2026-09论文中文摘要
英国议会两百年的性别歧视：对Hansard语料库中女性代表性的计算分析
Two Centuries of Sexism in British Parliament: A Computational Analysis of Women's Representation in the Hansard Corpus
arXiv 2608.30485 · 2026-09-03DICS：探索数据内在一致性用于视觉指令选择
DICS: Exploring Data Intrinsic Consistency for Visual Instruction Selection
arXiv 2608.30209 · 2026-09-03GPAgentBench-2K：复杂临床动作空间中的大语言模型智能体基准测试
GPAgentBench-2K: Benchmarking Large Language Model Agents in Complex Clinical Action Space
arXiv 2608.30188 · 2026-09-03带等号条件的Jensen迹不等式与非交换Lamperti定理
Jensen' s trace inequality with equality condition and noncommutative Lamperti's theorem
arXiv 2608.30172 · 2026-09-03在流匹配模型中将生成样本溯源至训练数据簇
Tracing Generated Samples to Training-Data Clusters in Flow-Matching Models
arXiv 2608.30081 · 2026-09-03仙王座γ系统：更新轨道、动力学结构及额外伴星的限制
The $γ$ Cephei System: Updated Orbits, Dynamical Architecture, and Limits on Additional Companions
arXiv 2608.30030 · 2026-09-03由Hadamard三元组生成的自相似测度谱的Beurling密度
The Beurling density of the spectrum of self-similar measure generated by Hadamard triple
arXiv 2608.29660 · 2026-09-03升级渠道能否将奖励黑客行为转向缺陷披露？
Can escalation channels redirect reward hacking toward defect disclosure?
arXiv 2608.29460 · 2026-09-03EITWatch：集成智能手表的平面电阻抗断层扫描技术用于手势识别
EITWatch: Smartwatch-Integrated Planar Electrical Impedance Tomography for Hand Gesture Recognition
arXiv 2608.29415 · 2026-09-03通过核心扩展路由与统一计算调度加速统一多模态模型
Accelerating Unified Multimodal Models with Core-Expansion Routing and Unified Computation Scheduling
arXiv 2608.29291 · 2026-09-03自动研究人员可可靠缓解对齐失败问题
Automated Researchers Can Mitigate Well-characterized Alignment Failures
arXiv 2608.28945 · 2026-09-03可收缩到图上的空间中的跟踪与逆跟踪
Shadowing and inverse shadowing in spaces retractable onto graphs
arXiv 2608.28845 · 2026-09-03高阶斐波那契关系推广的稳定解
Stable Solutions to Generalizations of Fibonacci Relations of Higher Order
arXiv 2608.28782 · 2026-09-03对《利用强引力透镜引力波信号测量哈勃常数》的评论
Comment on `Measuring the Hubble Constant Using Strongly Lensed Gravitational Wave Signals'
arXiv 2608.28765 · 2026-09-03闭λ-自展形的刚性
Rigidity of closed $λ$-self-expanders
arXiv 2608.28307 · 2026-09-03我应该使用这个合成数据集进行训练吗？如何用最少的真实数据进行测试
Should I Use This Synthetic Dataset for Training? How to Test with Minimal Real Data
arXiv 2608.27996 · 2026-09-03当证据塑造协作：面向多智能体系统的知识条件拓扑生成
When Evidence Shapes Collaboration: Knowledge-Conditioned Topology Generation for Multi-Agent Systems
arXiv 2608.27984 · 2026-09-03欺骗模式作为一种社会技术现象：综述、分类与讨论
Deceptive Patterns as a Sociotechnical Phenomenon: Review, Catalog, and Discussion
arXiv 2608.27684 · 2026-09-03评估评估者：用于大语言模型评估的拉施测量理论
Rating the Raters: Rasch Measurement Theory for LLM Evaluation
arXiv 2608.27463 · 2026-09-03平面箔位置处电子束的场驱动阿秒偏转
Field-driven attosecond deflection of electron beams at the position of planar foils
arXiv 2608.27015 · 2026-09-03通量工程量子线结中拓扑保护的完美交叉安德烈耶夫反射
Topologically protected perfect crossed Andreev reflection in flux-engineered quantum wire junctions
arXiv 2608.26702 · 2026-09-03带多元时间的分数布朗运动：持续指数
Fractional Brownian motion with multivariate time: persistence exponents
arXiv 2608.26680 · 2026-09-03组织混合熵加权重建用于部分容积感知的脑部MRI超分辨率
Tissue-Mixture Entropy-Weighted Reconstruction for Partial-Volume-Aware Brain MRI Super-Resolution
arXiv 2608.26647 · 2026-09-03SPEAR：通过强化学习中的序列符号对齐提炼领域自适应推理骨架
SPEAR: Distilling Domain-Adaptive Reasoning Skeletons via Sequential Symbolic Alignment in Reinforcement Learning
arXiv 2608.26550 · 2026-09-03研究跨生成与执行环境的大语言模型生成软件系统中的软件老化现象
Software Aging in LLM-Generated Applications: Runtime Evidence, Static Analysis, and Human-Written Comparisons
arXiv 2608.26391 · 2026-09-03SKILL.state：可扩展的长程智能体技能
