|
创作新主题 |
社区所有版块导航
DATA
| docker Elasticsearch |
WEB开发
| linux MongoDB Redis DATABASE NGINX 其他Web框架 web工具 zookeeper tornado NoSql Bootstrap js peewee Git bottle IE MQ Jquery |
机器学习
| 机器学习算法 |
产品
| 短视频 |
印度
| 印度 |
一周十大热门主题
点击阅读原文访问arxivdaily.com，涵盖CS|物理|数学|经济|统计|金融|生物|电气领域，更有搜索、收藏等功能！
cs.LG 方向，今日共计113篇
大模型相关(18篇)
【1】LLM Unlearning using Gradient Ratio-Based Influence Estimation and Noise Injection
标题：使用基于梯度比的影响估计和噪音注入的LLM去学习
链接：https://arxiv.org/abs/2508.06467
备注：14 Pages, 3 Figures, 11 Tables
摘要：随着对大型语言模型（LLM）的法律和道德审查日益严格，有效的机器去学习成为必要，特别是对于敏感或未经授权的数据。现有的经验方法往往会产生不完全遗忘或无意中退化的不相关的知识，由于本地化差。在这项工作中，我们提出了GRIN：一个模块化和有针对性的框架LLM unlearning。GRIN引入了一种新的基于梯度比的度量来识别最负责记忆遗忘数据的参数。然后，我们在微调之前对这些参数进行选择性噪声注入，这在保持模型实用性的同时提高了学习性能。最后，我们提出了新的评估指标量身定制的LLM设置和验证我们的方法，如TOFU，WMDP和SafePKU的标准基准。
摘要：The growing legal and ethical scrutiny of large language models (LLMs) necessitates effective machine unlearning, particularly for sensitive or unauthorized data. Existing empirical methods often yield incomplete forgetting or unintended degradation of unrelated knowledge due to poor localization. In this work, we propose GRIN: a modular and targeted framework for LLM unlearning. GRIN introduces a novel gradient-ratio-based metric to identify parameters most responsible for memorizing forget data. We then perform selective noise injection into these parameters prior to fine-tuning, which improves unlearning performance while maintaining model utility. Finally, we propose new evaluation metrics tailored to the LLM setting and validate our approach on standard benchmarks such as TOFU, WMDP, and SafePKU.
【2】Sample-efficient LLM Optimization with Reset Replay
标题：具有重置重播的样本高效LLM优化
链接：https://arxiv.org/abs/2508.06412
摘要：最近在训练后的大型语言模型（LLM）方面取得的进展，特别是通过强化学习（RL）和偏好优化方法，是增强其推理能力的关键驱动因素。然而，这些方法往往受到样本效率低和易受首因偏差的困扰，过度拟合初始经验会降低政策质量并损害学习过程。为了解决这些挑战，我们引入了LLM优化与重置重放（LoRR），一个通用的和强大的插件，旨在提高任何基于偏好的优化框架中的样本效率。LoRR核心机制支持在高重放次数下进行训练，最大限度地提高每个收集的数据批次的效用。为了抵消高重放训练中固有的过度拟合风险，LoRR采用了周期性重置策略，并重复使用初始数据，从而保持了网络的可塑性。此外，它利用混合优化目标，结合监督微调（SFT）和基于偏好的损失，以进一步支持数据利用。我们的大量实验表明，LoRR显着提高了各种偏好优化方法在数学和一般推理基准上的性能。值得注意的是，使用LoRR增强的迭代DPO方法在具有挑战性的数学任务上实现了相当的性能，优于一些复杂且计算密集的基于RL的算法。这些研究结果强调，LoRR为LLM微调提供了一个实用、高效和高效的范例，从有限的数据中释放出更高的性能。
摘要：Recent advancements in post-training Large Language Models (LLMs), particularly through Reinforcement Learning (RL) and preference optimization methods, are key drivers for enhancing their reasoning capabilities. However, these methods are often plagued by low sample efficiency and a susceptibility to primacy bias, where overfitting to initial experiences degrades policy quality and damages the learning process. To address these challenges, we introduce LLM optimization with Reset Replay (LoRR), a general and powerful plugin designed to enhance sample efficiency in any preference-based optimization framework. LoRR core mechanism enables training at a high replay number, maximizing the utility of each collected data batch. To counteract the risk of overfitting inherent in high-replay training, LoRR incorporates a periodic reset strategy with reusing initial data, which preserves network plasticity. Furthermore, it leverages a hybrid optimization objective, combining supervised fine-tuning (SFT) and preference-based losses to further bolster data exploitation. Our extensive experiments demonstrate that LoRR significantly boosts the performance of various preference optimization methods on both mathematical and general reasoning benchmarks. Notably, an iterative DPO approach augmented with LoRR achieves comparable performance on challenging math tasks, outperforming some complex and computationally intensive RL-based algorithms. These findings highlight that LoRR offers a practical, sample-efficient, and highly effective paradigm for LLM finetuning, unlocking greater performance from limited data.
【3】End-to-End Text-to-SQL with Dataset Selection: Leveraging LLMs for Adaptive Query Generation
标题：具有数据集选择的端到端文本到SQL：利用LLM进行自适应查询生成
链接：https://arxiv.org/abs/2508.06387
备注：Accepted in IJCNN25
摘要：Text-to-SQL弥合了自然语言和结构化数据库语言之间的差距，从而允许非技术用户轻松查询数据库。传统方法将文本到SQL建模为直接翻译任务，其中给定的自然语言查询（NLQ）被映射到SQL命令。大型语言模型（LLM）的最新进展显着提高了翻译准确性，然而，这些方法都需要预先指定目标数据库。这在具有多个广泛数据库的场景中变得有问题，其中识别正确的数据库成为关键但被忽视的步骤。在本文中，我们提出了一个三阶段的端到端的文本到SQL框架，以确定用户的预期数据库生成SQL查询之前。我们的方法利用LLM和提示工程从自然语言查询（NLQs）中以规则的形式提取隐式信息。然后，我们训练一个大型db\_id预测模型，其中包括一个基于RoberTa的微调编码器，以预测正确的数据库标识符（db\_id）的基础上NLQ和LLM生成的规则。最后，我们通过使用评论家代理来纠正错误来改进生成的SQL。实验结果表明，我们的框架优于当前国家的最先进的模型在数据库意图预测和SQL生成准确性。
摘要：Text-to-SQL bridges the gap between natural language and structured database language, thus allowing non-technical users to easily query databases. Traditional approaches model text-to-SQL as a direct translation task, where a given Natural Language Query (NLQ) is mapped to an SQL command. Recent advances in large language models (LLMs) have significantly improved translation accuracy, however, these methods all require that the target database is pre-specified. This becomes problematic in scenarios with multiple extensive databases, where identifying the correct database becomes a crucial yet overlooked step. In this paper, we propose a three-stage end-to-end text-to-SQL framework to identify the user's intended database before generating SQL queries. Our approach leverages LLMs and prompt engineering to extract implicit information from natural language queries (NLQs) in the form of a ruleset. We then train a large db\_id prediction model, which includes a RoBERTa-based finetuned encoder, to predict the correct Database identifier (db\_id) based on both the NLQ and the LLM-generated rules. Finally, we refine the generated SQL by using critic agents to correct errors. Experimental results demonstrate that our framework outperforms the current state-of-the-art models in both database intent prediction and SQL generation accuracy.
【4】Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts
标题：超越谎言诱导的谎言：调查LLM对良性肿瘤的欺骗
链接：https://arxiv.org/abs/2508.06361
摘要：大型语言模型（LLM）已被广泛部署在推理，规划和决策任务中，使其可信度成为一个关键问题。故意欺骗的可能性，即LLM故意编造或隐藏信息以服务于隐藏的目标，仍然是一个重大的和未充分探索的威胁。现有的研究通常通过提示或微调明确设置“隐藏”目标来诱导这种欺骗，这可能无法完全反映现实世界中的人类-LLM互动。超越这种人为诱导的欺骗，我们调查LLM的自我发起的欺骗良性提示。为了解决在这种评估中缺乏基础事实，我们提出了一个新的框架，使用“接触搜索问题。“这个框架引入了两个来自心理学原理的统计指标来量化欺骗的可能性。第一个是欺骗意图分数，衡量模型对隐藏目标的偏见。第二，欺骗行为得分，衡量LLM的内部信念和表达输出之间的不一致性。在评估14个领先的LLM后，我们发现这两个指标随着任务难度的增加而升级，对于大多数模型来说，这两个指标都是平行上升的。基于这些发现，我们建立了一个数学模型来解释这种行为。这些结果表明，即使是最先进的LLM在处理复杂问题时也表现出越来越多的欺骗倾向，这引起了人们对LLM代理在复杂和关键领域部署的严重关注。
摘要：Large Language Models (LLMs) have been widely deployed in reasoning, planning, and decision-making tasks, making their trustworthiness a critical concern. The potential for intentional deception, where an LLM deliberately fabricates or conceals information to serve a hidden objective, remains a significant and underexplored threat. Existing studies typically induce such deception by explicitly setting a "hidden" objective through prompting or fine-tuning, which may not fully reflect real-world human-LLM interactions. Moving beyond this human-induced deception, we investigate LLMs' self-initiated deception on benign prompts. To address the absence of ground truth in this evaluation, we propose a novel framework using "contact searching questions." This framework introduces two statistical metrics derived from psychological principles to quantify the likelihood of deception. The first, the Deceptive Intention Score, measures the model's bias towards a hidden objective. The second, Deceptive Behavior Score, measures the inconsistency between the LLM's internal belief and its expressed output. Upon evaluating 14 leading LLMs, we find that both metrics escalate as task difficulty increases, rising in parallel for most models. Building on these findings, we formulate a mathematical model to explain this behavior. These results reveal that even the most advanced LLMs exhibit an increasing tendency toward deception when handling complex problems, raising critical concerns for the deployment of LLM agents in complex and crucial domains.
【5】LLM Robustness Leaderboard v1 --Technical report
标题：LLM稳健排行榜v1 --技术报告
链接：https://arxiv.org/abs/2508.06296
摘要：本技术报告伴随PRISM Eval为巴黎人工智能行动峰会发布的LLM稳健性排行榜。我们介绍了PRISM Eval Behavior Elicitation Tool（BET），这是一个通过动态对抗优化执行自动化红队的AI系统，可以对41个最先进的LLM中的37个实现100%的攻击成功率（ASR）。除了二进制成功指标，我们提出了一个细粒度的鲁棒性指标，估计引发有害行为所需的平均尝试次数，揭示了攻击难度在不同模型之间的差异超过300倍，尽管普遍存在漏洞。我们引入连续级漏洞分析，以确定哪些越狱技术是最有效的特定危险类别。我们与来自AI安全网络的可信第三方的合作评估展示了在整个社区进行分布式鲁棒性评估的实用途径。
摘要：This technical report accompanies the LLM robustness leaderboard published by PRISM Eval for the Paris AI Action Summit. We introduce PRISM Eval Behavior Elicitation Tool (BET), an AI system performing automated red-teaming through Dynamic Adversarial Optimization that achieves 100% Attack Success Rate (ASR) against 37 of 41 state-of-the-art LLMs. Beyond binary success metrics, we propose a fine-grained robustness metric estimating the average number of attempts required to elicit harmful behaviors, revealing that attack difficulty varies by over 300-fold across models despite universal vulnerability. We introduce primitive-level vulnerability analysis to identify which jailbreaking techniques are most effective for specific hazard categories. Our collaborative evaluation with trusted third parties from the AI Safety Network demonstrates practical pathways for distributed robustness assessment across the community.
【6】Large Language Model Data Generation for Enhanced Intent Recognition in German Speech
标题：用于增强德语语音意图识别的大语言模型数据生成
链接：https://arxiv.org/abs/2508.06277
备注：11 pages, 3 figures, accepted at KONVENS 2025
摘要：语音命令的意图识别（IR）对于人工智能（AI）辅助系统至关重要;然而，大多数现有方法仅限于短命令，并且主要针对英语开发。本文针对这些局限性，通过集中在IR从老年人的德语发言。我们提出了一种新的方法，该方法结合了一个适应的Whisper ASR模型，对老年人的德语语音（SVC-de）进行了微调，并在三个著名的大型语言模型（LLM）生成的合成文本数据集上训练了基于transformer的语言模型：LeoLM，Llama 3和ChatGPT。为了评估我们的方法的鲁棒性，我们用文本到语音模型生成合成语音，并进行广泛的跨数据集测试。我们的研究结果表明，合成LLM生成的数据显着提高了分类性能和鲁棒性，以不同的说话风格和看不见的词汇。值得注意的是，我们发现LeoLM，一个较小的，特定于领域的13 B LLM，在德国意图识别的数据集质量上超过了更大的ChatGPT（175 B）。我们的方法表明，生成式人工智能可以有效地弥合低资源领域的数据差距。我们提供数据生成和培训过程的详细文档，以确保透明度和可重复性。
摘要：Intent recognition (IR) for speech commands is essential for artificial intelligence (AI) assistant systems; however, most existing approaches are limited to short commands and are predominantly developed for English. This paper addresses these limitations by focusing on IR from speech by elderly German speakers. We propose a novel approach that combines an adapted Whisper ASR model, fine-tuned on elderly German speech (SVC-de), with Transformer-based language models trained on synthetic text datasets generated by three well-known large language models (LLMs): LeoLM, Llama3, and ChatGPT. To evaluate the robustness of our approach, we generate synthetic speech with a text-to-speech model and conduct extensive cross-dataset testing. Our results show that synthetic LLM-generated data significantly boosts classification performance and robustness to different speaking styles and unseen vocabulary. Notably, we find that LeoLM, a smaller, domain-specific 13B LLM, surpasses the much larger ChatGPT (175B) in dataset quality for German intent recognition. Our approach demonstrates that generative AI can effectively bridge data gaps in low-resource domains. We provide detailed documentation of our data generation and training process to ensure transparency and reproducibility.
【7】In-Training Defenses against Emergent Misalignment in Language Models
标题：训练中防止语言模型中出现的失调
链接：https://arxiv.org/abs/2508.06249
备注：Under review
摘要：微调可以让从业者为新的领域重新调整对齐的大型语言模型（LLM），但最近的工作揭示了紧急错位（EMA）：即使是一个小的，特定于领域的微调也会导致远离目标领域的有害行为。即使在模型权重隐藏在微调API后面的情况下，这也会使攻击者无意中访问一个广泛不对齐的模型，而这种方式很难单独从微调数据中检测到。我们提出了针对EMA的培训保障措施的第一个系统性研究，这些措施对于通过API进行微调的提供商来说是实用的。我们研究了四种训练正则化干预：（i）KL-发散正则化到安全的参考模型，（ii）特征空间中的距离，（iii）投影到安全子空间（SafeLoRA），以及（iv）从一般的非线性调整数据集中交错少量安全的训练样本。我们首先评估方法的紧急错位效果在四个恶意的，EMA诱导的任务。其次，我们评估了方法对良性任务的影响。最后，我们讨论了在紧急错位研究的开放性问题。
摘要 ：Fine-tuning lets practitioners repurpose aligned large language models (LLMs) for new domains, yet recent work reveals emergent misalignment (EMA): Even a small, domain-specific fine-tune can induce harmful behaviors far outside the target domain. Even in the case where model weights are hidden behind a fine-tuning API, this gives attackers inadvertent access to a broadly misaligned model in a way that can be hard to detect from the fine-tuning data alone. We present the first systematic study of in-training safeguards against EMA that are practical for providers who expose fine-tuning via an API. We investigate four training regularization interventions: (i) KL-divergence regularization toward a safe reference model, (ii) $\ell_2$ distance in feature space, (iii) projecting onto a safe subspace (SafeLoRA), and (iv) interleaving of a small amount of safe training examples from a general instruct-tuning dataset. We first evaluate the methods' emergent misalignment effect across four malicious, EMA-inducing tasks. Second, we assess the methods' impacts on benign tasks. We conclude with a discussion of open questions in emergent misalignment research.
【8】Adaptive Backtracking for Privacy Protection in Large Language Models
标题：大型语言模型中隐私保护的自适应回溯
链接：https://arxiv.org/abs/2508.06087
摘要：隐私保护已成为人工智能时代的一个关键话题。然而，目前的工作重点是面向用户的隐私，忽视了严重的企业数据泄露风险加剧了检索增强生成范式。为了解决这一差距，我们的论文介绍了一个新的目标：面向企业的隐私问题。实现这一目标需要克服两个基本挑战：现有的方法，如数据净化严重降低模型性能，该领域缺乏公共数据集进行评估。我们通过多种解决方案来应对这些挑战。(1)为了防止性能下降，我们提出了ABack，这是一种无需训练的机制，它利用隐藏状态模型来查明泄漏意图的起源并安全地重写输出。(2)为了解决数据集的缺乏，我们构建了PriGenQA，这是医疗保健和金融领域企业隐私场景的新基准。为了确保严格的评估，我们超越了简单的静态攻击，开发了一个强大的自适应攻击与组相对策略优化。实验表明，针对这种优越的对手，ABack提高了整体隐私效用得分高达15%以上的强基线，避免了以前的方法的性能权衡。
摘要：The preservation of privacy has emerged as a critical topic in the era of artificial intelligence. However, current work focuses on user-oriented privacy, overlooking severe enterprise data leakage risks exacerbated by the Retrieval-Augmented Generation paradigm. To address this gap, our paper introduces a novel objective: enterprise-oriented privacy concerns. Achieving this objective requires overcoming two fundamental challenges: existing methods such as data sanitization severely degrade model performance, and the field lacks public datasets for evaluation. We address these challenges with several solutions. (1) To prevent performance degradation, we propose ABack, a training-free mechanism that leverages a Hidden State Model to pinpoint the origin of a leakage intention and rewrite the output safely. (2) To solve the lack of datasets, we construct PriGenQA, a new benchmark for enterprise privacy scenarios in healthcare and finance. To ensure a rigorous evaluation, we move beyond simple static attacks by developing a powerful adaptive attacker with Group Relative Policy Optimization. Experiments show that against this superior adversary, ABack improves the overall privacy utility score by up to 15\% over strong baselines, avoiding the performance trade-offs of prior methods.
【9】DP-LLM: Runtime Model Adaptation with Dynamic Layer-wise Precision Assignment
标题：DP-LLM：具有动态分层精度分配的NPS模型自适应
链接：https://arxiv.org/abs/2508.06041
摘要：我们如何有效地处理具有不同运行时约束（如延迟和准确性）的设备上大型语言模型（LLM）的查询？多尺度量化通过叠加量化为不同位宽的多个模型变量来实现LLM的存储器高效运行时模型自适应，从而解决了这一挑战。与此同时，一个重要的问题仍然是开放式的：如何正确配置模型以匹配目标精度或延迟？虽然混合精度提供了一个很有前途的解决方案，但我们通过利用每个层的灵敏度在解码迭代中动态变化的关键观察结果来进一步实现这一点。基于这一认识，我们引入了DP-LLM，这是一种新的机制，可以根据输入值动态地为每个层分配精度。DP-LLM使用精度选择器来增强LLM中的每个线性层，该精度选择器使用轻量级误差估计器和通过微调学习的阈值来确定运行时的位宽。多个模型和基准测试的实验结果表明，DP-LLM实现了卓越的性能-延迟权衡，优于先前的方法。
摘要：How can we effectively handle queries for on-device large language models (LLMs) with varying runtime constraints, such as latency and accuracy? Multi-scale quantization addresses this challenge by enabling memory-efficient runtime model adaptation of LLMs through the overlaying of multiple model variants quantized to different bitwidths. Meanwhile, an important question still remains open-ended: how can models be properly configured to match a target precision or latency? While mixed-precision offers a promising solution, we take this further by leveraging the key observation that the sensitivity of each layer dynamically changes across decoding iterations. Building on this insight, we introduce DP-LLM, a novel mechanism that dynamically assigns precision to each layer based on input values. DP-LLM augments each linear layer in an LLM with a precision selector that determines the bitwidth at runtime using a lightweight error estimator and threshold values learned through fine-tuning. Experimental results across multiple models and benchmarks demonstrate that DP-LLM achieves a superior performance-latency trade-off, outperforming prior approaches.
【10】Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddings
标题：通过调整预先训练的嵌入对大型语言模型进行高效知识探索
链接：https://arxiv.org/abs/2508.06030
摘要：大型语言模型（LLM）在生成式预训练过程中获得跨不同领域的知识，例如科学，历史和地理。然而，由于它们的随机性，很难预测LLM已经获得了什么。先前的工作已经开发了不同的方法来探索这种知识，通过调查隐藏的表示，制作特定的任务提示，策划代表性样本，并估计其不确定性。然而，这些方法需要通过底层模型进行正向传递，以探测LLM关于特定事实的知识，这使得它们在计算上昂贵且耗时。为了弥合这一差距，我们提出了$\textbf{PEEK}$或$\textbf{P}$roxy $\textbf{E}$mbeddings来$\textbf {E}$估计LLM的$\textbf{K}$nobody，通过利用预训练的嵌入模型，有效地将事实知识编码为文本或图形作为LLM的代理。首先，我们通过各种探测策略识别LLM已知的事实的训练集，然后调整嵌入模型以使用线性解码器层预测LLM输出。对$3$维基百科衍生数据集，$4$LLM和$7$嵌入模型的综合评估表明，嵌入可以预测LLM知识，准确率高达90%。此外，我们发现句子嵌入模型比图嵌入更适合预测LLM知识，从而揭示了事实景观的底层表示。因此，我们认为，知识适应嵌入可以用来识别大规模LLM中的知识缺口，并可以提供更深入的见解LLM的内部归纳偏见。代码和数据可在https://github.com/claws-lab/peek上获得。
摘要：Large language models (LLMs) acquire knowledge across diverse domains such as science, history, and geography encountered during generative pre-training. However, due to their stochasticity, it is difficult to predict what LLMs have acquired. Prior work has developed different ways to probe this knowledge by investigating the hidden representations, crafting specific task prompts, curating representative samples, and estimating their uncertainty. However, these methods require making forward passes through the underlying model to probe the LLM's knowledge about a specific fact, making them computationally expensive and time-consuming. To bridge this gap, we propose $\textbf{PEEK}$ or $\textbf{P}$roxy $\textbf{E}$mbeddings to $\textbf{E}$stimate $\textbf{K}$nowledge of LLMs, by leveraging the pre-trained embedding models that effectively encode factual knowledge as text or graphs as proxies for LLMs. First, we identify a training set of facts known by LLMs through various probing strategies and then adapt embedding models to predict the LLM outputs with a linear decoder layer. Comprehensive evaluation on $3$ Wikipedia-derived datasets, $4$ LLMs, and $7$ embedding models shows that embeddings can predict LLM knowledge on a held-out set with up to 90 % accuracy. Furthermore, we find that sentence embedding models are more suitable than graph embeddings to predict LLM knowledge, shedding light on the underlying representation of the factual landscape. Thus, we believe that knowledge-adapted embeddings can be used to identify knowledge gaps in LLMs at scale and can provide deeper insights into LLMs' internal inductive bias. The code and data are made available at https://github.com/claws-lab/peek.
【11】Optimizing Prompt Sequences using Monte Carlo Tree Search for LLM-Based Optimization
标题：使用蒙特卡罗树搜索优化提示序列基于LLM的优化
链接：https://arxiv.org/abs/2508.05995
摘要：大型语言模型（LLM）在代码生成和结构化推理方面表现出了卓越的能力;然而，在需要一致的多步规划的复杂任务中，它们的性能往往会下降。最近的工作已经探索了将LLM与Monte Carlo Tree Search（MCTS）相结合，但现有的方法主要集中在生成基于算法的代码以进行优化或针对简单的任务，其中仅正确性就足够了。在这项工作中，我们提出了MCTS-OPS，一种新的神经符号框架，制定迅速选择作为一个顺序的决策过程指导MCTS。我们的方法探索和细化多步提示序列的目标，提高代码生成质量和提高LLM在一般优化的解决问题的能力。网络优化的实验表明，无论是在执行生成的代码的成功率，并在优化结果与指定的目标和约束（2$\sim$4$\times$高奖励和3$\times$低标准差）的基线显着改善。此外，它提高了约10%的情况下，获得最佳解决方案的机会相比，在困难的问题的基线方法。这些结果突出了符号规划与LLM相结合的承诺，在复杂的领域中强大的，高质量的代码生成。
摘要：Large language models (LLMs) have demonstrated remarkable capabilities in code generation and structured reasoning; however, their performance often degrades on complex tasks that require consistent multi-step planning. Recent work has explored combining LLMs with Monte Carlo Tree Search (MCTS), yet existing approaches primarily focus on generating heuristic-based code for optimization or target simpler tasks where correctness alone is sufficient. In this work, we propose MCTS-OPS, a novel neural-symbolic framework that formulates prompt selection as a sequential decision process guided by MCTS. Our method explores and refines multi-step prompt sequences for the goal of improving code generation quality and enhancing the problem-solving capabilities of LLMs in general optimization. Experiments on network optimization show significant improvement over the baselines, both in the success rate of executing the generated code and in the optimization results with the specified objective and constraints (2$\sim$4$\times$ higher reward and 3$\times$ lower standard deviation). Moreover, it improves the chance of attaining the optimal solution by about 10\% of cases, compared to baseline methods in hard problems. These results highlight the promise of combining symbolic planning with LLMs for robust, high-quality code generation in complex domains.
【12】Mitigating Think-Answer Mismatch in LLM Reasoning Through Noise-Aware Advantage Reweighting
标题：通过噪音感知优势重新加权来缓解LLM推理中的思维-答案不匹配
链接：https://arxiv.org/abs/2508.05928
摘要：组相对策略优化（GRPO）是训练大型推理模型的关键技术，但它存在一个严重的漏洞：思考-回答不匹配，其中嘈杂的奖励信号破坏了学习过程。这个问题在反应不平衡的群体中最为严重，矛盾的是，恰恰在信号应该提供最多信息的时候，它却降低了信号的质量。为了应对这一挑战，我们提出了稳定的组相对策略优化（S-GRPO），这是一种原则性的增强，可以获得最佳的、噪声感知的优势权重来稳定训练。在数学推理基准上的综合实验证明了S-GRPO的有效性和鲁棒性。在各种型号上，S-GRPO的性能明显优于DR. GRPO，在Qwen-Math-7B-Base上实现了+2.5%的性能提升，在Llama-3.2 - 3B-Base上实现了+2.2%的性能提升，在Qwen-Math-1. 5B-Instruct上实现了+2.4%的性能提升。最关键的是，虽然标准GRPO在20%的合成奖励噪声下无法学习，但S-GRPO保持稳定的学习进度。这些结果突出了S-GRPO的潜力，更强大，更有效的训练大规模的推理模型。\footnote {代码和数据可在www.example.com上获得
摘要：Group-Relative Policy Optimization (GRPO) is a key technique for training large reasoning models, yet it suffers from a critical vulnerability: the \emph{Think-Answer Mismatch}, where noisy reward signals corrupt the learning process. This problem is most severe in unbalanced response groups, paradoxically degrading the signal precisely when it should be most informative. To address this challenge, we propose Stable Group-Relative Policy Optimization (S-GRPO), a principled enhancement that derives optimal, noise-aware advantage weights to stabilize training. Our comprehensive experiments on mathematical reasoning benchmarks demonstrate S-GRPO's effectiveness and robustness. On various models, S-GRPO significantly outperforms DR. GRPO, achieving performance gains of +2.5% on Qwen-Math-7B-Base, +2.2% on Llama-3.2-3B-Base, and +2.4% on Qwen-Math-1.5B-Instruct. Most critically, while standard GRPO fails to learn under 20% synthetic reward noise, S-GRPO maintains stable learning progress. These results highlight S-GRPO's potential for more robust and effective training of large-scale reasoning models. \footnote{Code and data are available at: https://github.com/shenpeijun0212/S-GRPO
【13】The Fourth State: Signed-Zero Ternary for Stable LLM Quantization (and More)
标题：第四种状态：稳定LLM量化的符号零三进制（及更多）
链接：https://arxiv.org/abs/2508.05905
摘要：量化通常被认为是一种以性能质量换取降低的计算要求的手段，即，作为次优近似。然而，如果从固定的总资源预算角度来审视，就会产生一种非常不同的观点。我们引入符号零三进制（SZT），2位量化，确定性地提供梯度信息，没有前向路径惩罚。我们的分析提供的证据表明，它可以提高信息密度相比，非量化的替代品。
摘要：Quantization is usually regarded as a means to trade quality of performance for reduced compute requirements, i.e., as a suboptimal approximation. However, if examined in terms of a fixed overall resource budget, a very different perspective arises. We introduce Signed-Zero Ternary (SZT), a 2-bit quantization that deterministically provides gradient information with no forward-path penalty. Our analysis provides evidence that it may improve information density compared to non-quantized alternatives.
【14】Leveraging large language models for SQL behavior-based database intrusion detection
标题：利用大型语言模型进行基于SQL行为的数据库入侵检测
链接：https://arxiv.org/abs/2508.05690
摘要：数据库系统广泛用于存储跨各种域的关键数据。然而，异常数据库访问行为的频率，如内部和外部攻击的数据库入侵，持续上升。内部伪装者通常拥有更多的组织知识，更容易有效地模仿员工的行为。相比之下，外部伪装者可能会表现得不同，因为他们对组织缺乏了解。当前的方法缺乏在操作级别检测异常所需的粒度，经常将整个操作序列误分类为异常，即使大多数操作可能代表正常行为。另一方面，一些异常行为通常与正常活动相似，使得现有的检测方法难以识别。本文介绍了一种两层的结构化查询语言（SQL）的异常检测方法，使用双向编码器表示从Transformers（BERT）模型，特别是蒸馏BERT，一个更有效的，预先训练的版本。我们的方法结合了无监督和有监督的机器学习技术，以准确识别异常活动，同时最大限度地减少对数据标记的需求。首先，无监督方法使用集合异常检测器，其标记远离数据库中典型用户行为的学习正常模式的嵌入向量（范围外查询）。其次，监督方法使用微调的基于transformer的模型来检测高精度的内部攻击（范围内查询），使用角色标记分类，即使是在有限的标记SQL数据上。我们的研究结果通过提供有效的解决方案来保护关键数据库系统免受复杂的威胁，从而做出了重大贡献。
摘要 ：Database systems are extensively used to store critical data across various domains. However, the frequency of abnormal database access behaviors, such as database intrusion by internal and external attacks, continues to rise. Internal masqueraders often have greater organizational knowledge, making it easier to mimic employee behavior effectively. In contrast, external masqueraders may behave differently due to their lack of familiarity with the organization. Current approaches lack the granularity needed to detect anomalies at the operational level, frequently misclassifying entire sequences of operations as anomalies, even though most operations are likely to represent normal behavior. On the other hand, some anomalous behaviors often resemble normal activities, making them difficult for existing detection methods to identify. This paper introduces a two-tiered anomaly detection approach for Structured Query Language (SQL) using the Bidirectional Encoder Representations from Transformers (BERT) model, specifically DistilBERT, a more efficient, pre-trained version. Our method combines both unsupervised and supervised machine learning techniques to accurately identify anomalous activities while minimizing the need for data labeling. First, the unsupervised method uses ensemble anomaly detectors that flag embedding vectors distant from learned normal patterns of typical user behavior across the database (out-of-scope queries). Second, the supervised method uses fine-tuned transformer-based models to detect internal attacks with high precision (in-scope queries), using role-labeled classification, even on limited labeled SQL data. Our findings make a significant contribution by providing an effective solution for safeguarding critical database systems from sophisticated threats.
