2026-08论文中文摘要
AISA：用于公路施工持续改进的AI安全助手框架
AISA: AI Safety Assistant Framework for Continuous Improvement of Highway Construction
arXiv 2608.17184 · 2026-08-19基准的基准：评估小型语言模型的自动化安全基准
Benchmarking the Benchmarks: Evaluating Automated Safety Benchmarks for Small Language Models
arXiv 2608.17183 · 2026-08-19RADmesh：感知重网格化的网格变形
RADmesh: Remesh-Aware Mesh Deformation
arXiv 2608.17182 · 2026-08-19作为（离散）势理论的强化学习
Reinforcement Learning as (Discrete) Potential Theory
arXiv 2608.17181 · 2026-08-19上下文强化学习的任务专业化微调
Task Specialization Fine-Tuning for Contextual Reinforcement Learning
arXiv 2608.17180 · 2026-08-19休眠稳定非传递竞争动态
Dormancy stabilizes non-transitive competitive dynamics
arXiv 2608.17179 · 2026-08-19屏蔽关键内容：面向自动驾驶的显著性引导视频自监督学习
Mask What Matters: Saliency-Guided Video Self-Supervised Learning for Autonomous Driving
arXiv 2608.17178 · 2026-08-19平衡安全与自主性：面向认知障碍群体的生成式AI可及性导向干预
Balancing Safety and Autonomy: Accessibility-Oriented Interventions in Generative AI for Cognitive Impairment
arXiv 2608.17175 · 2026-08-19基于人群健康的机器学习揭示社会心理因素与慢性肾脏病之间的关联
Population Health-Based Machine Learning Reveals Associations Between Psychosocial Factors and Chronic Kidney Disease
arXiv 2608.17174 · 2026-08-19在线上下文矩阵博弈的策略优化与统计推断
Policy Optimization and Statistical Inference for Online Contextual Matrix Games
arXiv 2608.17173 · 2026-08-19Polaris：基于检索反馈学习生成表格描述
Polaris: Learning to Generate Table Descriptions from Retrieval Feedback
arXiv 2608.17171 · 2026-08-19合成特征提取器：一种用于算法选择的智能体方法
Synthesizing Feature Extractors: An Agentic Approach for Algorithm Selection
arXiv 2608.17170 · 2026-08-19通往奇异吸引子的自主路径：混沌气泡轮的多生命阶段
Autonomous route to the strange attractor: the many life stages of the chaotic bubblewheel
arXiv 2608.17169 · 2026-08-19期望自由能作为Bethe拉格朗日量的信息约束
Expected free energy as an information constraint on the Bethe Lagrangian
arXiv 2608.17167 · 2026-08-19论巴扎德定理
On Buzzard's Theoren
arXiv 2608.17166 · 2026-08-19飓风后航拍图像的快速 debris 体积估算
Rapid Debris-Volume Estimation from Post-Hurricane Aerial Imagery
arXiv 2608.17165 · 2026-08-19SCENARIODIFF：面向多模态时间序列预测的场景级引导框架——扩展版
SCENARIODIFF: A Scenario-level Guidance Framework for Multimodal Time Series Forecasting--Extended Version
arXiv 2608.17164 · 2026-08-19结合世界模型的Q学习
Q-Learning With World Models
arXiv 2608.17163 · 2026-08-19OraclePhys：面向结构力学的大语言模型微调系统框架
OraclePhys: A Systematic Framework for LLM Fine-Tuning on Structural Mechanics
arXiv 2608.17162 · 2026-08-19树级胶子-胶子散射的闭式表达式：一种获取喷注-介质蒙特卡罗模拟理论系统不确定性的框架
Closed-form expressions for tree-level gluon-gluon scattering: a framework for obtaining theoretical systematic uncertainties for jet-medium Monte Carlo simulations
arXiv 2608.17161 · 2026-08-19有限温度QCD中树图级散射的高能行为：喷注-介质蒙特卡罗模拟中理论系统不确定性的估计
The high-energy behavior of tree-level scattering in finite-temperature QCD: estimates of theoretical systematic uncertainty in jet-medium Monte Carlo simulations
arXiv 2608.17160 · 2026-08-19软件引用元数据的多表面一致性审计
A Multi-Surface Consistency Audit of Software Citation Metadata
arXiv 2608.17159 · 2026-08-19一维三次散焦色散方程的全局解，第五部分：低正则性NLS
Global solutions for 1D cubic defocusing dispersive equations, Part V: low regularity NLS
arXiv 2608.17156 · 2026-08-19用于Lieb-Oxford不等式的固定粒子数优化器
Fixed-particle-number optimizers for the Lieb--Oxford inequality
arXiv 2608.17155 · 2026-08-19超越炒作：评估安全运营中心（SOC）中大型语言模型（LLM）的集成与实际局限性
Beyond the Hype: Evaluating LLM Integration and Practical Limitations in Security Operation Centers
arXiv 2608.17154 · 2026-08-19罗曼日冕仪社区参与计划：目标数据库与工具
The Roman Coronagraph Community Participation Program: target database and tools
