2026-10论文中文摘要
可操控的覆盖率：面向强化学习驱动的硬件感知神经架构搜索的在线共形校准
Coverage You Can Steer: Online Conformal Calibration for RL-Driven Hardware-Aware NAS
arXiv 2610.03127 · 2026-10-05Reeb变换
The Reeb Transform
arXiv 2610.03126 · 2026-10-05ParaGeo：将副语言变异分解为共享潜在几何结构
ParaGeo: Decomposing Paralinguistic Variation into a Shared Latent Geometry
arXiv 2610.03125 · 2026-10-05开放权重大语言模型中滥用检测的触发器标签机制的脆弱性
The Fragility of Trigger-Tag Mechanisms for Misuse Detection in Open-Weight LLMs
arXiv 2610.03124 · 2026-10-05Foresight：无需重训练即可在流式视觉语言模型中规划未来感知
Foresight: planning future perception in streaming VLMs without retraining
arXiv 2610.03123 · 2026-10-05串并联扩展与 Ehrhart 正性
Series-parallel extensions and Ehrhart positivity
arXiv 2610.03122 · 2026-10-05D(n)-三元组的分裂三次曲线：一个有界有限域普查
Split-Cubic Curves from D(n)-Triples: A Bounded Finite-Field Census
arXiv 2610.03121 · 2026-10-05如何在终身强化学习中寻找并复用策略以实现持续适应
How to Find and Reuse Policies for Continuous Adaptation in Lifelong Reinforcement Learning
arXiv 2610.03119 · 2026-10-05ParABS系统诱导拓扑修饰以时空组织复制中的C. crescentus细胞的母体与子代染色体
ParABS system induces topological modifications to spatio-temporally organize its mother and daughter chromosomes in the replicating C. crescentus cell
arXiv 2610.03118 · 2026-10-05探索深度神经网络中结构化剪枝与容错性之间的权衡：面向空间应用
Exploring the Trade-Off Between Structured Pruning and Fault Tolerance in Deep Neural Networks for Space Applications
arXiv 2610.03117 · 2026-10-05调和旋量的Calderón问题
The Calderón problem for harmonic spinors
arXiv 2610.03116 · 2026-10-05二维随机游走碰撞测度的尺度极限
Scaling limit of the collision measure for two-dimensional random walks
arXiv 2610.03115 · 2026-10-05量子选择组态相互作用中的电路增长与子空间读出：分离Hartree-Fock行列式
Circuit growth and subspace read-out in quantum-selected configuration interaction: Separating the Hartree-Fock determinant
arXiv 2610.03114 · 2026-10-05连续变量系统中高维纠缠的认证
Certification of high-dimensional entanglement in continuous-variable systems
arXiv 2610.03113 · 2026-10-05构建可解释的特征表示：通过蒸馏生产级LLM信号实现简历-职位匹配
Building Interpretable Feature Representations for Resume-Vacancy Matching by Distilling Production LLM Signals
arXiv 2610.03112 · 2026-10-05Jacobi-Stirling数的二项式展开及Jacobi-Stirling下降多项式的实根性
Binomial expansions of Jacobi-Stirling numbers and real-rootedness of Jacobi-Stirling descent polynomials
arXiv 2610.03111 · 2026-10-05本体不稳定性与统计放大：LLM生成文本“人性化”的悖论
Ontological Instability and Statistical Amplification: The Paradox of "Humanizing" LLM-Generated Text
arXiv 2610.03110 · 2026-10-05语言模型边际注意力空间中的涌现结构
Emergent Structure in the Marginal Attention Space of Language Models
arXiv 2610.03109 · 2026-10-05量子环面上临界指标处Bochner--Riesz平均的弱(1,1)有界性
Weak type $(1,1)$ boundedness of Bochner--Riesz means at the critical index on quantum tori
arXiv 2610.03107 · 2026-10-05S2S-JEPA：在次季节到季节时间尺度上预测可预测的部分
S2S-JEPA: Predicting the Predictable at Subseasonal-to-Seasonal Timescales
arXiv 2610.03106 · 2026-10-05空间锚定手势生成的基准
A Benchmark for Spatially Grounded Gesture Generation
arXiv 2610.03105 · 2026-10-05利用 Bargmann 不变量评估离散布里渊区中的陈拓扑
Evaluating Chern Topology in Discretized Brillouin Zones Using Bargmann Invariants
arXiv 2610.03104 · 2026-10-05轨道旋转阴影层析降低量子-经典辅助场量子蒙特卡洛的经典成本
Orbital-Rotation Shadow Tomography Reduces the Classical Cost of Quantum-Classical Auxiliary-Field Quantum Monte Carlo
arXiv 2610.03103 · 2026-10-05询问、放松还是行动？评估LLM偏好推理中的可操作不确定性
Ask, Relax, or Act? Evaluating Actionable Indeterminacy in LLM Preference Reasoning
arXiv 2610.03102 · 2026-10-05因果效应识别中聚类操作的不变性
Invariance of Clustering Operations in Causal Effect Identification
