2026-08论文中文摘要
各向异性弹性介质中相空间局部角度域波形反演的理论框架
Theoretical Framework for Phase-space Local-Angle-Domain Waveform Inversion in Anisotropic Elastic Media
arXiv 2608.04901 · 2026-08-07A-SR：通过分层协调实现符号回归的自进化智能体大语言模型
A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination
arXiv 2608.04872 · 2026-08-07马普切语中的动词前无屈折、无派生词根：wuno及其启示
Preverbal Uninflected and Underived Roots in Mapudungun. Wuno and Its Implications
arXiv 2608.04869 · 2026-08-07基于先验的多电压阈值采样作为结构化逆问题
Prior-Based Multi-Voltage Threshold Sampling as a Structured Inverse Problem
arXiv 2608.04863 · 2026-08-07协变量偏移下的非参数拟合优度检验
Nonparametric Goodness-of-fit Testing under Covariate Shift
arXiv 2608.04860 · 2026-08-07RepoProbe：基于清单的架构感知代码仓库理解基准测试
RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists
arXiv 2608.04783 · 2026-08-07InsightEmb：面向智能体洞察检索的动作-意图嵌入学习
InsightEmb: Learning Action-Intent Embeddings for Agentic Insight Retrieval
arXiv 2608.04761 · 2026-08-07EviGraph：证据引导的自主研究智能体
EviGraph: Evidence-Guided Autonomous Research Agents
arXiv 2608.04738 · 2026-08-07面向车辆的改进型平均场理论：用于随机交通流模型
An improved car-oriented mean-field theory for stochastic traffic flow models
arXiv 2608.04731 · 2026-08-07面向开源软件中智能体式AI编码工具的智能体计划探索性研究
An Exploratory Study of Agent Plans for Agentic AI Coding Tools in Open-Source Software
arXiv 2608.04661 · 2026-08-07MobileWAM：用前瞻链将世界动作模型（WAM）与移动操作任务对接
MobileWAM: Bridging World Action Models to Mobile Manipulation with Chain-of-Foresight
arXiv 2608.04657 · 2026-08-07DisMix：基于解耦序特征与非序特征的医学图像序感知混合增强方法
DisMix: Order-Aware Mixup for Medical Imaging via Disentangling Ordinal and Non-Ordinal Features
arXiv 2608.04652 · 2026-08-07关于一类一维振荡不等式
On a family of one-dimensional oscillation inequalities
arXiv 2608.04639 · 2026-08-07命题逻辑到可证性逻辑$\boldsymbol{S}$与$\boldsymbol{D}$的嵌入
Embeddings of Propositional Logics into the Provability Logics $\mathbf{S}$ and $\mathbf{D}$
arXiv 2608.04620 · 2026-08-07通过资源感知型语音编码器混合模型打破多对多语音到文本翻译中的多语言性诅咒
Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders
arXiv 2608.04586 · 2026-08-07EuroExec：前沿语言模型在欧洲行政决策任务上未能达到专家判断水平
EuroExec: Frontier Language Models Fall Short of Expert Judgment on European Executive Decision Tasks
arXiv 2608.04549 · 2026-08-07RESPClinBench：呼吸专科医疗中的多模态临床决策与纵向疾病管理基准测试
RESPClinBench: Benchmarking Multimodal Clinical Decision-Making and Longitudinal Disease Management in Respiratory Specialty Care
arXiv 2608.04514 · 2026-08-07音乐转录的双重评估
A Dual Evaluation for Music Transcription
arXiv 2608.04511 · 2026-08-07单神经元模加法中傅里叶对齐的一个反例
A Counterexample to Fourier Alignment in Single-Neuron Modular Addition
arXiv 2608.04451 · 2026-08-07两个绝对有界的行列式比值
Two absolutely bounded determinantal ratios
arXiv 2608.04294 · 2026-08-07瓶颈路径归约为确定性图博弈：对一项声称的线性时间算法的修正
Bottleneck Paths Reduce to Deterministic Graphical Games and a Counterexample to a Claimed Linear-Time Algorithm
arXiv 2608.04279 · 2026-08-07尼尔·格雷尔斯雨燕天文台的持续演进：二十年时域与多信使天体物理学的运行创新
The Constant Evolution of the Neil Gehrels Swift Observatory: Two Decades of Operational Innovation for Time-Domain and Multi-Messenger Astrophysics
arXiv 2608.04220 · 2026-08-07基于模拟的成像：从模拟数据学习声学逆问题
Simulation-Based Imaging: Learning Acoustic Inverse Problems from Simulated Data
arXiv 2608.04145 · 2026-08-07湍流环境下的结构光
Structured light under turbulence
arXiv 2608.04090 · 2026-08-07季风混乱到市场波动：斯里兰卡渔业韧性预测
Monsoon Mayhem to Market Waves: Forecasting Fisheries Resilience in Sri Lanka
arXiv 2608.04023 · 2026-08-07基于QIANGDA与VOXBLINK2-AVSE的身份保真视听目标说话人提取