【15】MM-FusionNet: Context-Aware Dynamic Fusion for Multi-modal Fake News Detection with Large Vision-Language Models
标题：MM-FusionNet：上下文感知动态融合，用于使用大型视觉语言模型的多模式假新闻检测
链接：https://arxiv.org/abs/2508.05684
摘要：社交媒体上多模态假新闻的泛滥对公众信任和社会稳定构成了重大威胁。传统的检测方法，主要是基于文本的，往往由于误导性文本和图像之间的欺骗性相互作用而不足。虽然大型视觉语言模型（LVLM）为多模态理解提供了有希望的途径，但有效融合不同的模态信息，特别是当它们的重要性不平衡或矛盾时，仍然是一个关键的挑战。本文介绍了MM-FusionNet，这是一个利用LVLM进行鲁棒多模态假新闻检测的创新框架。我们的核心贡献是上下文感知动态融合模块（CADFM），它采用双向跨模态注意力和一种新的动态模态门控网络。该机制基于文本和视觉特征的上下文相关性自适应地学习和分配重要性权重，从而实现信息的智能优先级排序。在包含80，000个样本的大规模多模态假新闻数据集（LMFND）上进行评估，MM-FusionNet达到了最先进的F1分数0.938，超过了现有的多模态基线约0.5%，并显著优于单模态方法。进一步的分析证明了该模型的动态加权能力，对模态扰动的鲁棒性，以及非常接近人类水平的性能，强调了其在真实世界假新闻检测中的实际有效性和可解释性。
摘要：The proliferation of multi-modal fake news on social media poses a significant threat to public trust and social stability. Traditional detection methods, primarily text-based, often fall short due to the deceptive interplay between misleading text and images. While Large Vision-Language Models (LVLMs) offer promising avenues for multi-modal understanding, effectively fusing diverse modal information, especially when their importance is imbalanced or contradictory, remains a critical challenge. This paper introduces MM-FusionNet, an innovative framework leveraging LVLMs for robust multi-modal fake news detection. Our core contribution is the Context-Aware Dynamic Fusion Module (CADFM), which employs bi-directional cross-modal attention and a novel dynamic modal gating network. This mechanism adaptively learns and assigns importance weights to textual and visual features based on their contextual relevance, enabling intelligent prioritization of information. Evaluated on the large-scale Multi-modal Fake News Dataset (LMFND) comprising 80,000 samples, MM-FusionNet achieves a state-of-the-art F1-score of 0.938, surpassing existing multi-modal baselines by approximately 0.5% and significantly outperforming single-modal approaches. Further analysis demonstrates the model's dynamic weighting capabilities, its robustness to modality perturbations, and performance remarkably close to human-level, underscoring its practical efficacy and interpretability for real-world fake news detection.
【16】Fine-Tuning Vision-Language Models for Markdown Conversion of Financial Tables in Malaysian Audited Financial Reports
标题：马来西亚审计财务报告中财务表降价转换的微调视觉语言模型
链接：https://arxiv.org/abs/2508.05669
备注：28 pages, 14 figures, 5 tables. Evaluation code (LLM-as-a-judge and Markdown TEDS) is available at this https URL. The development dataset and evaluation benchmark are available on Hugging Face at this https URL and this https URL respectively
摘要：从财务文档中准确提取和表示表格数据的结构仍然是文档理解的关键挑战，特别是对于监管和分析用例。这项研究解决了从马来西亚审计财务报告转换为Markdown格式的财务表的复杂性，旋转布局，多级标题和隐式结构线索复杂的任务。我们提出了一个微调的视觉语言模型（VLM），基于Qwen2.5-VL-7 B，针对从文档图像生成高保真Markdown进行了优化。我们的方法包括一个包含2，152个图像-文本对的精选数据集，以及使用LoRA的监督微调策略。为了评估性能，我们使用双重框架在100个样本表上评估了我们的模型：基于标准的LLM作为细粒度准确性的判断，以及我们新颖的基于Markdown树编辑距离的相似性（TEDS）度量，用于整体结构保真度。我们的模型在基于标准的评估中达到了92.20%的总体准确率和96.53%的Markdown TEDS得分。这一性能大大超过了Qwen2.5-VL-7 B基础模型、更大规模的VLM和支持推理的专用模型。与这些自托管的替代方案相比，它还显着减少了推理时间。此外，它的准确性超过了广泛使用的专有模型，如OpenAI的GPT-4 o和Gemini 2.5 Flash。这些结果表明，特定领域的微调提供了一种有效和高效的方法来弥合非结构化财务文档和下游自动化之间的差距，可以在没有计算开销的情况下与更大和更通用的模型相媲美。
摘要：Accurately extracting and representing the structure of tabular data from financial documents remains a critical challenge in document understanding, particularly for regulatory and analytical use cases. This study addresses the complexity of converting financial tables from Malaysian audited financial reports into Markdown format, a task complicated by rotated layouts, multi-level headers, and implicit structural cues. We propose a fine-tuned vision-language model (VLM), based on Qwen2.5-VL-7B, optimized for high-fidelity Markdown generation from document images. Our approach includes a curated dataset of 2,152 image-text pairs with augmentations and a supervised fine-tuning strategy using LoRA. To assess performance, we evaluated our model on 100 out-of-sample tables using a dual framework: a criteria-based LLM-as-a-judge for fine-grained accuracy and our novel Markdown Tree-Edit-Distance-based Similarity (TEDS) metric for holistic structural fidelity. Our model achieves a 92.20% overall accuracy on the criteria-based assessment and a 96.53% Markdown TEDS score. This performance significantly surpasses its Qwen2.5-VL-7B base model, larger-scale VLMs, and specialized reasoning-enabled models. Compared to these self-hosted alternatives, it also significantly reduces inference time. Furthermore, its accuracy exceeds that of widely used proprietary models such as OpenAI's GPT-4o and Gemini 2.5 Flash. These results demonstrate that domain-specific fine-tuning provides an effective and efficient method to bridge the gap between unstructured financial documents and downstream automation, rivalling much larger and more general models without their computational overhead.
【17】AttriLens-Mol: Attribute Guided Reinforcement Learning for Molecular Property Prediction with Large Language Models
标题：AttriLens-Mol：使用大型语言模型进行分子性质预测的属性引导强化学习
链接：https://arxiv.org/abs/2508.04748
备注：9 pages
摘要：大型语言模型（LLM）在协助分子性质预测任务方面表现出了希望，但通常依赖于人工制作的提示和思维链模板。虽然最近的高级大型推理模型，如DeepSeek-R1，采用强化学习来扩展“思考”过程，但它们的推理可能是冗长的，缺乏相关性。我们介绍了AttriLens-Mol，这是一个用于LLM分子性质预测的属性引导强化学习框架。AttriLens-Mol通过以下方式引导模型的推理：（1）鼓励基于属性的结构化输出的格式奖励，（2）避免枚举不相关属性的计数奖励，以及（3）使用高级LLM和RDKit验证生成属性的相关性的合理性奖励。这种方法在推理过程中隐含地引出模型对相关分子属性的固有知识，使得能够更有效地对分子属性进行预测。在分布内和分布外数据集上的实验表明，使用我们提出的AttriLens-Mol方法在4，000个样本上训练7 B大小的R1-Distilled-Qwen 2.5和R1-Distilled-LLaMA 3.1模型显着提高了性能，获得了与监督微调模型（Mol-Instructions，ChemDFM等）相当或更好的结果。和先进型号（GPT-3.5、GPT-4 o、DeepSeek-V3、DeepSeek-R1等）。此外，我们提取的目标属性，当用作可解释的决策树模型的特征时，与提示LLM生成的属性相比，会产生更好的性能。这表明AttriLens-Mol有效地消除了更多相关和预测性的分子属性，从而增强了属性预测的可解释性和性能。我们将在https://github.com/szu-tera/AttriLens-Mol中发布代码。
摘要 ：Large Language Models (LLMs) have shown promise in assisting molecular property prediction tasks but often rely on human-crafted prompts and chain-of-thought templates. While recent advanced large reasoning models like DeepSeek-R1 employ reinforcement learning for an extended ``thinking'' process, their reasoning can be verbose and lack relevance. We introduce AttriLens-Mol, an attribute-guided reinforcement learning framework for molecular property prediction with LLMs. AttriLens-Mol steers the model's reasoning by using: (1) a format reward encouraging attribute-based structured output, (2) a count reward to avoid enumerating irrelevant attributes, and (3) a rationality reward using advanced LLMs and RDKit to verify the relatedness of the generated attributes. This approach implicitly elicits the model's inherent knowledge of relevant molecular attributes during reasoning, enables making predictions for the molecular property more effectively. Experiments on both in-distribution and out-of-distribution datasets show that, training both 7B-size R1-Distilled-Qwen2.5 and R1-Distilled-LLaMA3.1 models on 4,000 samples with our proposed AttriLens-Mol method significantly boosts the performance, getting comparable or better results than supervised fine-tuning models (Mol-Instructions, ChemDFM, etc.) and advanced models (GPT-3.5, GPT-4o, DeepSeek-V3, DeepSeek-R1, etc.). Further, our extracted attributes for the target property, when used as features for an interpretable decision tree model, yield superior performance compared to attributes generated by prompting LLMs. This shows that AttriLens-Mol effectively elicits more relevant and predictive molecular attributes, leading to enhanced interpretability and performance for property prediction. We release the code in https://github.com/szu-tera/AttriLens-Mol.
【18】LLM Serving Optimization with Variable Prefill and Decode Lengths
标题：使用可变预填充和解码LLM服务优化
链接：https://arxiv.org/abs/2508.06133
摘要：我们研究的问题，服务LLM（大语言模型）的请求，每个请求具有异构的预填充和解码长度。在LLM服务中，预填充长度对应于输入提示长度，其确定KV缓存中的初始内存使用。解码长度是指顺序生成的输出令牌的数量，每个额外的令牌将KV高速缓存使用量增加一个单位。给定一组n个请求，我们的目标是调度和处理它们，以最小化总完成时间。我们发现，这个问题是NP-难的，由于相互作用的布局，位置约束，优先关系，和线性增加内存使用。然后，我们分析了常用的调度策略在实践中，如先来先服务（FCFS）和最短的第一（SF），并证明其竞争比规模次线性的内存限制，一个显着的缺点，在现实世界中的设置，内存需求很大。为了解决这个问题，我们提出了一种新的算法的基础上，一个新的选择度量，有效地形成批次随着时间的推移。我们证明了该算法实现了一个常数的竞争比。最后，我们开发和评估了一些受这种方法启发的算法变体，包括动态编程变体，局部搜索方法和基于LP的调度程序，通过全面的模拟证明它们在保持计算效率的同时优于标准基线。
摘要：We study the problem of serving LLM (Large Language Model) requests where each request has heterogeneous prefill and decode lengths. In LLM serving, the prefill length corresponds to the input prompt length, which determines the initial memory usage in the KV cache. The decode length refers to the number of output tokens generated sequentially, with each additional token increasing the KV cache memory usage by one unit. Given a set of n requests, our goal is to schedule and process them to minimize the total completion time. We show that this problem is NP-hard due to the interplay of batching, placement constraints, precedence relationships, and linearly increasing memory usage. We then analyze commonly used scheduling strategies in practice, such as First-Come-First-Serve (FCFS) and Shortest-First (SF), and prove that their competitive ratios scale up sublinearly with the memory limit-a significant drawback in real-world settings where memory demand is large. To address this, we propose a novel algorithm based on a new selection metric that efficiently forms batches over time. We prove that this algorithm achieves a constant competitive ratio. Finally, we develop and evaluate a few algorithm variants inspired by this approach, including dynamic programming variants, local search methods, and an LP-based scheduler, demonstrating through comprehensive simulations that they outperform standard baselines while maintaining computational efficiency.
Graph相关(图学习|图神经网络|图优化等)(7篇)
【1】Harnessing Adaptive Topology Representations for Zero-Shot Graph Question Answering
标题：利用自适应的拓扑表示进行Zero-Shot图问题解答
链接：https://arxiv.org/abs/2508.06345
摘要：大型多模态模型（LLM）在不同领域的问答（QA）任务中表现出广义的zero-shot能力，包括涉及复杂图拓扑的图QA。然而，大多数当前的方法只使用单一类型的图表示，即拓扑表示形式（TRF），如非统一的文本描述或样式固定的视觉样式。这些“一刀切”的方法没有考虑到不同模型或任务的具体偏好，往往导致不正确或过长的答复。为了解决这个问题，我们首先分析了现有的TRFs的特点和弱点，然后设计了一组TRFs，表示为$F_{ZS}$，适合于zero-shot图QA。然后，我们引入了一个新的度量，图响应效率（GRE），它衡量的性能和简洁性之间的平衡图QA。在此基础上，我们开发了DynamicTRF框架，旨在提高图QA的准确性和简洁性。具体来说，DynamicTRF首先创建一个TRF偏好（TRFP）数据集，该数据集根据GRE分数对TRF进行排名，以探测特定于问题的TRF偏好。然后在TRFP数据集上训练TRF路由器，在推理过程中为每个问题自适应地分配来自$F_{ZS}$的最佳TRF。在7个域内算法图QA任务和2个域外下游任务上的大量实验表明，DynamicTRF在准确性方面显著增强了LSTO的zero-shot图QA
摘要：Large Multimodal Models (LMMs) have shown generalized zero-shot capabilities in diverse domain question-answering (QA) tasks, including graph QA that involves complex graph topologies. However, most current approaches use only a single type of graph representation, namely Topology Representation Form (TRF), such as prompt-unified text descriptions or style-fixed visual styles. Those "one-size-fits-all" approaches fail to consider the specific preferences of different models or tasks, often leading to incorrect or overly long responses. To address this, we first analyze the characteristics and weaknesses of existing TRFs, and then design a set of TRFs, denoted by $F_{ZS}$, tailored to zero-shot graph QA. We then introduce a new metric, Graph Response Efficiency (GRE), which measures the balance between the performance and the brevity in graph QA. Built on these, we develop the DynamicTRF framework, which aims to improve both the accuracy and conciseness of graph QA. To be specific, DynamicTRF first creates a TRF Preference (TRFP) dataset that ranks TRFs based on their GRE scores, to probe the question-specific TRF preferences. Then it trains a TRF router on the TRFP dataset, to adaptively assign the best TRF from $F_{ZS}$ for each question during the inference. Extensive experiments across 7 in-domain algorithmic graph QA tasks and 2 out-of-domain downstream tasks show that DynamicTRF significantly enhances the zero-shot graph QA of LMMs in terms of accuracy
【2】Multi-Omics Analysis for Cancer Subtype Inference via Unrolling Graph Smoothness Priors
标题：通过展开图光滑性先验进行癌症亚型推断的多组学分析
链接：https://arxiv.org/abs/2508.06257
摘要：通过数据驱动分析整合多组学数据集，可以全面了解各种疾病（特别是癌症）背后的复杂生物学过程。图神经网络（GNN）最近展示了利用生物数据中的关系结构的卓越能力，使癌症亚型分类的多组学整合取得了进展。现有的方法往往忽视了异质组学之间的复杂耦合，限制了它们解决精细癌症亚型异质性的能力，这对精确肿瘤学至关重要。为了解决这些局限性，我们提出了一个框架命名为图Transformer的多组学癌症亚型分类（GTMancer）。该框架基于GNN优化问题，并将其应用扩展到复杂的多组学数据。具体来说，我们的方法利用对比学习将多组学数据嵌入到统一的语义空间中。我们在统一空间中展开多重图优化问题，并引入双组注意力系数来捕获多组学数据内和多组学数据之间的结构图先验。这种方法使全局组学信息能够指导个体组学表示的细化。在七个真实世界癌症数据集上的实证实验表明，GTMancer优于现有的最先进的算法。
摘要 ：Integrating multi-omics datasets through data-driven analysis offers a comprehensive understanding of the complex biological processes underlying various diseases, particularly cancer. Graph Neural Networks (GNNs) have recently demonstrated remarkable ability to exploit relational structures in biological data, enabling advances in multi-omics integration for cancer subtype classification. Existing approaches often neglect the intricate coupling between heterogeneous omics, limiting their capacity to resolve subtle cancer subtype heterogeneity critical for precision oncology. To address these limitations, we propose a framework named Graph Transformer for Multi-omics Cancer Subtype Classification (GTMancer). This framework builds upon the GNN optimization problem and extends its application to complex multi-omics data. Specifically, our method leverages contrastive learning to embed multi-omics data into a unified semantic space. We unroll the multiplex graph optimization problem in that unified space and introduce dual sets of attention coefficients to capture structural graph priors both within and among multi-omics data. This approach enables global omics information to guide the refining of the representations of individual omics. Empirical experiments on seven real-world cancer datasets demonstrate that GTMancer outperforms existing state-of-the-art algorithms.
【3】Graph Federated Learning for Personalized Privacy Recommendation
标题：基于图联邦学习的个性化隐私推荐
链接：https://arxiv.org/abs/2508.06208
摘要：联邦推荐系统（FedRecs）已经获得了显着的关注，提供隐私保护的推荐服务。然而，现有的FedRecs假设所有用户都有相同的隐私保护要求，即，他们不上传任何数据到服务器。这些方法忽略了通过利用公开的用户数据来增强推荐服务的潜力。在现实世界的应用程序中，用户可以选择私有或公共。私人用户的交互数据不共享，而公共用户的交互数据可以共享。受此启发，本文提出了一种新的基于图联邦学习的个性化隐私推荐算法（GFed-PP），该算法能够适应不同的隐私需求，同时提高推荐性能。GFed-PP结合公共用户的交互数据构建用户-项目交互图，然后使用该交互图形成用户关系图。采用轻量级图卷积网络（GCN）来学习每个用户的用户特定的个性化项目嵌入。为了保护用户隐私，每个客户端在本地学习用户嵌入和评分函数。此外，GFed-PP通过在客户端初始化项目嵌入和在服务器端聚合用户关系图来实现联邦推荐框架的优化。实验结果表明，GFed-PP在五个数据集上的性能明显优于现有方法，在不影响隐私的情况下提供了更高的推荐准确率。该框架提供了一个实用的解决方案，以适应不同的隐私偏好在联邦推荐系统。
摘要：Federated recommendation systems (FedRecs) have gained significant attention for providing privacy-preserving recommendation services. However, existing FedRecs assume that all users have the same requirements for privacy protection, i.e., they do not upload any data to the server. The approaches overlook the potential to enhance the recommendation service by utilizing publicly available user data. In real-world applications, users can choose to be private or public. Private users' interaction data is not shared, while public users' interaction data can be shared. Inspired by the issue, this paper proposes a novel Graph Federated Learning for Personalized Privacy Recommendation (GFed-PP) that adapts to different privacy requirements while improving recommendation performance. GFed-PP incorporates the interaction data of public users to build a user-item interaction graph, which is then used to form a user relationship graph. A lightweight graph convolutional network (GCN) is employed to learn each user's user-specific personalized item embedding. To protect user privacy, each client learns the user embedding and the scoring function locally. Additionally, GFed-PP achieves optimization of the federated recommendation framework through the initialization of item embedding on clients and the aggregation of the user relationship graph on the server. Experimental results demonstrate that GFed-PP significantly outperforms existing methods for five datasets, offering superior recommendation accuracy without compromising privacy. This framework provides a practical solution for accommodating varying privacy preferences in federated recommendation systems.
【4】Adaptive Heterogeneous Graph Neural Networks: Bridging Heterophily and Heterogeneity
标题：自适应异类图神经网络：弥合异类与异类
链接：https://arxiv.org/abs/2508.06034
备注：Accepted tp CIKM 2025
摘要：异构图（HGs）在现实世界中很常见，并且经常表现出异质性。然而，大多数现有的研究集中在异质性或异嗜性孤立，忽视了异嗜性HGs在实际应用中的流行。这种无知导致他们的性能下降。在这项工作中，我们首先确定了两个主要的挑战，在建模heterophily HG：（1）不同的hops和元路径的heterophily分布;（2）复杂的，往往heterophily驱动的语义信息的多样性在不同的元路径。然后，我们提出了自适应异构图神经网络（AHGNN）来解决这些挑战。AHGNN采用了一种异质性感知卷积，该卷积考虑了特定于跳和元路径的异质性分布。然后，它使用从粗到细的注意力机制整合来自不同语义空间的消息，该机制过滤掉噪音并强调信息信号。七个真实世界的图形和20个基线上的实验证明了AHGNN的优越性能，特别是在高度异质性的情况下。
摘要：Heterogeneous graphs (HGs) are common in real-world scenarios and often exhibit heterophily. However, most existing studies focus on either heterogeneity or heterophily in isolation, overlooking the prevalence of heterophilic HGs in practical applications. Such ignorance leads to their performance degradation. In this work, we first identify two main challenges in modeling heterophily HGs: (1) varying heterophily distributions across hops and meta-paths; (2) the intricate and often heterophily-driven diversity of semantic information across different meta-paths. Then, we propose the Adaptive Heterogeneous Graph Neural Network (AHGNN) to tackle these challenges. AHGNN employs a heterophily-aware convolution that accounts for heterophily distributions specific to both hops and meta-paths. It then integrates messages from diverse semantic spaces using a coarse-to-fine attention mechanism, which filters out noise and emphasizes informative signals. Experiments on seven real-world graphs and twenty baselines demonstrate the superior performance of AHGNN, particularly in high-heterophily situations.
【5】An Effective Approach for Node Classification in Textual Graphs
标题：文本图中节点分类的一种有效方法
链接：https://arxiv.org/abs/2508.05836
摘要：文本属性图（TAG）对于建模复杂网络（如引文网络）至关重要，但由于难以将文本的丰富语义与结构图信息集成，因此有效的节点分类仍然具有挑战性。现有的方法通常难以捕捉细微的特定领域术语，建模长期依赖关系，适应时间演变以及扩展到大规模数据集。为了解决这些问题，我们提出了一个新的框架，集成TAPE（文本属性图表示增强）与Graphormer。我们的方法利用TAPE框架内的大型语言模型（LLM），特别是ChatGPT，从论文内容中生成语义丰富的解释，然后将其融合到增强的节点表示中。这些嵌入与结构特征相结合，使用具有学习注意力权重的新型集成层。Graphormer的路径感知位置编码和多头注意机制被用来有效地捕捉整个引文网络的长距离依赖关系。我们证明了我们的框架在具有挑战性的ogbn-arxiv数据集上的有效性，实现了最先进的性能，分类准确率为0.772，显著超过了最佳GCN基线0.713。我们的方法在精确度（0.671），召回率（0.577）和F1得分（0.610）方面也取得了很好的结果。我们通过全面的消融研究来验证我们的方法，这些研究量化了每个组件的贡献，展示了语义和结构信息之间的协同作用。我们的框架提供了一个可扩展的和强大的解决方案，在动态标签的节点分类，提供了一个有前途的方向，为未来的研究，知识系统和科学发现。
摘要：Textual Attribute Graphs (TAGs) are critical for modeling complex networks like citation networks, but effective node classification remains challenging due to difficulties in integrating rich semantics from text with structural graph information. Existing methods often struggle with capturing nuanced domain-specific terminology, modeling long-range dependencies, adapting to temporal evolution, and scaling to massive datasets. To address these issues, we propose a novel framework that integrates TAPE (Text-Attributed Graph Representation Enhancement) with Graphormer. Our approach leverages a large language model (LLM), specifically ChatGPT, within the TAPE framework to generate semantically rich explanations from paper content, which are then fused into enhanced node representations. These embeddings are combined with structural features using a novel integration layer with learned attention weights. Graphormer's path-aware position encoding and multi-head attention mechanisms are employed to effectively capture long-range dependencies across the citation network. We demonstrate the efficacy of our framework on the challenging ogbn-arxiv dataset, achieving state-of-the-art performance with a classification accuracy of 0.772, significantly surpassing the best GCN baseline of 0.713. Our method also yields strong results in precision (0.671), recall (0.577), and F1-score (0.610). We validate our approach through comprehensive ablation studies that quantify the contribution of each component, demonstrating the synergy between semantic and structural information. Our framework provides a scalable and robust solution for node classification in dynamic TAGs, offering a promising direction for future research in knowledge systems and scientific discovery.
【6】A Graph Neural Network Approach for Mapping the Conceptual Structure and Inter-Branch Connectivity of Physics
标题：映射物理学概念结构和分支间连通性的图神经网络方法
链接：https://arxiv.org/abs/2508.05724
备注：14 pages, 9 figures
摘要：这项工作介绍了一种新的框架表示和分析物理定律作为一个加权的知识图。我们构建了一个包含659个不同物理方程的数据库，经过严格的语义清理以解决符号上的歧义，从而产生了一个包含400个高级物理方程的语料库。我们开发了一种增强的图形表示，其中物理概念和方程都是节点，通过加权方程间桥连接。这些权重是使用变量重叠、物理学重要性分数和文献计量数据的归一化指标客观定义的。图注意力网络（GAT）被训练用于链接预测，在五次独立运行中实现了0.9742 +/- 0.0018的测试AUC，显著优于经典算法（最佳基线AUC：0.9487）和已建立的GNN架构（如GraphSAGE）（AUC：0.9504，p = 0.029）。统计学检验证实了所有比较的显著性（p < 0.05），与最佳基线相比改善了2.7%。我们的分析揭示了三个关键发现：（i）该模型自主地重新发现了已知的物理学宏观结构，确定了电磁学和统计力学之间的强概念轴。(ii)它确定了中央枢纽方程，作为多个物理域之间的关键桥梁。(iii)该模型生成稳定的，计算衍生的跨域关系的假设，确定已知的原则，并提出新的数学类比，为进一步的理论研究。该框架可以生成数百个这样的假设，从而能够创建专门的数据集，用于对特定物理子领域进行有针对性的分析。代码和数据可在https://github.com/kingelanci/graphysics上获得
摘要：This work introduces a novel framework for representing and analyzing physical laws as a weighted knowledge graph. We constructed a database of 659 distinct physical equations, subjected to rigorous semantic cleaning to resolve notational ambiguities, resulting in a corpus of 400 advanced physics equations. We developed an enhanced graph representation where both physical concepts and equations are nodes, connected by weighted inter-equation bridges. These weights are objectively defined using normalized metrics for variable overlap, physics-informed importance scores, and bibliometric data. A Graph Attention Network (GAT) was trained for link prediction, achieving a test AUC of 0.9742 +/- 0.0018 across five independent runs, significantly outperforming both classical heuristics (best baseline AUC: 0.9487) and established GNN architectures like GraphSAGE (AUC: 0.9504, p = 0.029). Statistical testing confirmed significance of all comparisons (p < 0.05), with 2.7% improvement over the best baseline. Our analysis reveals three key findings: (i) The model autonomously rediscovers the known macroscopic structure of physics, identifying strong conceptual axes between Electromagnetism and Statistical Mechanics. (ii) It identifies central hub equations that serve as critical bridges between multiple physical domains. (iii) The model generates stable, computationally-derived hypotheses for cross-domain relationships, identifying both known principles and suggesting novel mathematical analogies for further theoretical investigation. The framework can generate hundreds of such hypotheses, enabling the creation of specialized datasets for targeted analysis of specific physics subfields. Code and data available at https://github.com/kingelanci/graphysics
【7】Ensemble-Based Graph Representation of fMRI Data for Cognitive Brain State Classification
标题：用于认知大脑状态分类的fMRI数据基于集合的图表示
链接：https://arxiv.org/abs/2508.06118
摘要：基于神经影像数据的认知脑状态的理解和分类是神经科学中最重要和最具挑战性的问题之一，由于信号的高维性和固有噪声。在这项工作中，我们提出了一个基于集合的图表示方法的功能磁共振成像（fMRI）数据的任务，二进制脑状态分类。我们的方法通过利用多个基本机器学习模型来构建图：每个边权重反映了两个认知状态之间的后验概率差异，产生范围[-1，1]内的值，对给定状态的置信度进行编码。我们将这种方法应用于人类连接组项目（HCP 1200主题发布）的七个认知任务，包括工作记忆，赌博，运动活动，语言，社会认知，关系处理和情绪处理。仅使用图的平均事件边缘权重作为特征，一个简单的逻辑回归分类器实现了从97.07%到99.74%的平均准确率。我们还比较了我们的集成图与经典的基于相关性的图在分类任务与图神经网络（GNN）。在所有的实验中，最高的分类准确率得到集成图。这些结果表明，集成图传达了更丰富的拓扑信息，增强了大脑状态的歧视。我们的方法保留了边缘水平的可解释性的功能磁共振成像图表示，是适应多类和回归任务，并可以扩展到其他神经成像方式和病理状态分类。
摘要：Understanding and classifying human cognitive brain states based on neuroimaging data remains one of the foremost and most challenging problems in neuroscience, owing to the high dimensionality and intrinsic noise of the signals. In this work, we propose an ensemble-based graph representation method of functional magnetic resonance imaging (fMRI) data for the task of binary brain-state classification. Our method builds the graph by leveraging multiple base machine-learning models: each edge weight reflects the difference in posterior probabilities between two cognitive states, yielding values in the range [-1, 1] that encode confidence in a given state. We applied this approach to seven cognitive tasks from the Human Connectome Project (HCP 1200 Subject Release), including working memory, gambling, motor activity, language, social cognition, relational processing, and emotion processing. Using only the mean incident edge weights of the graphs as features, a simple logistic-regression classifier achieved average accuracies from 97.07% to 99.74%. We also compared our ensemble graphs with classical correlation-based graphs in a classification task with a graph neural network (GNN). In all experiments, the highest classification accuracy was obtained with ensemble graphs. These results demonstrate that ensemble graphs convey richer topological information and enhance brain-state discrimination. Our approach preserves edge-level interpretability of the fMRI graph representation, is adaptable to multiclass and regression tasks, and can be extended to other neuroimaging modalities and pathological-state classification.
Transformer(1篇)
【1】eSASRec: Enhancing Transformer-based Recommendations in a Modular Fashion
标题：eSASRec：以模块化方式增强基于转换器的推荐
链接：https://arxiv.org/abs/2508.06450
备注：Accepted at ACM RecSys 2025
摘要：自推出以来，基于Transformer的模型，如SASRec和BERT 4 Rec，已经成为顺序推荐的常用基线，超过了早期的神经和非神经方法。下面的一些出版物已经表明，这些模型的有效性可以通过例如稍微更新Transformer层的架构、使用更好的训练目标和采用改进的损失函数来提高。然而，这些模块化改进的可加性还没有被系统地基准化-这是我们在本文中旨在缩小的差距。通过我们的实验，我们确定了一个非常强大的模型，它使用SASRec的训练目标，LiGR Transformer层和采样Softmax损耗。我们将这种组合称为eSASRec（增强型SASRec）。虽然我们主要关注现实的、类似生产的评估，但在我们的初步研究中，我们发现常见的学术基准显示，与最新的最先进模型（例如ActionPiece）相比，eSASRec的有效性高出23%。在我们的主要生产类基准中，eSASRec在准确性和覆盖率权衡方面处于帕累托前沿（与最近的工业模型HSTU和FuXI一起）。由于与原始SASRec相比，修改相对简单，并且不需要额外的功能（例如HSTU中的时间戳），因此我们认为eSASRec可以轻松集成到现有的推荐管道中，并且可以作为新兴复杂算法的强大但非常简单的基线。为了便于实现，我们在存储库https://github.com/blondered/transformer_benchmark中为我们的模型和基准测试提供了开源实现
摘要 ：Since their introduction, Transformer-based models, such as SASRec and BERT4Rec, have become common baselines for sequential recommendations, surpassing earlier neural and non-neural methods. A number of following publications have shown that the effectiveness of these models can be improved by, for example, slightly updating the architecture of the Transformer layers, using better training objectives, and employing improved loss functions. However, the additivity of these modular improvements has not been systematically benchmarked - this is the gap we aim to close in this paper. Through our experiments, we identify a very strong model that uses SASRec's training objective, LiGR Transformer layers, and Sampled Softmax Loss. We call this combination eSASRec (Enhanced SASRec). While we primarily focus on realistic, production-like evaluation, in our preliminarily study we find that common academic benchmarks show eSASRec to be 23% more effective compared to the most recent state-of-the-art models, such as ActionPiece. In our main production-like benchmark, eSASRec resides on the Pareto frontier in terms of the accuracy-coverage tradeoff (alongside the recent industrial models HSTU and FuXi. As the modifications compared to the original SASRec are relatively straightforward and no extra features are needed (such as timestamps in HSTU), we believe that eSASRec can be easily integrated into existing recommendation pipelines and can can serve as a strong yet very simple baseline for emerging complicated algorithms. To facilitate this, we provide the open-source implementations for our models and benchmarks in repository https://github.com/blondered/transformer_benchmark
GAN|对抗|攻击|生成相关(7篇)
【1】Synthetic Data Generation and Differential Privacy using Tensor Networks' Matrix Product States (MPS)
标题：使用张量网络矩阵产品状态（MPS）的合成数据生成和差异隐私
链接：https://arxiv.org/abs/2508.06251
备注：10 pages
摘要：合成数据生成是现代人工智能中的一项关键技术，可以解决数据稀缺、隐私限制以及训练鲁棒模型时对不同数据集的需求。在这项工作中，我们提出了一种使用张量网络生成隐私保护的高质量合成表格数据的方法，特别是矩阵乘积状态（MPS）。我们将基于MPS的生成模型与最先进的模型（如CTGAN，VAE和PrivBayes）进行基准测试，重点关注保真度和隐私保护功能。为了确保差分隐私（DP），我们在训练期间集成了噪声注入和梯度裁剪，通过R'enyi差分隐私会计实现隐私保证。在分析数据保真度和下游机器学习任务性能的多个指标中，我们的结果表明MPS优于经典模型，特别是在严格的隐私限制下。这项工作突出了MPS作为隐私感知合成数据生成的一个有前途的工具。通过将张量网络表示的表达能力与正式的隐私机制相结合，所提出的方法为安全数据共享提供了一种可解释和可扩展的替代方案。其结构化设计便于集成到敏感领域，其中数据质量和机密性都至关重要。
摘要：Synthetic data generation is a key technique in modern artificial intelligence, addressing data scarcity, privacy constraints, and the need for diverse datasets in training robust models. In this work, we propose a method for generating privacy-preserving high-quality synthetic tabular data using Tensor Networks, specifically Matrix Product States (MPS). We benchmark the MPS-based generative model against state-of-the-art models such as CTGAN, VAE, and PrivBayes, focusing on both fidelity and privacy-preserving capabilities. To ensure differential privacy (DP), we integrate noise injection and gradient clipping during training, enabling privacy guarantees via R\'enyi Differential Privacy accounting. Across multiple metrics analyzing data fidelity and downstream machine learning task performance, our results show that MPS outperforms classical models, particularly under strict privacy constraints. This work highlights MPS as a promising tool for privacy-aware synthetic data generation. By combining the expressive power of tensor network representations with formal privacy mechanisms, the proposed approach offers an interpretable and scalable alternative for secure data sharing. Its structured design facilitates integration into sensitive domains where both data quality and confidentiality are critical.