arXiv 2610.03101 · 2026-10-05超越单一视频：电商跨视频推理的基准构建与主动证据寻求
Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning
arXiv 2610.03099 · 2026-10-05预测器引导的潜空间密码子优化以最大化蛋白质表达
Predictor-Guided Latent Space Codon Optimization for Maximizing Protein Expression
arXiv 2610.03098 · 2026-10-05Sawada-Kotera 方程的柯西问题：孤子分解猜想、Painlevé 超越函数与渐近稳定性
On the Cauchy Problem for the Sawada-Kotera Equation: Soliton resolution conjecture, Painlevé transcendents and asymptotic stability
arXiv 2610.03097 · 2026-10-05$\mathrm{SL}_n$情形下perverse滤过的乘法性
Multiplicativity of the perverse filtration in the $\mathrm{SL}_n$ case
arXiv 2610.03096 · 2026-10-05异构AI模型间的同伴影响
Peer Influence across Heterogeneous AI Models
arXiv 2610.03095 · 2026-10-05量子临界超导性：接近力学不稳定性的稠密费米-稀薄玻色混合物
Quantum critical superconductivity in a dense fermi dilute bose mixture close to mechanical instability
arXiv 2610.03094 · 2026-10-05LS-AR：自回归大语言模型中的未来预测潜在引导
LS-AR: Future-Predictive Latent Steering in Autoregressive LLMs
arXiv 2610.03093 · 2026-10-05ULTRADISCOVERY：在相互关联、认识论开放宇宙中的溯因探索
ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe
arXiv 2610.03092 · 2026-10-05奇异轮廓动力学与仿微分约化
Singular Contour Dynamics and Paradifferential Reduction
arXiv 2610.03091 · 2026-10-05PaNGEA：GPU上的并行节点生成与探索算法
PaNGEA: Parallel Node Generation and Exploration Algorithm on GPU
arXiv 2610.03090 · 2026-10-05保护计算机使用代理免受分支转向攻击
Securing Computer-Use Agents Against Branch Steering Attacks
arXiv 2610.03089 · 2026-10-05Coda：利用准入灵活性优化编码智能体服务
Coda: Exploiting Admission Flexibility for Coding-Agent Serving
arXiv 2610.03088 · 2026-10-05Zephon：用于在线、有状态基础模型数据加载管道的弹性确定性
Zephon: Elastic Determinism for Online, Stateful Foundation Model Data Loading Pipelines
arXiv 2610.03087 · 2026-10-05$[0,1]^n$ 中的小型有影响力联盟：基于 Junta 定理
Small Influential Coalitions in $[0,1]^n$ via the Junta Theorem
arXiv 2610.03086 · 2026-10-05黎曼流形上的轻量熵最优传输
Light Entropic Optimal Transport on Riemannian Manifolds
arXiv 2610.03085 · 2026-10-05NegT2IBench：当否定改变画面——面向文生图模型的极性基准
NegT2IBench: When Negation Changes the Picture. A Polarity Benchmark for Text-to-Image Models
arXiv 2610.03084 · 2026-10-05智能传感助力桥梁安全：从传感器信号到AI驱动的异常检测
Smart Sensing for Safer Bridges: From Sensor Signals to AI-Driven Anomaly Detection
arXiv 2610.03082 · 2026-10-05线性约束 Kloosterman 族的同调：Newton 多面体、权与边界幺单性
Cohomology of Linearly Constrained Kloosterman Families: Newton Polytopes, Weights, and Boundary Monodromy
arXiv 2610.03081 · 2026-10-05MintEval：大语言模型是否实现了您要求的交易策略？一个面向自然语言到策略代码的行为等价基准
MintEval: Do LLMs Implement the Trading Strategy You Asked For? A Behavioural-Equivalence Benchmark for Natural-Language-to-Strategy Code
arXiv 2610.03080 · 2026-10-05RIFAR：面向持续机器人学习的可靠性与遗忘感知重放
RIFAR: Reliability and Forgetting-Aware Replay for Continual Robot Learning
arXiv 2610.03079 · 2026-10-05自发对话中标准化语音单元标注的自动化流程
An automated pipeline for standardised speech-unit annotation in spontaneous dialogue
arXiv 2610.03078 · 2026-10-05揭露宣传：掩码语言模型与因果语言模型的比较分析
Unmasking Propaganda: A Comparative Analysis of Masked and Causal Language Models
arXiv 2610.03077 · 2026-10-05生成真核生物参考基因组组装：地球生物基因组计划质量标准与建议
Generating eukaryotic reference genome assemblies: Earth BioGenome Project quality standards and recommendations
arXiv 2610.03075 · 2026-10-05幂零群中共轭可分性增长的统一上界
Uniform Upper Bounds for Conjugacy Separability Growth in Nilpotent Groups
arXiv 2610.03074 · 2026-10-05SecJev：将安全专业知识引入系统一决策模型
SecJev: Bringing Security Expertise to System One Decision Models
arXiv 2610.03073 · 2026-10-05
