2026-09论文中文摘要
IaC-Guard-V：面向LLM生成的基础设施即代码修复的验证框架
IaC-Guard-V: A Verification Framework for LLM-Generated Infrastructure-as-Code Repairs
arXiv 2609.28488 · 2026-09-25通过措辞与选择进行框架构建：2022-2025年法国新闻标题的大规模二维审计
Framing by Wording, Framing by Selection: A Large-Scale Two-Dimensional Audit of French News Headlines, 2022-2025
arXiv 2609.28487 · 2026-09-25政治分化可通过用户反馈驱动AI模型彼此分离
Political Sorting Can Drive AI Models Apart Through User Feedback
arXiv 2609.28486 · 2026-09-25Make it SewSimple：在英国中学计算教育中通过电子纺织品导航国家课程与课堂实践
Make it SewSimple: Navigating UK Curriculum and Classroom Practice in Secondary Computing Education with E-textiles
arXiv 2609.28485 · 2026-09-25衡量基础模型的专业教育教学能力
Measuring the Professional Educational Competence of Foundation Models
arXiv 2609.28484 · 2026-09-25生成式人工智能可能强化软件工程教育中的社会偏见
Generative AI May Reinforce Social Biases in Software Engineering Education
arXiv 2609.28483 · 2026-09-25解开繁文缛节：监管系统的计算基础设施
Unsnarling the Red Tape: Computational Infrastructure for Regulatory Systems
arXiv 2609.28482 · 2026-09-25Drafter：用于CS1全栈Web开发的Python库
Drafter: A Python Library for Full-Stack Web Development in CS1
arXiv 2609.28481 · 2026-09-25RADAR：面向AI发现与智能体触达的准备度
RADAR: Readiness for AI Discovery and Agentic Reach
arXiv 2609.28480 · 2026-09-25家庭非保护区：对话式AI中的算法治理与施暴者话语再生产
The Domestic Unprotected Zone: Algorithmic Governance and the Reproduction of Perpetrator Discourse in Conversational AI
arXiv 2609.28479 · 2026-09-25一种用于测量人行道社会生活视觉语言框架
A Vision-Language Framework for Measuring Social Life on Sidewalks
arXiv 2609.28476 · 2026-09-25预测智能体何时应进行推理？可靠性路由的行为压力测试
When Should Forecasting Agents Reason? Behavioral Stress Tests for Reliability Routing
arXiv 2609.28475 · 2026-09-25纯对数时间与常数空间开销的容错量子计算
Purely-logarithmic-time- and constant-space-overhead fault-tolerant quantum computation
arXiv 2609.28461 · 2026-09-25模拟非常外围相对论重离子碰撞中的发射源函数
Simulating the emission source function in very peripheral relativistic heavy-ion collisions
arXiv 2609.28394 · 2026-09-25振荡区域中临界Strauss型指数下半线性Tricomi方程的爆破
Blow-up for a semilinear Tricomi equation in the oscillatory regime at the critical Strauss-type exponent
arXiv 2609.28389 · 2026-09-25学习可靠推理的成本
Learning the Cost of Reliable Inference
arXiv 2609.28322 · 2026-09-25UNITE-AUDIO：面向文本到音频生成的连续分词与潜在流匹配联合学习
UNITE-AUDIO: Joint Learning of Continuous Tokenization and Latent Flow Matching for Text-to-Audio Generation
arXiv 2609.28206 · 2026-09-25三维爱因斯坦-高斯-邦纳引力中的黑洞与标量传播
Black Holes and Scalar Propagation in Three-Dimensional Einstein--Gauss--Bonnet Gravity
arXiv 2609.28158 · 2026-09-25基于条件流匹配的高效多任务操作策略蒸馏
Distillation for Efficient Multitask Manipulation Policies via Conditional Flow Matching
arXiv 2609.28107 · 2026-09-25LAYERSCOPE：视频和多模态学习表示的分层特征刻画
LAYERSCOPE: A Layerwise Characterization of Video and Multimodal Learned Representations
arXiv 2609.28086 · 2026-09-25重离子碰撞中的奇异粒子产生：色绳还是流体动力学演化？
Strangeness Production in Heavy-Ion Collisions: Color Ropes or Hydrodynamic Evolution?