【2】Membership Inference Attack with Partial Features
标题：具有部分特征的成员推断攻击
链接：https://arxiv.org/abs/2508.06244
摘要：机器学习模型已经被证明容易受到隶属推理攻击，这可以用来确定给定的样本是否出现在训练数据中。现有的隶属度推断方法通常假设对手可以完全访问目标样本的特征。然而，这种假设在许多现实世界的场景中并不成立，在这些场景中只有部分特征信息可用，从而限制了这些方法的适用性。在这项工作中，我们研究了一个推理场景，对手只观察每个样本的部分特征，目的是推断这个观察到的子集是否存在于目标模型的训练集中。我们将此问题定义为部分特征隶属度推断（PFMI）。为了解决这个问题，我们提出了MRAD（内存引导的重建和异常检测），一个两阶段的攻击框架。在第一阶段，MRAD优化未知的特征值，以最大限度地减少样本的损失。在第二阶段，它使用异常检测来测量重构样本与训练分布之间的偏差。实证结果表明，MRAD是有效的，在一系列的数据集，并保持与各种现成的异常检测技术的兼容性。例如，在STL-10上，即使有40%的缺失特征，我们的攻击也达到了大约0.6的AUC。
摘要：Machine learning models have been shown to be susceptible to membership inference attack, which can be used to determine whether a given sample appears in the training data. Existing membership inference methods commonly assume that the adversary has full access to the features of the target sample. This assumption, however, does not hold in many real-world scenarios where only partial features information is available, thereby limiting the applicability of these methods. In this work, we study an inference scenario where the adversary observes only partial features of each sample and aims to infer whether this observed subset was present in the training set of the target model. We define this problem as Partial Feature Membership Inference (PFMI). To address this problem, we propose MRAD (Memory-guided Reconstruction and Anomaly Detection), a two-stage attack framework. In the first stage, MRAD optimizes the unknown feature values to minimize the loss of the sample. In the second stage, it measures the deviation between the reconstructed sample and the training distribution using anomaly detection. Empirical results demonstrate that MRAD is effective across a range of datasets, and maintains compatibility with various off-the-shelf anomaly detection techniques. For example, on STL-10, our attack achieves an AUC of around 0.6 even with 40% of the missing features.
【3】Improved Sub-Visible Particle Classification in Flow Imaging Microscopy via Generative AI-Based Image Synthesis
标题：通过基于人工智能的生成式图像合成改进流成像显微镜中的亚可见颗粒分类
链接：https://arxiv.org/abs/2508.06021
摘要：使用流动成像显微镜结合深度学习的亚可见颗粒分析已被证明在识别颗粒类型方面是有效的，能够区分硅油等无害成分和蛋白质颗粒。然而，可用数据的稀缺性和数据集内粒子类型之间的严重不平衡仍然是将多类分类器应用于此类问题时的重大障碍，通常迫使研究人员依赖于不太有效的方法。上述问题对于无意出现且数量较少的颗粒类型（例如硅油和气泡）尤其具有挑战性，而不是蛋白质颗粒，其中通过受控设置获得大量图像相对简单。在这项工作中，我们开发了一种最先进的扩散模型，通过生成可以增强训练数据集的高保真图像来解决数据不平衡问题，从而实现对多类深度神经网络的有效训练。我们验证了这种方法，证明所生成的样本非常类似于真实的粒子图像的视觉质量和结构。为了评估在训练数据集中使用扩散生成图像的有效性，我们在包含50万个蛋白质颗粒图像的验证数据集上进行了大规模实验，并证明这种方法提高了分类性能，并且没有可忽略的缺点。最后，为了促进开放研究和可重复性，我们在https://github.com/utkuozbulak/svp-generative-ai上公开发布了我们的扩散模型和训练的多类深度神经网络分类器，以及一个简单的界面，以便轻松集成到未来的研究中。
摘要：Sub-visible particle analysis using flow imaging microscopy combined with deep learning has proven effective in identifying particle types, enabling the distinction of harmless components such as silicone oil from protein particles. However, the scarcity of available data and severe imbalance between particle types within datasets remain substantial hurdles when applying multi-class classifiers to such problems, often forcing researchers to rely on less effective methods. The aforementioned issue is particularly challenging for particle types that appear unintentionally and in lower numbers, such as silicone oil and air bubbles, as opposed to protein particles, where obtaining large numbers of images through controlled settings is comparatively straightforward. In this work, we develop a state-of-the-art diffusion model to address data imbalance by generating high-fidelity images that can augment training datasets, enabling the effective training of multi-class deep neural networks. We validate this approach by demonstrating that the generated samples closely resemble real particle images in terms of visual quality and structure. To assess the effectiveness of using diffusion-generated images in training datasets, we conduct large-scale experiments on a validation dataset comprising 500,000 protein particle images and demonstrate that this approach improves classification performance with no negligible downside. Finally, to promote open research and reproducibility, we publicly release both our diffusion models and the trained multi-class deep neural network classifiers, along with a straightforward interface for easy integration into future studies, at https://github.com/utkuozbulak/svp-generative-ai.
【4】Boosting Adversarial Transferability via Residual Perturbation Attack
标题
：通过残余扰动攻击提高对抗性可移植性
链接：https://arxiv.org/abs/2508.05689
备注：Accepted to ieee/cvf international conference on computer vision (ICCV2025)
摘要：深度神经网络容易受到对抗性样本的影响，同时会因不可感知的扰动而遭受错误的预测。基于转移的攻击为代理模型创建对抗性示例，并在黑盒场景下将这些示例转移到目标模型。最近的研究表明，平坦损失景观中的对抗性示例表现出优越的可转移性，以减轻代理模型的过拟合。然而，现有技术忽略了扰动方向的影响，导致有限的可转移性。在本文中，我们提出了一种新的攻击方法，称为剩余扰动攻击（ResPA），依靠剩余梯度作为扰动方向，以引导对抗性的例子对损失函数的平坦区域。具体而言，ResPA对输入梯度进行指数移动平均，以获得一阶矩作为参考梯度，其包含历史梯度的方向。代替严重依赖于源自当前梯度的局部平坦度作为扰动方向，ResPA进一步考虑当前梯度和参考梯度之间的残差以捕获全局扰动方向上的变化。实验结果表明，ResPA的可移植性优于现有的典型的基于转移的攻击方法，而将ResPA与现有的输入变换方法相结合，可以进一步提高其可移植性。该代码可在https://github.com/ZezeTao/ResPA上获得。
摘要：Deep neural networks are susceptible to adversarial examples while suffering from incorrect predictions via imperceptible perturbations. Transfer-based attacks create adversarial examples for surrogate models and transfer these examples to target models under black-box scenarios. Recent studies reveal that adversarial examples in flat loss landscapes exhibit superior transferability to alleviate overfitting on surrogate models. However, the prior arts overlook the influence of perturbation directions, resulting in limited transferability. In this paper, we propose a novel attack method, named Residual Perturbation Attack (ResPA), relying on the residual gradient as the perturbation direction to guide the adversarial examples toward the flat regions of the loss function. Specifically, ResPA conducts an exponential moving average on the input gradients to obtain the first moment as the reference gradient, which encompasses the direction of historical gradients. Instead of heavily relying on the local flatness that stems from the current gradients as the perturbation direction, ResPA further considers the residual between the current gradient and the reference gradient to capture the changes in the global perturbation direction. The experimental results demonstrate the better transferability of ResPA than the existing typical transfer-based attack methods, while the transferability can be further improved by combining ResPA with the current input transformation methods. The code is available at https://github.com/ZezeTao/ResPA.
【5】Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation
标题：基于强化学习的医学问卷系统的对抗攻击：输入级扰动策略和医学约束验证
链接：https://arxiv.org/abs/2508.05677
备注：30 pages (21 pages main text, 3 pages references, 6 pages appendix), 4 figures
摘要：基于RL的医疗问卷系统在医疗场景中显示出巨大的潜力。然而，它们的安全性和鲁棒性仍然没有得到解决。本研究对对抗性攻击方法进行了全面的评估，以识别和分析其潜在的漏洞。我们将诊断过程表述为马尔可夫决策过程（MDP），其中状态是患者的反应和未问的问题，动作是提出问题或进行诊断。我们实现了六种流行的主要攻击方法，包括快速梯度签名方法（FGSM），投影梯度下降（PGD），Carlini & Wagner攻击（C&W）攻击，基本迭代方法（BIM），DeepFool和AutoAttack，每种方法都有七个参数值。为了确保生成的对抗性示例在临床上是合理的，我们开发了一个全面的医疗验证框架，由247个医疗约束组成，包括生理界限、症状相关性和条件医疗约束。我们在生成临床上合理的对抗样本方面取得了97.6%的成功率。我们在全国健康访谈调查（NHIS）数据集（https：//www.cdc.gov/nchs/nhis/）上进行了实验，该数据集由182，630个样本组成，以预测参与者的4年死亡率。我们评估了对arXiv：2004.00994中提出的AdaptiveFS框架的攻击。我们的研究结果表明，对抗性攻击可以显著影响诊断准确性，攻击成功率从33.08%（FGSM）到64.70%（AutoAttack）不等。我们的工作表明，即使在严格的医疗限制的输入，这种基于RL的医疗问卷系统仍然显示出显着的漏洞。
摘要：RL-based medical questionnaire systems have shown great potential in medical scenarios. However, their safety and robustness remain unresolved. This study performs a comprehensive evaluation on adversarial attack methods to identify and analyze their potential vulnerabilities. We formulate the diagnosis process as a Markov Decision Process (MDP), where the state is the patient responses and unasked questions, and the action is either to ask a question or to make a diagnosis. We implemented six prevailing major attack methods, including the Fast Gradient Signed Method (FGSM), Projected Gradient Descent (PGD), Carlini & Wagner Attack (C&W) attack, Basic Iterative Method (BIM), DeepFool, and AutoAttack, with seven epsilon values each. To ensure the generated adversarial examples remain clinically plausible, we developed a comprehensive medical validation framework consisting of 247 medical constraints, including physiological bounds, symptom correlations, and conditional medical constraints. We achieved a 97.6% success rate in generating clinically plausible adversarial samples. We performed our experiment on the National Health Interview Survey (NHIS) dataset (https://www.cdc.gov/nchs/nhis/), which consists of 182,630 samples, to predict the participant's 4-year mortality rate. We evaluated our attacks on the AdaptiveFS framework proposed in arXiv:2004.00994. Our results show that adversarial attacks could significantly impact the diagnostic accuracy, with attack success rates ranging from 33.08% (FGSM) to 64.70% (AutoAttack). Our work has demonstrated that even under strict medical constraints on the input, such RL-based medical questionnaire systems still show significant vulnerabilities.
【6】HySemRAG: A Hybrid Semantic Retrieval-Augmented Generation Framework for Automated Literature Synthesis and Methodological Gap Analysis
标题：HySemRAG：用于自动文献合成和方法学差距分析的混合语义检索-增强生成框架
链接：https://arxiv.org/abs/2508.05666
备注：47 pages, 10 figures. Code: this https URL. Demo: this https URL. ETL+multi-agent RAG framework for literature synthesis, 35.1% improvement over PDF chunking. Real application: reduced 17,400 papers to 24 relevant ones (99.86%) in 10 minutes for wastewater epidemiology review
摘要：我们提出了HySemRAG，一个框架，结合提取，转换，加载（ETL）管道与检索增强生成（RAG）自动化大规模的文献合成和识别方法研究的差距。该系统通过多层方法解决了现有RAG架构的局限性：结合语义搜索，关键字过滤和知识图遍历的混合检索;具有迭代质量保证的代理自我纠正框架;以及事后引用验证，确保完全的可追溯性。我们的实现过程中的学术文献，通过八个综合阶段：多源元数据采集，异步PDF检索，自定义文档布局分析，使用修改后的Docling架构，书目管理，基于LLM的字段提取，主题建模，语义统一，知识图建设。该系统创建了双重数据产品-支持复杂关系查询的Neo4j知识图和支持语义搜索的Qdrant矢量集合-作为可验证信息合成的基础设施。从60个测试会话的643个观察结果的评估表明，结构化字段提取实现了35.1%的语义相似性分数（0.655 $\pm $0.178）相比，PDF分块方法（0.485 $\pm $0.204，p < 0.000001）。代理质量保证机制实现了68.3%的单程成功率与99.0%的引文准确率在验证的响应。该系统应用于关于臭氧暴露和心血管疾病的地理空间流行病学文献，确定了方法趋势和研究差距，展示了跨科学领域的广泛适用性，以加速证据合成和发现。
摘要 ：We present HySemRAG, a framework that combines Extract, Transform, Load (ETL) pipelines with Retrieval-Augmented Generation (RAG) to automate large-scale literature synthesis and identify methodological research gaps. The system addresses limitations in existing RAG architectures through a multi-layered approach: hybrid retrieval combining semantic search, keyword filtering, and knowledge graph traversal; an agentic self-correction framework with iterative quality assurance; and post-hoc citation verification ensuring complete traceability. Our implementation processes scholarly literature through eight integrated stages: multi-source metadata acquisition, asynchronous PDF retrieval, custom document layout analysis using modified Docling architecture, bibliographic management, LLM-based field extraction, topic modeling, semantic unification, and knowledge graph construction. The system creates dual data products - a Neo4j knowledge graph enabling complex relationship queries and Qdrant vector collections supporting semantic search - serving as foundational infrastructure for verifiable information synthesis. Evaluation across 643 observations from 60 testing sessions demonstrates structured field extraction achieving 35.1% higher semantic similarity scores (0.655 $\pm$ 0.178) compared to PDF chunking approaches (0.485 $\pm$ 0.204, p < 0.000001). The agentic quality assurance mechanism achieves 68.3% single-pass success rates with 99.0% citation accuracy in validated responses. Applied to geospatial epidemiology literature on ozone exposure and cardiovascular disease, the system identifies methodological trends and research gaps, demonstrating broad applicability across scientific domains for accelerating evidence synthesis and discovery.
【7】Random Walk Learning and the Pac-Man Attack
标题：随机步行学习和吃豆人攻击
链接：https://arxiv.org/abs/2508.05663
摘要：基于随机游走（RW）的算法由于低开销和可扩展性而长期以来在分布式系统中很受欢迎，最近在分散学习中的应用越来越多。然而，它们对本地交互的依赖使它们天生容易受到恶意行为的攻击。在这项工作中，我们调查了一个对抗性的威胁，我们称之为“吃豆人”攻击，其中恶意节点可能会终止任何访问它的RW。这种隐形行为逐渐消除了网络中的活动RW，有效地停止了学习过程，而不会触发故障警报。为了应对这一威胁，我们提出了平均交叉（AC）算法-一个完全分散的机制，用于复制RW，以防止RW灭绝的存在吃豆人。我们的理论分析建立，（i）RW人口几乎肯定有界下AC和（ii）基于RW的随机梯度下降仍然收敛下AC，即使在吃豆人的存在，与真正的最优值有可量化的偏差。我们在合成和真实世界数据集上的广泛实证结果证实了我们的理论发现。此外，他们发现了一个相变的灭绝概率作为复制阈值的函数。我们通过分析AC的简化变体提供理论见解，这揭示了所观察到的相变。
摘要：Random walk (RW)-based algorithms have long been popular in distributed systems due to low overheads and scalability, with recent growing applications in decentralized learning. However, their reliance on local interactions makes them inherently vulnerable to malicious behavior. In this work, we investigate an adversarial threat that we term the ``Pac-Man'' attack, in which a malicious node probabilistically terminates any RW that visits it. This stealthy behavior gradually eliminates active RWs from the network, effectively halting the learning process without triggering failure alarms. To counter this threat, we propose the Average Crossing (AC) algorithm--a fully decentralized mechanism for duplicating RWs to prevent RW extinction in the presence of Pac-Man. Our theoretical analysis establishes that (i) the RW population remains almost surely bounded under AC and (ii) RW-based stochastic gradient descent remains convergent under AC, even in the presence of Pac-Man, with a quantifiable deviation from the true optimum. Our extensive empirical results on both synthetic and real-world datasets corroborate our theoretical findings. Furthermore, they uncover a phase transition in the extinction probability as a function of the duplication threshold. We offer theoretical insights by analyzing a simplified variant of the AC, which sheds light on the observed phase transition.
半/弱/无/有监督|不确定性|主动学习(4篇)
【1】WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion
标题：WGAST：通过时空融合估计每日10 m陆地表面温度的弱监督生成网络
链接：https://arxiv.org/abs/2508.06485
备注：Submitted to IEEE Transactions on Geoscience and Remote Sensing (TGRS)
摘要：城市化、气候变化和农业压力正在增加对精确和及时环境监测的需求。在这方面，地表温度是一个关键变量，从遥感卫星中检索。然而，这些系统面临空间和时间分辨率之间的权衡。虽然时空融合的方法提供了有前途的解决方案，很少有解决的估计每日LST在10米的分辨率。在这项研究中，我们提出了WGAST，每天10米LST估计通过时空融合的Terra MODIS，Landsat 8和哨兵-2的弱监督生成网络。WGAST是第一个为这项任务设计的端到端深度学习框架。它采用条件生成对抗架构，生成器由四个阶段组成：特征提取，融合，LST重建和噪声抑制。第一阶段采用一组编码器从输入中提取多级潜在表示，然后在第二阶段使用余弦相似性，归一化和时间注意机制进行融合。第三阶段将融合的特征解码成高分辨率的LST，然后是高斯滤波器以抑制高频噪声。训练遵循基于物理平均原则的弱监督策略，并由PatchGAN训练器加强。实验表明，WGAST优于现有的方法在定量和定性评价。与性能最佳的基线相比，WGAST平均将RMSE降低了17.18%，将SSIM提高了11.00%。此外，WGAST对云引起的LST具有鲁棒性，并有效地捕获了精细尺度的热模式，并对33个地面传感器进行了验证。该代码可在https://github.com/Sofianebouaziz1/WGAST.git上获得。
摘要：Urbanization, climate change, and agricultural stress are increasing the demand for precise and timely environmental monitoring. Land Surface Temperature (LST) is a key variable in this context and is retrieved from remote sensing satellites. However, these systems face a trade-off between spatial and temporal resolution. While spatio-temporal fusion methods offer promising solutions, few have addressed the estimation of daily LST at 10 m resolution. In this study, we present WGAST, a Weakly-Supervised Generative Network for Daily 10 m LST Estimation via Spatio-Temporal Fusion of Terra MODIS, Landsat 8, and Sentinel-2. WGAST is the first end-to-end deep learning framework designed for this task. It adopts a conditional generative adversarial architecture, with a generator composed of four stages: feature extraction, fusion, LST reconstruction, and noise suppression. The first stage employs a set of encoders to extract multi-level latent representations from the inputs, which are then fused in the second stage using cosine similarity, normalization, and temporal attention mechanisms. The third stage decodes the fused features into high-resolution LST, followed by a Gaussian filter to suppress high-frequency noise. Training follows a weakly supervised strategy based on physical averaging principles and reinforced by a PatchGAN discriminator. Experiments demonstrate that WGAST outperforms existing methods in both quantitative and qualitative evaluations. Compared to the best-performing baseline, on average, WGAST reduces RMSE by 17.18% and improves SSIM by 11.00%. Furthermore, WGAST is robust to cloud-induced LST and effectively captures fine-scale thermal patterns, as validated against 33 ground-based sensors. The code is available at https://github.com/Sofianebouaziz1/WGAST.git.
【2】TRUST: Leveraging Text Robustness for Unsupervised Domain Adaptation
标题：TRUST：利用文本鲁棒性进行无监督领域适应
链接：https://arxiv.org/abs/2508.06452
摘要：最近的无监督域自适应（UDA）方法在解决经典域偏移（例如，合成到真实），但它们仍然受到复杂变化（例如地理变化）的影响，其中背景和对象外观在域之间显著不同。先前的研究表明，语言模态可以帮助适应过程，对这种复杂的转变表现出更强的鲁棒性。在本文中，我们介绍TRUST，一种新的UDA方法，利用语言模态的鲁棒性来指导视觉模型的适应。TRUST从标题中为目标样本生成伪标签，并引入了一种新的不确定性估计策略，该策略使用归一化的CLIP相似性得分来估计生成的伪标签的不确定性。然后，这种估计的不确定性被用于重新加权分类损失，减轻从低质量字幕获得的错误伪标签的不利影响。为了进一步提高视觉模型的鲁棒性，我们提出了一种多模态软对比学习损失，通过利用字幕来引导视觉模型在目标图像上的对比训练，使视觉和语言特征空间保持一致。在我们的对比损失中，每一对图像都是积极和消极的一对，它们的特征表示被吸引和排斥的强度与它们的标题的相似性成正比。该解决方案避免了几乎不确定正负对的需要，这在UDA设置中是至关重要的。我们的方法优于以前的方法，在经典（DomainNet）和复杂（GeoNet）域转移上设置了新的最先进技术。代码将在接受后提供。
摘要 ：Recent unsupervised domain adaptation (UDA) methods have shown great success in addressing classical domain shifts (e.g., synthetic-to-real), but they still suffer under complex shifts (e.g. geographical shift), where both the background and object appearances differ significantly across domains. Prior works showed that the language modality can help in the adaptation process, exhibiting more robustness to such complex shifts. In this paper, we introduce TRUST, a novel UDA approach that exploits the robustness of the language modality to guide the adaptation of a vision model. TRUST generates pseudo-labels for target samples from their captions and introduces a novel uncertainty estimation strategy that uses normalised CLIP similarity scores to estimate the uncertainty of the generated pseudo-labels. Such estimated uncertainty is then used to reweight the classification loss, mitigating the adverse effects of wrong pseudo-labels obtained from low-quality captions. To further increase the robustness of the vision model, we propose a multimodal soft-contrastive learning loss that aligns the vision and language feature spaces, by leveraging captions to guide the contrastive training of the vision model on target images. In our contrastive loss, each pair of images acts as both a positive and a negative pair and their feature representations are attracted and repulsed with a strength proportional to the similarity of their captions. This solution avoids the need for hardly determining positive and negative pairs, which is critical in the UDA setting. Our approach outperforms previous methods, setting the new state-of-the-art on classical (DomainNet) and complex (GeoNet) domain shifts. The code will be available upon acceptance.
【3】Unsupervised Partner Design Enables Robust Ad-hoc Teamwork
标题：无监督合作伙伴设计实现强大的临时团队合作
链接：https://arxiv.org/abs/2508.06336
备注：16 pages
摘要：我们介绍了无监督合作伙伴设计（UPD）-一个无人口，多智能体强化学习框架，用于强大的特设团队合作，自适应地生成训练伙伴，而不需要预先训练的合作伙伴或手动参数调整。UPD构建不同的合作伙伴随机混合的自我代理的政策与偏见的随机行为，并使用基于方差的可学习性度量，优先考虑合作伙伴附近的自我代理的当前学习前沿的分数。我们表明，UPD可以与无监督的环境设计相结合，从而在第一种方法，使完全无监督的课程，在合作环境中的水平和合作伙伴的分布。通过对Overcooked-AI和Overcooked Generalisation Challenge的广泛评估，我们证明了这种动态合作伙伴课程非常有效：UPD始终优于基于人口和无人口的基线以及消融。在一项用户研究中，我们进一步表明，UPD比所有基线都获得了更高的回报，并且被认为具有更强的适应性，更人性化，更好的合作者，更少的挫折感。
摘要：We introduce Unsupervised Partner Design (UPD) - a population-free, multi-agent reinforcement learning framework for robust ad-hoc teamwork that adaptively generates training partners without requiring pretrained partners or manual parameter tuning. UPD constructs diverse partners by stochastically mixing an ego agent's policy with biased random behaviours and scores them using a variance-based learnability metric that prioritises partners near the ego agent's current learning frontier. We show that UPD can be integrated with unsupervised environment design, resulting in the first method enabling fully unsupervised curricula over both level and partner distributions in a cooperative setting. Through extensive evaluations on Overcooked-AI and the Overcooked Generalisation Challenge, we demonstrate that this dynamic partner curriculum is highly effective: UPD consistently outperforms both population-based and population-free baselines as well as ablations. In a user study, we further show that UPD achieves higher returns than all baselines and was perceived as significantly more adaptive, more human-like, a better collaborator, and less frustrating.
【4】Diagrams-to-Dynamics (D2D): Exploring Causal Loop Diagram Leverage Points under Uncertainty
标题：动力图（D2 D）：探索不确定性下的因果循环图杠杆点
链接：https://arxiv.org/abs/2508.05659
备注：21 pages, 4 figures, 4 tables
摘要：因果循环图（CLD）被广泛用于健康和环境研究，以表示复杂问题背后的假设因果结构。然而，作为定性和静态表示，CLDs在支持动态分析和告知干预策略方面的能力有限。此外，定量CLD分析方法，如网络中心性分析，往往会导致错误的推断。我们提出了动态图（D2 D），这是一种在缺乏经验数据的情况下将CLD转换为探索性系统动力学模型（SDM）的方法。通过最少的用户输入-遵循将变量标记为存量、流量/辅助或常量的协议-D2 D利用CLD中已经编码的结构信息，即链接存在和极性，来模拟假设的干预并探索不确定性下的潜在杠杆点。结果表明，D2 D有助于区分高和低排名的杠杆点。我们将D2 D与从相同CLD和变量标签构造的数据驱动SDM进行比较。与网络中心性分析相比，D2 D与数据驱动模型的一致性更高，同时为未来的数据收集提供了不确定性估计和指导。该方法在一个开源Python包和一个基于Web的应用程序中实现，以支持进一步的测试，并为使用CLD的研究人员降低动态建模的障碍。我们预计额外的验证将进一步建立该方法的效用在广泛的情况下和域。
摘要：Causal loop diagrams (CLDs) are widely used in health and environmental research to represent hypothesized causal structures underlying complex problems. However, as qualitative and static representations, CLDs are limited in their ability to support dynamic analysis and inform intervention strategies. Additionally, quantitative CLD analysis methods like network centrality analysis often lead to false inference. We propose Diagrams-to-Dynamics (D2D), a method for converting CLDs into exploratory system dynamics models (SDMs) in the absence of empirical data. With minimal user input - following a protocol to label variables as stocks, flows/auxiliaries, or constants - D2D leverages the structural information already encoded in CLDs, namely, link existence and polarity, to simulate hypothetical interventions and explore potential leverage points under uncertainty. Results suggest that D2D helps distinguish between high- and low-ranked leverage points. We compare D2D to a data-driven SDM constructed from the same CLD and variable labeling. D2D showed greater consistency with the data-driven model than network centrality analysis, while providing uncertainty estimates and guidance for future data collection. The method is implemented in an open-source Python package and a web-based application to support further testing and lower the barrier to dynamic modeling for researchers working with CLDs. We expect additional validation will further establish the approach's utility across a broad range of cases and domains.
迁移|Zero/Few/One-Shot|自适应(4篇)
【1】ETA: Energy-based Test-time Adaptation for Depth Completion
标题：埃塔：深度完成的基于能量的测试时间调整
链接：https://arxiv.org/abs/2508.05989
摘要：我们提出了一种预训练深度补全模型的测试时自适应方法。在一些“源”数据上训练的深度补全模型，由于协变量的变化，在转移到在新的环境条件下捕获的“目标”数据时，经常预测错误的输出。我们的方法的关键在于量化属于源数据分布的深度预测的可能性。面临的挑战是在部署前无法获得分发外（目标）数据。因此，我们利用对抗扰动作为探索数据空间的机制，而不是对目标分布进行假设。这使我们能够训练能量模型，该模型将深度预测的局部区域评分为分布内或分布外。我们在测试时更新预训练的深度补全模型的参数，以最小化能量，有效地将测试时的预测与源分布的预测对齐。我们称我们的方法为“基于能量的测试时自适应”，简称ETA。我们在三个室内和三个室外数据集上评估了我们的方法，其中ETA比以前的最先进方法平均提高了6.94%（室外）和10.23%（室内）。项目页面：https://fuzzythecat.github.io/eta。
摘要：We propose a method for test-time adaptation of pretrained depth completion models. Depth completion models, trained on some ``source'' data, often predict erroneous outputs when transferred to ``target'' data captured in novel environmental conditions due to a covariate shift. The crux of our method lies in quantifying the likelihood of depth predictions belonging to the source data distribution. The challenge is in the lack of access to out-of-distribution (target) data prior to deployment. Hence, rather than making assumptions regarding the target distribution, we utilize adversarial perturbations as a mechanism to explore the data space. This enables us to train an energy model that scores local regions of depth predictions as in- or out-of-distribution. We update the parameters of pretrained depth completion models at test time to minimize energy, effectively aligning test-time predictions to those of the source distribution. We call our method ``Energy-based Test-time Adaptation'', or ETA for short. We evaluate our method across three indoor and three outdoor datasets, where ETA improve over the previous state-of-the-art method by an average of 6.94% for outdoors and 10.23% for indoors. Project Page: https://fuzzythecat.github.io/eta.
【2】DAFMSVC: One-Shot Singing Voice Conversion with Dual Attention Mechanism and Flow Matching
标题：DAFMSVC：具有双重注意力机制和流量匹配的一次歌唱声音转换
链接
：https://arxiv.org/abs/2508.05978
备注：Accepted by INTERSPEECH 2025
摘要：歌唱声音转换（SVC）将源歌手的音色转换为目标，同时保留旋律和歌词。任何对任何SVC的关键挑战是在不降低质量的情况下使看不见的扬声器音色适应源音频。现有方法要么面临音色泄漏，要么无法在生成的音频中实现令人满意的音色相似性和质量。为了解决这些挑战，我们提出了DAFMSVC，其中来自源音频的自监督学习（SSL）特征被替换为来自目标音频的最相似的SSL特征，以防止音色泄漏。它还采用了双重交叉注意机制，用于自适应融合说话人嵌入，旋律和语言内容。此外，我们引入了一个流匹配模块，用于从融合的特征生成高质量的音频。实验结果表明，DAFMSVC显著提高了音色的相似性和自然度，在主观和客观评价方面都优于现有的方法。
摘要：Singing Voice Conversion (SVC) transfers a source singer's timbre to a target while keeping melody and lyrics. The key challenge in any-to-any SVC is adapting unseen speaker timbres to source audio without quality degradation. Existing methods either face timbre leakage or fail to achieve satisfactory timbre similarity and quality in the generated audio. To address these challenges, we propose DAFMSVC, where the self-supervised learning (SSL) features from the source audio are replaced with the most similar SSL features from the target audio to prevent timbre leakage. It also incorporates a dual cross-attention mechanism for the adaptive fusion of speaker embeddings, melody, and linguistic content. Additionally, we introduce a flow matching module for high quality audio generation from the fused features. Experimental results show that DAFMSVC significantly enhances timbre similarity and naturalness, outperforming state-of-the-art methods in both subjective and objective evaluations.