Identity-Faithful Audio-Visual Target Speaker Extraction with REAL-2MIX and VOXBLINK2-AVSE
arXiv 2608.03964 · 2026-08-07用于SMILES与自然语言联合表示学习的双语义化学嵌入器
Bi-semantic Chemical Embedder for Joint Representation Learning of SMILES and Natural Language
arXiv 2608.03855 · 2026-08-07射影流形上复Hessian型方程的数值准则
A numerical criterion for complex Hessian type equations on projective manifolds
arXiv 2608.03815 · 2026-08-07Thompson群V的Dehn函数至多为六次
The Dehn function of Thompson's group $V$ is at most sextic
arXiv 2608.03813 · 2026-08-07AFLOW-EMERALD：先进层状材料中的电磁模式工程
AFLOW-EMERALD: ElectroMagnetic modes EngineeRing in Advanced LayereD materials
arXiv 2608.03759 · 2026-08-07基于cuGraph在GPU架构上加速动态图聚类
Accelerating Dynamic Graph Clustering on GPU Architectures with cuGraph
arXiv 2608.03695 · 2026-08-07真实课堂环境下的英语语音说话人验证
Speaker Verification Under Real Classroom Conditions for English Speech
arXiv 2608.03623 · 2026-08-07SFT冲突，RL共存：大语言模型多任务学习的理论与实证分析
SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs
arXiv 2608.03573 · 2026-08-07超越单纯的环境规模扩展：为多模态智能体学习设计有效的环境分布
Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning
arXiv 2608.03571 · 2026-08-07引力红移作为量子通道：在量子光学中建模引力红移的效应
Gravitational redshift as a quantum channel: modeling the effects of gravitational redshift in quantum optics
arXiv 2608.03549 · 2026-08-07嵌套分形图上的连通常数
Connective Constants on Nested Fractal Graphs
arXiv 2608.03497 · 2026-08-07混合维边界区域中Poisson-Dirichlet问题的可解性
Solvability of the Poisson-Dirichlet problem in domains with boundaries of mixed dimension
arXiv 2608.03373 · 2026-08-07截图还是工具？在混合GUI-MCP计算机使用智能体中引出工具使用并管理多模态上下文
Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MCP Computer-Use Agents
arXiv 2608.03327 · 2026-08-07半图厄系统擦除中的右可除性：入侵者推导的最小视角
Right Divisibility in Erasing Semi-Thue Systems: A Minimal View of Intruder Deduction
arXiv 2608.03274 · 2026-08-07SAKI：面向长上下文KV检索的分数感知低秩键索引
SAKI: Score-Aware Low-Rank Key Indexing with Random-Matrix Noise Correction for KV Retrieval
arXiv 2608.03228 · 2026-08-07HomoEnsNER：古吉拉特语命名实体识别中语言对齐是否优于架构复杂度？
HomoEnsNER: Does Language Alignment Outperform Architectural Complexity in Gujarati Named Entity Recognition?
arXiv 2608.03105 · 2026-08-07AI安全排行榜：方法、结果与最低标准
AI Security Leaderboard: Methodology, Results and Minimal Standard
arXiv 2608.03070 · 2026-08-07激活引导的神经元干预以在大型语言模型中诱导阿尔茨海默病相关的计算语言表型
Activation-Guided Neuron Intervention to Induce Alzheimer's-Related Computational Language Phenotypes in a Large Language Model
arXiv 2608.03067 · 2026-08-07超越单位激励与光滑性的随机鞍点规避：一种路径式李雅普诺夫-佩龙框架
Stochastic Saddle Avoidance Beyond Unit Excitation and Smoothness: A Pathwise Lyapunov-Perron Framework
arXiv 2608.03001 · 2026-08-07纪念埃里克·博尔特博士
Memorial for Dr. Erik Bollt
arXiv 2608.02973 · 2026-08-07当压缩分数无法做出决策时：群体鲁棒大语言模型剪枝的信息边界
When Compression Scores Cannot Decide: Information Boundaries for Group-Robust LLM Pruning
arXiv 2608.02940 · 2026-08-07风力涡轮发电机的协调一次调频与电网形成控制
Coordinated Primary Frequency Regulation and Grid-Forming Control for Wind Turbine Generators
arXiv 2608.02813 · 2026-08-07四个州的席位分配中，配额与人口单调性随议院规模变化互不兼容
Quota and population monotonicity across house sizes are incompatible for apportionment to four states
arXiv 2608.02759 · 2026-08-07施密特规范非局域魔性：表示、最优性与数学性质
Schmidt-Gauge Non-Local Magic: Representation, Optimality, and Mathematical Properties
arXiv 2608.02745 · 2026-08-07知识-几何解耦：面向流式推荐的可刷新预训练迁移
Knowledge-Geometry Decoupling: Refreshable Pretrained Transfer for Streaming Recommendation
arXiv 2608.02738 · 2026-08-07
