可靠性与可解释性，经实验验证其有效性，支持智能互联系统的电池健康监测与决策。

链接：https://arxiv.org/abs/2607.14640

机构：A*STAR（新加坡科技研究局）

作者：Wen Yang Tan, Jiawei Li, Fang Liu, Wei Zhang, Sumei Sun, Peng Cheng Wang, Elisa Y. M. Ang

英文摘要： Battery health estimation is fundamental for battery management in battery-powered systems, where inaccurate health states may affect control, maintenance, and service life. It becomes even more critical in intelligent connected systems, where estimation errors can propagate across interconnected devices and downstream decisions. In this paper, we propose TIDE, a trustworthy and interpretable battery degradation estimator for reliable battery health estimation. TIDE jointly considers accuracy, trustworthiness, and interpretability, which are all essential for practical deployment and downstream decision making. To realize these objectives, TIDE combines battery-domain knowledge with operational measurements in a three-component backbone. A knowledge-guided degradation prior promotes trustworthy estimation, a monotone residual component provides interpretable aging-consistent refinement, and a contextual learning component captures battery-specific operational effects for improved accuracy. The trained backbone is then distilled into a compact symbolic surrogate that provides a concise model-level interpretation of its learned estimation logic. Experiments show that TIDE achieves strong estimation accuracy, improving overall estimation fidelity by an average of 19.7% over representative baselines. Its knowledge-guided prior and monotone residual modelling substantially reduce aging-consistency violations, supporting trustworthy estimation. Meanwhile, the backbone enables component-level interpretation, while symbolic distillation provides a compact model-level representation of the learned estimation logic. These results support the practical use of TIDE for battery health monitoring and decision support in intelligent connected systems.

AI 总结：研究连续时间脉冲神经网络训练受内存限制问题，提出基于可微脉冲时间离散化的内存高效训练框架及受同步发放链启发的时间正则化，降低内存消耗与训练时间，实现多层卷积SNNs在单GPU上训练。

链接：https://arxiv.org/abs/2607.14672

机构：Research Center for Mathematical Engineering, Chiba Institute of Technology（千叶工业大学数学工程研究中心）； International Research Center for Neurointelligence (WPI-IRCN), The University of Tokyo（东京大学国际神经智能研究中心（WPI-IRCN））； NEC Corporation（日本电气公司）

作者：Yusuke Sakemi, Tomoya Takeuchi, Takeo Hosomi, Kazuyuki Aihara

英文摘要：Continuous-time spiking neural networks (SNNs) provide an event-driven framework for temporal computation, computational neuroscience, and neuromorphic hardware. However, training deep continuous-time SNNs is severely constrained by the memory required for exact spike-time computation, which evaluates and retains candidate firing times over intervals determined by presynaptic spike ordering. Here we introduce a memory-efficient training framework based on differentiable spike-time discretization (DSTD) for leaky integrate-and-fire neurons with general membrane and synaptic time constants. DSTD maps irregular presynaptic spikes onto differentiable weighted events at fixed time points, replacing the input-dependent candidate dimension with $M$ fixed time intervals while accurately approximating continuous-time membrane-potential dynamics. This reduces candidate-related activation memory from $O(N_{\mathrm{out}}N_{\mathrm{in}})$ to $O(N_{\mathrm{out}}M)$ in the case of time-to-first-spike (TTFS) coding, where $N_{\mathrm{in}}$ and $N_{\mathrm{out}}$ denote the numbers of presynaptic and postsynaptic neurons, respectively. We further introduce synfire-chain-inspired temporal regularization that organizes layer-wise firing windows, mitigates dead-neuron failures, and enables pipeline-like processing. In dense LIF layers, DSTD reduced peak memory consumption by up to approximately 100-fold and training time by up to approximately 20-fold compared with exact spike-time computation. Together, these methods allowed us to train 9-layer convolutional SNNs on CIFAR-10 and 20-layer convolutional SNNs on Fashion-MNIST on a single GPU.