【3】ASLSL: Adaptive shared latent structure learning with incomplete multi-modal physiological data for multi-dimensional emotional feature selection
标题：ASLSL：利用不完整的多模式生理数据进行自适应共享潜在结构学习，用于多维情感特征选择
链接：https://arxiv.org/abs/2508.05934
摘要：近年来，基于多模态生理信号的情感识别在脑机接口领域受到越来越多的关注。神经元作为多模态生理特征，往往是高维的，不可避免地包含了无关、冗余和噪声的表示，这很容易导致情感分类器的过拟合、性能差和计算复杂度高。特征选择已被广泛应用于解决这些挑战。然而，以前的研究一般假设多模态生理数据是完整的，而在现实中，由于采集和操作环境的开放性，数据往往是不完整的。例如，一部分样本在几种模式中可用，但在其他模式中不可用。为了解决这个问题，我们提出了一种新的方法不完整的多模态生理信号特征选择自适应共享潜在结构学习（ASLSL）。基于相似特征共享相似情感标签的特性，ASLSL采用自适应共享潜在结构学习，探索不完整多模态生理信号和多维情感标签共享的共同潜在空间，从而减轻缺失信息的影响，挖掘共识信息。利用两个最流行的多模态生理情感数据集（DEAP和DREAMER）的多维情感标签，比较ASLSL和17个特征选择方法之间的性能。在这些数据集上的综合实验结果证明了ASLSL的有效性。
摘要：Recently, multi-modal physiological signals based emotion recognition has garnered increasing attention in the field of brain-computer interfaces. Nevertheness, the associated multi-modal physiological features are often high-dimensional and inevitably include irrelevant, redundant, and noisy representation, which can easily lead to overfitting, poor performance, and high computational complexity in emotion classifiers. Feature selection has been widely applied to address these challenges. However, previous studies generally assumed that multi-modal physiological data are complete, whereas in reality, the data are often incomplete due to the openness of the acquisition and operational environment. For example, a part of samples are available in several modalities but not in others. To address this issue, we propose a novel method for incomplete multi-modal physiological signal feature selection called adaptive shared latent structure learning (ASLSL). Based on the property that similar features share similar emotional labels, ASLSL employs adaptive shared latent structure learning to explore a common latent space shared for incomplete multi-modal physiological signals and multi-dimensional emotional labels, thereby mitigating the impact of missing information and mining consensus information. Two most popular multi-modal physiological emotion datasets (DEAP and DREAMER) with multi-dimensional emotional labels were utilized to compare the performance between compare ASLSL and seventeen feature selection methods. Comprehensive experimental results on these datasets demonstrate the effectiveness of ASLSL.
【4】IOCC: Aligning Semantic and Cluster Centers for Few-shot Short Text Clustering
标题：IOCC：协调语义和集群中心以实现Few-Shot短文本集群
链接：https://arxiv.org/abs/2508.06126
摘要：在聚类任务中，将特征空间构造成清晰、分离良好的分布是至关重要的。然而，由于短文本表示具有有限的表现力，传统方法难以识别真正捕获每个类别的底层语义的聚类中心，从而导致表示在次优方向上被优化。为了解决这个问题，我们提出了IOCC，一种新的Few-Shot对比学习方法，实现了聚类中心和语义中心之间的对齐。IOCC由两个关键模块组成：交互增强型最优传输（IEOT）和中心感知对比学习（CACL）。具体来说，IEOT将单个样本之间的语义交互纳入到传统的最优运输问题中，并生成伪标签。基于这些伪标签，我们聚集高置信度的样本，以构建近似的语义中心的伪中心。接下来，CACL将文本表示优化为对应的伪中心。随着训练的进行，两个模块之间的协作逐渐缩小了聚类中心和语义中心之间的差距。因此，该模型将学习高质量的分布，提高聚类性能。在8个基准数据集上的大量实验表明，IOCC算法在具有挑战性的生物医学数据集上的聚类性能提高了7.34%，并且在聚类稳定性和聚类效率方面也表现出色.该代码可从以下网址获得：https://anonymous.4open.science/r/IOCC-C438。
摘要：In clustering tasks, it is essential to structure the feature space into clear, well-separated distributions. However, because short text representations have limited expressiveness, conventional methods struggle to identify cluster centers that truly capture each category's underlying semantics, causing the representations to be optimized in suboptimal directions. To address this issue, we propose IOCC, a novel few-shot contrastive learning method that achieves alignment between the cluster centers and the semantic centers. IOCC consists of two key modules: Interaction-enhanced Optimal Transport (IEOT) and Center-aware Contrastive Learning (CACL). Specifically, IEOT incorporates semantic interactions between individual samples into the conventional optimal transport problem, and generate pseudo-labels. Based on these pseudo-labels, we aggregate high-confidence samples to construct pseudo-centers that approximate the semantic centers. Next, CACL optimizes text representations toward their corresponding pseudo-centers. As training progresses, the collaboration between the two modules gradually reduces the gap between cluster centers and semantic centers. Therefore, the model will learn a high-quality distribution, improving clustering performance. Extensive experiments on eight benchmark datasets show that IOCC outperforms previous methods, achieving up to 7.34\% improvement on challenging Biomedical dataset and also excelling in clustering stability and efficiency. The code is available at: https://anonymous.4open.science/r/IOCC-C438.
强化学习(5篇)
【1】GCHR : Goal-Conditioned Hindsight Regularization for Sample-Efficient Reinforcement Learning
标题：GSYS：目标条件后见之明正规化，用于样本高效的强化学习
链接：https://arxiv.org/abs/2508.06108
摘要 ：具有稀疏奖励的目标条件强化学习（GCRL）仍然是强化学习中的一个基本挑战。虽然后见之明经验重放（HER）已显示出通过重新标记收集的轨迹与实现的目标的承诺，我们认为，轨迹重新标记单独不充分利用现有的经验，在关闭政策GCRL方法，导致有限的样本效率。在本文中，我们提出了后见之明目标条件正则化（HGR），一种基于后见之明目标生成动作正则化先验的技术。当与后见之明自我模仿正则化（HSR）相结合时，我们的方法使非策略RL算法能够最大限度地利用经验。与采用HER和自我模仿技术的现有GCRL方法相比，我们的后见之明正则化实现了更有效的样本重用和最佳性能，这是我们在一系列导航和操作任务上经验证明的。
摘要：Goal-conditioned reinforcement learning (GCRL) with sparse rewards remains a fundamental challenge in reinforcement learning. While hindsight experience replay (HER) has shown promise by relabeling collected trajectories with achieved goals, we argue that trajectory relabeling alone does not fully exploit the available experiences in off-policy GCRL methods, resulting in limited sample efficiency. In this paper, we propose Hindsight Goal-conditioned Regularization (HGR), a technique that generates action regularization priors based on hindsight goals. When combined with hindsight self-imitation regularization (HSR), our approach enables off-policy RL algorithms to maximize experience utilization. Compared to existing GCRL methods that employ HER and self-imitation techniques, our hindsight regularizations achieve substantially more efficient sample reuse and the best performances, which we empirically demonstrate on a suite of navigation and manipulation tasks.
【2】LinguaFluid: Language Guided Fluid Control via Semantic Rewards in Reinforcement Learning
标题：LinguaFluid：通过强化学习中的语义奖励进行语言引导的流体控制
链接：https://arxiv.org/abs/2508.05977
摘要：在科学机器学习领域，设计有效的奖励函数仍然是强化学习（RL）中的一个挑战，特别是在任务目标难以用数字指定的环境中。现有工作中的奖励功能主要基于人工设计、手动工程或特定于任务的调整。在这项工作中，我们介绍了一种语义对齐的强化学习方法，其中奖励是通过使用来自Transformers（SBERT）的句子双向编码器表示将当前状态与目标语义指令对齐来计算的。该策略不是依赖于手动定义的奖励函数，而是基于奖励接收反馈，该奖励是目标文本描述与情节中的语句描述之间的余弦相似度。我们在几个环境中评估了我们的方法，并表明语义奖励可以指导学习实现竞争控制行为，即使在没有手工制作的奖励功能。我们的研究表明，语言嵌入空间和传统的欧氏空间之间的相关性。该框架为将代理行为与自然语言目标对齐开辟了新的视野，并为更大的语言模型（LLM）和流体控制应用程序的无缝集成奠定了基础。
摘要：In the domain of scientific machine learning, designing effective reward functions remains a challenge in reinforcement learning (RL), particularly in environments where task goals are difficult to specify numerically. Reward functions in existing work are predominantly based on heuristics, manual engineering, or task-specific tuning. In this work, we introduce a semantically aligned reinforcement learning method where rewards are computed by aligning the current state with a target semantic instruction using a Sentence-Bidirectional Encoder Representations from Transformers (SBERT). Instead of relying on manually defined reward functions, the policy receives feedback based on the reward, which is a cosine similarity between the goal textual description and the statement description in the episode. We evaluated our approach in several environments and showed that semantic reward can guide learning to achieve competitive control behavior, even in the absence of hand-crafted reward functions. Our study demonstrates a correlation between the language embedding space and the conventional Euclidean space. This framework opens new horizons for aligning agent behavior with natural language goals and lays the groundwork for a more seamless integration of larger language models (LLMs) and fluid control applications.
【3】Mildly Conservative Regularized Evaluation for Offline Reinforcement Learning
标题：离线强化学习的温和保守正规化评估
链接：https://arxiv.org/abs/2508.05960
摘要：离线强化学习（RL）试图从静态数据集中学习最优策略，而无需进一步的环境交互。一个关键的挑战是学习策略和行为策略之间的分布变化，导致分布外（OOD）行为和高估。为了防止严重高估，价值函数必须保持保守;然而，过度的保守可能会阻碍性能的改善。为了解决这个问题，我们提出了温和保守的正则化评估（MCRE）框架，它通过将时间差（TD）错误与Bellman备份中的行为克隆项相结合来平衡保守性和性能。在此基础上，我们开发了温和保守的正则化Q学习（MCRQ）算法，该算法将MCRE集成到一个非策略的演员-评论家框架中。实验表明，MCRQ在基准数据集上优于强基线和最先进的离线RL算法。
摘要：Offline reinforcement learning (RL) seeks to learn optimal policies from static datasets without further environment interaction. A key challenge is the distribution shift between the learned and behavior policies, leading to out-of-distribution (OOD) actions and overestimation. To prevent gross overestimation, the value function must remain conservative; however, excessive conservatism may hinder performance improvement. To address this, we propose the mildly conservative regularized evaluation (MCRE) framework, which balances conservatism and performance by combining temporal difference (TD) error with a behavior cloning term in the Bellman backup. Building on this, we develop the mildly conservative regularized Q-learning (MCRQ) algorithm, which integrates MCRE into an off-policy actor-critic framework. Experiments show that MCRQ outperforms strong baselines and state-of-the-art offline RL algorithms on benchmark datasets.
【4】Integrating Vision Foundation Models with Reinforcement Learning for Enhanced Object Interaction
标题：将Vision Foundation模型与强化学习集成以增强对象交互
链接：https://arxiv.org/abs/2508.05838
备注：Published in the Proceedings of the 2025 3rd International Conference on Robotics, Control and Vision Engineering (RCVE'25). 6 pages, 3 figures, 1 table
摘要：本文提出了一种新的方法，将视觉基础模型与强化学习相结合，以增强模拟环境中的对象交互能力。通过将Segment Anything Model（SAM）和YOLOv 5与在AI 2-THOR仿真环境中运行的邻近策略优化（PPO）代理相结合，我们使代理能够更有效地感知对象并与之交互。我们的综合实验，在四个不同的室内厨房设置进行，展示了显着改善对象交互成功率和导航效率相比，基线代理没有先进的感知。结果显示，平均累积奖励增加了68%，对象交互成功率提高了52.5%，导航效率提高了33%。这些发现强调了将基础模型与强化学习集成在复杂机器人任务中的潜力，为更复杂和更有能力的自主代理铺平了道路。
摘要：This paper presents a novel approach that integrates vision foundation models with reinforcement learning to enhance object interaction capabilities in simulated environments. By combining the Segment Anything Model (SAM) and YOLOv5 with a Proximal Policy Optimization (PPO) agent operating in the AI2-THOR simulation environment, we enable the agent to perceive and interact with objects more effectively. Our comprehensive experiments, conducted across four diverse indoor kitchen settings, demonstrate significant improvements in object interaction success rates and navigation efficiency compared to a baseline agent without advanced perception. The results show a 68% increase in average cumulative reward, a 52.5% improvement in object interaction success rate, and a 33% increase in navigation efficiency. These findings highlight the potential of integrating foundation models with reinforcement learning for complex robotic tasks, paving the way for more sophisticated and capable autonomous agents.
【5】Domain-driven Metrics for Reinforcement Learning: A Case Study on Epidemic Control using Agent-based Simulation
标题：基于领域驱动的强化学习方法--以基于Agent的仿真在流行病控制中的应用为例
链接：https://arxiv.org/abs/2508.05154
摘要：为了开发和优化基于代理的模型（ABM）和基于理性代理的模型（RABM），优化算法，如强化学习被广泛使用。然而，由于建模系统的复杂性和随机性，以及缺乏用于比较RL算法的标准化指标，评估基于RL的ABM和RABMS模型的性能具有挑战性。在这项研究中，我们正在为RL开发领域驱动的指标，同时建立在最先进的指标之上。我们展示了我们的“域驱动的RL指标”使用政策优化的合理ABM疾病建模案例研究，以模拟掩蔽行为，疫苗接种，并在大流行病封锁。我们的研究结果表明，使用域驱动的奖励与传统的和国家的最先进的指标，为一些不同的模拟场景，如口罩的差异可用性。
摘要：For the development and optimization of agent-based models (ABMs) and rational agent-based models (RABMs), optimization algorithms such as reinforcement learning are extensively used. However, assessing the performance of RL-based ABMs and RABMS models is challenging due to the complexity and stochasticity of the modeled systems, and the lack of well-standardized metrics for comparing RL algorithms. In this study, we are developing domain-driven metrics for RL, while building on state-of-the-art metrics. We demonstrate our ``Domain-driven-RL-metrics'' using policy optimization on a rational ABM disease modeling case study to model masking behavior, vaccination, and lockdown in a pandemic. Our results show the use of domain-driven rewards in conjunction with traditional and state-of-the-art metrics for a few different simulation scenarios such as the differential availability of masks.
元学习(1篇)
【1】FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fields
标题：FedMeNF：用于神经领域的隐私保护联邦元学习
链接：https://arxiv.org/abs/2508.06301
备注：ICCV 2025
摘要：神经场提供了一种高效的数据表示方法，可以有效地处理不同的模态和大规模数据。然而，学习映射神经场通常需要大量的训练数据和计算，这可能限于资源受限的边缘设备。解决这一限制的一种方法是利用联邦元学习（FML），但传统的FML方法存在隐私泄露的问题。为了解决这些问题，我们引入了一种新的FML方法，称为FedMeNF。FedMeNF利用一种新的隐私保护损失函数，在局部元优化中调节隐私泄漏。这使得本地元学习器能够快速有效地进行优化，而无需保留客户端的私有数据。我们的实验表明，FedMeNF实现了快速的优化速度和鲁棒的重建性能，即使在不同的数据模式Few-Shot或非IID数据，同时保护客户端数据隐私。
摘要：Neural fields provide a memory-efficient representation of data, which can effectively handle diverse modalities and large-scale data. However, learning to map neural fields often requires large amounts of training data and computations, which can be limited to resource-constrained edge devices. One approach to tackle this limitation is to leverage Federated Meta-Learning (FML), but traditional FML approaches suffer from privacy leakage. To address these issues, we introduce a novel FML approach called FedMeNF. FedMeNF utilizes a new privacy-preserving loss function that regulates privacy leakage in the local meta-optimization. This enables the local meta-learner to optimize quickly and efficiently without retaining the client's private data. Our experiments demonstrate that FedMeNF achieves fast optimization speed and robust reconstruction performance, even with few-shot or non-IID data across diverse data modalities, while preserving client data privacy.
符号|符号学习(1篇)
【1】Tree-Based Deep Learning for Ranking Symbolic Integration Algorithms
标题：基于树的深度学习排序符号积分算法
链接：https://arxiv.org/abs/2508.06383
备注：29 pages, 13 figures, 5 tables, submitted to Transactions on Mathematical Software (TOMS)
摘要：计算机代数系统中的符号不定积分涉及从多种可用方法中选择最有效的算法。对于给定的问题，并非所有的方法都能成功，当有几种方法成功时，结果虽然在数学上是等价的，但在表达复杂性上可能会有很大的不同。传统上，这种选择是在对问题实例考虑最少的情况下做出的，导致效率低下。 我们提出了一种在两阶段架构中使用基于树的深度学习模型的机器学习（ML）方法：首先确定给定实例的适用方法，然后根据预测的输出复杂度对其进行排名。此外，我们发现将数学表达式表示为树结构显着提高了基于序列的表示的性能，并且我们的两阶段框架优于其他ML公式。 使用由六个不同的数据生成器生成的多样化数据集，我们的模型在70，000个示例保持测试集上选择最佳方法的准确率接近90%。在Maple内部测试套件的独立分布外基准测试中，我们的树Transformer模型保持了强大的泛化能力，优于Maple的内置选择器和先前的ML方法。 这些结果突出了ML中数据表示和问题框架在符号计算中的关键作用，我们希望我们的方法能有效地推广到数学软件中的类似优化问题。
摘要：Symbolic indefinite integration in Computer Algebra Systems such as Maple involves selecting the most effective algorithm from multiple available methods. Not all methods will succeed for a given problem, and when several do, the results, though mathematically equivalent, can differ greatly in presentation complexity. Traditionally, this choice has been made with minimal consideration of the problem instance, leading to inefficiencies. We present a machine learning (ML) approach using tree-based deep learning models within a two-stage architecture: first identifying applicable methods for a given instance, then ranking them by predicted output complexity. Furthermore, we find representing mathematical expressions as tree structures significantly improves performance over sequence-based representations, and our two-stage framework outperforms alternative ML formulations. Using a diverse dataset generated by six distinct data generators, our models achieve nearly 90% accuracy in selecting the optimal method on a 70,000 example holdout test set. On an independent out-of-distribution benchmark from Maple's internal test suite, our tree transformer model maintains strong generalisation, outperforming Maple's built-in selector and prior ML approaches. These results highlight the critical role of data representation and problem framing in ML for symbolic computation, and we expect our methodology to generalise effectively to similar optimisation problems in mathematical software.
医学相关(3篇)
【1】ActivityDiff: A diffusion model with Positive and Negative Activity Guidance for De Novo Drug Design
标题：ActivityDiff：用于从头开始药物设计的具有正和负活性指导的扩散模型
链接：https://arxiv.org/abs/2508.06364
摘要：实现精确控制分子的生物活性，包括有针对性的激活/抑制，合作多靶点调节，脱靶毒性减轻仍然是一个关键的挑战，从头药物设计。然而，现有的生成方法主要集中于产生具有单一所需活性的分子，缺乏用于同时管理多种预期和非预期分子相互作用的集成机制。在这里，我们提出了ActivityDiff，一种基于扩散模型的分类指导技术的生成方法。它利用单独训练的药物靶标分类器进行积极和消极的指导，使模型能够增强所需的活动，同时最大限度地减少有害的脱靶效应。实验结果表明，ActivityDiff有效地处理基本药物设计任务，包括单/双靶标生成，片段约束的双靶标设计，选择性生成以增强靶标特异性，以及减少脱靶效应。这些结果证明了分类器引导扩散在分子设计中平衡功效和安全性的有效性。总的来说，我们的工作介绍了一种新的模式，实现综合控制分子活性，并提供ActivityDiff作为一个通用的和可扩展的框架。
摘要 ：Achieving precise control over a molecule's biological activity-encompassing targeted activation/inhibition, cooperative multi-target modulation, and off-target toxicity mitigation-remains a critical challenge in de novo drug design. However, existing generative methods primarily focus on producing molecules with a single desired activity, lacking integrated mechanisms for the simultaneous management of multiple intended and unintended molecular interactions. Here, we propose ActivityDiff, a generative approach based on the classifier-guidance technique of diffusion models. It leverages separately trained drug-target classifiers for both positive and negative guidance, enabling the model to enhance desired activities while minimizing harmful off-target effects. Experimental results show that ActivityDiff effectively handles essential drug design tasks, including single-/dual-target generation, fragment-constrained dual-target design, selective generation to enhance target specificity, and reduction of off-target effects. These results demonstrate the effectiveness of classifier-guided diffusion in balancing efficacy and safety in molecular design. Overall, our work introduces a novel paradigm for achieving integrated control over molecular activity, and provides ActivityDiff as a versatile and extensible framework.
【2】Improving Diagnostic Accuracy for Oral Cancer with inpainting Synthesis Lesions Generated Using Diffusion Models
标题：通过修复使用扩散模型生成的合成病变来提高口腔癌的诊断准确性
链接：https://arxiv.org/abs/2508.06151
摘要：在口腔癌诊断中，注释数据集的有限可用性经常限制诊断模型的性能，特别是由于训练数据的可变性和不足。为了应对这些挑战，本研究提出了一种新的方法，通过使用具有微调扩散模型的修复技术合成逼真的口腔癌病变来提高诊断准确性。我们从多个来源汇编了一个综合数据集，其中包含各种口腔癌图像。我们的方法生成的合成病变表现出高度的视觉保真度的实际病变，从而显着提高诊断算法的性能。结果表明，我们的分类模型在区分癌组织和非癌组织方面的诊断准确率达到了0.97，而我们的检测模型准确地识别了病变位置，准确率为0.85。该方法验证了医学诊断中合成图像生成的潜力，并为进一步研究将这些方法扩展到其他类型的癌症诊断铺平了道路。
摘要：In oral cancer diagnostics, the limited availability of annotated datasets frequently constrains the performance of diagnostic models, particularly due to the variability and insufficiency of training data. To address these challenges, this study proposed a novel approach to enhance diagnostic accuracy by synthesizing realistic oral cancer lesions using an inpainting technique with a fine-tuned diffusion model. We compiled a comprehensive dataset from multiple sources, featuring a variety of oral cancer images. Our method generated synthetic lesions that exhibit a high degree of visual fidelity to actual lesions, thereby significantly enhancing the performance of diagnostic algorithms. The results show that our classification model achieved a diagnostic accuracy of 0.97 in differentiating between cancerous and non-cancerous tissues, while our detection model accurately identified lesion locations with 0.85 accuracy. This method validates the potential for synthetic image generation in medical diagnostics and paves the way for further research into extending these methods to other types of cancer diagnostics.
【3】A Physiologically-Constrained Neural Network Digital Twin Framework for Replicating Glucose Dynamics in Type 1 Diabetes
标题：用于复制1型糖尿病葡萄糖动力学的生理约束神经网络数字双胞胎框架
链接：https://arxiv.org/abs/2508.05705
摘要：模拟1型糖尿病（T1 D）患者的葡萄糖动力学对于开发个性化治疗和支持数据驱动的临床决策至关重要。现有的模型往往错过关键的生理方面，很难个性化。在这里，我们引入生理约束神经网络（NN）数字孪生来模拟T1 D中的葡萄糖动力学。为了确保可解释性和生理一致性，我们首先建立了一个人口水平的NN状态空间模型与一组描述葡萄糖调节的常微分方程（ODE）。该模型经过正式验证，符合已知的T1 D动力学。然后，通过使用个体特定的模型来增强群体模型来创建数字双胞胎，其中包括个人数据，例如葡萄糖管理和上下文信息，捕获个体间和个体内的变异性。我们使用来自T1 D运动倡议研究的真实数据来验证我们的方法。每个参与者两周的数据被分成5小时的序列，并将模拟的血糖曲线与观察到的血糖曲线进行比较。临床相关结局用于通过配对等效性t检验和预定义的临床等效性界值评估相似性。在394例数字双胞胎中，模拟数据和观察数据之间的血糖结果相当：（70-180 mg/dL）为75.1%（模拟）与74.4$\pm$15.4%（真实; P<0.001）;低于范围的时间（<70 mg/dL）2.5$\pm$5.2% vs.3.0$\pm$3.3%（P=0.022）;高于范围的时间（>180 mg/dL）22.4$\pm$22.0% vs.22.6$\pm$15.9%（P<0.001）。我们的框架可以结合未建模的因素，如睡眠和活动，同时保留关键动态。这种方法可以对治疗进行个性化的计算机测试，支持胰岛素优化，并集成了基于物理和数据驱动的建模。代码：https://github.com/mosqueralopez/T1DSim_AI
摘要：Simulating glucose dynamics in individuals with type 1 diabetes (T1D) is critical for developing personalized treatments and supporting data-driven clinical decisions. Existing models often miss key physiological aspects and are difficult to individualize. Here, we introduce physiologically-constrained neural network (NN) digital twins to simulate glucose dynamics in T1D. To ensure interpretability and physiological consistency, we first build a population-level NN state-space model aligned with a set of ordinary differential equations (ODEs) describing glucose regulation. This model is formally verified to conform to known T1D dynamics. Digital twins are then created by augmenting the population model with individual-specific models, which include personal data, such as glucose management and contextual information, capturing both inter- and intra-individual variability. We validate our approach using real-world data from the T1D Exercise Initiative study. Two weeks of data per participant were split into 5-hour sequences and simulated glucose profiles were compared to observed ones. Clinically relevant outcomes were used to assess similarity via paired equivalence t-tests with predefined clinical equivalence margins. Across 394 digital twins, glucose outcomes were equivalent between simulated and observed data: time in range (70-180 mg/dL) was 75.1$\pm$21.2% (simulated) vs. 74.4$\pm$15.4% (real; P<0.001); time below range (<70 mg/dL) 2.5$\pm$5.2% vs. 3.0$\pm$3.3% (P=0.022); and time above range (>180 mg/dL) 22.4$\pm$22.0% vs. 22.6$\pm$15.9% (P<0.001). Our framework can incorporate unmodeled factors like sleep and activity while preserving key dynamics. This approach enables personalized in silico testing of treatments, supports insulin optimization, and integrates physics-based and data-driven modeling. Code: https://github.com/mosqueralopez/T1DSim_AI
推荐(1篇)
【1】Breaking the Top-$K$ Barrier: Advancing Top-$K$ Ranking Metrics Optimization in Recommender Systems
标题：打破顶级$K$障碍：推进推荐系统中顶级$K$排名收件箱优化
链接：https://arxiv.org/abs/2508.05673
备注：Accepted by KDD 2025
摘要：在推荐系统（RS）领域，诸如NDCG@$K$之类的Top $K$ ranking度量是评估推荐性能的黄金标准。然而，在推荐模型的训练过程中，由于其固有的不连续性和复杂的Top-$K$截断，优化NDCG@$K$带来了巨大的挑战。最近优化NDCG@$K$的努力要么忽略了Top-$K$截断，要么遭受了高计算成本和训练不稳定性。为了克服这些限制，我们提出了SoftmaxLoss@$K$（SL@$K$），一种专为NDCG@$K$优化而设计的新型推荐损失。具体来说，我们整合了分位数技术来处理Top-$K$截断，并推导出一个平滑的上限，用于优化NDCG@$K$来解决不连续性。由此产生的SL@$K$损失有几个理想的属性，包括理论保证，易于实现，计算效率，梯度稳定性和噪声鲁棒性。在四个真实数据集和三个推荐主干上的广泛实验表明，SL@$K$优于现有的损失，平均改善6.03%。该代码可在https://github.com/Tiny-Snow/IR-Benchmark上获得。
摘要：In the realm of recommender systems (RS), Top-$K$ ranking metrics such as NDCG@$K$ are the gold standard for evaluating recommendation performance. However, during the training of recommendation models, optimizing NDCG@$K$ poses significant challenges due to its inherent discontinuous nature and the intricate Top-$K$ truncation. Recent efforts to optimize NDCG@$K$ have either overlooked the Top-$K$ truncation or suffered from high computational costs and training instability. To overcome these limitations, we propose SoftmaxLoss@$K$ (SL@$K$), a novel recommendation loss tailored for NDCG@$K$ optimization. Specifically, we integrate the quantile technique to handle Top-$K$ truncation and derive a smooth upper bound for optimizing NDCG@$K$ to address discontinuity. The resulting SL@$K$ loss has several desirable properties, including theoretical guarantees, ease of implementation, computational efficiency, gradient stability, and noise robustness. Extensive experiments on four real-world datasets and three recommendation backbones demonstrate that SL@$K$ outperforms existing losses with a notable average improvement of 6.03%. The code is available at https://github.com/Tiny-Snow/IR-Benchmark.
聚类(1篇)
【1】Differentially Private Federated Clustering with Random Rebalancing
标题：具有随机再平衡的差异私有联合集群
链接：https://arxiv.org/abs/2508.06183
备注：21 pages
摘要：联合聚类的目的是将相似的客户机分组到集群中，并为每个集群生成一个模型。与训练单个模型来服务所有客户端相比，这种个性化方法通常会提高模型性能，但可能更容易受到隐私泄露的影响。直接将客户端级别的差异私有（DP）机制应用于联邦集群可能会显着降低实用程序。我们确定，这种缺陷主要是由于每个集群内的平均隐私噪声（以下标准的隐私机制）的困难，因为分配给相同的集群的客户端的数量是不受控制的。为此，我们提出了一个简单而有效的技术，称为RR集群，可以被视为一个轻量级的附加到许多联邦聚类算法。RR-Cluster通过随机重新平衡集群分配来降低隐私噪声，保证分配给每个集群的客户端数量最少。我们分析了降低隐私噪声方差和可能增加的偏见不正确的分配之间的权衡，并提供收敛界RR-Clsuter。从经验上讲，我们证明了插入到强大的联邦聚类算法中的RR-集群在合成数据集和真实世界数据集上都显着改善了隐私/实用性权衡。
摘要：Federated clustering aims to group similar clients into clusters and produce one model for each cluster. Such a personalization approach typically improves model performance compared with training a single model to serve all clients, but can be more vulnerable to privacy leakage. Directly applying client-level differentially private (DP) mechanisms to federated clustering could degrade the utilities significantly. We identify that such deficiencies are mainly due to the difficulties of averaging privacy noise within each cluster (following standard privacy mechanisms), as the number of clients assigned to the same clusters is uncontrolled. To this end, we propose a simple and effective technique, named RR-Cluster, that can be viewed as a light-weight add-on to many federated clustering algorithms. RR-Cluster achieves reduced privacy noise via randomly rebalancing cluster assignments, guaranteeing a minimum number of clients assigned to each cluster. We analyze the tradeoffs between decreased privacy noise variance and potentially increased bias from incorrect assignments and provide convergence bounds for RR-Clsuter. Empirically, we demonstrate the RR-Cluster plugged into strong federated clustering algorithms results in significantly improved privacy/utility tradeoffs across both synthetic and real-world datasets.
