2026-10论文中文摘要
TED：面向提示异常定位的文本轴证据分解
TED:Text-Axis Evidence Decomposition for Prompted Anomaly Localization
arXiv 2609.39033 · 2026-10-01预测MOS在复现人类对语音增强系统级偏好方面的可靠性如何？
How Reliable Are Predicted MOS for Reproducing Human System-Level Preferences in Speech Enhancement?
arXiv 2609.39032 · 2026-10-01$L^p$-算子代数的Morita等价性与étale群胚
Morita equivalence for $L^p$-operator algebras associated with étale groupoids
arXiv 2609.39031 · 2026-10-01SURE-EVAL：一个用于可复现评估的系统化统一智能体框架
SURE-EVAL: A Systematic and Unified Agentic Framework for Reproducible Evaluation
arXiv 2609.39030 · 2026-10-01胶子碎裂为$^1S_0^{[1,8]}$夸克偶素中阈值双对数的重求和
Resummation of threshold double logarithms in gluon fragmentation into $^1S_0^{[1,8]}$ quarkonia
arXiv 2609.39029 · 2026-10-01改进预测的MOS分数，而非感知质量：增强语音的多预测器测试时优化
Improving Predicted MOS Scores, Not Perceived Quality: Multi-Predictor Test-Time Optimization of Enhanced Speech
arXiv 2609.39028 · 2026-10-01可信 AI 审稿人缺失的一环：从修辞鲁棒性基准测试到 SciCore 审稿
A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review
arXiv 2609.39027 · 2026-10-01搜索塑造结论：审计深度研究智能体中的证据选择偏差
Search Shapes Conclusions: Auditing Evidence Selection Bias in Deep Research Agents
arXiv 2609.39026 · 2026-10-01算法公平性的秩毕业度量
A Rank Graduation metric for Algorithmic fairness
arXiv 2609.39025 · 2026-10-01文本到图像模型的持久水印
Persistent Watermarking of Text-to-Image Models
arXiv 2609.39024 · 2026-10-01当注意力护栏成为学习的障碍：迈向临界点
When Attention Guardrails Become Barriers to Learning: Towards the Tipping Point
arXiv 2609.39023 · 2026-10-01视频推理的帧差分在线策略自蒸馏
Frame Differential On-Policy Self-Distillation for Video Reasoning
arXiv 2609.39021 · 2026-10-01深度ReLU神经网络学习谱Barron函数的极小极大速率
Minimax rates for learning spectral Barron functions by deep ReLU neural networks
arXiv 2609.39020 · 2026-10-01同步多视角神经扩散
Synchronous Multi-view Neural Diffusion
arXiv 2609.39019 · 2026-10-01让代码即策略再次伟大：前沿智能体编写、调用并进化机器人工具
Make Code as Policy Great Again: Frontier Agents Write, Call, and Evolve Robot Tools
arXiv 2609.39018 · 2026-10-01OccluDex：自遮挡下第一人称灵巧操作的分层三维视觉-触觉表示学习
OccluDex: Hierarchical 3D Visuo-Tactile Representation Learning for Egocentric Dexterous Manipulation under Self-Occlusion
arXiv 2609.39017 · 2026-10-01熵阈值：量子纠错性能的一个简单代理指标
Entropy threshold: A simple proxy for performance of quantum error correction
arXiv 2609.39016 · 2026-10-01结合多面体的色数的双对数上界
A double-logarithmic upper bound on the chromatic number of the associahedron
arXiv 2609.39015 · 2026-10-01测度维数的半连续性
The semicontinuity of dimensions of measures
arXiv 2609.39014 · 2026-10-01证据优先，算术其次：DocSem 系统报告与失败分析
Evidence First, Arithmetic Second: A System Report and Failure Analysis for DocSem
arXiv 2609.39013 · 2026-10-01社会比较塑造结构化种群中合作的演化
Social comparison shapes the evolution of cooperation in structured populations
arXiv 2609.39012 · 2026-10-01相对导出解环层与$\tau$-倾斜模
Relative Derived Delooping Levels and $τ$-Tilting Modules
arXiv 2609.39011 · 2026-10-01不确定性引导的数字孪生框架用于头颈部肿瘤在线自适应质子治疗：可行性研究
An Uncertainty-Guided Digital Twin Framework for Online Adaptive Proton Therapy in Head and Neck Cancer: A Feasibility Study
arXiv 2609.39010 · 2026-10-01改进的三态数乘法及其在 Rocq 中的形式化验证
Improved Tristate Multiplication With Formalization in Rocq
arXiv 2609.39009 · 2026-10-01振荡特殊函数的Turán型不等式
Turán type inequalities for oscillatory special functions
arXiv 2609.39008 · 2026-10-01RouteRec：行为引导的稀疏路由用于序列推荐
RouteRec: Behavior-Guided Sparse Routing for Sequential Recommendation
