2026-08论文中文摘要
千禧年难题的反思
Reflections on the Millennium Problems
arXiv 2608.24965 · 2026-08-27神经网络为何及何时能优化局部近似效果
Why and When Neural Networks Improve Local Approximation in Optimization
arXiv 2608.24963 · 2026-08-27评估与防范AI生成Ansible代码中的安全隐患
Evaluating and Preventing Security Smells in AI-Generated Ansible Code
arXiv 2608.24962 · 2026-08-27AI4Math 中的淘金热：我们现在处于何处？
The Gold Rush in AI4Math: Where Are We Now?
arXiv 2608.24961 · 2026-08-27通过InDEx实验中超热$C_2H_2F_4$靶的暗物质-电子散射探测亚GeV暗物质
Probing sub-GeV dark matter through dark matter-electron scattering in the superheated $C_2H_2F_4$ target of the InDEx experiment
arXiv 2608.24960 · 2026-08-27GaussVLA：面向视觉-语言-动作模型的几何感知空间推理
GaussVLA: Geometry-Aware Spatial Reasoning for Vision-Language-Action Model
arXiv 2608.24959 · 2026-08-27我们能否解读音频大语言模型的思维？一个可解读的多语言中间层工作空间
Can We Read the Mind of an Audio LLM? A Verbalizable, Multilingual Middle-Layer Workspace
arXiv 2608.24958 · 2026-08-27ToolMinimize：审计与重写大语言模型智能体的工具调用以最小化隐私暴露
ToolMinimize: Auditing and Rewriting LLM Agent Tool Calls to Minimize Privacy Exposure
arXiv 2608.24957 · 2026-08-27现代时代的二元反编译技术演进：分类法、文献综述与未来展望
The Evolution of Binary Decompilation in the Modern Era: A Taxonomy, Literature Review, and Future Perspectives
arXiv 2608.24955 · 2026-08-27AFDBench：面向国家气象局预报讨论的推理优先AI科学家
AFDBench: A Reasoning-First AI Scientist for NationalWeather Service Forecast Discussions
arXiv 2608.24954 · 2026-08-27超越Token：探究学习到的蛋白质表征中的高阶上位效应
Beyond Tokens: Probing Higher-Order Epistasis in Learned Protein Representations
arXiv 2608.24953 · 2026-08-27方言税：方言偏见在语言建模流程中持续存在
The Dialect Tax: Dialectal Biases Persist throughout the Language Modeling Pipeline
arXiv 2608.24952 · 2026-08-27光滑量子流体动力学模型的一种简单正则化方法
A Simple Regularization of the Smooth Quantum Hydrodynamic Model
arXiv 2608.24950 · 2026-08-27去卷积数位和测度的等号情形 $P_t(\mathbb{N})=\tfrac12$
The equality cases $P_t(\mathbb{N})=\tfrac12$ for the deconvolved sum-of-digits measures
arXiv 2608.24948 · 2026-08-27MacroAgent：结合大语言模型智能体设计轮廓算法的感知规则性宏合法化方法
MacroAgent: Regularity-Aware Macro Legalization with LLM-Agent-Designed Contour Algorithms
arXiv 2608.24946 · 2026-08-27Secret MCP：基于证据约束和上下文隔离的网页截图设计规范生成系统
Secret MCP: Evidence-Bounded and Context-Isolated Design Specification Generation from Web Screenshots
arXiv 2608.24944 · 2026-08-27关于扭结接触结构的三维辛化问题
The three-dimensional symplectization question for overtwisted contact structures
arXiv 2608.24942 · 2026-08-27罗巴切夫斯基的几何观
Lobachevsky's Views of Geometry
arXiv 2608.24941 · 2026-08-27频率分解何时有益于物理信息神经网络？一项初步消融研究
When Does Frequency Decomposition Benefit Physics-Informed Neural Networks? A Preliminary Ablation Study
arXiv 2608.24940 · 2026-08-27雅各布梯子、几乎线性公式和费马-怀尔斯定理对应的ζ-泛函与ζ-等价式的新和变体类
Jacob's ladders, new classes of sum variants of almost linear formula and corresponding $ζ$-functionals and $ζ$-equivalents of the Fermat-Wiles theorem
arXiv 2608.24939 · 2026-08-27ExFold：用于无训练MoE预填充-解码加速的统一专家折叠方法
ExFold: Unified Expert Folding for Training-Free MoE Prefill-Decode Acceleration
arXiv 2608.24938 · 2026-08-27多模态异常检测：一项综述
Multi-Modal Anomaly Detection: A Survey
arXiv 2608.24937 · 2026-08-27GreenLeaf Law Embed Tiny：一款面向法律领域检索的紧凑嵌入模型
GreenLeaf Law Embed Tiny: A Compact Embedding Model for Legal Domain Retrieval
arXiv 2608.24936 · 2026-08-27面向商业果园早期解剖结构青果分类的轻量级多模态视觉-语言框架
A Lightweight Multimodal Vision-Language Framework for Early-Stage Anatomical Green Fruit Classification in Commercial Orchards
arXiv 2608.24935 · 2026-08-27关于加权凸图
On Weighted Convex Graphs
arXiv 2608.24933 · 2026-08-27无穷大素数模下的Tonelli–Shanks幂的超越性
Transcendence of Tonelli--Shanks Power Modulo Infinitely Large Primes
arXiv 2608.24932 · 2026-08-27模态贡献分数——一种用于量化阿尔茨海默病中结构MRI与淀粉样PET相对诊断贡献的患者专属框架
Modality Contribution Score - A Per-Patient Framework for Quantifying the Relative Diagnostic Contribution of Structural MRI and Amyloid PET in Alzheimer's Disease
