2026-10论文中文摘要
自主开源软件威胁检测：基于分类对齐的大语言模型
Autonomous OSS Threat Detection via Taxonomy-Aligned LLMs
arXiv 2610.01263 · 2026-10-02无需等待的反馈：在大型数学课堂中试点生成式人工智能练习平台
Feedback Without the Wait: Piloting a Generative AI Practice Platform in a Large Maths Class
arXiv 2610.01262 · 2026-10-02分布式天线系统中的仅多普勒扩展目标跟踪
Doppler-Only Extended Target Tracking in a Distributed Antenna System
arXiv 2610.01261 · 2026-10-02PROMO：面向四足机器人的偏好条件多目标强化学习
PROMO: Preference-conditioned Multi-Objective Reinforcement Learning for Quadrupedal Robots
arXiv 2610.01260 · 2026-10-02一种基于分层中心引导加权聚合的联邦深度伪造语音检测方法
A Federated Deepfake Speech Detection Method Based on Layer-Wise Center-Guided Weighting Aggregation
arXiv 2610.01259 · 2026-10-02ColoACT：用于自推进内窥镜机器人平滑自主结肠导航的多线索动作分块
ColoACT: Multi-Cue Action Chunking for Smooth Autonomous Colon Navigation on a Self-Propelled Endoscopic Robot
arXiv 2610.01258 · 2026-10-02科学乌托邦？学术研究生态系统的闭环LLM模拟
Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems
arXiv 2610.01257 · 2026-10-02DeFA：面向LLM智能体的依赖引导失败归因
DeFA: Dependency-Guided Failure Attribution for LLM Agents
arXiv 2610.01256 · 2026-10-02带荷物质下CMC环带上的带电Hawking质量
Charged Hawking Mass on CMC Collars with Charged Matter
arXiv 2610.01255 · 2026-10-02从测地线汇动力学重建 $f(Q)$ 引力：Raychaudhuri 方程
Reconstruction of $f(Q)$ Gravity from Geodesic Congruence Dynamics: Raychaudhuri Equation
arXiv 2610.01254 · 2026-10-02面向NISQ系统上混合量子强化学习的上下文感知错误缓解编排
Context-Aware Error Mitigation Orchestration for Hybrid Quantum Reinforcement Learning on NISQ Systems
arXiv 2610.01253 · 2026-10-02基于微波光子与表面声波声子之间混合纠缠的关联成像
Correlation Imaging via Hybrid Entanglement between Microwave Photons and Surface Acoustic Wave Phonons
arXiv 2610.01252 · 2026-10-02迈向太阳多谱线反演
Towards solar many-line inversions
arXiv 2610.01251 · 2026-10-02面向主机入侵检测的资源感知行为重构与分层语义学习框架
A Resource-Aware Behavior Reconstruction and Hierarchical Semantic Learning Framework for Host Intrusion Detection
arXiv 2610.01250 · 2026-10-02面向动态推理的修订感知独立智能体图
Revision-Aware Independent Agent Graphs for Dynamic Reasoning
arXiv 2610.01249 · 2026-10-02具有给定子轨道截面的拟copula
Quasi-copulas with a prescribed sub-track section
arXiv 2610.01247 · 2026-10-02通过 Knuth-Bendix 完备化扩充重写规则集
Augmenting Rewrite Rule Sets via Knuth-Bendix Completion
arXiv 2610.01246 · 2026-10-02概率密度函数的非线性Fokker-Planck方程的存在性与遍历性
Existence and Ergodicity for Nonlinear Fokker-Planck Equations for Probability Density Functions
arXiv 2610.01245 · 2026-10-02正确答案，错误状态：多智能体协作中的隐藏信息失败
Right Answers, Wrong States: Hidden Information Failures in Multi-Agent Collaboration
arXiv 2610.01244 · 2026-10-02当裁判行动时：审计VLM引导的图像选择在文化情境提示上的表现
When the Judge Acts: Auditing VLM-Guided Image Selection on Culturally Situated Prompts
arXiv 2610.01243 · 2026-10-02FedCFM：基于条件流匹配的联邦持续域泛化虚假语音检测
FedCFM: Federated Continual Domain Generalization for Fake Speech Detection via Conditional Flow Matching
arXiv 2610.01242 · 2026-10-02评估日本大语言模型对输入法相关错误和拼写错误的鲁棒性
Evaluating the Robustness of Japanese LLMs to IME-Related and Typographical Errors
arXiv 2610.01241 · 2026-10-02Lehmer 关于相邻交换图的置换猜想的证明
A proof of Lehmer's permutation conjecture for neighbor-swap graphs
arXiv 2610.01240 · 2026-10-02超新星前身星中的对流-反应区结构
Structure of Convective-Reactive Zone in a Supernova Progenitor
arXiv 2610.01239 · 2026-10-02混合训练合并：面向统一多目标模型
Mixture-Trained Merging for Unified Multi-Objective Models
arXiv 2610.01238 · 2026-10-02基于双层优化的非光滑估计器稀疏实验设计