自动驾驶|车辆|车道检测等(1篇)
【1】Lightweight Auto-bidding based on Traffic Prediction in Live Advertising
标题：基于流量预测的实时广告轻量级自动竞价
链接：https://arxiv.org/abs/2508.06069
摘要：互联网直播广泛应用于在线娱乐和电子商务，其中直播广告是主播的重要营销手段。广告活动希望在限制（如预算和每次点击成本）下最大化效果（如转换）。活动的主流控制是自动出价，其中性能取决于每个请求中的出价算法的决定。应用最广泛的自动竞价算法包括比例积分微分（PID）控制、线性规划（LP）、强化学习（RL）等。现有方法要么没有考虑整个时间流量，要么计算复杂度过高。在本文中，直播广告对实时竞价（秒级控制）的要求很高，面临着未来流量未知的困难。为此，本文提出了一种轻量级的竞价算法--二元约束竞价（Binary Constrained Bidding，BiCB），它巧妙地结合了数学分析给出的最优竞价公式和未来流量估计的统计方法，通过低复杂度的求解获得了对最优结果的良好逼近。此外，我们补充了传统的自动报价模型的上下限约束的形式，并给出了BiCB的理论分析。大量的离线和在线实验证明了BiCB的良好性能和较低的工程成本。
摘要：Internet live streaming is widely used in online entertainment and e-commerce, where live advertising is an important marketing tool for anchors. An advertising campaign hopes to maximize the effect (such as conversions) under constraints (such as budget and cost-per-click). The mainstream control of campaigns is auto-bidding, where the performance depends on the decision of the bidding algorithm in each request. The most widely used auto-bidding algorithms include Proportional-Integral-Derivative (PID) control, linear programming (LP), reinforcement learning (RL), etc. Existing methods either do not consider the entire time traffic, or have too high computational complexity. In this paper, the live advertising has high requirements for real-time bidding (second-level control) and faces the difficulty of unknown future traffic. Therefore, we propose a lightweight bidding algorithm Binary Constrained Bidding (BiCB), which neatly combines the optimal bidding formula given by mathematical analysis and the statistical method of future traffic estimation, and obtains good approximation to the optimal result through a low complexity solution. In addition, we complement the form of upper and lower bound constraints for traditional auto-bidding modeling and give theoretical analysis of BiCB. Sufficient offline and online experiments prove BiCB's good performance and low engineering cost.
联邦学习|隐私保护|加密(1篇)
【1】Blockchain-Enabled Federated Learning
标题：区块链支持的联邦学习
链接：https://arxiv.org/abs/2508.06406
备注：32 pages, 6 figures, chapter for edited book (Federated Learning: Foundations and Applications)
摘要：基于区块链的联邦学习（BCFL）解决了协作AI系统中信任、隐私和协调的基本挑战。本章通过系统的四维分类法研究协调结构、共识机制、存储架构和信任模型，提供了BCFL系统的全面架构分析。我们分析了从区块链验证的集中式协调到完全分散的对等网络的设计模式，评估了可扩展性，安全性和性能方面的权衡。通过详细检查为联邦学习环境设计的共识机制，包括质量证明和联邦学习证明，我们展示了如何将计算工作从任意加密难题重新利用到高效的机器学习任务。本章通过研究多层架构来解决关键的存储挑战，该架构平衡了区块链的交易约束与神经网络的大参数要求，同时保持了加密的完整性。TrustMesh框架的技术案例研究通过分布式图像分类训练说明了BCFL系统中的实际实施考虑因素，展示了具有高度非IID数据分布的物联网设备之间的有效协作学习，同时保持完全的透明度和容错性。对医疗联盟、金融服务和物联网安全应用的实际部署进行的分析验证了BCFL系统的实际可行性，实现了与集中式方法相当的性能，同时提供了增强的安全保障，并实现了无需信任的协作智能新模型。
摘要：Blockchain-enabled federated learning (BCFL) addresses fundamental challenges of trust, privacy, and coordination in collaborative AI systems. This chapter provides comprehensive architectural analysis of BCFL systems through a systematic four-dimensional taxonomy examining coordination structures, consensus mechanisms, storage architectures, and trust models. We analyze design patterns from blockchain-verified centralized coordination to fully decentralized peer-to-peer networks, evaluating trade-offs in scalability, security, and performance. Through detailed examination of consensus mechanisms designed for federated learning contexts, including Proof of Quality and Proof of Federated Learning, we demonstrate how computational work can be repurposed from arbitrary cryptographic puzzles to productive machine learning tasks. The chapter addresses critical storage challenges by examining multi-tier architectures that balance blockchain's transaction constraints with neural networks' large parameter requirements while maintaining cryptographic integrity. A technical case study of the TrustMesh framework illustrates practical implementation considerations in BCFL systems through distributed image classification training, demonstrating effective collaborative learning across IoT devices with highly non-IID data distributions while maintaining complete transparency and fault tolerance. Analysis of real-world deployments across healthcare consortiums, financial services, and IoT security applications validates the practical viability of BCFL systems, achieving performance comparable to centralized approaches while providing enhanced security guarantees and enabling new models of trustless collaborative intelligence.
推理|分析|理解|解释(6篇)
【1】Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal
标题：修剪不令人惊讶的：通过第一个令牌惊喜进行高效代码推理
链接：https://arxiv.org/abs/2508.05988
备注：Code and model available at this https URL
摘要：最近，大型推理模型（LRM）通过扩展思想链（CoT）的长度在代码推理中表现出了显着的能力。然而，过长的推理轨迹在训练成本、推理延迟和部署可行性方面带来了巨大的挑战。虽然已经出现了各种CoT压缩方法来解决这一挑战，但它们面临着固有的权衡：令牌级方法通常会破坏语法和逻辑一致性，而基于困惑的步骤级方法无法可靠地捕获逻辑关键推理步骤。在本文中，我们提出了ASAP（锚点引导，惊喜为基础的修剪），一种新的CoT压缩的粗到细的框架。ASAP首先进行锚点引导的剪枝以保留核心推理结构，有效地减少了后续处理的搜索空间。然后，它使一个逻辑感知修剪选择逻辑上必要的推理步骤的基础上，一个新的第一令牌抽象度量。最后，ASAP教导模型在推理时自主生成和利用这些简洁的CoT，从而在编码任务中实现高效推理。实验表明，ASAP在多个代码生成基准测试中实现了最先进的准确性，同时大大降低了训练和推理成本。在具有挑战性的LiveCodeBench v4_v5基准测试中，与最强基线相比，我们的方法将令牌生成减少了23.5%，推理延迟减少了43.5%，同时在Pass@1中实现了36.19%的竞争准确性。我们的研究结果突出了一个有前途的方向，建立强大而高效的LRM。
摘要：Recently, Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in code reasoning by scaling up the length of Chain-of-Thought (CoT). However, excessively long reasoning traces introduce substantial challenges in terms of training cost, inference latency, and deployment feasibility. While various CoT compression approaches have emerged to address this challenge, they face inherent trade-offs: token-level methods often disrupt syntactic and logical coherence, while step-level methods based on perplexity fail to reliably capture the logically critical reasoning steps. In this paper, we propose ASAP (Anchor-guided, Surprisal-based Pruning), a novel coarse-to-fine framework for CoT compression. ASAP first performs anchor-guided pruning to preserve the core reasoning structure, which efficiently reduces the search space for subsequent processing. It then enables a logic-aware pruning by selecting logically essential reasoning steps based on a novel first-token surprisal metric. Finally, ASAP teaches models to autonomously generate and leverage these concise CoTs at inference time, enabling efficient reasoning in coding tasks. Experiments show that ASAP achieves state-of-the-art accuracy across multiple code generation benchmarks while substantially reducing training and inference costs. On the challenging LiveCodeBench v4_v5 benchmark, our approach reduces token generation by 23.5% and inference latency by 43.5% compared to the strongest baseline, while achieving a competitive accuracy of 36.19% in Pass@1. Our results highlight a promising direction for building powerful and efficient LRMs.
【2】Enhancing Construction Site Analysis and Understanding with 3D Segmentation
标题：利用3D分割增强建筑工地分析和理解
链接：https://arxiv.org/abs/2508.05922
摘要：监测施工进度至关重要，但需要大量资源，这促使人们探索基于计算机视觉的方法，以提高效率和可扩展性。传统的数据采集方法，主要集中在室内环境，动摇在建筑工地的复杂，杂乱，动态变化的条件。本文批判性地评估了两种先进的3D分割方法，Segment Anything Model（SAM）和Mask3D在具有挑战性的室外和室内条件下的应用。最初在室内数据集上进行训练，这两个模型的适应性和性能在现实世界的建筑环境中进行评估，突出了由于缺乏室外场景基准而导致的当前分割方法的差距。通过比较分析，这项研究不仅展示了SAM和Mask3D的相对有效性，而且还解决了定制分割工作流程的关键需求，这些工作流程能够从施工现场数据中提取可操作的见解，从而将该领域推向更加自动化和精确的监控技术。
摘要：Monitoring construction progress is crucial yet resource-intensive, prompting the exploration of computer-vision-based methodologies for enhanced efficiency and scalability. Traditional data acquisition methods, primarily focusing on indoor environments, falter in construction site's complex, cluttered, and dynamically changing conditions. This paper critically evaluates the application of two advanced 3D segmentation methods, Segment Anything Model (SAM) and Mask3D, in challenging outdoor and indoor conditions. Trained initially on indoor datasets, both models' adaptability and performance are assessed in real-world construction settings, highlighting the gap in current segmentation approaches due to the absence of benchmarks for outdoor scenarios. Through a comparative analysis, this study not only showcases the relative effectiveness of SAM and Mask3D but also addresses the critical need for tailored segmentation workflows capable of extracting actionable insights from construction site data, thereby advancing the field towards more automated and precise monitoring techniques.
【3】From Imperfect Signals to Trustworthy Structure: Confidence-Aware Inference from Heterogeneous and Reliability-Varying Utility Data
标题：从不完美的信号到值得信赖的结构：来自异类和可靠性变化的公用事业数据的信任意识推理
链接：https://arxiv.org/abs/2508.05791
备注：10 pages
摘要：精确的配电网拓扑结构对于可靠的现代电网运行至关重要。然而，真实世界的公用事业数据来自多个来源，具有不同的特征和质量水平。在这项工作中，与Oncor电力交付合作开发，我们提出了一个可扩展的框架，重建一个值得信赖的网格拓扑结构，系统地整合异构数据。我们观察到，分布拓扑结构从根本上由两个互补的维度控制：物理基础设施的空间布局（例如，GIS和资产元数据）和系统在信号域中的动态行为（例如，电压时间序列）。当联合利用时，这些维度支持网络连接的完整和物理上一致的重建。为了在不影响可观测性的情况下解决数据质量不均匀的挑战，我们引入了一种置信度感知的推理机制，该机制保留了结构上信息丰富但不完美的输入，同时量化了每个推断连接的可靠性以供操作员解释。这种对不确定性的软处理与物理可行性的硬执行紧密耦合：我们将操作约束（如Transformer容量限制和径向拓扑要求）直接嵌入学习过程。这些组件共同确保推理既具有不确定性，又具有结构上的有效性，从而能够在实际部署条件下快速收敛到可操作的、值得信赖的拓扑。所提出的框架进行了验证，使用超过8000米的数据在3个馈线Oncor的服务领域，证明超过95%的准确性，拓扑结构重建和大幅改善的信心校准和计算效率相对于基线方法。
摘要：Accurate distribution grid topology is essential for reliable modern grid operations. However, real-world utility data originates from multiple sources with varying characteristics and levels of quality. In this work, developed in collaboration with Oncor Electric Delivery, we propose a scalable framework that reconstructs a trustworthy grid topology by systematically integrating heterogeneous data. We observe that distribution topology is fundamentally governed by two complementary dimensions: the spatial layout of physical infrastructure (e.g., GIS and asset metadata) and the dynamic behavior of the system in the signal domain (e.g., voltage time series). When jointly leveraged, these dimensions support a complete and physically coherent reconstruction of network connectivity. To address the challenge of uneven data quality without compromising observability, we introduce a confidence-aware inference mechanism that preserves structurally informative yet imperfect inputs, while quantifying the reliability of each inferred connection for operator interpretation. This soft handling of uncertainty is tightly coupled with hard enforcement of physical feasibility: we embed operational constraints, such as transformer capacity limits and radial topology requirements, directly into the learning process. Together, these components ensure that inference is both uncertainty-aware and structurally valid, enabling rapid convergence to actionable, trustworthy topologies under real-world deployment conditions. The proposed framework is validated using data from over 8000 meters across 3 feeders in Oncor's service territory, demonstrating over 95% accuracy in topology reconstruction and substantial improvements in confidence calibration and computational efficiency relative to baseline methods.
【4】A Framework for Inherently Safer AGI through Language-Mediated Active Inference
标题：通过数据介导的主动推理实现本质上更安全的AGI框架
链接：https://arxiv.org/abs/2508.05766
摘要 ：本文提出了一种新的框架，开发安全的人工通用智能（AGI）结合主动推理原则与大型语言模型（LLM）。我们认为，传统的人工智能安全方法，专注于事后可解释性和奖励工程，具有根本的局限性。我们提出了一个架构，安全保证集成到系统的核心设计，通过透明的信念表示和层次值对齐。我们的框架利用自然语言作为表示和操纵信念的媒介，在保持计算易处理性的同时实现直接的人类监督。该体系结构实现了一个多代理系统，代理自组织根据主动推理原则，通过层次马尔可夫毯流动的偏好和安全约束。我们概述了确保安全的具体机制，包括：（1）在自然语言中明确分离信念和偏好，（2）通过资源感知自由能最小化的有限理性，以及（3）通过模块化代理结构的组合安全。本文的结论与研究议程集中的抽象和推理语料库（ARC）基准，提出实验来验证我们的框架的安全性能。我们的方法提供了一条通往AGI发展的道路，这种道路本质上更安全，而不是通过安全措施进行改造。
摘要：This paper proposes a novel framework for developing safe Artificial General Intelligence (AGI) by combining Active Inference principles with Large Language Models (LLMs). We argue that traditional approaches to AI safety, focused on post-hoc interpretability and reward engineering, have fundamental limitations. We present an architecture where safety guarantees are integrated into the system's core design through transparent belief representations and hierarchical value alignment. Our framework leverages natural language as a medium for representing and manipulating beliefs, enabling direct human oversight while maintaining computational tractability. The architecture implements a multi-agent system where agents self-organize according to Active Inference principles, with preferences and safety constraints flowing through hierarchical Markov blankets. We outline specific mechanisms for ensuring safety, including: (1) explicit separation of beliefs and preferences in natural language, (2) bounded rationality through resource-aware free energy minimization, and (3) compositional safety through modular agent structures. The paper concludes with a research agenda centered on the Abstraction and Reasoning Corpus (ARC) benchmark, proposing experiments to validate our framework's safety properties. Our approach offers a path toward AGI development that is inherently safer, rather than retrofitted with safety measures.
【5】G-UBS: Towards Robust Understanding of Implicit Feedback via Group-Aware User Behavior Simulation
标题：G-UBS：通过群体意识用户行为模拟来稳健地理解隐性反馈
链接：https://arxiv.org/abs/2508.05709
摘要：用户反馈对于改进推荐系统至关重要，但明确的反馈（例如，喜欢或不喜欢）在实践中仍然很少。作为更可行的替代方案，从大量隐式反馈中推断用户偏好已经显示出巨大的潜力（例如，用户快速跳过推荐的视频通常表示不感兴趣）。不幸的是，隐式反馈通常是嘈杂的：用户可能会由于意外点击或其他原因而跳过视频，而不是不喜欢它。这种噪音很容易误判用户的兴趣，从而影响推荐性能。为了解决这个问题，我们提出了一种新的群体感知用户行为模拟（G-UBS）范式，它利用相关用户群体的上下文指导，使个人用户的隐式反馈的强大和深入的解释。具体而言，G-UBS通过两个关键代理商运营。首先，用户组管理器（UGM）有效地集群用户生成组配置文件，利用基于LLM的"摘要-集群-反映”工作流。其次，用户反馈建模器（UFM）采用了一种创新的群体感知强化学习方法，在强化学习过程中，每个用户都受到相关群体配置文件的指导，从而使UFM能够强大而深入地研究隐式反馈背后的原因。为了评估我们的G-UBS范式，我们构建了一个具有隐式反馈的视频推荐基准（IF-VR）。据我们所知，这是视频推荐中隐式反馈评估的第一个多模态基准，包括15 k用户，25 k视频和933 k具有隐式反馈的交互记录。在IF-VR上进行的大量实验表明，G-UBS的性能明显优于主流LLM和MLLM，在IF-VR上实现播放率> 30%的视频比例高出4.0%，推理准确率高出14.9%。
摘要：User feedback is critical for refining recommendation systems, yet explicit feedback (e.g., likes or dislikes) remains scarce in practice. As a more feasible alternative, inferring user preferences from massive implicit feedback has shown great potential (e.g., a user quickly skipping a recommended video usually indicates disinterest). Unfortunately, implicit feedback is often noisy: a user might skip a video due to accidental clicks or other reasons, rather than disliking it. Such noise can easily misjudge user interests, thereby undermining recommendation performance. To address this issue, we propose a novel Group-aware User Behavior Simulation (G-UBS) paradigm, which leverages contextual guidance from relevant user groups, enabling robust and in-depth interpretation of implicit feedback for individual users. Specifically, G-UBS operates via two key agents. First, the User Group Manager (UGM) effectively clusters users to generate group profiles utilizing a ``summarize-cluster-reflect" workflow based on LLMs. Second, the User Feedback Modeler (UFM) employs an innovative group-aware reinforcement learning approach, where each user is guided by the associated group profiles during the reinforcement learning process, allowing UFM to robustly and deeply examine the reasons behind implicit feedback. To assess our G-UBS paradigm, we have constructed a Video Recommendation benchmark with Implicit Feedback (IF-VR). To the best of our knowledge, this is the first multi-modal benchmark for implicit feedback evaluation in video recommendation, encompassing 15k users, 25k videos, and 933k interaction records with implicit feedback. Extensive experiments on IF-VR demonstrate that G-UBS significantly outperforms mainstream LLMs and MLLMs, with a 4.0% higher proportion of videos achieving a play rate > 30% and 14.9% higher reasoning accuracy on IF-VR.
【6】Reduction Techniques for Survival Analysis
标题：生存分析的归约技术
链接：https://arxiv.org/abs/2508.05715
摘要：在这项工作中，我们讨论了我们所说的生存分析的减少技术，也就是说，“减少”生存任务到一个更常见的回归或分类任务的技术，而不忽略生存数据的具体情况。这些技术特别有利于基于机器学习的生存分析，因为它们允许将机器和深度学习的标准工具应用于许多生存任务，而不需要自定义学习器。我们提供了不同的减少技术的概述，并讨论各自的优点和缺点。我们还提供了其中一些减少的原则性实现，以便它们可以直接在标准机器学习工作流程中使用。我们使用专门的例子来说明每个减少，并执行基准分析，将其预测性能与已建立的机器学习方法进行生存分析。
摘要：In this work, we discuss what we refer to as reduction techniques for survival analysis, that is, techniques that "reduce" a survival task to a more common regression or classification task, without ignoring the specifics of survival data. Such techniques particularly facilitate machine learning-based survival analysis, as they allow for applying standard tools from machine and deep learning to many survival tasks without requiring custom learners. We provide an overview of different reduction techniques and discuss their respective strengths and weaknesses. We also provide a principled implementation of some of these reductions, such that they are directly available within standard machine learning workflows. We illustrate each reduction using dedicated examples and perform a benchmark analysis that compares their predictive performance to established machine learning methods for survival analysis.
检测相关(3篇)
【1】Classification is a RAG problem: A case study on hate speech detection
标题：分类是一个RAG问题：仇恨言论检测的案例研究
链接：https://arxiv.org/abs/2508.06204
摘要：强大的内容审核要求分类系统能够快速适应不断变化的政策，而无需昂贵的重新培训。我们使用检索增强生成（RAG）进行分类，该方法将传统的分类任务从根据预先训练的参数确定正确的类别转变为评估与推理时检索到的上下文知识相关的内容。在仇恨言论检测中，这将任务从“这是仇恨言论吗？“到“这是否违反了仇恨言论政策？" 我们的上下文策略引擎（CPE）-一个代理RAG系统-演示了这种方法，并提供了三个关键优势：（1）与领先的商业系统相当的强大分类准确性，（2）通过检索策略段的内在可解释性，以及（3）无需模型再训练的动态策略更新。通过三个实验，我们展示了强大的基线性能，并表明该系统可以通过正确调整对特定身份组的保护来应用细粒度的策略控制，而无需重新训练或牺牲整体性能。这些发现表明，RAG可以将分类转变为一个更灵活，透明和适应性更强的过程，以解决内容审核和更广泛的分类问题。
摘要 ：Robust content moderation requires classification systems that can quickly adapt to evolving policies without costly retraining. We present classification using Retrieval-Augmented Generation (RAG), which shifts traditional classification tasks from determining the correct category in accordance with pre-trained parameters to evaluating content in relation to contextual knowledge retrieved at inference. In hate speech detection, this transforms the task from "is this hate speech?" to "does this violate the hate speech policy?" Our Contextual Policy Engine (CPE) - an agentic RAG system - demonstrates this approach and offers three key advantages: (1) robust classification accuracy comparable to leading commercial systems, (2) inherent explainability via retrieved policy segments, and (3) dynamic policy updates without model retraining. Through three experiments, we demonstrate strong baseline performance and show that the system can apply fine-grained policy control by correctly adjusting protection for specific identity groups without requiring retraining or compromising overall performance. These findings establish that RAG can transform classification into a more flexible, transparent, and adaptable process for content moderation and wider classification problems.
【2】MambaITD: An Efficient Cross-Modal Mamba Network for Insider Threat Detection
标题：MambaITD：用于内部威胁检测的高效跨模式Mamba网络
链接：https://arxiv.org/abs/2508.05695
备注：Submitted to the 2025 IEEE International Conference on Data Mining (ICDM)
摘要：企业面临的内部威胁风险越来越大，而现有的检测方法由于时间动态特征建模不足、计算效率和实时性瓶颈以及跨模态信息孤岛问题等原因，无法有效应对这些挑战。提出了一种基于Mamba状态空间模型和跨模态自适应融合的内部威胁检测框架MambaITD。首先，多源日志预处理模块通过行为序列编码、区间平滑和统计特征提取来对齐异构数据。其次，Mamba编码器对行为和间隔序列中的长程依赖性进行建模，并结合门控特征融合机制动态地组合序列和统计信息。最后，提出了一种基于类间方差最大化的自适应阈值优化方法，通过分析概率分布动态调整决策阈值，有效识别异常，消除类别不平衡和概念漂移。与传统方法相比，MambaITD在建模效率和特征融合能力方面表现出显著优势，优于基于Transformer的方法，为内部威胁检测提供了更有效的解决方案。
摘要：Enterprises are facing increasing risks of insider threats, while existing detection methods are unable to effectively address these challenges due to reasons such as insufficient temporal dynamic feature modeling, computational efficiency and real-time bottlenecks and cross-modal information island problem. This paper proposes a new insider threat detection framework MambaITD based on the Mamba state space model and cross-modal adaptive fusion. First, the multi-source log preprocessing module aligns heterogeneous data through behavioral sequence encoding, interval smoothing, and statistical feature extraction. Second, the Mamba encoder models long-range dependencies in behavioral and interval sequences, and combines the sequence and statistical information dynamically in combination with the gated feature fusion mechanism. Finally, we propose an adaptive threshold optimization method based on maximizing inter-class variance, which dynamically adjusts the decision threshold by analyzing the probability distribution, effectively identifies anomalies, and alleviates class imbalance and concept drift. Compared with traditional methods, MambaITD shows significant advantages in modeling efficiency and feature fusion capabilities, outperforming Transformer-based methods, and provides a more effective solution for insider threat detection.
【3】Detecting Model Misspecification in Cosmology with Scale-Dependent Normalizing Flows
标题：利用尺度相关的标准化流检测宇宙学中的模型错误规范
链接：https://arxiv.org/abs/2508.05744
备注：14 + 5 pages, 6 + 4 figures
摘要：当前和即将到来的宇宙学调查将产生前所未有的大量高维数据，这需要复杂的高保真正演模拟来准确地模拟描述数据生成过程的物理过程和系统效应。然而，验证我们的理论模型是否准确地描述了观察到的数据集仍然是一个根本性的挑战。这项任务的另一个复杂性来自于选择适当的数据表示，保留所有相关的宇宙学信息，同时减少原始数据集的维数。在这项工作中，我们提出了一种新的框架结合尺度依赖的神经汇总统计与规范化流检测模型的错误指定在宇宙学模拟通过贝叶斯证据估计。通过调节我们的神经网络模型，以进行数据压缩和平滑尺度上的证据估计，我们系统地识别理论模型以数据驱动的方式崩溃的地方。我们展示了第一个应用程序，我们的方法使用物质和气体密度场从三个CAMELS模拟套件与不同的子网格物理实现。
摘要：Current and upcoming cosmological surveys will produce unprecedented amounts of high-dimensional data, which require complex high-fidelity forward simulations to accurately model both physical processes and systematic effects which describe the data generation process. However, validating whether our theoretical models accurately describe the observed datasets remains a fundamental challenge. An additional complexity to this task comes from choosing appropriate representations of the data which retain all the relevant cosmological information, while reducing the dimensionality of the original dataset. In this work we present a novel framework combining scale-dependent neural summary statistics with normalizing flows to detect model misspecification in cosmological simulations through Bayesian evidence estimation. By conditioning our neural network models for data compression and evidence estimation on the smoothing scale, we systematically identify where theoretical models break down in a data-driven manner. We demonstrate a first application to our approach using matter and gas density fields from three CAMELS simulation suites with different subgrid physics implementations.
分类|识别(3篇)
【1】Introducing Fractional Classification Loss for Robust Learning with Noisy Labels
标题：引入分数分类损失以实现具有噪音标签的鲁棒学习
链接：https://arxiv.org/abs/2508.06346
备注：25 pages, 6 figures, 2 table. Submitted to Pattern Recognition
摘要：鲁棒的损失函数对于在存在标签噪声的情况下训练深度神经网络至关重要，但现有方法需要广泛的、特定于标签的超参数调整。在这项工作中，我们引入了分数分类损失（FCL），这是一种自适应鲁棒损失，可以在训练过程中自动校准其对标签噪声的鲁棒性。在有源-无源损耗框架内，FCL采用交叉熵（CE）损耗的分数阶导数作为其有源分量，平均绝对误差（MAE）作为其无源损耗分量。有了这个公式，我们证明了分数阶导数阶$\mu$跨越一个家庭的损失函数，MAE样的鲁棒性和CE样的快速收敛之间的插值。此外，我们将$\mu$作为一个可学习的参数集成到基于梯度的优化中，并自动调整它以优化鲁棒性和收敛速度之间的权衡。我们发现，FCL的独特属性建立了一个关键的权衡，使$\mu$的稳定学习：较低的日志惩罚困难或错误标记的例子提高鲁棒性，但容易或干净的数据施加更高的处罚，降低模型的信心。因此，FCL可以动态地重塑其损失景观，以实现有效的分类性能下的标签噪声。在基准数据集上的大量实验表明，FCL实现了最先进的结果，而无需手动调整超参数。
摘要：Robust loss functions are crucial for training deep neural networks in the presence of label noise, yet existing approaches require extensive, dataset-specific hyperparameter tuning. In this work, we introduce Fractional Classification Loss (FCL), an adaptive robust loss that automatically calibrates its robustness to label noise during training. Built within the active-passive loss framework, FCL employs the fractional derivative of the Cross-Entropy (CE) loss as its active component and the Mean Absolute Error (MAE) as its passive loss component. With this formulation, we demonstrate that the fractional derivative order $\mu$ spans a family of loss functions that interpolate between MAE-like robustness and CE-like fast convergence. Furthermore, we integrate $\mu$ into the gradient-based optimization as a learnable parameter and automatically adjust it to optimize the trade-off between robustness and convergence speed. We reveal that FCL's unique property establishes a critical trade-off that enables the stable learning of $\mu$: lower log penalties on difficult or mislabeled examples improve robustness but impose higher penalties on easy or clean data, reducing model confidence in them. Consequently, FCL can dynamically reshape its loss landscape to achieve effective classification performance under label noise. Extensive experiments on benchmark datasets show that FCL achieves state-of-the-art results without the need for manual hyperparameter tuning.
【2】EmoAugNet: A Signal-Augmented Hybrid CNN-LSTM Framework for Speech Emotion Recognition
标题：CLARAugNet：用于语音情感识别的信号增强混合CNN-LSTM框架
链接：https://arxiv.org/abs/2508.06321
备注：To be published in ICCCNT 2025 (16th International Conference on Computing Communication and Networking Technologies)
摘要：语音中情感信号的识别对提高人机交互的有效性有着重要的影响。这项研究介绍了一种混合深度学习框架，它将长短期记忆（LSTM）层与一维卷积神经网络（1D-CNN）相结合，以实现可靠的语音情感识别（SER）。从语音信号中提取的特征的质量和多样性对SER系统的性能有很大的影响。一个全面的语音数据增强策略被用来结合传统的方法，如噪声添加，音调移动，和时间拉伸，与一个新的组合为基础的增强流水线，以提高泛化和减少过拟合。每个音频样本被转换成一个高维特征向量，使用均方根能量（RMSE），梅尔频率倒谱系数（MFCC），和零交叉率（ZCR）。我们的模型在IEMOCAP数据集上具有95.78\%的加权准确度和92.52\%的未加权准确度，并且具有ELU激活，具有96.75\%的加权准确度和91.28\%的未加权准确度。在RAVDESS数据集上，ReLU激活的加权准确率为94.53\%，未加权准确率为94.98\%，ELU激活的加权准确率为93.72\%，未加权准确率为94.64\%。这些结果突出了EAR-AugNet通过集成数据增强和混合建模在提高SER系统的鲁棒性和性能方面的有效性。
摘要：Recognizing emotional signals in speech has a significant impact on enhancing the effectiveness of human-computer interaction (HCI). This study introduces EmoAugNet, a hybrid deep learning framework, that incorporates Long Short-Term Memory (LSTM) layers with one-dimensional Convolutional Neural Networks (1D-CNN) to enable reliable Speech Emotion Recognition (SER). The quality and variety of the features that are taken from speech signals have a significant impact on how well SER systems perform. A comprehensive speech data augmentation strategy was used to combine both traditional methods, such as noise addition, pitch shifting, and time stretching, with a novel combination-based augmentation pipeline to enhance generalization and reduce overfitting. Each audio sample was transformed into a high-dimensional feature vector using root mean square energy (RMSE), Mel-frequency Cepstral Coefficient (MFCC), and zero-crossing rate (ZCR). Our model with ReLU activation has a weighted accuracy of 95.78\% and unweighted accuracy of 92.52\% on the IEMOCAP dataset and, with ELU activation, has a weighted accuracy of 96.75\% and unweighted accuracy of 91.28\%. On the RAVDESS dataset, we get a weighted accuracy of 94.53\% and 94.98\% unweighted accuracy for ReLU activation and 93.72\% weighted accuracy and 94.64\% unweighted accuracy for ELU activation. These results highlight EmoAugNet's effectiveness in improving the robustness and performance of SER systems through integated data augmentation and hybrid modeling.
【3】Training chord recognition models on artificially generated audio
标题：在人工生成的音频上训练和弦识别模型
链接：https://arxiv.org/abs/2508.05878
摘要：音乐信息检索中的一个挑战性问题是获得足够的非版权音频记录用于模型训练和评估。本研究比较了两种基于transformer的神经网络模型，用于音频记录中的和弦序列识别，并研究了使用人工生成的数据集进行此目的的有效性。这些模型在人工音频多轨（AAM），Schubert的Winterreise数据集和McGill Billboard数据集的各种组合上进行训练，并使用三个指标进行评估：Root，MajMin和Chord Content Metric（CCM）。实验证明，尽管人工生成的音乐和人类创作的音乐在复杂性和结构上确实存在差异，但前者在某些情况下是有用的。具体来说，AAM可以丰富由人类创作的音乐的较小训练数据集，或者甚至可以用作预测流行音乐中和弦序列的模型的独立训练集，如果没有其他数据可用的话。
摘要：One of the challenging problems in Music Information Retrieval is the acquisition of enough non-copyrighted audio recordings for model training and evaluation. This study compares two Transformer-based neural network models for chord sequence recognition in audio recordings and examines the effectiveness of using an artificially generated dataset for this purpose. The models are trained on various combinations of Artificial Audio Multitracks (AAM), Schubert's Winterreise Dataset, and the McGill Billboard Dataset and evaluated with three metrics: Root, MajMin and Chord Content Metric (CCM). The experiments prove that even though there are certainly differences in complexity and structure between artificially generated and human-composed music, the former can be useful in certain scenarios. Specifically, AAM can enrich a smaller training dataset of music composed by a human or can even be used as a standalone training set for a model that predicts chord sequences in pop music, if no other data is available.