arXiv 2609.28070 · 2026-09-25Lettericity 是 NP-完全的
Lettericity Is NP-Complete
arXiv 2609.28023 · 2026-09-25MIDIBack：通过联合人声-伴奏符号建模实现和声感知的歌唱音高修正
MIDIBack: Harmony-Aware Singing Pitch Correction via Joint Vocal-Accompaniment Symbolic Modeling
arXiv 2609.28008 · 2026-09-25辐射性相对论阿尔文湍流中轻子和光子的各向异性与能量分布
Anisotropy and energy distribution of leptons and photons in radiative relativistic Alfvénic turbulence
arXiv 2609.27995 · 2026-09-25Shor正交测量猜想的一个证明与信息最优量子测量的结构
A Proof of Shor's Orthogonal-Measurement Conjecture and the Structure of Information-Optimal Quantum Measurements
arXiv 2609.27992 · 2026-09-25最短公共超串问题的紧环覆盖不等式
A Tight Cycle-Cover Inequality for Shortest Common Superstring
arXiv 2609.27921 · 2026-09-25Bergman 在圆上的融合问题
Bergman's amalgamation problem over the circle
arXiv 2609.27820 · 2026-09-25有向无环图中的稠密过程间支配关系：上下文界限与紧凑查询
Dense Interprocedural Dominance in Acyclic Graphs: Context Bounds and Compact Queries
arXiv 2609.27818 · 2026-09-25嵌套复样本协方差矩阵的分数对数定律
A Law of Fractional Logarithm for Nested Complex Sample Covariance Matrices
arXiv 2609.27804 · 2026-09-25具有与交叉多胞体大Banach-Mazur距离的高斯多胞体
Gaussian polytopes with large Banach-Mazur distance to the cross-polytope
arXiv 2609.27796 · 2026-09-25单位根处的量子化六顶点模型：Frobenius 性质与自由-parafermion 谱
Quantized six-vertex model at roots of unity: Frobenius property and free-parafermion spectra
arXiv 2609.27740 · 2026-09-25SkillGym：将人类技能内化为大语言模型能力以解决现实世界问题
SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving
arXiv 2609.27717 · 2026-09-25从超调和函数出发的离散高斯自由场Glauber动力学的混合剖面
Mixing profile for Glauber dynamics of the discrete Gaussian Free Field starting from super-harmonic functions
arXiv 2609.27689 · 2026-09-25脑到语言解码：任务、信号、方法、评估、实际应用及展望
Brain-to-Language Decoding: Tasks, Signals, Methods, Evaluation, Practical Use and Beyond
arXiv 2609.27650 · 2026-09-25SHRAV：面向物理建模与逆向设计的状态-假设-推理-行动-验证框架
SHRAV: State-Hypothesis-Reason-Action-Verify Framework for Physical Modeling and Inverse Design
arXiv 2609.27621 · 2026-09-25CCR：面向欧洲网络安全自动化的通用、质量门控CACAO集成注册表
CCR: Towards a Common, Quality-Gated CACAO Integrations Registry for European Cybersecurity Automation
arXiv 2609.27567 · 2026-09-25ProCredit：从结果奖励到智能体强化学习中的进度信用
ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning
arXiv 2609.27532 · 2026-09-25朗道奇点与凸几何
Landau singularities and convex geometry
arXiv 2609.27508 · 2026-09-25潜在演化世界动作模型
Latent evolving World Action Model
arXiv 2609.27455 · 2026-09-25防弹业务？迈向检测 Telegram 上的基础设施即服务供应
A Bulletproof Business? Towards Detecting Infrastructure-as-a-Service Offerings on Telegram
arXiv 2609.27428 · 2026-09-25具有Volterra和单侧Lipschitz扰动的极大单调微分包含在非局部初始条件下的应用
Maximal Monotone Differential Inclusions with Volterra and One-Sided Lipschitz Perturbations under Nonlocal Initial Conditions and Applications
arXiv 2609.27414 · 2026-09-25招募较小一侧的力量：在双边市场中额外两名交易者即足够
The Power of Recruiting the Smaller Side: Two Additional Traders Suffice in Two-Sided Markets
arXiv 2609.27304 · 2026-09-25关于双基因竞争系统双稳定性的注记
A note on bistability of a two-gene competitive system
arXiv 2609.27270 · 2026-09-25保真度指标遗漏之处：对合成教育数据的结构性检查
What fidelity metrics miss: a structural check on synthetic educational data
arXiv 2609.27265 · 2026-09-25通过在 WavLM 空间中学习 kNN 传输实现一步式语音转换
One-Step Voice Conversion by Learning kNN Transport in WavLM Space
arXiv 2609.27230 · 2026-09-25LOCKR：一种隐藏状态轨迹引导的规划器，用于检测和修复扩散语言模型中的稳定但错误锁定
LOCKR: A Hidden-State Trajectory-Guided Planner for Detecting and Repairing Stable-but-Wrong Lock-In in Diffusion Language Models
arXiv 2609.27220 · 2026-09-25大型推理模型在推理时间上的能力与效率缩放
Scaling of Capability and Efficiency at Inference Time in Large Reasoning Models
arXiv 2609.27166 · 2026-09-25模型误设定下多层次数据的贝叶斯框架
A Bayesian framework for multilevel data under model mis-specification
arXiv 2609.27112 · 2026-09-25宽场NV色心磁成像用于无损材料检测的研究
Investigation of Widefield NV-Center Magnetic Imaging for Non-Destructive Materials Testing
arXiv 2609.27097 · 2026-09-25数学推理在LLM中按方法而非主题组织
Math Reasoning in LLMs is Organized by Approach, Not Topic
arXiv 2609.27041 · 2026-09-25