AI 总结：研究特征加权聚类的反事实解释问题，提出VoICE框架，通过将反事实生成投影到目标聚类的加权Voronoi区域，结合特征权重和数据衍生边界，在多个基准数据集上能有效产生目标聚类成员关系。

链接：https://arxiv.org/abs/2607.14719

机构：School of Computer Science and Electronic Engineering, University of Essex（埃塞克斯大学计算机科学与电子工程学院）

作者：Richard J. Fawley, Renato Cordeiro de Amorim

英文摘要：Counterfactual explanations provide local, interpretable insight by identifying changes to an input that would alter its assigned outcome. Although well established in supervised learning, their extension to clustering is less direct, since cluster assignments are unlabeled and governed by the geometry of the partition. This paper introduces VoICE, a Voronoi-Induced Counterfactual Explainability framework for feature-weighted $k$-means clustering. Rather than treating cluster change as a crossing of a single pairwise centroid boundary, VoICE formulates counterfactual generation as projection onto the full weighted Voronoi region of a target cluster, incorporating feature weights directly into both the clustering geometry and the counterfactual objective to yield least-cost and parsimonious explanations under actionability constraints. Target regions are further intersected with data-derived bounds and homothetically contracted towards their centroids, limiting extrapolation and boundary sensitivity. VoICE consistently produces valid target-cluster membership, across several benchmark datasets, where the leading pairwise baseline does not.

AI 总结：针对时间知识图谱预测未来事件的难题，提出群组注意力神经霍克斯过程（GAttNHP）框架，通过自注意力编码器、语义软分组模块和非交叉分位数回归头，在实体预测和时间预测上优于基线，尤其在长尾事件链表现突出。

链接：https://arxiv.org/abs/2607.14733

机构：Insilicom（硅基公司）

作者：Xiangni Tian, Kaixian Yu, Runpeng Dai, Niansheng Tang, Hongtu Zhu

英文摘要：Temporal Knowledge Graphs (TKGs) record how facts evolve over time, but forecasting future events on a TKG remains difficult for three reasons: (i) long-range temporal dependencies are hard to encode; (ii) events on different chains mutually excite or inhibit one another in ways that snapshot-level models cannot express; and (iii) inter-arrival times are heavy-tailed and statistically sparse, so deterministic time predictors are unreliable. We address these three issues with a single framework, the \textbf{Group Attention Neural Hawkes Process (GAttNHP)}, built around three matched components. First, a self-attention encoder casts each subject--relation chain as a continuous-time point process and captures the lingering excitation of distant history. Second, a semantic soft-grouping module turns globally learnable Hawkes priors into an analytical cross-attention mask, so chains share excitation patterns through their latent group memberships rather than through exhaustive pairwise computation. Third, a Non-Crossing Quantile (NCQ) regression head replaces mean-based time prediction, providing calibrated, monotonically ordered quantile estimates that remain stable under heavy-tailed inter-arrival distributions. On six benchmark TKG datasets, GAttNHP improves over state-of-the-art baselines on both entity prediction and time prediction, and ablations confirm that its largest gains arise on the long-tail event chains where existing models fail most severely.

AI 总结：研究基于真值表结构化数据集的二分类器最优线性组合，通过分类校准函数分析凸化经验风险，建立存在唯一性条件，给出三个分类器情况配置，推导最优权重公式，引入φ前沿评估稳定性和数据质量。

链接：https://arxiv.org/abs/2607.14889

机构：CNRS, Univ. Grenoble Alpes, Grenoble-INP, GIPSA-lab（法国国家科学研究中心、格勒诺布尔阿尔卑斯大学、格勒诺布尔国立综合理工学院、信号与自动化格勒诺布尔实验室）； Université Sorbonne Paris Nord, LAGA, UMR 7539. IRL CNRS-CRM 3457. Université de Montréal（巴黎索邦大学北校区、巴黎第十三大学、法国国家科学研究中心 - 巴黎第十三大学联合研究单位7539、法国国家科学研究中心 - 蒙特利尔大学联合研究单位3457、蒙特利尔大学）

