2026-10论文中文摘要
针对AI拉取请求审查者的自适应代码修订攻击
Adaptive Code Revision Attacks on AI Pull Request Reviewers
arXiv 2610.05399 · 2026-10-06MMPostTrainBench：多模态后训练自主研究的基准测试
MMPostTrainBench: Benchmarking Autonomous Research for Multimodal Post-Training
arXiv 2610.05398 · 2026-10-06通过直接预测与流匹配的高效图生成
Efficient Graph Generation via Direct Prediction and Flow Matching
arXiv 2610.05397 · 2026-10-06上三角辛Renner幺半群的枚举
Enumeration of Upper Triangular Symplectic Renner Monoids
arXiv 2610.05396 · 2026-10-06Kitaev 蜂窝自旋液体的精确张量网络完整纠缠结构
Complete Entanglement Structure of the Kitaev Honeycomb Spin Liquid from Exact Tensor Networks
arXiv 2610.05395 · 2026-10-06隐藏状态食谱：工业中噪声鲁棒对话意图分类的大规模消融研究
The Hidden States Cookbook: A Large-Scale Ablation Study for Noise-Robust Conversational Intent Classification in Industry
arXiv 2610.05394 · 2026-10-06路径图上量子游走的Walk/Zeta对应：由广义反射原理蕴含的前几何结构
Walk/Zeta correspondence for quantum walks on path graphs: a pre-geometric structure implied by a generalized reflection principle
arXiv 2610.05393 · 2026-10-06形式实域上四元数代数的属
Genus of quaternion algebras over formally real fields
arXiv 2610.05392 · 2026-10-06全次临界区间内若干非局部或非平移不变Anderson算子的随机偏微分方程构造
Stochastic PDE construction of some non-local or non-translation-invariant Anderson operators in the full subcritical regime
arXiv 2610.05391 · 2026-10-065G NR PDSCH 能效优化：跨层链路抽象框架
Energy Efficiency Optimization for 5G NR PDSCH: A Cross-Layer Link Abstraction Framework
arXiv 2610.05390 · 2026-10-06关于无逆查询的状态区分
On State Distinguishing Without Inverse Queries
arXiv 2610.05389 · 2026-10-06GNN-CB：面向人类与LLM评估的图神经网络竞赛基准
GNN-CB: A Graph Neural Network Competition Benchmark for Human and LLM Evaluation
arXiv 2610.05387 · 2026-10-06中子星磁层相对论磁化激波中的辐射反作用
Radiation Reaction in Relativistic Magnetized Shocks of Neutron Star Magnetospheres
arXiv 2610.05386 · 2026-10-06论问题的计算复杂性：形式化对不确定性的敏感性与参数化复杂性类
On the Computational Complexity of Problems: Formalizing Sensitivity to Uncertainty and Parametric Complexity Classes
arXiv 2610.05385 · 2026-10-06一个简单nil环的简单构造
A simple construction of a simple nil ring
arXiv 2610.05384 · 2026-10-06Sibyl：面向长时程任务的高效小-大模型协作框架
Sibyl: An Efficient Small-large Model Collaboration Framework for Long-horizon Tasks
arXiv 2610.05383 · 2026-10-06Harness-Search：通过多智能体协调引导长时程搜索
Harness-Search: Guiding Long-Horizon Search through Multi-Agent Coordination
arXiv 2610.05382 · 2026-10-06带记忆的备用控制障碍函数用于在线集合扩展
Backup Control Barrier Functions with Memory for Online Set Expansion
arXiv 2610.05381 · 2026-10-06VHDL-REPOBENCH：用于评估大型语言模型在VHDL设计生成能力的仓库级基准
VHDL-REPOBENCH: A Repository-Level Benchmark for Evaluating Large Language Models on VHDL Design Generation
arXiv 2610.05380 · 2026-10-06可解释性是否在数据漂移下幸存？
Does Explainability Survive Data Drift?
arXiv 2610.05379 · 2026-10-06分布式潜意识学习：用随机载体输出替代模型更新
Distributed Subliminal Learning: Replacing Model Updates with Random-Carrier Outputs
arXiv 2610.05378 · 2026-10-06通过吨级暗物质探测器中的太阳中微子-电子散射探索无异常暗光子模型
Exploring Anomaly-Free Dark Photon Models Through Solar Neutrino-Electron Scattering in Ton-Scale Dark Matter Detectors
arXiv 2610.05377 · 2026-10-06物理信息神经控制逆流换热器热流率：建模、辨识与实验验证
Physics-informed neural control of heat flow rate in a counter-flow heat exchanger: modeling, identification and experimental validation
arXiv 2610.05376 · 2026-10-06已知迹距离球内的极小极大量子态层析
Minimax Quantum State Tomography in a Known Trace-Distance Ball
arXiv 2610.05374 · 2026-10-06面向块扩散语言模型的无偏在线蒸馏
Towards Unbiased On-Policy Distillation for Block Diffusion Language Models
arXiv 2610.05373 · 2026-10-06双胞胎范艾伦探测器轨道衰减为何分道扬镳？
What Caused the Orbital Decay of the Twin Van Allen Probes to Diverge?
