2026-08论文中文摘要
UI-Mate：利用上下文内演示推进开放权重基础图形用户界面智能体
UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations
arXiv 2608.15930 · 2026-08-18基于逆强化学习的统一行人路径预测
Unified Pedestrian Path Prediction Using Inverse Reinforcement Learning
arXiv 2608.15929 · 2026-08-18像化学家一样合成：用于材料发现的迭代式反馈驱动循环
Synthesizing like a chemist: an iterative, feedback-driven loop for materials discovery
arXiv 2608.15928 · 2026-08-18CQELS-TrieGS报告：流图查询的快照一致常延迟枚举
CQELS-TrieGS Report: Snapshot-Consistent Constant-Delay Enumeration for Streaming Graph Queries
arXiv 2608.15927 · 2026-08-18全局工作空间理论的控制论表述
A Control-Theoretic Formulation of Global Workspace Theory
arXiv 2608.15926 · 2026-08-18RAPAC-DP：延迟执行场景下扩散策略的响应对齐待执行动作补偿
RAPAC-DP: Response-Aligned Pending-Action Compensation for Diffusion Policies under Delayed Execution
arXiv 2608.15924 · 2026-08-18二维马尔可夫和乐场的普适性
Universality of two-dimensional Markovian holonomy fields
arXiv 2608.15923 · 2026-08-18用实用集合协调协议扩展闪电网络
Scaling the Lightning Network with Practical Set Reconciliation
arXiv 2608.15921 · 2026-08-18$S^3$：用于优化动力系统离散抽象的平滑仿真代理
$S^3$: A Smooth Simulation Surrogate for Optimizing Discrete Abstractions of Dynamical Systems
arXiv 2608.15920 · 2026-08-18Noesis：具备自适应并行性与跨知识库语义发现的双向图检索增强生成
Noesis: Bidirectional Graph-RAG with Adaptive Parallelism and Cross-Knowledge-Base Semantic Discovery
arXiv 2608.15919 · 2026-08-18伽马射线暴多波段余辉中能量注入平台期的统计关系
A statistical relation of energy injection plateaus in multi-band afterglows of gamma-ray bursts
arXiv 2608.15918 · 2026-08-18测地量子f-散度的信息几何
Information Geometry of the Geodesic Quantum $f$-Divergences
arXiv 2608.15916 · 2026-08-18用于肺癌组织病理学的深度学习架构的综合基准测试
Comprehensive Benchmarking of Deep Learning Architectures for Lung Cancer Histopathology
arXiv 2608.15915 · 2026-08-18带舍入的高斯随机动力系统的吸收截断与平稳奇点
Absorption cutoff and stationary singularities for rounded Gaussian random dynamical systems
arXiv 2608.15914 · 2026-08-18AI供应链应用中的联合中毒攻击
Conjunctive Poisoning in AI Supply-Chain Applications
arXiv 2608.15913 · 2026-08-18直接成像伴星宿主的高分辨率光谱巡天：III. 冷成像行星宿主AF Lep A与ε Indi A的表征
A High-Resolution Spectroscopic Survey of Directly Imaged Companion Hosts: III. Characterization of the Cold Imaged Planet Hosts AF Lep A and $ε$ Indi A
arXiv 2608.15912 · 2026-08-18用于高表现力文本到语音合成的迭代自学习
Iterative Self-Learning for Expressive Text-to-Speech Synthesis
arXiv 2608.15910 · 2026-08-18大语言模型辅助的科学文献队列发现
Large language model-assisted discovery of cohorts from scientific literature
arXiv 2608.15909 · 2026-08-18大压力梯度下多孔介质中启动流动的相似性
Similarity of start-up flow in porous media for large pressure gradients
arXiv 2608.15908 · 2026-08-18到紧支撑对数凹目标的Brenier映射的无维度Lipschitz界
Dimension-Free Lipschitz Bounds for Brenier Maps to Compactly Supported Log-Concave Targets
arXiv 2608.15906 · 2026-08-18可表示为两个单位之和的整数
On integers that are representable as the sum of two units
arXiv 2608.15903 · 2026-08-18层很重要：为何持续学习正则化应是层自适应的
Layers Matter: Why Continual Learning Regularization Should Be Layer-Adaptive
arXiv 2608.15901 · 2026-08-18基于基元语言的智能体AI晶体结构设计
Crystal-structure design by agentic AI in a language of motifs
arXiv 2608.15900 · 2026-08-18自主量子活塞热机中的反芝诺增强效应
Anti-Zeno boost in an autonomous quantized-piston thermal machine
arXiv 2608.15899 · 2026-08-18当搜索吞噬网络：生成式提取下的语料库侵蚀模型
When Search Eats the Web: A Model of Corpus Erosion under Generative Extraction