SKILL.state: Scalable Long-Horizon Agent Skills
arXiv 2608.26263 · 2026-09-03关于短Weyl和与几乎成比例求和项的华林问题的中间范围估计
Intermediate-Range Estimates for Short Weyl Sums and Waring's Problem with Almost Proportional Summands
arXiv 2608.25787 · 2026-09-03三次曲面的行列式表示的模空间与根系的不变量理论
The Moduli Space of Determinantal Representations of Cubic Surfaces and Invariant Theory of Root Systems
arXiv 2608.25695 · 2026-09-03弱引力与规范场背景下的粒子对产生：自旋场与双星系统
Pair creation in weak gravity and gauge backgrounds: spinning fields and binary stars
arXiv 2608.25540 · 2026-09-03MACGen：通过多智能体协作实现功能正确且安全的代码生成
MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration
arXiv 2608.25457 · 2026-09-03SPECMINE：一个大规模的规范驱动开发制品语料库
SpecMine: A Large-Scale Corpus of Spec-Driven Development Artifacts
arXiv 2608.25202 · 2026-09-03面向含拓扑重构的配电网多相交流最优潮流的可扩展自监督学习
Scalable Self-Supervised Learning for Multiphase AC-OPF in Distribution Systems with Topology Reconfiguration
arXiv 2608.25095 · 2026-09-03超二次哈密顿-雅可比方程的极大正则性：Lions猜想的端点情形
Endpoint Maximal Regularity for Superquadratic Hamilton-Jacobi Equations and Applications to Ergodic Mean-field Games Systems
arXiv 2608.25066 · 2026-09-03反超局域性与暴胀的平台模型
Anti-Ultralocality and Plateau Models of Inflation
arXiv 2608.24997 · 2026-09-03莫比乌斯函数部分和的振荡与黎曼ζ函数的零点
Oscillation of partial sums of the Möbius function and zeros of Riemann's zeta function
arXiv 2608.24878 · 2026-09-03紧窗口中的Weil正性：有限约化、认证的双侧界及Landau-Widom衰减定律
Weil positivity in compact windows: a finite reduction, certified two-sided bounds, and a Landau-Widom decay law
arXiv 2608.24827 · 2026-09-03用于内存高效的稀疏-二元自组织映射的特征主导码本：在单个消费级GPU上将MEDLINE图谱扩展至105万个神经元
A Feature-Major Codebook for Memory-Efficient Sparse-Binary Self-Organizing Maps: Scaling a MEDLINE Atlas to 1.05 Million Neurons on a Single Consumer GPU
arXiv 2608.24067 · 2026-09-03限制玉夫座的内暗物质斜率：动力学方法的比较分析
Constraining the Inner Dark-Matter Slope of Sculptor: A Comparative Analysis of Dynamical Methods
arXiv 2608.23618 · 2026-09-03带有抛物因子的乘积流形上的有界调和函数
Bounded Harmonic Functions on Products with a Parabolic Factor
arXiv 2608.22942 · 2026-09-03Mol-JEPA：用于分子的多模态联合嵌入预测架构
Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules
arXiv 2608.22642 · 2026-09-03用于文化根基型情感支持的诗意遗产：一种交互设计框架及其多模态智能体实例化
Poetic Heritage for Culturally Grounded Emotional Support: An Interaction Design Framework and Its Multimodal Agentic Instantiation
arXiv 2608.22639 · 2026-09-03弱Hopf Galois扩张的Hochschild上同调与AS-Gorenstein性质
Hochschild cohomology and AS-Gorenstein property of weak Hopf Galois extensions
arXiv 2608.22195 · 2026-09-03ToSCA：利用对话智能体的时间与策略抽象实现分层强化学习
ToSCA: Leveraging Hierarchical Reinforcement Learning on Temporal and Strategic Abstractions of Conversational Agents
arXiv 2608.21969 · 2026-09-03沿光滑非退化曲线的受限投影的正测度
Positive measure for restricted projections along smooth non-degenerate curves
arXiv 2608.21822 · 2026-09-03智能体式支架会放大大语言模型中的谄媚行为
Agentic Scaffolding Amplifies Sycophantic Behavior in Large Language Models
arXiv 2608.21377 · 2026-09-03交变磁拓扑体系中范霍夫奇点的光导率特征
Optical conductivity signature of Van Hove singularity in altermagnetic topological systems
arXiv 2608.20986 · 2026-09-03FlavourBench：基于可执行烹饪基准真值的前沿语言模型排名
FlavourBench: Executable Culinary Reward Maps for Language Model Evaluation and Post-Training
arXiv 2608.20574 · 2026-09-03确定性与随机最大正则性的必要条件
Necessary conditions for deterministic and stochastic maximal regularity
arXiv 2608.20266 · 2026-09-03LoRA-GA²：具有多步梯度自适应对齐的低秩适配
LoRA-GA$^2$: Low Rank Adaptation with Multi-step Gradient Adaptive Alignment
arXiv 2608.19800 · 2026-09-03图on平均场系统的凸序保持性
Convex ordering for graphon mean-field systems
arXiv 2608.19576 · 2026-09-03