arXiv 2608.24931 · 2026-08-27短区间内最小素因子的和
On the sum of least prime factors in short intervals
arXiv 2608.24930 · 2026-08-27关于Kanigowski和Ravotti的好特殊流定义的一个注记
A note on the definition of good special flows of Kanigowski and Ravotti
arXiv 2608.24929 · 2026-08-27外在方法能否揭示内在结构？用QStr补充整合信息理论（IIT）
Can extrinsic methods reveal intrinsic structure? Complementing IIT with QStr
arXiv 2608.24928 · 2026-08-27对《关于： kagome金属中虚电荷密度波的微观特征》的评论的回复
Reply to Comment on: Microscopic signatures of an imaginary charge density wave in a kagome metal
arXiv 2608.24927 · 2026-08-27评估灰色文献的路径：利用人工智能从征稿启事（Calls for Papers, CfPs）中提取会议元数据与主办方信息
A Pathway for Assessing Grey Literature: Leveraging AI to Extract Conference Metadata and Organiser Information from Calls for Papers
arXiv 2608.24926 · 2026-08-27金属表面上石墨炔与二石墨炔分子线的自组装及电子性质
Self-assembly and Electronic Properties of Graphyne and Graphdiyne Molecular Wires on Metallic Surfaces
arXiv 2608.24925 · 2026-08-27聚苯胺作为导电聚合物及其在提升钙钛矿太阳能电池效率与导电性中的作用
Polyaniline as a conductive polymer and its role in improving the efficiency and conductivity of perovskite solar cells
arXiv 2608.24924 · 2026-08-27关于《监督量子机器学习模型是核方法》的评论
Comment on 'Supervised quantum machine learning models are kernel methods'
arXiv 2608.24923 · 2026-08-27基于半电池开路电位数据的商用NCA正极的多物种多反应模型参数化
Multi-Species Multi-Reaction Model Parametrization of a Commercial NCA Positive Electrode from Half-Cell Open-Circuit Potential Data
arXiv 2608.24922 · 2026-08-27不同大语言模型（LLM）生成回复的语义变异性：对基于对话的评估设计的启示
Semantic Variability of Replies Across LLMs: Implications for Designing Conversation-Based Assessment
arXiv 2608.24920 · 2026-08-27液氮、液氦和液氩中直流电气击穿分布的对比测量
Comparative measurements of DC electrical breakdown distributions in liquid nitrogen, liquid helium, and liquid argon
arXiv 2608.24919 · 2026-08-27面向工业数字线程的语义图统一：通过本体驱动知识图谱连接11个异构制造系统
Semantic Graph Unification for Industrial Digital Threads: Bridging 11 Heterogeneous Manufacturing Systems Through Ontology-Driven Knowledge Graphs
arXiv 2608.24918 · 2026-08-27面向电话智能体的领域自适应ASR：针对企业联络中心应用微调Canary Flash模型
Domain-Adaptive ASR for Telephony AI Agents: Fine-tuning Canary Flash Models for Enterprise Contact Center Applications
arXiv 2608.24916 · 2026-08-27我们在测量什么？联结、信任与人机关系的评估
What Are We Measuring? Bonding, Trust, and the Evaluation of Human-Robot Relationships
arXiv 2608.24915 · 2026-08-27计算社会科学中面向AI的研究工作流：构建跨学科协作共享语言的经验
AI-Ready Research Workflows in Computational Social Science: Lessons on Building a Shared Language for Interdisciplinary Collaboration
arXiv 2608.24914 · 2026-08-27从盲编辑到经验证的修复：构建可信的用户端大语言模型智能体以实现网页可访问性
From Blind Edits to Verified Repair: Building Trustworthy User-Side LLM Agents for Web Accessibility
arXiv 2608.24913 · 2026-08-27分析与修正大语言模型中的善意偏差
Analyzing and Correcting Benevolence Bias in Large Language Models
arXiv 2608.24912 · 2026-08-27儿童青少年心理健康中患者轨迹与障碍共现的可视化
Visualizing Patient Trajectories and Disorder Co-occurrences in Child and Adolescent Mental Health
arXiv 2608.24911 · 2026-08-27从图表到文本：模型感知的多模态解释作为可访问非视觉交互的基础
From Plots to Words: Model-Aware Multimodal Explanations as a Foundation for Accessible, Non-Visual Interaction
arXiv 2608.24910 · 2026-08-27超级明星：面向数字人的流式实时交互智能体
Super Star: Towards Streaming Real-time Interactive Agents for Digital Humans
arXiv 2608.24909 · 2026-08-27LLM辅助鉴别诊断中的代理幻觉
Hallucination by proxy in LLM-assisted differential diagnosis
arXiv 2608.24908 · 2026-08-27PA-CoT：面向个性化营养咨询的画像自适应思维链
PA-CoT: Profile-Adaptive Chain-of-Thought for Personalized Nutritional Consulting
arXiv 2608.24907 · 2026-08-27铁基超导体中量子阱镜面对称破缺诱导的奇偶宇称STS谱
Even/Odd-parity STS spectra induced by quantum well mirror symmetry breaking in iron-based superconductors
arXiv 2608.24906 · 2026-08-27