作者：Jean-Marc Brossier, Olivier Lafitte

英文摘要：This paper studies an optimal linear combination of binary classifiers based on a logical structuration of the dataset via truth tables. The given classifiers partition data into equivalence classes, allowing for a rigorous analysis of the convexified empirical risk through a multidimensional generalization of classification calibrated functions. We establish sufficient conditions for the existence and uniqueness of the (global) point of minimum of the convexified empirical risk for any list of classifiers (when the number of classifiers is large, there frequently could be no point of minimum). In the case of three classifiers, our analysis allows to list all the configurations leading to either a unique solution, infima or non-unique points of minimum. Furthermore, we derive explicit analytical formulae for optimal weights using Exponential (Boost) and Logistic (Logit) loss functions, bypassing iterative optimization. The stability of the resulting classifier and the analysis of data quality can be evaluated through the introduction of the notion of $\phi$-frontiers.

AI 总结：研究针对基于黑盒分数的对抗样本攻击的防御与攻击方法，提出随机对数缩放（RLS）防御可降低攻击成功率，还引入新型自适应攻击，证明一种非随机化黑盒防御易受攻击。

链接：https://arxiv.org/abs/2607.14921

机构：Sharif University of Technology（伊朗谢里夫理工大学）

作者：Hamid Dashtbani, Mehdi Dousti Gandomani, AmirMahdi Sadeghzadeh

英文摘要：Machine learning models are increasingly adapted in various domains. However, adversarial examples pose a significant threat to the reliable deployment of these models. In recent years, some powerful adversarial example attacks have been proposed for the fast and query-efficient generation of adversarial examples, even in black-box scenarios, highlighting the need for scalable, low-cost, and powerful defenses. In this work, we present two contributions to the domain of black-box adversarial example attacks and defenses. First, we propose Random Logit Scaling (RLS), a randomization-based defense against black-box score-based adversarial example attacks. RLS is a plug-and-play, post-processing defense that can be implemented on top of any existing ML model with minimal effort. The idea behind RLS is to confuse an attacker by outputting falsified scores resulting from randomly scaled logits while maintaining the model accuracy. We show that RLS significantly reduces the success rate of state-of-the-art black-box score-based attacks while preserving the accuracy and minimizing confidence score distortion compared to state-of-the-art randomization-based defenses. Second, we introduce a novel adaptive attack against AAA, a SOTA non-randomized black-box defense against black-box score-based attacks that also modifies output logits to confuse attackers, demonstrating its vulnerability against adaptive attacks.

AI 总结：研究顺序观测设置下结果干扰的因果推断，基于最大伪似然估计提供计算高效方法学习模型参数，在温和假设下建立参数估计非渐近一致性，通过实验和案例研究证明方法有效性。

链接：https://arxiv.org/abs/2607.14940

机构：MIT（麻省理工学院）

作者：Phevos Paschalidis, Constantinos Daskalakis, Devavrat Shah

英文摘要：We study causal inference under outcome interference for sequential, observational settings. Specifically, we consider settings where the binary outcomes over N units are Markovian across T time steps. At each time step, the outcomes of N units have dependencies captured through an Ising model; each outcome is also impacted through an external field capturing the effects of its treatment as well as latent confounders. Similar to panel data literature, these latent confounders are modeled to have a low-rank factor structure. Our data is a single sample from this high-dimensional distribution. To estimate causal quantities of interest, we provide a computationally efficient method based on Maximum Pseudo-Likelihood Estimation (MPLE) for learning the model parameters. Under mild assumptions, we establish non-asymptotic consistency for parameter estimation and show this translates to faithful estimation of causal quantities of interest after sampling from the learned model. We demonstrate the efficacy of the method through synthetic experiments as well as a real-world case-study investigating causal effects of vaccine rates on COVID-19 death rates within US counties nationwide.