arXiv 2608.17152 · 2026-08-19基于区域级组织推理与非平衡最优传输的淋巴细胞模拟修正
Lymphocyte Mimicry Correction via Region-Level Tissue Reasoning and Unbalanced Optimal Transport
arXiv 2608.17151 · 2026-08-19KnowSim：用学习的用户模拟器评估大语言模型助手的信息校准
KnowSim: Evaluating Information Calibration in LLM Assistants with User Simulators that Learn
arXiv 2608.17150 · 2026-08-19Cu(111)表面负载Zn₃团簇的温度诱导重组：从最低能量结构到有限温度系综
Temperature-Induced Reorganization of Supported Zn$_3$ Clusters on Cu(111): From Minimum-Energy Structures to Finite-Temperature Ensembles
arXiv 2608.17149 · 2026-08-19上下文之前的授权：一种针对智能体系统中跨受众记忆泄露的模型无关受众边界
Authorization Before Context: A Model-Neutral Audience Boundary Against Cross-Audience Memory Leakage in Agentic Systems
arXiv 2608.17148 · 2026-08-19PDDL-ART：基于演示的自主符号抽象方法，用于使用视觉语言模型的长时程机器人操纵
PDDL-ART: Autonomous Symbolic Abstraction From Demonstration For Long-Horizon Robotic Manipulation Using Vision-Language Models
arXiv 2608.17146 · 2026-08-19嵌入协议的合规性：隐私保护的非托管数字支付
Protocol-Embedded Compliance for Privacy-Preserving, Non-Custodial Digital Payments
arXiv 2608.17145 · 2026-08-19AI辅助健康咨询：共情表达与对话语境如何影响用户的沟通行为
Health Inquiry with AI: How Empathetic Expression and Conversational Contexts Shape Users' Communicative Acts
arXiv 2608.17144 · 2026-08-19随机拟蒙特卡罗积分
Randomized quasi-Monte Carlo integration
arXiv 2608.17143 · 2026-08-19位错环相互作用能的均匀化
Homogenization of Interaction Energy of Dislocation Loops
arXiv 2608.17141 · 2026-08-19TREC 2025 产品搜索与推荐赛道概述
Overview of the TREC 2025 Product Search and Recommendation Track
arXiv 2608.17138 · 2026-08-19与指数分离全纯迭代函数系（IFS）相关的自共形测度的维数
Dimension of self-conformal measures associated to an exponentially separated holomorphic IFS
arXiv 2608.17137 · 2026-08-19用于初等函数与滤波函数逐元素评估的迭代张量网络变换
Iterative tensor network transformations for element-wise evaluation of elementary and filtering functions
arXiv 2608.17135 · 2026-08-19罗曼日冕仪社区参与计划：偏振模式的观测规划与数据处理
The Roman Coronagraph Community Participation Program: Observation planning and data reduction for polarimetric mode
arXiv 2608.17133 · 2026-08-19通过SURE调优的岭回归实现等方差线性高斯有向无环图的因果发现
Causal Discovery in Equal Variance Linear Gaussian DAGs via SURE-Tuned Ridge Regression
arXiv 2608.17132 · 2026-08-19用于结构识别的带自适应基函数精化的降阶物理信息神经网络
Reduced-Order Physics-Informed Neural Network with Adaptive Basis Refinement for Structural Identification
arXiv 2608.17131 · 2026-08-19多拟阵的带笼收缩
Caged Retractions of Polymatroids
arXiv 2608.17130 · 2026-08-19通过协同观察实现个人智能
Toward Personal Intelligence Through Cooperative Observation
arXiv 2608.17128 · 2026-08-19可解码性准则预测大型语言模型中隐藏状态选择何时优于多数投票
A decodability criterion predicts when hidden-state selection beats majority voting in large language models
arXiv 2608.17124 · 2026-08-19基于小波的多层框架用于ℓ₁正则化图像去模糊
Wavelet-based multilevel framework for $\ell_1$-regularized image deblurring
arXiv 2608.17123 · 2026-08-19可重构无线系统的物理一致性信道建模与信号处理
Physically Consistent Channel Modeling and Signal Processing for Reconfigurable Wireless Systems
arXiv 2608.17122 · 2026-08-19多阶段随机优化的界及其在发电与输电扩展规划中的应用
Bounds for multi-horizon stochastic optimization with application to power generation and transmission expansion planning
arXiv 2608.17121 · 2026-08-19儿童在词汇学习中表现出加速回报，而语言模型则不然
Children, but not language models, show accelerating returns in word learning
arXiv 2608.17120 · 2026-08-19利用耦合PIC与蒙特卡罗模拟的激光尾波场加速优化钼-99生产的贝叶斯方法
Bayesian Optimization of Molybdenum-99 Production by Laser Wakefield Acceleration Using Coupled PIC and Monte Carlo Simulations
arXiv 2608.17119 · 2026-08-19纠缠辅助量子(r,δ)本地可恢复码
Entanglement assisted quantum $(r,δ)$-locally recoverable codes
arXiv 2608.17118 · 2026-08-19