表征(2篇)
【1】Structural Equation-VAE: Disentangled Latent Representations for Tabular Data
标题：结构方程-VAE：表格数据的解开潜在表示
链接：https://arxiv.org/abs/2508.06347
备注：10 pages, 2 figures
摘要：从表格数据中学习可解释的潜在表示仍然是深度生成建模中的一个挑战。我们介绍了SE-VAE（结构方程变分自动编码器），一种新的架构，直接嵌入测量结构的变分自动编码器的设计。受结构方程建模的启发，SE-VAE将潜在子空间与已知的指标分组对齐，并引入全局滋扰潜在来隔离特定于构建体的混淆变化。这种模块化架构可以通过设计而不是仅仅通过统计正则化器来实现解纠缠。我们评估SE-VAE一套模拟的表格数据集和基准测试其性能对一系列领先的基线使用标准的解纠缠指标。SE-VAE在因子恢复、可解释性和对干扰变化的鲁棒性方面始终优于替代方案。消融结果表明，架构结构，而不是正则化强度，是性能的关键驱动力。SE-VAE为科学和社会领域的白盒生成建模提供了一个原则性框架，其中潜在结构是理论驱动的，测量有效性是必不可少的。
摘要：Learning interpretable latent representations from tabular data remains a challenge in deep generative modeling. We introduce SE-VAE (Structural Equation-Variational Autoencoder), a novel architecture that embeds measurement structure directly into the design of a variational autoencoder. Inspired by structural equation modeling, SE-VAE aligns latent subspaces with known indicator groupings and introduces a global nuisance latent to isolate construct-specific confounding variation. This modular architecture enables disentanglement through design rather than through statistical regularizers alone. We evaluate SE-VAE on a suite of simulated tabular datasets and benchmark its performance against a series of leading baselines using standard disentanglement metrics. SE-VAE consistently outperforms alternatives in factor recovery, interpretability, and robustness to nuisance variation. Ablation results reveal that architectural structure, rather than regularization strength, is the key driver of performance. SE-VAE offers a principled framework for white-box generative modeling in scientific and social domains where latent constructs are theory-driven and measurement validity is essential.
【2】Benchmarking Pretrained Molecular Embedding Models For Molecular Representation Learning
标题：对预先训练的分子嵌入模型进行分子表示学习的基准
链接：https://arxiv.org/abs/2508.06199
摘要：预训练的神经网络在化学和小分子药物设计中引起了极大的兴趣。这些模型的嵌入被广泛用于分子化学中的分子性质预测、虚拟筛选和小数据学习。这项研究提出了迄今为止最广泛的此类模型的比较，评估了25个数据集的25个模型。在一个公平的比较框架下，我们评估了跨越各种模式，架构和预训练策略的模型。使用专用的分层贝叶斯统计测试模型，我们得出了一个令人惊讶的结果：几乎所有的神经模型都显示出与基线ECFP分子指纹相比可以忽略不计或没有改善。只有同样基于分子指纹的CLAMP模型在统计学上显著优于替代模型。这些发现引起了人们对现有研究中评价严谨性的关注。我们讨论潜在的原因，提出解决方案，并提供实用的建议。
摘要 ：Pretrained neural networks have attracted significant interest in chemistry and small molecule drug design. Embeddings from these models are widely used for molecular property prediction, virtual screening, and small data learning in molecular chemistry. This study presents the most extensive comparison of such models to date, evaluating 25 models across 25 datasets. Under a fair comparison framework, we assess models spanning various modalities, architectures, and pretraining strategies. Using a dedicated hierarchical Bayesian statistical testing model, we arrive at a surprising result: nearly all neural models show negligible or no improvement over the baseline ECFP molecular fingerprint. Only the CLAMP model, which is also based on molecular fingerprints, performs statistically significantly better than the alternatives. These findings raise concerns about the evaluation rigor in existing studies. We discuss potential causes, propose solutions, and offer practical recommendations.
优化|敛散性(7篇)
【1】Near-Optimal Regret for Efficient Stochastic Combinatorial Semi-Bandits
标题：有效随机组合半强盗的近最优遗憾
链接：https://arxiv.org/abs/2508.06247
摘要：组合多臂强盗（CMAB）是顺序决策框架的基石，由两个算法家族主导：基于UCB的方法和对抗方法，如遵循正则化领导者（FTRL）和在线镜像下降（OMD）。然而，突出的基于UCB的方法，如CUCB遭受额外的遗憾因子$\log T$，这是有害的长期视野，而对抗性的方法，如EXP3.M和HYBRID施加显着的计算开销。为了解决这一问题，我们引入了随机环境下的组合极小极大最优策略（CMOSS）。CMOSS是一种计算效率高的算法，在半强盗反馈下实现了$O\big（（\log k）^2\sqrt{kmT}\big）$的实例独立遗憾，其中$m$是手臂的数量，$k$是可行动作的最大基数。重要的是，这个结果消除了对$\log T$的依赖，并将已建立的$\Omega\big（\sqrt{kmT}\big）$下限匹配到$O\big（（\log k）^2\big）$。然后，我们扩展我们的分析表明，CMOSS也适用于级联反馈。在合成数据集和真实数据集上的实验验证了CMOSS在遗憾和运行效率方面始终优于基准算法。
摘要：The combinatorial multi-armed bandit (CMAB) is a cornerstone of sequential decision-making framework, dominated by two algorithmic families: UCB-based and adversarial methods such as follow the regularized leader (FTRL) and online mirror descent (OMD). However, prominent UCB-based approaches like CUCB suffer from additional regret factor $\log T$ that is detrimental over long horizons, while adversarial methods such as EXP3.M and HYBRID impose significant computational overhead. To resolve this trade-off, we introduce the Combinatorial Minimax Optimal Strategy in the Stochastic setting (CMOSS). CMOSS is a computationally efficient algorithm that achieves an instance-independent regret of $O\big( (\log k)^2\sqrt{kmT}\big )$ under semi-bandit feedback, where $m$ is the number of arms and $k$ is the maximum cardinality of a feasible action. Crucially, this result eliminates the dependency on $\log T$ and matches the established $\Omega\big( \sqrt{kmT}\big)$ lower bound up to $O\big((\log k)^2\big)$. We then extend our analysis to show that CMOSS is also applicable to cascading feedback. Experiments on synthetic and real-world datasets validate that CMOSS consistently outperforms benchmark algorithms in both regret and runtime efficiency.
【2】Reparameterization Proximal Policy Optimization
标题：重新参数化近端政策优化
链接：https://arxiv.org/abs/2508.06214
摘要：重新参数化策略梯度（RPG）是有前途的提高样本效率，利用可微动力学。然而，一个关键的障碍是它的训练不稳定性，其中高方差梯度可能会破坏学习过程。为了解决这个问题，我们从最近策略优化（PPO）中汲取灵感，PPO使用代理目标来实现无模型设置中的稳定样本重用。我们首先建立了这个代理目标和RPG之间的联系，这在很大程度上是未开发的，是不平凡的。然后，我们弥合这一差距，证明了一个PPO类代理目标的重新参数化梯度可以有效地计算通过时间使用反向传播。基于这一关键见解，我们提出了重新参数化近似策略优化（RPO），一个稳定的和样本高效的基于RPG的方法。RPO通过优化为RPG量身定制的裁剪代理目标来实现多个时期的稳定样本重用，同时通过Kullback-Leibler（KL）发散正则化进一步稳定，并与现有的方差缩减方法保持完全兼容。我们评估RPO一套具有挑战性的运动和操作任务，实验表明，我们的方法实现了卓越的采样效率和强大的性能。
摘要：Reparameterization policy gradient (RPG) is promising for improving sample efficiency by leveraging differentiable dynamics. However, a critical barrier is its training instability, where high-variance gradients can destabilize the learning process. To address this, we draw inspiration from Proximal Policy Optimization (PPO), which uses a surrogate objective to enable stable sample reuse in the model-free setting. We first establish a connection between this surrogate objective and RPG, which has been largely unexplored and is non-trivial. Then, we bridge this gap by demonstrating that the reparameterization gradient of a PPO-like surrogate objective can be computed efficiently using backpropagation through time. Based on this key insight, we propose Reparameterization Proximal Policy Optimization (RPO), a stable and sample-efficient RPG-based method. RPO enables multiple epochs of stable sample reuse by optimizing a clipped surrogate objective tailored for RPG, while being further stabilized by Kullback-Leibler (KL) divergence regularization and remaining fully compatible with existing variance reduction methods. We evaluate RPO on a suite of challenging locomotion and manipulation tasks, where experiments demonstrate that our method achieves superior sample efficiency and strong performance.
【3】Parameter-free Optimal Rates for Nonlinear Semi-Norm Contractions with Applications to $Q$-Learning
标题：非线性半范压缩的无参数最优速率及其在$Q$-Learning中的应用
链接：https://arxiv.org/abs/2508.05984
摘要：求解\textit{非线性}不动点方程的算法--例如平均奖励\textit{$Q$-learning}和\textit{TD-learning} --通常涉及半范数压缩。通过Polyak-Ruppert平均实现这些方法的无参数最优收敛速度仍然难以捉摸，主要是由于这种半范数的非单调性。我们通过（i.）将所述平均误差重铸为涉及非线性扰动的线性递归，以及（ii.）通过耦合半范数的收缩与适当诱导范数的单调性来驯服非线性。我们的主要结果产生了第一个无参数的$\tilde{O}（1/\sqrt{t}）$最优率为$Q$学习在平均奖励和指数折扣设置，其中$t$表示迭代指数。该结果适用于一个广泛的框架，该框架可容纳同步和异步更新、单代理和分布式部署以及从模拟器或沿着马尔可夫轨迹获得的数据流。
摘要：Algorithms for solving \textit{nonlinear} fixed-point equations -- such as average-reward \textit{$Q$-learning} and \textit{TD-learning} -- often involve semi-norm contractions. Achieving parameter-free optimal convergence rates for these methods via Polyak--Ruppert averaging has remained elusive, largely due to the non-monotonicity of such semi-norms. We close this gap by (i.) recasting the averaged error as a linear recursion involving a nonlinear perturbation, and (ii.) taming the nonlinearity by coupling the semi-norm's contraction with the monotonicity of a suitably induced norm. Our main result yields the first parameter-free $\tilde{O}(1/\sqrt{t})$ optimal rates for $Q$-learning in both average-reward and exponentially discounted settings, where $t$ denotes the iteration index. The result applies within a broad framework that accommodates synchronous and asynchronous updates, single-agent and distributed deployments, and data streams obtained either from simulators or along Markovian trajectories.
【4】Multi-Armed Bandits-Based Optimization of Decision Trees
标题：基于多武装土匪的决策树优化
链接：https://arxiv.org/abs/2508.05957
摘要：决策树，如果没有适当的约束，很容易变得过于复杂，容易过拟合，捕捉噪音，而不是概括的模式。为了解决这个问题，剪枝操作是优化决策树的关键部分，因为它不仅降低了树的复杂性，而且降低了产生过拟合模型的概率。传统的剪枝技术，如成本复杂度剪枝（CCP）和减少错误剪枝（REP）主要是基于贪婪的方法，专注于立即获得性能，同时修剪决策树的节点。然而，从长远来看，这可能会导致泛化能力降低，从而在引入看不见的数据样本时，特别是在使用小型复杂数据集进行训练时，会损害树模型的鲁棒性。为了应对这一挑战，我们提出了一种基于多臂强盗（MAB）的修剪方法，一种基于强化学习（RL）的技术，它将动态修剪树以生成具有更好泛化能力的最佳决策树。我们提出的方法假设修剪过程作为一个探索-开发问题，我们利用MAB算法来找到最佳的分支节点修剪的基础上，从每个修剪动作的反馈。在多个基准数据集上的实验结果表明，该方法比传统方法具有更好的预测性能。这表明利用MAB进行决策树修剪的动态和概率方式的潜力，进而优化基于决策树的模型。
摘要：Decision trees, without appropriate constraints, can easily become overly complex and prone to overfit, capturing noise rather than generalizable patterns. To resolve this problem,pruning operation is a crucial part in optimizing decision trees, as it not only reduces the complexity of trees but also decreases the probability of generating overfit models. The conventional pruning techniques like Cost-Complexity Pruning (CCP) and Reduced Error Pruning (REP) are mostly based on greedy approaches that focus on immediate gains in performance while pruning nodes of the decision tree. However, this might result in a lower generalization in the long run, compromising the robust ability of the tree model when introduced to unseen data samples, particularly when trained with small and complex datasets. To address this challenge, we are proposing a Multi-Armed Bandits (MAB)-based pruning approach, a reinforcement learning (RL)-based technique, that will dynamically prune the tree to generate an optimal decision tree with better generalization. Our proposed approach assumes the pruning process as an exploration-exploitation problem, where we are utilizing the MAB algorithms to find optimal branch nodes to prune based on feedback from each pruning actions. Experimental evaluation on several benchmark datasets, demonstrated that our proposed approach results in better predictive performance compared to the traditional ones. This suggests the potential of utilizing MAB for a dynamic and probabilistic way of decision tree pruning, in turn optimizing the decision tree-based model.
【5】Optimal Linear Baseline Models for Scientific Machine Learning
标题：科学机器学习的最佳线性基线模型
链接：https://arxiv.org/abs/2508.05831
备注：40 pages, 10 Figures, 9 Tables
摘要：在整个科学领域，一个根本的挑战是表征和计算从底层物理过程到观察到的信号和测量的映射。虽然非线性神经网络已经取得了相当大的成功，但它们在理论上仍然是不透明的，这阻碍了在可解释性至关重要的环境中的采用。相比之下，线性神经网络是洞察这些复杂关系的简单而有效的基础。在这项工作中，我们开发了一个统一的理论框架，通过贝叶斯风险最小化的镜头来分析线性编码器-解码器架构，以解决数据驱动的科学机器学习问题。我们推导出封闭形式，秩约束的线性和仿射线性最优映射的正向建模和逆恢复任务。我们的研究结果概括了现有的配方，通过适应秩不足的数据，向前运营商，和测量过程。我们通过对简单的生物医学成像，金融因素分析和浅水方程涉及非线性流体动力学的模拟数据集进行数值实验来验证我们的理论结果。这项工作为理解和基准测试科学机器学习问题的学习神经网络模型提供了一个强大的基线。
摘要：Across scientific domains, a fundamental challenge is to characterize and compute the mappings from underlying physical processes to observed signals and measurements. While nonlinear neural networks have achieved considerable success, they remain theoretically opaque, which hinders adoption in contexts where interpretability is paramount. In contrast, linear neural networks serve as a simple yet effective foundation for gaining insight into these complex relationships. In this work, we develop a unified theoretical framework for analyzing linear encoder-decoder architectures through the lens of Bayes risk minimization for solving data-driven scientific machine learning problems. We derive closed-form, rank-constrained linear and affine linear optimal mappings for forward modeling and inverse recovery tasks. Our results generalize existing formulations by accommodating rank-deficiencies in data, forward operators, and measurement processes. We validate our theoretical results by conducting numerical experiments on datasets from simple biomedical imaging, financial factor analysis, and simulations involving nonlinear fluid dynamics via the shallow water equations. This work provides a robust baseline for understanding and benchmarking learned neural network models for scientific machine learning problems.
【6】Data-Driven Density Steering via the Gromov-Wasserstein Optimal Transport Distance
标题：通过Gromov-Wasserstein最佳运输距离进行数据驱动的密度引导
链接：https://arxiv.org/abs/2508.06052
备注：To be presented at the IEEE CDC, Rio de Janeiro, 2025
摘要：我们使用Gromov-Wasserstein度量来解决数据驱动的机会约束密度转向问题。基本的动力系统是一个未知的线性控制递归，与足够丰富的输入输出数据的假设，从预操作实验是可用的。初始状态被建模为高斯混合，而终端状态需要匹配指定的高斯分布。我们重新制定的最优控制问题作为一个差异的凸计划，并表明它可以有效地和tractably解决使用DC算法。数值结果验证了我们的方法，通过各种数据驱动的计划。
摘要：We tackle the data-driven chance-constrained density steering problem using the Gromov-Wasserstein metric. The underlying dynamical system is an unknown linear controlled recursion, with the assumption that sufficiently rich input-output data from pre-operational experiments are available. The initial state is modeled as a Gaussian mixture, while the terminal state is required to match a specified Gaussian distribution. We reformulate the resulting optimal control problem as a difference-of-convex program and show that it can be efficiently and tractably solved using the DC algorithm. Numerical results validate our approach through various data-driven schemes.
【7】Stochastic Trace Optimization of Parameter Dependent Matrices Based on Statistical Learning Theory
标题：基于统计学习理论的参数相关矩阵随机踪迹优化
链接：https://arxiv.org/abs/2508.05764
备注：3 figures
摘要：我们考虑矩阵$\boldsymbol{A}（\boldsymbol\theta）\in\mathbb{R}^{m\times m}$可能非线性地依赖于紧致参数空间$\Theta$中的参数$\boldsymbol\theta $。我们提出了一个Monte Carlo估计最小化$\text{trace}（\boldsymbol{A}（\boldsymbol\theta））$在所有$\boldsymbol\theta\in\Theta$，并确定抽样量，使估计的向后误差是有界的高概率.我们推导出两种类型的界限，基于Anchornets和通用链。这两种类型预测一个小的采样量矩阵$\boldsymbol{A}（\boldsymbol\theta）$与小的非对角质量，和参数空间$\Theta$的小``大小。''对矩阵维数~$m$的依赖性很弱或不显式。基于双网的边界更容易计算，并且带有完全指定的常数。相比之下，基于链接的界限取决于Talagrand泛函，除了在非常特殊的情况下，难以评估。这两种类型的界限之间的比较是困难的，虽然文献表明，链接界限可以是优越的。
摘要 ：We consider matrices $\boldsymbol{A}(\boldsymbol\theta)\in\mathbb{R}^{m\times m}$ that depend, possibly nonlinearly, on a parameter $\boldsymbol\theta$ from a compact parameter space $\Theta$. We present a Monte Carlo estimator for minimizing $\text{trace}(\boldsymbol{A}(\boldsymbol\theta))$ over all $\boldsymbol\theta\in\Theta$, and determine the sampling amount so that the backward error of the estimator is bounded with high probability. We derive two types of bounds, based on epsilon nets and on generic chaining. Both types predict a small sampling amount for matrices $\boldsymbol{A}(\boldsymbol\theta)$ with small offdiagonal mass, and parameter spaces $\Theta$ of small ``size.'' Dependence on the matrix dimension~$m$ is only weak or not explicit. The bounds based on epsilon nets are easier to evaluate and come with fully specified constants. In contrast, the bounds based on chaining depend on the Talagrand functionals which are difficult to evaluate, except in very special cases. Comparisons between the two types of bounds are difficult, although the literature suggests that chaining bounds can be superior.
其他神经网络|深度学习|模型|建模(15篇)
【1】Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks
标题：灾难性人工智能风险的维度特征和路径建模
链接：https://arxiv.org/abs/2508.06411
备注：24 pages including references, 6 figures. To be presented in Technical AI Governance Forum 2025
摘要：虽然围绕人工智能（AI）风险的讨论已经增长，但它往往缺乏一个全面的，多维度的框架，以及将危害映射到伤害的具体因果路径。本文旨在通过研究六种常见的人工智能灾难性风险来弥补这一差距：CBRN、网络攻击、突然失控、逐渐失控、环境风险和地缘政治风险。首先，我们从七个关键维度来描述这些风险，即意图、能力、实体、极性、线性、范围和顺序。接下来，我们通过映射从初始危害到最终危害的逐步进展来进行风险路径建模。维度方法支持系统的风险识别和可推广的缓解战略，而风险路径模型有助于确定针对具体社区的干预措施。总之，这些方法为管理整个价值链中的灾难性人工智能风险提供了一个更加结构化和可操作的基础。
摘要：Although discourse around the risks of Artificial Intelligence (AI) has grown, it often lacks a comprehensive, multidimensional framework, and concrete causal pathways mapping hazard to harm. This paper aims to bridge this gap by examining six commonly discussed AI catastrophic risks: CBRN, cyber offense, sudden loss of control, gradual loss of control, environmental risk, and geopolitical risk. First, we characterize these risks across seven key dimensions, namely intent, competency, entity, polarity, linearity, reach, and order. Next, we conduct risk pathway modeling by mapping step-by-step progressions from the initial hazard to the resulting harms. The dimensional approach supports systematic risk identification and generalizable mitigation strategies, while risk pathway models help identify scenario-specific interventions. Together, these methods offer a more structured and actionable foundation for managing catastrophic AI risks across the value chain.
【2】A Study on Regularization-Based Continual Learning Methods for Indic ASR
标题：基于规则化的独立ASB持续学习方法研究
链接：https://arxiv.org/abs/2508.06280
摘要：印度的语言多样性对开发包容性的自动语音识别（ASR）系统构成了重大挑战。传统的多语言模型需要同时访问所有语言数据，由于数据的顺序到达和隐私限制，这是不切实际的。持续学习（CL）提供了一种解决方案，使模型能够连续学习新的语言，而不会灾难性地忘记以前学习的知识。本文研究CL ASR印度语言使用的一个子集的IndicSUPERB基准。我们采用了一个基于Conformer的混合RNN-T/CTC模型，最初在印地语上进行预训练，然后在另外8种印度语言上进行增量训练，总共有9种语言。我们评估了三种突出的基于正则化和蒸馏的CL策略：弹性权重合并（EWC），记忆感知突触（MAS）和无遗忘学习（LwF），选择它们在无重放，隐私意识场景中的适用性。使用RNN-T和CTC路径的字错误率（WER）对干净和有噪声的数据进行性能分析，以及通过反向传输进行知识保留。我们还探索了每个任务不同训练时期（1，2，5和10）的影响。结果，与天真的微调相比，表明CL在减轻遗忘方面的有效性，使其成为现实约束下不同印度语言中可扩展ASR的一种有前途的方法。该代码可从以下网址获得：https://github.com/FrozenWolf-Cyber/Indic-CL-ASR
摘要：Indias linguistic diversity poses significant challenges for developing inclusive Automatic Speech Recognition (ASR) systems. Traditional multilingual models, which require simultaneous access to all language data, are impractical due to the sequential arrival of data and privacy constraints. Continual Learning (CL) offers a solution by enabling models to learn new languages sequentially without catastrophically forgetting previously learned knowledge. This paper investigates CL for ASR on Indian languages using a subset of the IndicSUPERB benchmark. We employ a Conformer-based hybrid RNN-T/CTC model, initially pretrained on Hindi, which is then incrementally trained on eight additional Indian languages, for a total sequence of nine languages. We evaluate three prominent regularization- and distillation-based CL strategies: Elastic Weight Consolidation (EWC), Memory Aware Synapses (MAS), and Learning without Forgetting (LwF), selected for their suitability in no-replay, privacy-conscious scenarios. Performance is analyzed using Word Error Rate (WER) for both RNN-T and CTC paths on clean and noisy data, as well as knowledge retention via Backward Transfer. We also explore the impact of varying the number of training epochs (1, 2, 5, and 10) per task. Results, compared against naive fine-tuning, demonstrate CLs effectiveness in mitigating forgetting, making it a promising approach for scalable ASR in diverse Indian languages under realistic constraints. The code is available at: https://github.com/FrozenWolf-Cyber/Indic-CL-ASR
【3】One Size Does Not Fit All: A Distribution-Aware Sparsification for More Precise Model Merging
标题：一刀切并不适合所有人：具有分布意识的精简化，以实现更精确的模型合并
链接：https://arxiv.org/abs/2508.06163
备注：Under review
摘要：模型合并已成为多任务学习的一种引人注目的无数据范式，能够将多个微调模型融合为单个强大的实体。合并方法的一个关键技术是稀疏化，它从任务向量中删除冗余参数以减轻干扰。然而，普遍的方法采用“一刀切”的战略，采用统一的稀疏率，忽略了模型参数固有的结构和统计异质性。这通常会导致次优的权衡，其中关键参数被无意中修剪，而不太有用的参数被保留。为了解决这个限制，我们引入了\textbf{TADrop}（\textbf{T}ensor-wise \textbf{A}daptive \textbf{Drop}），这是一种尊重这种异质性的自适应稀疏化策略。TADrop不是全局比率，而是根据其分布特性为每个参数张量分配一个定制的稀疏级别。核心直觉是，具有更密集、更冗余分布的张量可以被积极地修剪，而更稀疏、更关键的张量则被保留。作为一个简单的即插即用模块，我们通过将其与基础，经典和SOTA合并方法集成来验证TADrop。在不同的任务（视觉，语言和多模态）和模型（ViT，BEiT）上进行的广泛实验表明，TADrop始终显着提高了他们的表现。例如，当增强领先的合并方法时，它在8个ViT-B/32任务上实现了2.0%的平均性能增益。TADrop提供了一种更有效的方法来减轻参数干扰，通过定制稀疏化模型的结构，提供了一个新的基线高性能模型合并。
摘要：Model merging has emerged as a compelling data-free paradigm for multi-task learning, enabling the fusion of multiple fine-tuned models into a single, powerful entity. A key technique in merging methods is sparsification, which prunes redundant parameters from task vectors to mitigate interference. However, prevailing approaches employ a ``one-size-fits-all'' strategy, applying a uniform sparsity ratio that overlooks the inherent structural and statistical heterogeneity of model parameters. This often leads to a suboptimal trade-off, where critical parameters are inadvertently pruned while less useful ones are retained. To address this limitation, we introduce \textbf{TADrop} (\textbf{T}ensor-wise \textbf{A}daptive \textbf{Drop}), an adaptive sparsification strategy that respects this heterogeneity. Instead of a global ratio, TADrop assigns a tailored sparsity level to each parameter tensor based on its distributional properties. The core intuition is that tensors with denser, more redundant distributions can be pruned aggressively, while sparser, more critical ones are preserved. As a simple and plug-and-play module, we validate TADrop by integrating it with foundational, classic, and SOTA merging methods. Extensive experiments across diverse tasks (vision, language, and multimodal) and models (ViT, BEiT) demonstrate that TADrop consistently and significantly boosts their performance. For instance, when enhancing a leading merging method, it achieves an average performance gain of 2.0\% across 8 ViT-B/32 tasks. TADrop provides a more effective way to mitigate parameter interference by tailoring sparsification to the model's structure, offering a new baseline for high-performance model merging.
【4】Recurrent Deep Differentiable Logic Gate Networks
标题：循环深度可微逻辑门网络
链接：https://arxiv.org/abs/2508.06097
摘要：虽然可微逻辑门在前馈网络中表现出了希望，但它们在时序建模中的应用仍然没有得到探索。本文介绍了递归深度可微逻辑门网络（RDDLGN）的第一个实现，将布尔运算与递归架构相结合，用于序列到序列的学习。 在WMT'14英德翻译中进行评估，RDDLGN在训练期间达到5.00 BLEU和30.9%的准确率，接近GRU性能（5.41 BLEU）和推理期间的适度降级（4.39 BLEU）。这项工作建立了基于递归逻辑的神经计算作为可行的，开放的研究方向FPGA加速顺序建模和其他递归网络架构。
摘要：While differentiable logic gates have shown promise in feedforward networks, their application to sequential modeling remains unexplored. This paper presents the first implementation of Recurrent Deep Differentiable Logic Gate Networks (RDDLGN), combining Boolean operations with recurrent architectures for sequence-to-sequence learning. Evaluated on WMT'14 English-German translation, RDDLGN achieves 5.00 BLEU and 30.9\% accuracy during training, approaching GRU performance (5.41 BLEU) and graceful degradation (4.39 BLEU) during inference. This work establishes recurrent logic-based neural computation as viable, opening research directions for FPGA acceleration in sequential modeling and other recursive network architectures.
【5】Architecture-Aware Generalization Bounds for Temporal Networks: Theory and Fair Comparison Methodology
标题：时态网络的架构感知概括界限：理论和公平比较方法
链接：https://arxiv.org/abs/2508.06066
摘要：Deep temporal architectures such as Temporal Convolutional Networks (TCNs) achieve strong predictive performance on sequential data, yet theoretical understanding of their generalization remains limited. We address this gap by providing both the first non-vacuous, architecture-aware generalization bounds for deep temporal models and a principled evaluation methodology. For exponentially $\beta$-mixing sequences, we derive bounds scaling as $ O\!\Bigl(R\,\sqrt{\tfrac{D\,p\,n\,\log N}{N}}\Bigr), $ where $D$ is network depth, $p$ kernel size, $n$ input dimension, and $R$ weight norm. Our delayed-feedback blocking mechanism transforms dependent samples into effectively independent ones while discarding only $O(1/\log N)$ of the data, yielding $\sqrt{D}$ scaling instead of exponential, implying that doubling depth requires approximately quadrupling the training data. We also introduce a fair-comparison methodology that fixes the effective sample size to isolate the effect of temporal structure from information content. Under $N_{\text{eff}}=2{,}000$, strongly dependent sequences ($\rho=0.8$) exhibit $\approx76\%$ smaller generalization gaps than weakly dependent ones ($\rho=0.2$), challenging the intuition that dependence is purely detrimental. Yet convergence rates diverge from theory: weak dependencies follow $N_{\text{eff}}^{-1.21}$ scaling and strong dependencies follow $N_{\text{eff}}^{-0.89}$, both steeper than the predicted $N^{-0.5}$. These findings reveal that temporal dependence can enhance learning under fixed information budgets, while highlighting gaps between theory and practice that motivate future research.
摘要：Deep temporal architectures such as Temporal Convolutional Networks (TCNs) achieve strong predictive performance on sequential data, yet theoretical understanding of their generalization remains limited. We address this gap by providing both the first non-vacuous, architecture-aware generalization bounds for deep temporal models and a principled evaluation methodology. For exponentially $\beta$-mixing sequences, we derive bounds scaling as $ O\!\Bigl(R\,\sqrt{\tfrac{D\,p\,n\,\log N}{N}}\Bigr), $ where $D$ is network depth, $p$ kernel size, $n$ input dimension, and $R$ weight norm. Our delayed-feedback blocking mechanism transforms dependent samples into effectively independent ones while discarding only $O(1/\log N)$ of the data, yielding $\sqrt{D}$ scaling instead of exponential, implying that doubling depth requires approximately quadrupling the training data. We also introduce a fair-comparison methodology that fixes the effective sample size to isolate the effect of temporal structure from information content. Under $N_{\text{eff}}=2{,}000$, strongly dependent sequences ($\rho=0.8$) exhibit $\approx76\%$ smaller generalization gaps than weakly dependent ones ($\rho=0.2$), challenging the intuition that dependence is purely detrimental. Yet convergence rates diverge from theory: weak dependencies follow $N_{\text{eff}}^{-1.21}$ scaling and strong dependencies follow $N_{\text{eff}}^{-0.89}$, both steeper than the predicted $N^{-0.5}$. These findings reveal that temporal dependence can enhance learning under fixed information budgets, while highlighting gaps between theory and practice that motivate future research.
【6】AGI for the Earth, the path, possibilities and how to evaluate intelligence of models that work with Earth Observation Data?
标题：地球AGI、路径、可能性以及如何评估与地球观测数据一起工作的模型的智能性？
链接：https://arxiv.org/abs/2508.06057
备注：Accepted in IGARSS 2025!
摘要：通用人工智能（AGI）比以往任何时候都更接近成为现实，在研究界引发了广泛的热情，收集和使用各种形式，包括文本，图像，视频和音频。尽管最近作出了努力，但卫星光谱图像作为一种补充方式尚未得到应有的重视。这一领域提出了独特的挑战，但也在提高AGI理解自然世界的能力方面具有巨大的潜力。在本文中，我们认为，为什么地球观测数据是有用的智能模型，然后我们回顾现有的基准，并强调其局限性，在这一领域的基础模型的泛化能力进行评估。本文强调需要一个更全面的基准来评估地球观测模型。为了促进这一点，我们提出了一套全面的任务，一个基准应该包括有效地评估模型的能力，理解和与地球观测数据的互动。
摘要：Artificial General Intelligence (AGI) is closer than ever to becoming a reality, sparking widespread enthusiasm in the research community to collect and work with various modalities, including text, image, video, and audio. Despite recent efforts, satellite spectral imagery, as an additional modality, has yet to receive the attention it deserves. This area presents unique challenges, but also holds great promise in advancing the capabilities of AGI in understanding the natural world. In this paper, we argue why Earth Observation data is useful for an intelligent model, and then we review existing benchmarks and highlight their limitations in evaluating the generalization ability of foundation models in this domain. This paper emphasizes the need for a more comprehensive benchmark to evaluate earth observation models. To facilitate this, we propose a comprehensive set of tasks that a benchmark should encompass to effectively assess a model's ability to understand and interact with Earth observation data.