Sparse Experimental Design for Nonsmooth Estimators via Bilevel Optimization
arXiv 2610.01237 · 2026-10-02学会提问：预算约束下的SLM-LLM协作信息获取
Learning to Ask: Information Acquisition for SLM-LLM Collaboration, under a budget
arXiv 2610.01236 · 2026-10-02Harness 退火：学习在较少外部控制下行动
Harness Annealing: Learning to Act with Less External Control
arXiv 2610.01235 · 2026-10-02ASCRIBE：基于原子事实与临床显著性推理的泰语临床SOAP笔记生成
ASCRIBE: Atomic and Significance-Based Reasoning for Thai Clinical SOAP Note Generation
arXiv 2610.01234 · 2026-10-02流匹配强化用于基于动态归位优化的三维网格生成
Flow Matching Reinforcement for 3D Mesh Generation via Dynamic Homing Optimization
arXiv 2610.01233 · 2026-10-02人工生态中的继承学习：控制与更新分配如何塑造收益
Inherited Learning in an Artificial Ecology: How Controls and Update Allocation Shape Benefits
arXiv 2610.01232 · 2026-10-02杰文斯时代的判断：从评估稀缺到评估丰裕
Judgement in the Age of Jev: From Evaluation Scarcity to Evaluation Abundance
arXiv 2610.01231 · 2026-10-02HHR：面向高效大语言模型生成的分层哈希检索
HHR: Hierarchical Hash Retrieval for Efficient LLM Generation
arXiv 2610.01230 · 2026-10-02动态场景的紧凑显式4D表示
A Compact Explicit 4D Representation for Dynamic Scenes
arXiv 2610.01229 · 2026-10-02面向任务的布尔函数计算：实用码构造
Task-Oriented Boolean Function Computation: Practical Code Constructions
arXiv 2610.01228 · 2026-10-02一组量子态的量子相干性的实验量化
Experimental quantification of quantum coherence for a set of quantum states
arXiv 2610.01227 · 2026-10-02通过高分辨率光学光谱探测V1180 Cas中的吸积与外流
Probing Accretion and Outflow in V1180 Cas through High-Resolution Optical Spectroscopy
arXiv 2610.01226 · 2026-10-02半空间带流入边界条件的BGK模型的瞬时指数不适定性
Instantaneous Exponential Ill-posedness of the BGK Model in a Half-Space with Inflow Boundary Conditions
arXiv 2610.01225 · 2026-10-02监督决定成功的关键：面向潜在世界模型规划的准则对齐辅助损失
Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model Planning
arXiv 2610.01224 · 2026-10-02让大语言模型编写异常检测器：自主发现紧凑、可解释的时间序列检测器
Have an LLM Write Your Anomaly Detector: Autonomous Discovery of Compact, Interpretable Detectors for Time Series
arXiv 2610.01223 · 2026-10-02声誉、策略与情感对生成式人工智能合作的影响：推理型与非推理型模型的比较
Reputation, Strategy, and Emotion Effects on Generative AI Cooperation: A Comparison Across Reasoning and Non-Reasoning Models
arXiv 2610.01222 · 2026-10-02Kähler 曲面上 Hermitian-Yang-Mills 联络的代数极限
Algebraic limits of Hermitian-Yang-Mills connections on Kähler surfaces
arXiv 2610.01221 · 2026-10-02基于多步高斯过程回归预测的车辆横向控制学习型预测控制方法
Learning-Based Predictive Control Method for Vehicle Lateral Control with a Multi-Step Gaussian Process Regression Prediction
arXiv 2610.01220 · 2026-10-02EIDA：面向真实到仿真到真实机器人导航的执行接口动力学自适应
EIDA: Execution-Interface Dynamics Adaptation for Real-to-Sim-to-Real Robot Navigation
arXiv 2610.01219 · 2026-10-02AGO AI 质量门：面向检索增强生成的基于证据的发布决策
AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation
arXiv 2610.01218 · 2026-10-02理想Chern带中的复合费米子
Composite fermions in ideal Chern bands
arXiv 2610.01217 · 2026-10-02高维中的莫利单纯形：正则性、反射与反例
Morley Simplices in Higher Dimensions: Regularity, Reflections, and Counterexamples
arXiv 2610.01216 · 2026-10-02AutoGUIWorld：图像生成器作为GUI智能体的视觉世界模型
AutoGUIWorld: Image Generators as Visual World Models for GUI Agent
arXiv 2610.01215 · 2026-10-02XMM-Newton 观测 Mrk 421 的 25 年：揭示结构化的喷流与能量依赖的逃逸
25 Years of Mrk 421 with XMM-Newton: Unveiling Structured Jets and Energy-Dependent Escape
arXiv 2610.01214 · 2026-10-02从语言模型股票排名到可检验的经济规则：一项计算审计
From language-model stock rankings to testable economic rules: A computational audit
arXiv 2610.01213 · 2026-10-02