arXiv 2608.15896 · 2026-08-18非线性豪斯多夫-杨不等式
The nonlinear Hausdorff-Young inequality
arXiv 2608.15895 · 2026-08-18针对无导数随机函数与确定性等式约束的自适应采样信赖域优化
Adaptive Sampling Trust Region Optimization for Derivative-free Stochastic Functions and Deterministic Equality Constraints
arXiv 2608.15894 · 2026-08-18突破与防御：基于大语言模型的社交媒体机器人检测系统
Breaking and Defending LLM-Powered Social Media Bot Detection Systems
arXiv 2608.15893 · 2026-08-18宇宙线膝的种群视角：超新星最大刚度方差的作用
A Population View of the Cosmic-Ray Knee: The Role of Variance in Supernova Maximum Rigidities
arXiv 2608.15892 · 2026-08-18整函数的高度刚性
Height Rigidity for Entire Functions
arXiv 2608.15891 · 2026-08-18COOL：面向先进3D/3.5D IC封装热预测的感知冷却的点Transformer框架
COOL: A Cooling-Aware Point Transformer Framework for Thermal Prediction in Advanced 3D/3.5D IC Packaging
arXiv 2608.15890 · 2026-08-18资源高效的锚定货币套利QUBO公式化
Resource-Efficient QUBO Formulation for Anchored Currency Arbitrage
arXiv 2608.15889 · 2026-08-18有界智能体：多智能体AI系统的委托安全
Bounded Agents: Delegation Security for Multi-Agent AI Systems
arXiv 2608.15888 · 2026-08-18SMTpip：面向Python源码可执行性恢复的感知解释器的基于SMT的依赖冲突解决方法
SMTpip: Interpreter-Aware SMT-Based Dependency Conflict Resolution for Restoring Python Source-Code Executability
arXiv 2608.15886 · 2026-08-18单输入高阶过程的单范畴su-范畴
Monoidal su-categories
arXiv 2608.15885 · 2026-08-18多机器人系统中用于分布式任务分配的分组拍卖共识算法
Grouping Auction-Consensus Algorithm for Decentralized Task Allocation in Multi-Robot Systems
arXiv 2608.15884 · 2026-08-18詹姆斯·韦伯空间望远镜通用观测项目的社交网络分析：去中心化等级制的出现
A Social Network Analysis of JWST General Observer Programs: The Emergence of a Decentralized Heterarchy
arXiv 2608.15883 · 2026-08-18稀土硫族钙钛矿：一类用于光电子应用的极具潜力的材料
Rare-earth chalcogenide perovskites: A promising class of materials for optoelectronic applications
arXiv 2608.15882 · 2026-08-18在多物理场AI助手MOOSEnger中部署前沿智能体技术
Deploying Frontier Agentic Technology in MOOSEnger, a Multiphysics-Capable AI Assistant
arXiv 2608.15881 · 2026-08-18n×kn网格与沙堆模型中的Loehr-Remmel双射
A Loehr-Remmel bijection in the $n \times kn$ grid and sandpiles
arXiv 2608.15880 · 2026-08-18当少即是多：孟加拉语新闻标题生成的上下文选择与提示策略
When Less Is Enough: Context Selection and Prompting Strategies for Bengali News Headline Generation
arXiv 2608.15879 · 2026-08-18《农夫的投资组合：利用作物选择测量历史风险偏好》
The Yeoman's Portfolio: Measuring Historical Risk Preferences Using Crop Choice
arXiv 2608.15876 · 2026-08-18GigaBrain-0.7：采用三系统架构扩展具身基础模型以获得涌现能力
GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture
arXiv 2608.15875 · 2026-08-18希尔伯特值鞅的自归一化贝内特不等式
Self-normalised Bennett inequalities for Hilbert-valued martingales
arXiv 2608.15874 · 2026-08-18关于$G$-调和元组的两个问题
Two Questions on $G$-harmonic Tuples
arXiv 2608.15873 · 2026-08-18非阿贝尔布伦-闵可夫斯基不等式 II
A nonabelian Brunn-Minkowski inequality II
arXiv 2608.15872 · 2026-08-18大型语言模型作为隐含的社会学模型：从社会人口统计特征重建投票行为
Large Language Models as Implicit Sociological Models: Reconstructing Voting Behaviour from Sociodemographic Profiles
arXiv 2608.15871 · 2026-08-18超越视觉思维链：用于主动视频推理的内化视觉思维
Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning
arXiv 2608.15869 · 2026-08-18CoupVisor：基于回合与挑战决策支持的策略优化
CoupVisor: Strategy Optimization by Round and Challenge Decision Support
arXiv 2608.15868 · 2026-08-18结合表格与序列出行属性的可行且新颖的合成人群生成
Feasible and Novel Synthetic Population Generation with Tabular and Sequential Travel Attributes
arXiv 2608.15867 · 2026-08-18