【7】Fast, Convex and Conditioned Network for Multi-Fidelity Vectors and Stiff Univariate Differential Equations
标题：多保真量和刚性一元方程的快速、凸和条件网络
链接：https://arxiv.org/abs/2508.05921
摘要：神经PDE求解器的准确性通常不是因为有限的表达能力，而是由于病态引起的优化不良，特别是在多保真度和僵硬的问题中。我们在物理信息极端学习机（PIELM）中研究了这个问题，PIELM是神经PDE求解器的凸变体，并表明控制方程中的渐近分量可以产生高度病态的激活矩阵，严重限制收敛。我们引入了移位高斯编码，这是一个简单而有效的激活过滤步骤，可以在保持凸性的同时增加矩阵秩和表达性。我们的方法将稳定对流扩散方程中Peclet数的可解范围扩展了两个数量级以上，在多频函数学习上实现了高达六个数量级的低误差，并且比具有超过一百万个参数的深度网络更准确，更快地拟合高保真图像向量。这项工作强调了条件反射，而不是深度，通常是科学神经求解器的瓶颈，简单的架构变化可以解锁实质性的收益。
摘要：Accuracy in neural PDE solvers often breaks down not because of limited expressivity, but due to poor optimisation caused by ill-conditioning, especially in multi-fidelity and stiff problems. We study this issue in Physics-Informed Extreme Learning Machines (PIELMs), a convex variant of neural PDE solvers, and show that asymptotic components in governing equations can produce highly ill-conditioned activation matrices, severely limiting convergence. We introduce Shifted Gaussian Encoding, a simple yet effective activation filtering step that increases matrix rank and expressivity while preserving convexity. Our method extends the solvable range of Peclet numbers in steady advection-diffusion equations by over two orders of magnitude, achieves up to six orders lower error on multi-frequency function learning, and fits high-fidelity image vectors more accurately and faster than deep networks with over a million parameters. This work highlights that conditioning, not depth, is often the bottleneck in scientific neural solvers and that simple architectural changes can unlock substantial gains.
【8】Machine Learning-Based Nonlinear Nudging for Chaotic Dynamical Systems
标题：基于机器学习的混乱动力系统非线性推动
链接：https://arxiv.org/abs/2508.05778
备注：21 pages, 5 figures, 6 tables
摘要：轻推是一种经验数据同化技术，它将观测驱动的控制项纳入模式动力学。即使初始条件不同，轻推系统的轨迹也会随着时间的推移接近真实系统轨迹。对于线性状态空间模型，这样的控制项可以在温和的假设下导出。然而，设计有效的轻推条款变得更加具有挑战性的非线性设置。在这项工作中，我们提出了神经网络轻推，数据驱动的方法学习轻推条款的非线性状态空间模型。基于Kazantzis-Kravaris-Luenberger观测器理论，我们建立了一个理论上的存在性结果.所提出的方法进行评估，表现出混沌行为的三个基准问题：洛伦兹96模型，Kuramoto-Sivashinsky方程，和Kolmogorov流。
摘要：Nudging is an empirical data assimilation technique that incorporates an observation-driven control term into the model dynamics. The trajectory of the nudged system approaches the true system trajectory over time, even when the initial conditions differ. For linear state space models, such control terms can be derived under mild assumptions. However, designing effective nudging terms becomes significantly more challenging in the nonlinear setting. In this work, we propose neural network nudging, a data-driven method for learning nudging terms in nonlinear state space models. We establish a theoretical existence result based on the Kazantzis--Kravaris--Luenberger observer theory. The proposed approach is evaluated on three benchmark problems that exhibit chaotic behavior: the Lorenz 96 model, the Kuramoto--Sivashinsky equation, and the Kolmogorov flow.
【9】Domain-Specific Fine-Tuning and Prompt-Based Learning: A Comparative Study for developing Natural Language-Based BIM Information Retrieval Systems
标题：特定领域微调和基于预算的学习：开发基于自然地理的BMI信息检索系统的比较研究
链接：https://arxiv.org/abs/2508.05676
摘要：建筑信息建模（BIM）对于管理整个生命周期的建筑数据至关重要，支持从设计到维护的任务。自然语言接口（NLI）系统越来越多地被探索为建筑信息建模（BIM）环境中的用户友好的信息检索工具。尽管它们具有潜力，但由于使用查询的复杂性和领域知识的特殊性，通过自然语言查询准确提取BIM相关数据仍然是一个持续的挑战。这项研究提出了一个比较分析的两个突出的方法来开发基于NLI的BIM信息检索系统：特定领域的微调和基于学习的学习使用大型语言模型（LLM）。实现了一个由意图识别和基于表格的问题回答组成的两阶段框架来评估这两种方法的有效性。为了支持这一评估，构建了一个特定于BIM的数据集，其中包含69个模型中不同类型的1，740个带注释的查询。实验结果表明，特定领域的微调在意图识别任务中提供了优异的性能，而基于文本的学习，特别是GPT-4 o，在基于表格的问题回答中表现出了优势。基于这些发现，本研究确定了一种混合配置，该配置将意图识别的微调与基于问题回答的学习相结合，从而在任务中实现更平衡和更强大的性能。通过涉及不同复杂性的BIM模型的案例研究，进一步测试了这种集成方法。这项研究提供了一个系统的分析，每种方法的优势和局限性，并讨论了NLI的适用性，以现实世界的BIM方案。这些发现为研究人员和从业人员设计智能，语言驱动的BIM系统提供了见解。
摘要：Building Information Modeling (BIM) is essential for managing building data across the entire lifecycle, supporting tasks from design to maintenance. Natural Language Interface (NLI) systems are increasingly explored as user-friendly tools for information retrieval in Building Information Modeling (BIM) environments. Despite their potential, accurately extracting BIM-related data through natural language queries remains a persistent challenge due to the complexity use queries and specificity of domain knowledge. This study presents a comparative analysis of two prominent approaches for developing NLI-based BIM information retrieval systems: domain-specific fine-tuning and prompt-based learning using large language models (LLMs). A two-stage framework consisting of intent recognition and table-based question answering is implemented to evaluate the effectiveness of both approaches. To support this evaluation, a BIM-specific dataset of 1,740 annotated queries of varying types across 69 models is constructed. Experimental results show that domain-specific fine-tuning delivers superior performance in intent recognition tasks, while prompt-based learning, particularly with GPT-4o, shows strength in table-based question answering. Based on these findings, this study identify a hybrid configuration that combines fine-tuning for intent recognition with prompt-based learning for question answering, achieving more balanced and robust performance across tasks. This integrated approach is further tested through case studies involving BIM models of varying complexity. This study provides a systematic analysis of the strengths and limitations of each approach and discusses the applicability of the NLI to real-world BIM scenarios. The findings offer insights for researchers and practitioners in designing intelligent, language-driven BIM systems.
【10】Epidemic Control on a Large-Scale-Agent-Based Epidemiology Model using Deep Deterministic Policy Gradient
标题：使用深度确定性政策梯度的基于大规模代理的流行病模型中的流行病控制
链接：https://arxiv.org/abs/2304.04475
摘要：为减轻疫情的影响，多项措施包括封锁、快速疫苗接种计划、关闭学校和经济刺激。这些干预措施可能产生积极或意外的消极后果。目前通过往返自动建模和确定最佳干预措施的研究受到模拟目标、规模（几千人）、不适合干预研究的模型类型以及他们可以探索的干预策略数量（离散与连续）的限制。我们使用基于深度确定性策略梯度（DDPG）的策略优化框架来解决这些挑战，该框架基于大规模（100，000个个体）基于流行病学代理的模拟，在该模拟中我们执行多目标优化。我们确定了最优的政策，锁定和疫苗接种在一个最小的年龄分层的多疫苗的情况下，基本的模拟经济活动。在没有封锁和疫苗接种的情况下（中年和老年人），结果显示最佳经济（贫困线以下的个人）与平衡的健康目标（感染和住院）。需要进行深入的模拟来进一步验证我们的结果并开源我们的框架。
摘要：To mitigate the impact of the pandemic, several measures include lockdowns, rapid vaccination programs, school closures, and economic stimulus. These interventions can have positive or unintended negative consequences. Current research to model and determine an optimal intervention automatically through round-tripping is limited by the simulation objectives, scale (a few thousand individuals), model types that are not suited for intervention studies, and the number of intervention strategies they can explore (discrete vs continuous). We address these challenges using a Deep Deterministic Policy Gradient (DDPG) based policy optimization framework on a large-scale (100,000 individual) epidemiological agent-based simulation where we perform multi-objective optimization. We determine the optimal policy for lockdown and vaccination in a minimalist age-stratified multi-vaccine scenario with a basic simulation for economic activity. With no lockdown and vaccination (mid-age and elderly), results show optimal economy (individuals below the poverty line) with balanced health objectives (infection, and hospitalization). An in-depth simulation is needed to further validate our results and open-source our framework.
【11】Intuition emerges in Maximum Caliber models at criticality
标题：直觉在最大口径模型中出现在临界点
链接：https://arxiv.org/abs/2508.06477
摘要：大型预测模型是否只是模仿它们的训练数据或产生真正的洞察力缺乏物理解释。这项工作报告了一种原始形式的直觉，它作为学习的亚稳态阶段出现，批判性地平衡了下一个令牌预测与未来路径熵。直觉机制是通过思维调谐发现的，思维调谐是一种最小原则，它在具有控制温度类参数$\lambda$的预测模型中施加最大口径。在确定性迷宫中随机行走的训练揭示了一个丰富的相图：模仿（低$\lambda$），打破规则的幻觉（高$\lambda$），以及一个脆弱的中间窗口，表现出强烈的协议依赖性（滞后）和多稳定性，模型自发地发现新的目标导向策略。这些结果被一个有效的低维理论和框架直觉捕捉到，作为一种在记忆是什么和想知道可能是什么之间的关键平衡的涌现属性。
摘要：Whether large predictive models merely parrot their training data or produce genuine insight lacks a physical explanation. This work reports a primitive form of intuition that emerges as a metastable phase of learning that critically balances next-token prediction against future path-entropy. The intuition mechanism is discovered via mind-tuning, the minimal principle that imposes Maximum Caliber in predictive models with a control temperature-like parameter $\lambda$. Training on random walks in deterministic mazes reveals a rich phase diagram: imitation (low $\lambda$), rule-breaking hallucination (high $\lambda$), and a fragile in-between window exhibiting strong protocol-dependence (hysteresis) and multistability, where models spontaneously discover novel goal-directed strategies. These results are captured by an effective low-dimensional theory and frame intuition as an emergent property at the critical balance between memorizing what is and wondering what could be.
【12】Enhancing the Scalability of Classical Surrogates for Real-World Quantum Machine Learning Applications
标题：增强现实世界量子机器学习应用经典替代品的可扩展性
链接：https://arxiv.org/abs/2508.06131
备注：9 pages, 8 figures
摘要：量子机器学习（QML）具有早期工业应用的潜力，但对量子硬件的有限访问仍然是部署QML解决方案的重要瓶颈。这项工作探索了使用经典代理来绕过这一限制，这是一种允许构建（训练）量子模型的轻量级经典表示的技术，能够在完全经典的设备上执行推理。我们揭示了禁止高计算需求与以前提出的方法产生经典的代理人从量子模型，并提出了一种替代管道，使经典的代理人在一个更大的规模比以前可能的。以前的方法需要至少一个高性能计算（HPC）系统，用于低于工业规模的量子模型（约1000万）。20量子比特），这引发了对其实用性的质疑。我们极大地减少了以前方法的冗余，只利用了以前所需资源的一小部分。我们证明了我们的方法在现实世界的能源需求预测问题上的有效性，在模拟和量子硬件上对性能和计算需求进行了严格的测试。我们的研究结果表明，我们的方法在测试数据集上实现了高精度，而其计算资源需求呈线性而不是指数增长。这项工作提出了一种轻量级的方法，将量子解决方案转换为经典的可部署版本，促进量子技术在工业环境中的更快集成。此外，它可以作为一个强有力的研究工具，在寻找实际的量子优势的经验设置。
摘要：Quantum machine learning (QML) presents potential for early industrial adoption, yet limited access to quantum hardware remains a significant bottleneck for deployment of QML solutions. This work explores the use of classical surrogates to bypass this restriction, which is a technique that allows to build a lightweight classical representation of a (trained) quantum model, enabling to perform inference on entirely classical devices. We reveal prohibiting high computational demand associated with previously proposed methods for generating classical surrogates from quantum models, and propose an alternative pipeline enabling generation of classical surrogates at a larger scale than was previously possible. Previous methods required at least a high-performance computing (HPC) system for quantum models of below industrial scale (ca. 20 qubits), which raises questions about its practicality. We greatly minimize the redundancies of the previous approach, utilizing only a minute fraction of the resources previously needed. We demonstrate the effectiveness of our method on a real-world energy demand forecasting problem, conducting rigorous testing of performance and computation demand in both simulations and on quantum hardware. Our results indicate that our method achieves high accuracy on the testing dataset while its computational resource requirements scale linearly rather than exponentially. This work presents a lightweight approach to transform quantum solutions into classically deployable versions, facilitating faster integration of quantum technology in industrial settings. Furthermore, it can serve as a powerful research tool in search practical quantum advantage in an empirical setup.
【13】Hybrid Physics-Machine Learning Models for Quantitative Electron Diffraction Refinements
标题：用于定量电子折射细化的混合物理-机器学习模型
链接：https://arxiv.org/abs/2508.05908
摘要：定量晶体结构细化所需的高保真电子显微镜模拟面临着一个根本性的挑战：虽然物理相互作用在理论上得到了很好的描述，但现实世界的实验效应在分析建模方面具有挑战性。为了解决这一差距，我们提出了一种新的混合物理-机器学习框架，将可微物理模拟与神经网络集成在一起。通过在整个仿真管道中利用自动微分，我们的方法可以对代表实验变量的物理参数和神经网络组件进行基于梯度的联合优化，与传统的二阶方法相比，具有更好的可扩展性。我们通过应用于三维电子衍射（3D-ED）结构细化来展示这个框架，在这个框架中，我们的方法直接从衍射数据中学习复杂的厚度分布，而不是依赖于简化的几何模型。该方法在合成和实验数据集上实现了最先进的细化性能，以高保真度恢复原子位置，热位移和厚度分布。所提出的模块化架构可以自然地扩展以适应额外的物理现象，并扩展到其他电子显微镜技术。这建立了微分混合建模作为一个强大的新的范例定量电子显微镜，实验的复杂性，历史上有限的分析。
摘要：High-fidelity electron microscopy simulations required for quantitative crystal structure refinements face a fundamental challenge: while physical interactions are well-described theoretically, real-world experimental effects are challenging to model analytically. To address this gap, we present a novel hybrid physics-machine learning framework that integrates differentiable physical simulations with neural networks. By leveraging automatic differentiation throughout the simulation pipeline, our method enables gradient-based joint optimization of physical parameters and neural network components representing experimental variables, offering superior scalability compared to traditional second-order methods. We demonstrate this framework through application to three-dimensional electron diffraction (3D-ED) structure refinement, where our approach learns complex thickness distributions directly from diffraction data rather than relying on simplified geometric models. This method achieves state-of-the-art refinement performance across synthetic and experimental datasets, recovering atomic positions, thermal displacements, and thickness profiles with high fidelity. The modular architecture proposed can naturally be extended to accommodate additional physical phenomena and extended to other electron microscopy techniques. This establishes differentiable hybrid modeling as a powerful new paradigm for quantitative electron microscopy, where experimental complexities have historically limited analysis.
【14】Evaluating Universal Machine Learning Force Fields Against Experimental Measurements
标题：根据实验测量评估通用机器学习力场
链接：https://arxiv.org/abs/2508.05762
摘要 ：通用机器学习力场（UMLFF）有望通过在元素周期表中实现快速原子模拟来彻底改变材料科学。然而，他们的评估仅限于计算基准，可能无法反映现实世界的性能。在这里，我们提出了UniFFBench，一个全面的框架，用于评估UMLFF对实验测量的~1,500精心策划的矿物结构跨越不同的化学环境，键合类型，结构复杂性和弹性性能。我们对六个最先进的UMLFF的系统评估揭示了一个巨大的现实差距：在计算基准上取得令人印象深刻的性能的模型在面对实验复杂性时往往会失败。即使是性能最好的模型也表现出比实际应用所需的阈值更高的密度预测误差。最引人注目的是，我们观察到模拟稳定性和机械性能准确性之间的脱节，预测误差与训练数据表示而不是建模方法相关。这些研究结果表明，虽然目前的计算基准提供了有价值的控制比较，他们可能会高估模型的可靠性时，外推到实验复杂的化学空间。总之，UniFFBench建立了必要的实验验证标准，并揭示了必须解决的系统限制，以实现真正的通用力场能力。
摘要：Universal machine learning force fields (UMLFFs) promise to revolutionize materials science by enabling rapid atomistic simulations across the periodic table. However, their evaluation has been limited to computational benchmarks that may not reflect real-world performance. Here, we present UniFFBench, a comprehensive framework for evaluating UMLFFs against experimental measurements of ~1,500 carefully curated mineral structures spanning diverse chemical environments, bonding types, structural complexity, and elastic properties. Our systematic evaluation of six state-of-the-art UMLFFs reveals a substantial reality gap: models achieving impressive performance on computational benchmarks often fail when confronted with experimental complexity. Even the best-performing models exhibit higher density prediction error than the threshold required for practical applications. Most strikingly, we observe disconnects between simulation stability and mechanical property accuracy, with prediction errors correlating with training data representation rather than the modeling method. These findings demonstrate that while current computational benchmarks provide valuable controlled comparisons, they may overestimate model reliability when extrapolated to experimentally complex chemical spaces. Altogether, UniFFBench establishes essential experimental validation standards and reveals systematic limitations that must be addressed to achieve truly universal force field capabilities.
【15】Moment Estimate and Variational Approach for Learning Generalized Diffusion with Non-gradient Structures
标题：非梯度结构广义扩散学习的矩估计和变分方法
链接：https://arxiv.org/abs/2508.01854
摘要：本文提出了一个数据驱动的学习框架，用于识别具有非梯度分量的广义扩散的控制律。通过结合能量耗散律、物理相容罚函数和一阶矩演化，我们设计了一种两阶段方法来恢复广义扩散中一类非梯度漂移的逐点正交分解中的赝势和旋转.我们的两阶段方法适用于复杂的广义扩散过程，包括耗散旋转动力学，粗糙赝势和噪声数据。代表性的数值实验表明，我们的方法学习非梯度广义扩散的物理定律的有效性。
摘要：This paper proposes a data-driven learning framework for identifying governing laws of generalized diffusions with non-gradient components. By combining energy dissipation laws with a physically consistent penalty and first-moment evolution, we design a two-stage method to recover the pseudo-potential and rotation in the pointwise orthogonal decomposition of a class of non-gradient drifts in generalized diffusions. Our two-stage method is applied to complex generalized diffusion processes including dissipation-rotation dynamics, rough pseudo-potentials and noisy data. Representative numerical experiments demonstrate the effectiveness of our approach for learning physical laws in non-gradient generalized diffusions.
其他(22篇)
【1】Post-training for Efficient Communication via Convention Formation
标题：通过公约形成进行有效沟通的后期训练
链接：https://arxiv.org/abs/2508.06482
备注：Accepted to COLM 2025
摘要：人类通过调整语言和形成特定的约定，在多回合互动中提高了沟通效率。相比之下，先前的工作表明，LLM并不自然地表现出这种行为。我们开发了一个培训后的过程，通过有针对性的微调对公约形成的示范识别发展这种能力。我们用两个新的基准来评估这种能力。首先，我们设计了一个集中的，认知动机的互动基准，一贯eleclides强大的公约形成的趋势，在人类。其次，我们创建了一个新的基于文档的引用完成任务，它反映了野外惯例形成行为。我们的研究表明，在两种评估方法中，经过培训的LLM的惯例形成能力显着提高。
摘要：Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions. In contrast, prior work shows that LLMs do not naturally show this behavior. We develop a post-training process to develop this ability through targeted fine-tuning on heuristically identified demonstrations of convention formation. We evaluate with two new benchmarks focused on this capability. First, we design a focused, cognitively-motivated interaction benchmark that consistently elicits strong convention formation trends in humans. Second, we create a new document-grounded reference completion task that reflects in-the-wild convention formation behavior. Our studies show significantly improved convention formation abilities in post-trained LLMs across the two evaluation methods.
【2】Maximum Impact with Fewer Features: Efficient Feature Selection for Cold-Start Recommenders through Collaborative Importance Weighting
标题：以更少的功能实现最大影响：通过协作重要性加权为冷启动推荐者高效选择功能
链接：https://arxiv.org/abs/2508.06455
摘要：推荐系统中的冷启动挑战需要利用用户-项目交互之外的辅助功能。然而，不相关或噪声特征的存在会降低预测性能，而过多的特征会增加计算需求，导致更高的内存消耗和更长的训练时间。 为了解决这个问题，我们提出了一个功能选择策略，优先用户行为信息。我们的方法通过使用混合矩阵分解技术从协作行为数据中合并相关性来增强特征表示，然后使用基于最大体积算法的机制对特征进行排名。这种方法确定了最有影响力的功能，在推荐准确性和计算效率之间取得了平衡。我们对各种数据集和混合推荐模型进行了广泛的评估，证明了我们的方法通过选择最小但高效的特征子集在冷启动场景中表现出色。即使在严格的功能减少，我们的方法超越现有的功能选择技术，同时保持卓越的效率。
摘要：Cold-start challenges in recommender systems necessitate leveraging auxiliary features beyond user-item interactions. However, the presence of irrelevant or noisy features can degrade predictive performance, whereas an excessive number of features increases computational demands, leading to higher memory consumption and prolonged training times. To address this, we propose a feature selection strategy that prioritizes the user behavioral information. Our method enhances the feature representation by incorporating correlations from collaborative behavior data using a hybrid matrix factorization technique and then ranks features using a mechanism based on the maximum volume algorithm. This approach identifies the most influential features, striking a balance between recommendation accuracy and computational efficiency. We conduct an extensive evaluation across various datasets and hybrid recommendation models, demonstrating that our method excels in cold-start scenarios by selecting minimal yet highly effective feature subsets. Even under strict feature reduction, our approach surpasses existing feature selection techniques while maintaining superior efficiency.
【3】Memp: Exploring Agent Procedural Memory
标题：Memp：探索代理程序记忆
链接：https://arxiv.org/abs/2508.06433
备注 ：Work in progress
摘要：基于大型语言模型（LLM）的代理擅长于各种任务，但它们遭受脆弱的程序内存，这些内存是手动设计的或与静态参数纠缠在一起。在这项工作中，我们研究策略，赋予代理人的可学习，可更新，和终身的程序记忆。我们提出Memp，蒸馏过去的代理轨迹到细粒度的，一步一步的指令和更高级别的，脚本般的抽象，并探讨不同的策略的影响，建立，检索和更新的程序内存。再加上一个不断更新、更正和弃用其内容的动态方案，这个存储库与新的经验同步发展。在TravelPlanner和ALFWorld上的实证评估表明，随着记忆库的完善，智能体在类似任务上获得了更高的成功率和更高的效率。此外，从更强的模型构建的过程内存保留了它的价值：将过程内存迁移到更弱的模型会产生实质性的性能增益。
摘要：Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters. In this work, we investigate strategies to endow agents with a learnable, updatable, and lifelong procedural memory. We propose Memp that distills past agent trajectories into both fine-grained, step-by-step instructions and higher-level, script-like abstractions, and explore the impact of different strategies for Build, Retrieval, and Update of procedural memory. Coupled with a dynamic regimen that continuously updates, corrects, and deprecates its contents, this repository evolves in lockstep with new experience. Empirical evaluation on TravelPlanner and ALFWorld shows that as the memory repository is refined, agents achieve steadily higher success rates and greater efficiency on analogous tasks. Moreover, procedural memory built from a stronger model retains its value: migrating the procedural memory to a weaker model yields substantial performance gains.
【4】A New Lens on Homelessness: Daily Tent Monitoring with 311 Calls and Street Images
标题：无家可归者的新视角：通过311电话和街道图像进行日常帐篷监控
链接：https://arxiv.org/abs/2508.06409
备注：10 pages, Accepted to SBP-BRiMS 2025
摘要：美国的无家可归者人数已经上升到大萧条以来的最高水平。然而，现有的监测方法，如时间点（PIT）计数，在频率，一致性和空间细节方面存在局限性。这项研究提出了一种新的方法，使用公开的众包数据，特别是311服务呼叫和街道级图像，来跟踪和预测旧金山无家可归者的帐篷趋势。我们的预测模型捕捉精细的每日和社区水平的变化，揭示了传统统计经常忽略的模式，例如COVID-19大流行期间的快速波动和帐篷位置随时间的空间变化。通过提供更及时、本地化和具有成本效益的信息，这一方法成为指导政策反应和评估旨在减少无家可归者的干预措施的宝贵工具。
摘要：Homelessness in the United States has surged to levels unseen since the Great Depression. However, existing methods for monitoring it, such as point-in-time (PIT) counts, have limitations in terms of frequency, consistency, and spatial detail. This study proposes a new approach using publicly available, crowdsourced data, specifically 311 Service Calls and street-level imagery, to track and forecast homeless tent trends in San Francisco. Our predictive model captures fine-grained daily and neighborhood-level variations, uncovering patterns that traditional counts often overlook, such as rapid fluctuations during the COVID-19 pandemic and spatial shifts in tent locations over time. By providing more timely, localized, and cost-effective information, this approach serves as a valuable tool for guiding policy responses and evaluating interventions aimed at reducing unsheltered homelessness.
【5】Geometric-k-means: A Bound Free Approach to Fast and Eco-Friendly k-means
标题：几何k-均值：快速且环保的k-均值的束缚自由方法
链接：https://arxiv.org/abs/2508.06353
摘要：本文介绍了Geometric-k-means（简称Gk-means），这是一种新的方法，可以显着提高广泛使用的k-means算法的效率和能源经济性，尽管它在50多年前就开始了，但仍然是机器学习应用的基石。Gk-means的本质在于它积极利用几何原理，特别是标量投影，在不牺牲解质量的情况下显着加速算法。这种几何策略使我们能够更加专注于最有可能影响集群更新的数据点，我们称之为高表达数据（HE）。相比之下，低表达数据（LE），不影响聚类结果，有效地绕过，从而大大减少了计算开销。跨越合成，真实世界和高维数据集的实验表明，Gk-means在运行时间和距离计算（DC）方面明显优于传统和最先进的（SOTA）k-means变体。此外，Gk-means具有更好的资源效率，其减少的能源足迹证明了这一点，使其成为更可持续的替代品。
摘要：This paper introduces Geometric-k-means (or Gk-means for short), a novel approach that significantly enhances the efficiency and energy economy of the widely utilized k-means algorithm, which, despite its inception over five decades ago, remains a cornerstone in machine learning applications. The essence of Gk-means lies in its active utilization of geometric principles, specifically scalar projection, to significantly accelerate the algorithm without sacrificing solution quality. This geometric strategy enables a more discerning focus on data points that are most likely to influence cluster updates, which we call as high expressive data (HE). In contrast, low expressive data (LE), does not impact clustering outcome, is effectively bypassed, leading to considerable reductions in computational overhead. Experiments spanning synthetic, real-world and high-dimensional datasets, demonstrate Gk-means is significantly better than traditional and state of the art (SOTA) k-means variants in runtime and distance computations (DC). Moreover, Gk-means exhibits better resource efficiency, as evidenced by its reduced energy footprint, placing it as more sustainable alternative.
【6】Low-Bit Data Processing Using Multiple-Output Spiking Neurons with Non-linear Reset Feedback
标题：使用具有非线性重置反馈的多输出尖峰神经元进行低位数据处理
链接：https://arxiv.org/abs/2508.06292
备注：15 pages, 7 Tables, 6 Figures
摘要：神经形态计算是一种新兴的技术，能够实现低延迟和节能的信号处理。神经形态计算中的一个关键算法工具是尖峰神经网络（SNN）。SNN是生物启发的神经网络，其利用有状态神经元，并通过使用尖峰对信息进行编码和解码来提供低比特数据处理。与SNN类似，深度状态空间模型（SSM）使用有状态构建块。然而，最近在各种时间建模任务中取得竞争性性能的深度SSM通常设计有高精度激活函数，并且没有重置机制。为了弥补SNN和最近的深度SSM模型提供的增益，我们提出了一种新的多输出尖峰神经元模型，该模型将线性的一般SSM状态转换与通过重置的非线性反馈机制相结合。与现有的SNN神经元模型相比，我们提出的模型清楚地概念化了尖峰函数，复位条件和复位动作之间的差异。各种任务的实验结果，即，一个关键字定位任务，基于事件的视觉任务和顺序模式识别任务，表明我们提出的模型达到性能媲美现有的基准SNN文献。我们的研究结果说明了所提出的重置机制如何克服不稳定性，即使在神经元动力学的线性部分不稳定的情况下也能进行学习，从而使我们超越了最近深度SSM模型中线性动力学的严格强制稳定性。
摘要：Neuromorphic computing is an emerging technology enabling low-latency and energy-efficient signal processing. A key algorithmic tool in neuromorphic computing is spiking neural networks (SNNs). SNNs are biologically inspired neural networks which utilize stateful neurons, and provide low-bit data processing by encoding and decoding information using spikes. Similar to SNNs, deep state-space models (SSMs) utilize stateful building blocks. However, deep SSMs, which recently achieved competitive performance in various temporal modeling tasks, are typically designed with high-precision activation functions and no reset mechanisms. To bridge the gains offered by SNNs and the recent deep SSM models, we propose a novel multiple-output spiking neuron model that combines a linear, general SSM state transition with a non-linear feedback mechanism through reset. Compared to the existing neuron models for SNNs, our proposed model clearly conceptualizes the differences between the spiking function, the reset condition and the reset action. The experimental results on various tasks, i.e., a keyword spotting task, an event-based vision task and a sequential pattern recognition task, show that our proposed model achieves performance comparable to existing benchmarks in the SNN literature. Our results illustrate how the proposed reset mechanism can overcome instability and enable learning even when the linear part of neuron dynamics is unstable, allowing us to go beyond the strictly enforced stability of linear dynamics in recent deep SSM models.
【7】OM2P: Offline Multi-Agent Mean-Flow Policy
标题：OM 2P：离线多代理平均流量政策
链接：https://arxiv.org/abs/2508.06269
摘要：生成模型，特别是基于扩散和流的模型，在离线多智能体强化学习中很有前途。然而，将强大的生成模型集成到这个框架中带来了独特的挑战。特别是，扩散和基于流的策略由于其迭代生成过程而遭受低采样效率，使得它们在时间敏感或资源受限的设置中不切实际。为了解决这些困难，我们提出了OM 2 P（离线多智能体平均流策略），一种新的离线MARL算法，实现高效的一步动作采样。为了解决生成目标和奖励最大化之间的不一致，我们引入了一个奖励感知的优化方案，该方案将精心设计的平均流匹配损失与Q函数监督相结合。此外，我们设计了一个广义的时间步长分布和导数的估计策略，以减少内存开销，提高训练的稳定性。在Multi-Agent Particle和MuJoCo基准测试上的实证评估表明，OM 2 P实现了卓越的性能，GPU内存使用量减少了3.8倍，训练时间加速了10.8倍。我们的方法代表了第一个成功地将平均流模型集成到离线MARL中，为合作多智能体环境中的实用和可扩展的生成策略铺平了道路。
摘要：Generative models, especially diffusion and flow-based models, have been promising in offline multi-agent reinforcement learning. However, integrating powerful generative models into this framework poses unique challenges. In particular, diffusion and flow-based policies suffer from low sampling efficiency due to their iterative generation processes, making them impractical in time-sensitive or resource-constrained settings. To tackle these difficulties, we propose OM2P (Offline Multi-Agent Mean-Flow Policy), a novel offline MARL algorithm to achieve efficient one-step action sampling. To address the misalignment between generative objectives and reward maximization, we introduce a reward-aware optimization scheme that integrates a carefully-designed mean-flow matching loss with Q-function supervision. Additionally, we design a generalized timestep distribution and a derivative-free estimation strategy to reduce memory overhead and improve training stability. Empirical evaluations on Multi-Agent Particle and MuJoCo benchmarks demonstrate that OM2P achieves superior performance, with up to a 3.8x reduction in GPU memory usage and up to a 10.8x speed-up in training time. Our approach represents the first to successfully integrate mean-flow model into offline MARL, paving the way for practical and scalable generative policies in cooperative multi-agent settings.