arXiv 2610.05372 · 2026-10-06科学反问题的鲁棒集成引导
Robust Ensemble Guidance for Scientific Inverse Problems
arXiv 2610.05371 · 2026-10-06AutoDP-LLM：利用大型语言模型自动化入侵检测系统的数据预处理
AutoDP-LLM: Automating Data Pre-processing for Intrusion Detection Systems using Large Language Models
arXiv 2610.05369 · 2026-10-06缺失模式不匹配对时间序列分类方法选择的影响：一项受控实证研究
The Effect of Missingness-Pattern Mismatch on Method Selection for Time-Series Classification: A Controlled Empirical Study
arXiv 2610.05368 · 2026-10-06AIProver：通过证书驱动的演化工具实现数学研究的智能体自动形式化
AIProver: Agentic Auto-Formalization of Mathematical Research via Certificate-Driven Evolving Harness
arXiv 2610.05367 · 2026-10-06具有随机块模型结构的大规模网络上的泊松自回归
Poisson Autoregression on a Large Network with a Stochastic Block Model Structure
arXiv 2610.05365 · 2026-10-06四元数 $GL_n(D)$ 的温和辛区分：Prasad 的一个猜想
Tempered Symplectic Distinction For Quaternionic $GL_n(D)$: A Conjecture of PRASAD
arXiv 2610.05364 · 2026-10-06从能量景观和组合学出发的薄同质单层滑动与堆叠
Sliding and stacking thin homo-monolayers from energy landscapes and combinatorics
arXiv 2610.05363 · 2026-10-06几何局部 Lindblad 动力学的浅层量子电路
Shallow Quantum Circuits for Geometrically Local Lindblad Dynamics
arXiv 2610.05362 · 2026-10-06黏性变广义Chaplygin气体的热力学稳定性
Thermodynamic Stability of a Viscous Variable Generalised Chaplygin Gas
arXiv 2610.05361 · 2026-10-06具有两个不同来源输入的局部处理器中的调制与整合
Modulation and Integration in a local processor having input from two distinct sources
arXiv 2610.05360 · 2026-10-06未建模状态依赖下基于学习型评价函数的优化控制
Optimal Control with Learned Critics under Unmodeled State Dependencies
arXiv 2610.05359 · 2026-10-06天文学之卵：开普勒定律、托勒密偏心点和勒让德多项式
Astronomia Ova: Kepler's Laws, Ptolemy's Equant, and Legendre's Polynomials
arXiv 2610.05358 · 2026-10-06优化人工智能驱动的2型糖尿病管理信息传递：来自患者偏好引导的见解
Optimizing AI-Driven Messaging for Type 2 Diabetes Management: Insights from Patient Preference Elicitation
arXiv 2610.05357 · 2026-10-06一个受约束的log-HLS不等式及其相关的Wasserstein流
A constrained log-HLS inequality and its associated Wasserstein flow
arXiv 2610.05356 · 2026-10-06重新思考学术交流中的行内引文验证
Rethinking Inline Citation Verification in Scholarly Communication
arXiv 2610.05355 · 2026-10-06ODE振荡爆破解的代数-动力学对应关系
On Algebraic-Dynamical Correspondence of Oscillatory Blow-Up Solutions for ODEs
arXiv 2610.05354 · 2026-10-06FACET：面向高保真荧光显微成像合成的因子化非对称条件化高效传输方法
FACET: Factorized Asymmetric Conditioning for Efficient Transport in High-Fidelity Fluorescence Microscopy Synthesis
arXiv 2610.05353 · 2026-10-06重新思考数据流上的表格基础模型
Rethinking Tabular Foundation Models On Data Streams
arXiv 2610.05352 · 2026-10-06湍流之刷：利用XRISM探测合并中的牙刷星系团内介质动力学
A Brush with Turbulence: Probing the ICM Dynamics in the Merging Toothbrush Cluster using XRISM
arXiv 2610.05351 · 2026-10-06行为基础模型中超越最小二乘的任务推断
Task Inference Beyond Least Squares in Behavioral Foundation Models
arXiv 2610.05350 · 2026-10-06搜索引擎从不说“不”：当检索工具拒绝时冻结智能体如何反应
Search Engines Never Say No: How Frozen Agents React When the Retrieval Tool Refuses
arXiv 2610.05348 · 2026-10-06有限环上对数Sobolev不等式的尖锐一致稳定性及三次Sobolev不等式的稳定性
Sharp uniform stability of the logarithmic Sobolev inequality on finite cycles and stability of the cubic Sobolev inequality
arXiv 2610.05347 · 2026-10-06反思与碎片：保护大语言模型免受序列马赛克攻击
Reflections and Fragments: Securing LLMs Against Sequential Mosaic Attacks
arXiv 2610.05346 · 2026-10-06数据驱动的重味强子产生测量：在 \sqrt{s_{\mathrm{NN}}} = 5.02 和 8.16 TeV 的 p-Pb 碰撞中
Data-driven measurements of the beauty hadron production in p-Pb collisions at \sqrt{s_{\mathrm{NN}}} = 5.02 and 8.16 TeV
arXiv 2610.05345 · 2026-10-06