arXiv 2609.39007 · 2026-10-01功能超越形态：跨具身灵巧抓取生成的 functional correspondence
Function beyond Form: Functional Correspondence for Cross-Embodiment Dexterous Grasp Generation
arXiv 2609.39006 · 2026-10-01C-STRIDE：一种观测驱动的AI数字孪生，用于从稀疏水位计历史记录预测流域尺度洪水场
C-STRIDE: An Observation-Driven AI Digital Twin for Predicting Basin-Wide Flood Fields from Sparse Stream-Gauge Histories
arXiv 2609.39005 · 2026-10-01当积分遇见分解：一种用于多模态图像融合的信号级自监督特征分解范式
When Integral Meets Decomposition: A Signal-Level Self-Supervised Feature Decompose Paradigm for Multi-Modal Image Fusion
arXiv 2609.39004 · 2026-10-01图像幂零 η-扩张上的高阶余挠对
Higher Cotorsion Pairs on Image-Nilpotent \(η\)-Extensions
arXiv 2609.39003 · 2026-10-01一种基于原子的机器学习偶极矩模型及其在共轭体系中的应用
An atom-based machine-learned dipole-moment model and application to conjugated systems
arXiv 2609.39002 · 2026-10-01无形的语言税：2026年大语言模型分词器中法语及地区语言的令牌溢价，以及一个法语优化原型
The Invisible Language Tax: Token Premiums of French and Regional Languages in 2026 LLM Tokenizers, and a French-Optimized Prototype
arXiv 2609.39001 · 2026-10-01NEXUS：面向地形自适应遥操作的全感知全身控制
NEXUS: Perceptive Whole-Body Control for Terrain-Adaptive Teleoperation
arXiv 2609.39000 · 2026-10-01当LLM推断的用户上下文在生产级流式推荐中增加价值时
When LLM-Inferred User Context Adds Value in Production Streaming Recommendation
arXiv 2609.38999 · 2026-10-01并非所有解决方案都是平等的：深度线性神经网络中功能相似性与表征相似性的分析性分离
Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks
arXiv 2609.38998 · 2026-10-01Settle：学习何时停止推理
Settle: Learning When to Stop Reasoning
arXiv 2609.38997 · 2026-10-01具有完全可寻址横向T门的恒定速率码：好码与稀疏校验
Constant Rate Codes with Fully Addressable Transversal T: Good Codes, Sparse Checks
arXiv 2609.38996 · 2026-10-01当裁剪逆转修正：逐点前向KL在线策略自蒸馏的失败动力学
When Clipping Reverses Correction: Failure Dynamics of Pointwise Forward-KL On-Policy Self-Distillation
arXiv 2609.38995 · 2026-10-01有效哈密顿量的参考测度自由度：从随机热力学到宏观极限
Reference-Measure Freedom of the Effective Hamiltonian: From Stochastic Thermodynamics to the Macroscopic Limit
arXiv 2609.38994 · 2026-10-01超立方体的配对防御银色染色
Pair-Defensive Silver Colourings of Hypercubes
arXiv 2609.38993 · 2026-10-01广义Reedy范畴的规范化图与Dold-Kan等价
Normalization graphs and Dold-Kan equivalences for generalized Reedy categories
arXiv 2609.38992 · 2026-10-01锚定对抗轨迹到数据流形：一种双层迁移优化框架
Anchoring Adversarial Trajectories to Data Manifolds: A Bilevel Transfer Optimization Framework
arXiv 2609.38991 · 2026-10-01非奇异反弹中的RRR涨落
RRR fluctuations from non-singular bounce
arXiv 2609.38990 · 2026-10-01引导流动：面向开放世界投递操作的流动匹配策略引导
Cue the Flow: Steering Flow-Matching Policies for Open-World Delivery Manipulation
arXiv 2609.38989 · 2026-10-01使用边拉普拉斯动力学与里奇流进行社区检测
Community Detection using the Edge Laplacian Dynamics vis-a-vis Ricci Flow
arXiv 2609.38988 · 2026-10-01更小的模型，更好的拒绝样本：偏好蒸馏的规模效应
Smaller Models, Better Rejects: Preference Distillation Scaling
arXiv 2609.38987 · 2026-10-01量子伪随机纠错码
Quantum Pseudorandom Error-Correcting Codes
arXiv 2609.38986 · 2026-10-01Sparse-WAM：通过动作引导的稀疏想象加速世界动作模型
Sparse-WAM: Accelerating World Action Models via Action-Guided Sparse Imagination
arXiv 2609.38984 · 2026-10-01批准洗白：系统化AI编码代理框架中的批准-执行绑定失败
Approval Laundering: Systematizing Approval--Execution Binding Failures in AI Coding-Agent Harnesses
arXiv 2609.38983 · 2026-10-01SimEX：仿真集成的机器人自动研究
SimEX: Simulation-Integrated Robotics AutoResearch
arXiv 2609.38982 · 2026-10-01