【8】Symmetry breaking for inductive logic programming
标题：归纳逻辑编程的对称破坏
链接：https://arxiv.org/abs/2508.06263
摘要：归纳逻辑编程的目标是寻找一个假设，概括训练数据和背景知识。挑战在于寻找巨大的假设空间，这是加剧，因为存在许多逻辑上等价的假设。为了解决这一挑战，我们引入了一种方法来打破假设空间中的对称性。我们在答案集编程中实现了我们的想法。我们在多个领域（包括视觉推理和游戏）的实验表明，我们的方法可以将解决时间从一个多小时减少到17秒。
摘要：The goal of inductive logic programming is to search for a hypothesis that generalises training data and background knowledge. The challenge is searching vast hypothesis spaces, which is exacerbated because many logically equivalent hypotheses exist. To address this challenge, we introduce a method to break symmetries in the hypothesis space. We implement our idea in answer set programming. Our experiments on multiple domains, including visual reasoning and game playing, show that our approach can reduce solving times from over an hour to just 17 seconds.
【9】SCAR: State-Space Compression for AI-Driven Resource Management in 6G-Enabled Vehicular Infotainment Systems
标题：SWR：支持6G的车载信息娱乐系统中人工智能驱动的资源管理的状态空间压缩
链接：https://arxiv.org/abs/2508.06243
摘要：6 G网络的出现为车载环境中的互联信息娱乐服务开辟了新的可能性。然而，传统的无线电资源管理（RRM）技术与来自自动驾驶车辆的数据（诸如信道质量指示符（CQI））的增加的量和复杂性作斗争。为了解决这个问题，我们提出了SCAR（用于AI驱动的资源管理的状态空间压缩），这是一个边缘AI辅助框架，可以优化车辆信息娱乐中的调度和公平性。SCAR采用基于ML的压缩技术（例如，集群和径向基函数网络）以减少CQI数据大小，同时保留基本特征。这些压缩状态用于训练支持6 G的强化学习策略，以最大化吞吐量，同时满足NGMN定义的公平性目标。仿真结果表明，与没有CQI压缩的RL基线相比，SCAR使可行调度区域内的时间增加了14%，不公平调度时间减少了15%.此外，模拟退火与随机隧道（SAST）为基础的聚类CQI聚类失真减少了10%，证实了其效率。这些结果证明了SCAR对于动态车辆网络的可扩展性和公平性优势。
摘要：The advent of 6G networks opens new possibilities for connected infotainment services in vehicular environments. However, traditional Radio Resource Management (RRM) techniques struggle with the increasing volume and complexity of data such as Channel Quality Indicators (CQI) from autonomous vehicles. To address this, we propose SCAR (State-Space Compression for AI-Driven Resource Management), an Edge AI-assisted framework that optimizes scheduling and fairness in vehicular infotainment. SCAR employs ML-based compression techniques (e.g., clustering and RBF networks) to reduce CQI data size while preserving essential features. These compressed states are used to train 6G-enabled Reinforcement Learning policies that maximize throughput while meeting fairness objectives defined by the NGMN. Simulations show that SCAR increases time in feasible scheduling regions by 14\% and reduces unfair scheduling time by 15\% compared to RL baselines without CQI compression. Furthermore, Simulated Annealing with Stochastic Tunneling (SAST)-based clustering reduces CQI clustering distortion by 10\%, confirming its efficiency. These results demonstrate SCAR's scalability and fairness benefits for dynamic vehicular networks.
【10】Don't Forget Imagination!
标题：不要忘记想象力！
链接：https://arxiv.org/abs/2508.06062
备注：14 pages, 2 figures
摘要：认知想象是一种在人类思维中起着关键作用的想象。这不是一个“头脑中的图片”的想象。它是一种在心理上形象化连贯和整体的概念和因果联系系统的能力，这些系统作为推理，决策和预测的语义背景。我们的立场是，认知想象力的作用仍然被大大低估，这造成了许多问题，并削弱了人工智能目前的能力。例如，在推理时，人类依靠想象的上下文来检索背景信息。他们还不断地回到上下文进行语义验证，以证明他们的推理仍然是合理的。没有想象力的推理是盲目的。本文呼吁更多地关注认知想象，将其视为人工智能的下一个有希望的突破。作为一种模拟认知想象的工具，我们提出了语义模型--一种新的数学模型方法，它可以像神经网络一样学习，并且基于概率因果关系。语义模型可以模拟认知想象，因为它们确保了想象语境的一致性，并实现了一种玻璃盒方法，允许将语境作为一个整体和连贯的系统进行操作，这些系统由相互关联的事实和因果关系粘合在一起。
摘要 ：Cognitive imagination is a type of imagination that plays a key role in human thinking. It is not a ``picture-in-the-head'' imagination. It is a faculty to mentally visualize coherent and holistic systems of concepts and causal links that serve as semantic contexts for reasoning, decision making and prediction. Our position is that the role of cognitive imagination is still greatly underestimated, and this creates numerous problems and diminishes the current capabilities of AI. For instance, when reasoning, humans rely on imaginary contexts to retrieve background info. They also constantly return to the context for semantic verification that their reasoning is still reasonable. Thus, reasoning without imagination is blind. This paper is a call for greater attention to cognitive imagination as the next promising breakthrough in artificial intelligence. As an instrument for simulating cognitive imagination, we propose semantic models -- a new approach to mathematical models that can learn, like neural networks, and are based on probabilistic causal relationships. Semantic models can simulate cognitive imagination because they ensure the consistency of imaginary contexts and implement a glass-box approach that allows the context to be manipulated as a holistic and coherent system of interrelated facts glued together with causal relations.
【11】Stepwise Fine and Gray: Subject-Specific Variable Selection Shows When Hemodynamic Data Improves Prognostication of Comatose Post-Cardiac Arrest Patients
标题：分步细和灰色：特定对象变量选择显示血液动力学数据何时改善心脏骤停后昏迷患者的预后
链接：https://arxiv.org/abs/2508.06023
摘要：心脏骤停后昏迷患者的预后是一个关键的挑战，直接影响ICU的临床决策。随时间连续收集通知统计的临床信息。在心脏骤停之后不久，收集各种时不变基线特征（例如，人口统计学、心脏骤停特征）。在ICU入院后，收集额外的特征，包括时变血液动力学数据（例如，血压、血管加压药的剂量）。我们认为这是我们收集新功能的两个阶段。在这项研究中，我们提出了一种新的逐步动态竞争风险模型，该模型通过自动确定何时利用时不变特征（第一阶段）和时变特征（第二阶段）来改善神经系统结果的预测。值得注意的是，我们的模型找到了第二阶段（随时间变化的血流动力学）信息对血流动力学有利的患者，以及该信息何时有益（随着时间的推移，我们为患者收集了更多的血流动力学数据，这些数据对血流动力学的重要性不同）。我们的方法扩展了标准的精细和灰色模型，以明确地对两个阶段进行建模，并将神经网络灵活地捕获复杂的非线性特征关系。通过对2，278名昏迷的停搏后患者的回顾性队列进行评估，我们的模型显示出对觉醒，撤回生命维持治疗和死亡（尽管有最大支持）的竞争结果的强大区分性能。我们的方法可以推广到两个以上的阶段，在这些阶段中，新的特征被收集，并且可以用于其他动态预测任务，在这些任务中，了解新收集的特征何时以及对谁显着改善预测可能是有帮助的。
摘要：Prognostication for comatose post-cardiac arrest patients is a critical challenge that directly impacts clinical decision-making in the ICU. Clinical information that informs prognostication is collected serially over time. Shortly after cardiac arrest, various time-invariant baseline features are collected (e.g., demographics, cardiac arrest characteristics). After ICU admission, additional features are gathered, including time-varying hemodynamic data (e.g., blood pressure, doses of vasopressor medications). We view these as two phases in which we collect new features. In this study, we propose a novel stepwise dynamic competing risks model that improves the prediction of neurological outcomes by automatically determining when to take advantage of time-invariant features (first phase) and time-varying features (second phase). Notably, our model finds patients for whom this second phase (time-varying hemodynamic) information is beneficial for prognostication and also when this information is beneficial (as we collect more hemodynamic data for a patient over time, how important these data are for prognostication varies). Our approach extends the standard Fine and Gray model to explicitly model the two phases and to incorporate neural networks to flexibly capture complex nonlinear feature relationships. Evaluated on a retrospective cohort of 2,278 comatose post-arrest patients, our model demonstrates robust discriminative performance for the competing outcomes of awakening, withdrawal of life-sustaining therapy, and death despite maximal support. Our approach generalizes to more than two phases in which new features are collected and could be used in other dynamic prediction tasks, where it may be helpful to know when and for whom newly collected features significantly improve prediction.
【12】Position: Intelligent Coding Systems Should Write Programs with Justifications
标题：立场：智能编码系统应该编写有理由的程序
链接：https://arxiv.org/abs/2508.06017
备注：The first two authors contributed equally to this work
摘要：智能编码系统通过使用户能够用自然语言指定代码行为来改变软件开发。然而，人工智能驱动的编码器的不透明决策引起了信任和可用性问题，特别是对于无法检查低级别实现的非专家用户。我们认为，这些系统不仅应该生成代码，但也产生明确的，一致的理由，桥梁模型推理和用户的理解。为此，我们确定了两个关键的理由属性认知对齐和语义的忠实性，并强调现有方法的局限性，包括正式验证，静态分析，事后可解释性。我们提倡探索神经符号的方法来生成合理性，其中符号约束在训练过程中指导模型行为，并且通过神经表示来丰富程序语义，从而在推理时实现自动一致性检查。
摘要：Intelligent coding systems are transforming software development by enabling users to specify code behavior in natural language. However, the opaque decision-making of AI-driven coders raises trust and usability concerns, particularly for non-expert users who cannot inspect low-level implementations. We argue that these systems should not only generate code but also produce clear, consistent justifications that bridge model reasoning and user understanding. To this end, we identify two critical justification properties-cognitive alignment and semantic faithfulness-and highlight the limitations of existing methods, including formal verification, static analysis, and post-hoc explainability. We advocate exploring neuro-symbolic approaches for justification generation, where symbolic constraints guide model behavior during training and program semantics are enriched through neural representations, enabling automated consistency checks at inference time.
【13】Dual Signal Decomposition of Stochastic Time Series
标题：随机时间序列的双重信号分解
链接：https://arxiv.org/abs/2508.05915
备注：21 pages, 9 figures, 1 table
摘要：该研究论文解决了将随机时间序列分解为代表双重信号的三个时间序列，即，平均值和离散度，噪声被隔离。分解是通过应用机器学习来拟合对偶信号来完成的。机器学习最小化损失函数，该损失函数在拟合原始时间序列和惩罚双信号的不规则性之间进行折衷。后者包括基于沿时间的一阶和二阶导数的项。为了保持特殊的模式，加权的正则化组件的损失函数已被引入的统计过程控制方法的基础上。建议的分解可以作为一个平滑算法对时间序列的平均值和分散。通过隔离噪声，所提出的分解可以被看作是一种去噪算法。学习过程的两种方法被认为是：顺序和联合。前一种方法首先学习平均信号，然后学习离散度。后一种方法联合拟合双信号。联合学习可以揭示具有异方差性的时间序列的复杂关系。学习已经通过解决直接非线性无约束优化问题或通过应用具有顺序或双输出架构的神经网络来设置。损失函数超参数的调整集中在孤立的噪声是一个平稳的随机过程，没有自相关特性。根据不同的应用，学习的超参数可以通过步进信号或平滑序列调整到离散状态。分解后的对偶信号可以在二维空间上表示，并用于学习固有结构，预测均值和离散度，或者在多个时间序列的情况下分析交叉效应。
摘要：The research paper addresses decomposition of a stochastic time series into three time series representing a dual signal i.e., the mean and the dispersion, with noise isolated. Decomposition is done by applying machine learning to fit a dual signal. Machine learning minimizes the loss function which compromises between fitting the original time series and penalizing irregularities of the dual signal. The latter includes terms based on the first and second order derivatives along time. To preserve special patterns, weighting of the regularization components of the loss function has been introduced based on Statistical Process Control methodology. The proposed decomposition can be applied as a smoothing algorithm against the mean and dispersion of the time series. By isolating noise, the proposed decomposition can be seen as a denoising algorithm. Two approaches of the learning process have been considered: sequential and jointly. The former approach learns the mean signal first and then dispersion. The latter approach fits the dual signal jointly. Jointly learning can uncover complex relationships for the time series with heteroskedasticity. Learning has been set by solving the direct non-linear unconstrained optimization problem or by applying neural networks that have sequential or twin output architectures. Tuning of the loss function hyperparameters focuses on the isolated noise to be a stationary stochastic process without autocorrelation properties. Depending on the applications, the hyperparameters of the learning can be tuned towards either the discrete states by stepped signal or smoothed series. The decomposed dual signal can be represented on the 2D space and used to learn inherent structures, to forecast both mean and dispersion, or to analyze cross effects in case of multiple time series.
【14】A Markov Decision Process Framework for Early Maneuver Decisions in Satellite Collision Avoidance
标题：卫星避碰早期机动决策的马尔科夫决策过程框架
链接：https://arxiv.org/abs/2508.05876
备注：16 pages, 13 figures, submitted to the 2025 Astrodynamics Specialist Conference
摘要：本文提出了一种马尔可夫决策过程（MDP）框架来建模避碰机动（CAM）的决策，并提出了一种强化学习策略梯度（RL-PG）算法来利用历史CAM数据训练自主制导策略。除了保持可接受的碰撞风险外，该方法还寻求通过早期机动决策来最小化CAM的平均燃料消耗。我们CAM模型作为一个连续的状态，离散的行动和有限的地平线MDP，其中的关键决策是确定何时启动机动。MDP模型还包含会合风险、推进剂消耗和过境轨道几何形状的分析模型。马尔可夫策略有效地权衡了机动延迟，这提高了连接风险指标的可靠性与推进剂消耗，随着机动时间的减少而增加。使用历史数据的跟踪连接事件，我们验证了这一框架，并进行了广泛的消融研究中使用的超参数MDP。在合成会合事件中，与在最接近时刻（TCA）前24小时开始机动的传统切断策略相比，训练后的策略使每个CAM的总体和平均推进剂消耗量显著最小化。在历史会合事件上，训练后的策略总体上消耗更多的推进剂，但减少了每个CAM的平均推进剂消耗。对于历史和合成会合事件，训练后的策略实现了相等的（如果不是更高的）总体碰撞风险保证。
摘要：This work presents a Markov decision process (MDP) framework to model decision-making for collision avoidance maneuver (CAM) and a reinforcement learning policy gradient (RL-PG) algorithm to train an autonomous guidance policy using historic CAM data. In addition to maintaining acceptable collision risks, this approach seeks to minimize the average fuel consumption of CAMs by making early maneuver decisions. We model CAM as a continuous state, discrete action and finite horizon MDP, where the critical decision is determining when to initiate the maneuver. The MDP model also incorporates analytical models for conjunction risk, propellant consumption, and transit orbit geometry. The Markov policy effectively trades-off maneuver delay-which improves the reliability of conjunction risk indicators-with propellant consumption-which increases with decreasing maneuver time. Using historical data of tracked conjunction events, we verify this framework and conduct an extensive ablation study on the hyper-parameters used within the MDP. On synthetic conjunction events, the trained policy significantly minimizes both the overall and average propellant consumption per CAM when compared to a conventional cut-off policy that initiates maneuvers 24 hours before the time of closest approach (TCA). On historical conjunction events, the trained policy consumes more propellant overall but reduces the average propellant consumption per CAM. For both historical and synthetic conjunction events, the trained policy achieves equal if not higher overall collision risk guarantees.
【15】Towards Transparent Ethical AI: A Roadmap for Trustworthy Robotic Systems
标题：迈向透明的道德人工智能：值得信赖的机器人系统的路线图
链接：https://arxiv.org/abs/2508.05846
备注：Published in the Proceedings of the 2025 3rd International Conference on Robotics, Control and Vision Engineering (RCVE'25). 6 pages, 3 tables
摘要：随着人工智能（AI）和机器人技术越来越多地渗透到社会中，确保这些系统的道德行为变得至关重要。本文认为，人工智能决策过程的透明度是开发值得信赖和符合道德的机器人系统的基础。我们探讨了透明度如何促进问责制，实现知情同意，并支持道德算法的调试。本文概述了实施透明度的技术，道德和实践挑战，并提出了增强透明度的新方法，包括标准化指标，可解释的人工智能技术和用户友好的界面。本文介绍了一个框架，连接技术实现与机器人系统中的道德考虑，重点是在动态的，现实世界的背景下实现透明度的具体挑战。我们分析了优先透明度如何影响公众信任，监管政策和未来研究的途径。通过将透明度定位为道德人工智能系统设计的基本要素，我们的目标是增加正在进行的关于负责任的人工智能和机器人技术的讨论，为这一重要领域的未来发展提供方向。
摘要：As artificial intelligence (AI) and robotics increasingly permeate society, ensuring the ethical behavior of these systems has become paramount. This paper contends that transparency in AI decision-making processes is fundamental to developing trustworthy and ethically aligned robotic systems. We explore how transparency facilitates accountability, enables informed consent, and supports the debugging of ethical algorithms. The paper outlines technical, ethical, and practical challenges in implementing transparency and proposes novel approaches to enhance it, including standardized metrics, explainable AI techniques, and user-friendly interfaces. This paper introduces a framework that connects technical implementation with ethical considerations in robotic systems, focusing on the specific challenges of achieving transparency in dynamic, real-world contexts. We analyze how prioritizing transparency can impact public trust, regulatory policies, and avenues for future research. By positioning transparency as a fundamental element in ethical AI system design, we aim to add to the ongoing discussion on responsible AI and robotics, providing direction for future advancements in this vital field.
【16】Stochastic Bandits for Crowdsourcing and Multi-Platform Autobidding
标题：众包和多平台自动竞价的随机盗贼
链接：https://arxiv.org/abs/2508.05844
摘要：出于在众包中的应用程序，其中一个固定的金额是$K$工人之间的分割，和自动投标，其中一个固定的预算是用来出价在$K$同时拍卖，我们定义了一个随机强盗模型，武器属于$K$维概率单纯形，并表示分配给每个任务/拍卖的预算的一部分。每轮的奖励是$K$随机奖励的总和，其中每个奖励的解锁概率随分配给该任务/拍卖的预算比例而变化。我们设计了一个算法，其预期的遗憾后$T$步骤是为了$K\sqrt{T}$（最多日志因子），并证明了匹配的下界。当函数将预算映射到解锁奖励的概率（即，终止任务或赢得拍卖）满足附加的收益递减条件。
摘要：Motivated by applications in crowdsourcing, where a fixed sum of money is split among $K$ workers, and autobidding, where a fixed budget is used to bid in $K$ simultaneous auctions, we define a stochastic bandit model where arms belong to the $K$-dimensional probability simplex and represent the fraction of budget allocated to each task/auction. The reward in each round is the sum of $K$ stochastic rewards, where each of these rewards is unlocked with a probability that varies with the fraction of the budget allocated to that task/auction. We design an algorithm whose expected regret after $T$ steps is of order $K\sqrt{T}$ (up to log factors) and prove a matching lower bound. Improved bounds of order $K (\log T)^2$ are shown when the function mapping budget to probability of unlocking the reward (i.e., terminating the task or winning the auction) satisfies additional diminishing-returns conditions.
【17】Multi-Faceted Large Embedding Tables for Pinterest Ads Ranking
标题：Pinterest广告排名的多面大型嵌入表
链接：https://arxiv.org/abs/2508.05700
摘要：大型嵌入表在现代推荐系统中是不可或缺的，这要归功于它们能够有效地捕捉和记忆不同实体之间交互的复杂细节。当我们探索将大型嵌入表集成到Pinterest的广告排名模型中时，我们不仅遇到了稀疏性和可扩展性等常见挑战，还遇到了一些特定于我们环境的障碍。值得注意的是，我们最初从头开始训练大型嵌入表的尝试导致了中性指标。为了解决这个问题，我们引入了一种新颖的多方面预训练方案，该方案包含多个预训练算法。这种方法极大地丰富了嵌入表，并导致显着的性能改进。因此，多方面的大嵌入表在点击率（CTR）和转换率（CVR）域上都带来了巨大的性能增益。此外，我们还设计了一个CPU-GPU混合服务架构，以克服GPU内存限制，提高可扩展性。该框架已部署在Pinterest广告系统中，并实现了1.34%的在线CPC减少和2.60%的CTR增加，端到端延迟变化为中性。
摘要 ：Large embedding tables are indispensable in modern recommendation systems, thanks to their ability to effectively capture and memorize intricate details of interactions among diverse entities. As we explore integrating large embedding tables into Pinterest's ads ranking models, we encountered not only common challenges such as sparsity and scalability, but also several obstacles unique to our context. Notably, our initial attempts to train large embedding tables from scratch resulted in neutral metrics. To tackle this, we introduced a novel multi-faceted pretraining scheme that incorporates multiple pretraining algorithms. This approach greatly enriched the embedding tables and resulted in significant performance improvements. As a result, the multi-faceted large embedding tables bring great performance gain on both the Click-Through Rate (CTR) and Conversion Rate (CVR) domains. Moreover, we designed a CPU-GPU hybrid serving infrastructure to overcome GPU memory limits and elevate the scalability. This framework has been deployed in the Pinterest Ads system and achieved 1.34% online CPC reduction and 2.60% CTR increase with neutral end-to-end latency change.
【18】AI Guided Accelerator For Search Experience
标题：人工智能引导的搜索体验加速器
链接：https://arxiv.org/abs/2508.05649
备注：Accepted at SIGIR eCom'25. this https URL
摘要：在电子商务环境中，有效的查询重构是缩小用户探索性搜索行为与相关产品识别之间差距的关键。虽然传统方法主要将查询重写建模为孤立的对，但它们通常无法捕获真实世界用户行为中固有的顺序和过渡动态。在这项工作中，我们提出了一个新的框架，明确模型过渡查询-中间发生在用户的旅程对他们的最终购买意图的重新制定。通过挖掘eBay的大规模用户交互日志的结构化查询轨迹，我们重建的查询序列，反映意图的变化，同时保持语义的一致性。这种方法允许我们对用户的购物漏斗进行建模，其中中途过渡反映了探索性行为和意图细化。此外，我们将生成的大型语言模型（LLM），以产生语义多样和意图保留的替代查询，扩展超出可以通过协同过滤单独得出。这些重构可以用来填充Related搜索引擎，或者在搜索结果页面上为意图聚类的旋转木马提供动力，从而增强发现和参与。我们的贡献包括（i）过渡查询的正式识别和建模，（ii）引入结构化查询序列挖掘管道以理解意图流，以及（iii）应用LLM进行可扩展的意图感知查询扩展。实证评估表明，与现有的Related Website模块相比，我们在转换和参与度指标方面取得了可衡量的进步，验证了我们的方法在现实电子商务环境中的有效性。
摘要：Effective query reformulation is pivotal in narrowing the gap between a user's exploratory search behavior and the identification of relevant products in e-commerce environments. While traditional approaches predominantly model query rewrites as isolated pairs, they often fail to capture the sequential and transitional dynamics inherent in real-world user behavior. In this work, we propose a novel framework that explicitly models transitional queries--intermediate reformulations occurring during the user's journey toward their final purchase intent. By mining structured query trajectories from eBay's large-scale user interaction logs, we reconstruct query sequences that reflect shifts in intent while preserving semantic coherence. This approach allows us to model a user's shopping funnel, where mid-journey transitions reflect exploratory behavior and intent refinement. Furthermore, we incorporate generative Large Language Models (LLMs) to produce semantically diverse and intent-preserving alternative queries, extending beyond what can be derived through collaborative filtering alone. These reformulations can be leveraged to populate Related Searches or to power intent-clustered carousels on the search results page, enhancing both discovery and engagement. Our contributions include (i) the formal identification and modeling of transitional queries, (ii) the introduction of a structured query sequence mining pipeline for intent flow understanding, and (iii) the application of LLMs for scalable, intent-aware query expansion. Empirical evaluation demonstrates measurable gains in conversion and engagement metrics compared to the existing Related Searches module, validating the effectiveness of our approach in real-world e-commerce settings.
【19】Indian Legal NLP Benchmarks : A Survey
标题：印度法律NLP基准：调查
链接：https://arxiv.org/abs/2107.06056
摘要：具有挑战性的基准的可用性是AI在特定领域取得进步的关键。由于法律文本与普通英语文本有很大不同，因此需要为印度法律文本创建单独的自然语言处理基准，这些基准具有挑战性，并专注于法律系统特定的任务。这将刺激印度法律文本自然语言处理应用的创新，并将使人工智能社区和法律界受益。我们回顾了这一领域的现有工作，并提出了为印度法律自然语言处理创建新基准的想法。
摘要：Availability of challenging benchmarks is the key to advancement of AI in a specific field.Since Legal Text is significantly different than normal English text, there is a need to create separate Natural Language Processing benchmarks for Indian Legal Text which are challenging and focus on tasks specific to Legal Systems. This will spur innovation in applications of Natural language Processing for Indian Legal Text and will benefit AI community and Legal fraternity. We review the existing work in this area and propose ideas to create new benchmarks for Indian Legal Natural Language Processing.
【20】Multivariate Fields of Experts
标题：多元专家领域
链接：https://arxiv.org/abs/2508.06490
摘要：我们介绍了多变量领域的专家，一个新的框架，学习图像先验知识。我们的模型推广了现有领域的专家方法，将通过莫罗包络的$\ell_\infty$-范数构造的多元势函数。我们证明了我们的建议在一系列逆问题，包括图像去噪，去模糊，压缩传感磁共振成像，计算机断层扫描的有效性。所提出的方法优于可比的单变量模型，并实现了接近基于深度学习的正则化器的性能，同时速度更快，需要更少的参数，并且在更少的数据上进行训练。此外，由于其结构化设计，我们的模型保留了相对较高的可解释性。
摘要：We introduce the multivariate fields of experts, a new framework for the learning of image priors. Our model generalizes existing fields of experts methods by incorporating multivariate potential functions constructed via Moreau envelopes of the $\ell_\infty$-norm. We demonstrate the effectiveness of our proposal across a range of inverse problems that include image denoising, deblurring, compressed-sensing magnetic-resonance imaging, and computed tomography. The proposed approach outperforms comparable univariate models and achieves performance close to that of deep-learning-based regularizers while being significantly faster, requiring fewer parameters, and being trained on substantially fewer data. In addition, our model retains a relatively high level of interpretability due to its structured design.
【21】DP-SPRT: Differentially Private Sequential Probability Ratio Tests
标题：DP-SPRT：差异私人顺序概率比测试
链接：https://arxiv.org/abs/2508.06377
摘要 ：我们重温沃尔德的著名的序贯概率比检验的两个简单的假设，隐私的限制下的序贯检验。我们提出了DP-SPRT，一个包装器，可以校准，以实现所需的错误概率和隐私约束，解决了以前的工作中的一个显着差距。DP-SPRT依赖于一种私有机制，该机制处理一系列查询，并在私有地确定查询结果何时落在预定义的间隔之外之后停止。这种OutsideInterval机制改进了现有技术（如IncreveThreshold）的简单组合，可能有益于其他顺序算法。我们证明了通用的上界DP-SPRT的错误和样本的复杂性，可以适应各种噪声分布的从业者的隐私需求的基础上。我们在两种情况下对它们进行了加密：拉普拉斯噪声（纯差分隐私）和高斯噪声（R\'enyi差分隐私）。在前一种设置中，通过提供一个下限的样本复杂性的任何$\n $-DP测试与规定的I型和II型错误，我们表明，DP-SPRT是接近最优的两个错误时，两个假设是接近。此外，我们还进行了实验研究，显示了其良好的实用性能。
摘要：We revisit Wald's celebrated Sequential Probability Ratio Test for sequential tests of two simple hypotheses, under privacy constraints. We propose DP-SPRT, a wrapper that can be calibrated to achieve desired error probabilities and privacy constraints, addressing a significant gap in previous work. DP-SPRT relies on a private mechanism that processes a sequence of queries and stops after privately determining when the query results fall outside a predefined interval. This OutsideInterval mechanism improves upon naive composition of existing techniques like AboveThreshold, potentially benefiting other sequential algorithms. We prove generic upper bounds on the error and sample complexity of DP-SPRT that can accommodate various noise distributions based on the practitioner's privacy needs. We exemplify them in two settings: Laplace noise (pure Differential Privacy) and Gaussian noise (R\'enyi differential privacy). In the former setting, by providing a lower bound on the sample complexity of any $\epsilon$-DP test with prescribed type I and type II errors, we show that DP-SPRT is near optimal when both errors are small and the two hypotheses are close. Moreover, we conduct an experimental study revealing its good practical performance.
【22】Decorrelated feature importance from local sample weighting
标题：来自本地样本加权的装饰相关特征重要性
链接：https://arxiv.org/abs/2508.06337
摘要：特征重要性（FI）统计为深入了解机器学习（ML）模型的决策过程提供了一种突出而有价值的方法，但当训练数据中的特征之间存在相关性时，其有效性具有众所周知的局限性。在这种情况下，FI通常倾向于分布在与响应生成信号特征相关的所有特征中。更糟糕的是，如果多个信号特征与噪声特征强相关，而彼此仅适度相关，则这可能导致噪声特征具有比任何信号特征明显更大的FI分数。在这里，我们提出了局部样本加权（losaw），它可以灵活地集成到许多ML算法中，以在训练数据中存在特征相关性的情况下提高FI分数。我们的方法是从因果推理中的逆概率加权出发的，并且在ML模型中局部地使用样本加权方案来将目标特征与其余特征去相关。无论何时评估潜在信号特征的影响并将其与其他特征进行比较，这都会局部地减少模型偏差。此外，losaw带有一个自然的调整参数，即加权总体的最小有效样本大小，这对应于解释-预测-权衡，类似于经典ML调整参数的偏差-方差-权衡。我们演示了如何将losaw集成到基于决策树的ML方法和神经网络的小批量训练中。我们研究losaw的随机森林和卷积神经网络的模拟研究设置显示不同的相关模式。我们发现losaw持续改善FI。此外，它通常可以提高分布外的预测精度，同时保持分布内测试数据的类似精度。
摘要：Feature importance (FI) statistics provide a prominent and valuable method of insight into the decision process of machine learning (ML) models, but their effectiveness has well-known limitations when correlation is present among the features in the training data. In this case, the FI often tends to be distributed among all features which are in correlation with the response-generating signal features. Even worse, if multiple signal features are in strong correlation with a noise feature, while being only modestly correlated with one another, this can result in a noise feature having a distinctly larger FI score than any signal feature. Here we propose local sample weighting (losaw) which can flexibly be integrated into many ML algorithms to improve FI scores in the presence of feature correlation in the training data. Our approach is motivated from inverse probability weighting in causal inference and locally, within the ML model, uses a sample weighting scheme to decorrelate a target feature from the remaining features. This reduces model bias locally, whenever the effect of a potential signal feature is evaluated and compared to others. Moreover, losaw comes with a natural tuning parameter, the minimum effective sample size of the weighted population, which corresponds to an interpretation-prediction-tradeoff, analog to a bias-variance-tradeoff as for classical ML tuning parameters. We demonstrate how losaw can be integrated within decision tree-based ML methods and within mini-batch training of neural networks. We investigate losaw for random forest and convolutional neural networks in a simulation study on settings showing diverse correlation patterns. We found that losaw improves FI consistently. Moreover, it often improves prediction accuracy for out-of-distribution, while maintaining a similar accuracy for in-distribution test data.
机器翻译由腾讯交互翻译提供，仅供参考
点击“阅读原文”获取带摘要的学术速递
Python社区是高质量的Python/Django开发社区
本文地址：http://www.python88.com/topic/185500
本文地址：http://www.python88.com/topic/185500