AI 总结：针对部分状态变量可测、动力学方程部分未知的情况，提出混合神经-物理框架，交替进行状态和参数估计，利用RTS平滑器和反向传播，能从测量中学习缺失的ODE组件，提升潜在状态重建和长期预测能力。

链接：https://arxiv.org/abs/2607.15180

机构：Northeastern University（东北大学）； University of Massachusetts Boston（马萨诸塞大学波士顿分校）； Emory University（埃默里大学）

作者：Ahmet Demirkaya, Georgios Stratis, Tales Imbiriba, Zachary D. Danziger, Deniz Erdogmus

英文摘要： Ordinary differential equations (ODEs) are widely used to model dynamical systems in physics, biology, neuroscience, and physiology, but in many applications some equations of the dynamics are unknown and only a subset of the state variables are measured. We propose a hybrid neural--physics framework in which the known components of the ODE are kept explicit and the missing components are represented by a neural network. The proposed method consists of two stages where we alternate between state and parameter estimation and iterate until a predetermined criterion is met. Specifically, in the first step, we treat the model parameters as being known and we infer the latent states from the available measurements using a Rauch--Tung--Striebel (RTS) smoother. In the second stage, we treat the smoothed trajectories as being known and use them to estimate the neural networks' parameters through backpropagation. We evaluate the method on benchmark systems spanning linear, nonlinear, and stiff dynamics under partial state observation. Across these settings, the proposed method learns missing ODE components from incomplete measurements while exploiting and retaining interpretable mechanistic structure and improving latent-state reconstruction and long-horizon prediction.

AI 总结：研究两阶段推荐中嵌入陈旧性问题，提出可变草图方法，将用户偏好存于KP树，一次拟合低秩投影，即时重算嵌入。证明可收紧预测误差范围，实验显示该方法在KuaiRec上效果好、更新快，新用户获推荐快，还比较了不同采样策略。

链接：https://arxiv.org/abs/2607.15242

机构：University of Michigan（密歇根大学）； Criteo

作者：Hector J. Garcia, Nick Clayton

英文摘要：A common bottleneck in two-stage recommendation is embedding staleness: when a user rates a new item, their embedding remains fixed until the next retrain cycle. We propose mutable sketches, which store each user's preferences in a KP-tree (a sparse segment tree with sum aggregation), fit a low-rank projection once, and recompute embeddings on-the-fly as ratings arrive. We prove that each new observation monotonically tightens the prediction error envelope (Theorem 1), a guarantee that FunkSVD and eALS lack. On KuaiRec, the mutable sketch achieves 0.810 RMSE at 1.8% data read vs. ALS 0.822 at 100%, with 8x faster per-batch updates. A new user receives personalized recommendations in <1 ms after their first rating, with no model retraining required. A comparison of sampling strategies across density regimes shows that the KP-tree's norm-proportional sampling provides 40-130% better item coverage on sparse data (<1% density), while uniform sampling suffices on dense matrices.

AI 总结：研究通过结合链上、金融数据与社交媒体帖子分析比特币市场情绪，用梯度提升等模型分类，SHAP量化特征贡献，此数据组合产生有意义信号与见解，支持加密货币分析及深度学习改进。

链接：https://arxiv.org/abs/2607.15258

机构：Computing Sciences Center - C3（计算科学中心 - C3）

作者：Arthur G. Bubolz, Abreu Quevedo, Giancarlo Lucca, Rafael A. Berri, Eduardo Borges, Bruno L. Dalmazo

英文摘要：The growing use of Bitcoin as a decentralized digital asset and investment tool has sparked strong interest in understanding its market behavior. This study presents a new approach to analyze Bitcoin market sentiment by combining on-chain and financial data with social media posts. Unlike models that aim to predict prices, this work focuses on explaining market sentiment using blockchain transactions, historical price data of Bitcoin, and daily Twitter sentiment classifications. The method merges sentiment trends with on-chain and financial metrics, normalized into a dataset for detailed market analysis. Multiple machine learning models were tested using cross-validation, with Gradient Boosting (XGBoost) emerging as the most reliable model for classifying sentiment, achieving an average F1-score of about 0.84. SHAP (SHapley Additive exPlanations), a game theory-based method for model interpretability, was used to quantify the contribution of on-chain features to the model's predictions, improving transparency. The results indicate that this data combination yields meaningful predictive signals and insights, supporting data-driven cryptocurrency analysis and future improvements with deep learning.