2026-10论文中文摘要
Füredi-Hajnal 和 Stanley-Wilf 极限的典型增长
Typical growth of the Füredi-Hajnal and Stanley-Wilf limits
arXiv 2610.02707 · 2026-10-05AdaTempo：从示范中学习共享相对节奏以实现更快的机器人操作
AdaTempo: Learning Shared Relative Tempo from Demonstrations for Faster Robot Manipulation
arXiv 2610.02706 · 2026-10-05MuonIO：用于嵌入表和语言模型头的原则性范数感知下降
MuonIO: Principled Norm-Aware Descent for Embedding Tables and Language Model Heads
arXiv 2610.02705 · 2026-10-05大规模标签高效时间序列分类：具有反事实归因的双流OSSE-LSTM
Label-Efficient Time Series Classification at Scale: A Dual-Stream OSSE-LSTM with Counterfactual Attribution
arXiv 2610.02704 · 2026-10-05学习通过分段式策略内蒸馏进行推理修正
Learning to Revise Reasoning with Segment-wise On-Policy Distillation
arXiv 2610.02703 · 2026-10-05从演化错误中学习：用于在线策略蒸馏的自适应迭代修复
Learning from Evolving Errors: Adaptive Iterative Repair for On-Policy Distillation
arXiv 2610.02700 · 2026-10-05LearnAdapt Praxis：面向成人职场学习的受控AI辅助与证据追踪
LearnAdapt Praxis: Controlled AI Assistance and Evidence Traces for Adult Workplace Learning
arXiv 2610.02699 · 2026-10-05结构驱动方法论：一种新兴的跨领域范式
Structure-Driven Methodology: An Emerging Cross-Domain Paradigm
arXiv 2610.02698 · 2026-10-05GeoScaffold：通过重建学习紧凑几何潜变量以实现高效视觉-语言导航
GeoScaffold: Learning Compact Geometric Latents via Reconstruction for Efficient Vision-Language Navigation
arXiv 2610.02697 · 2026-10-05局部挠超群、亚幂零群与$T$-可解群的素图
Prime Graphs of Locally Torsion Ultragroups, Metanilpotent Groups, and $T$-Solvable Groups
arXiv 2610.02696 · 2026-10-05大语言模型推理的测试时校准学习
Test-time Calibration Learning for Large Language Model Reasoning
arXiv 2610.02695 · 2026-10-05谁在何时于月球表面去了哪里：识别拜占庭漫游车的取证轨迹分析
Who Went Where When on the Lunar Surface: Forensic Trajectory Analysis to Identify Byzantine Rovers
arXiv 2610.02694 · 2026-10-05温度-组分映射及生长历史对流动N$_2$下Fe-B上生长BN中rBN相关拉曼响应的依赖性
Temperature--Composition Mapping and Growth-History Dependence of rBN-Related Raman Responses in BN Grown on Fe--B under Flowing N$_2$
arXiv 2610.02693 · 2026-10-05多圆盘中$N_{\eta}$型商模的自交换子与交叉交换子的Hilbert-Schmidt范数
Hilbert-Schmidt Norms of Self-Commutator and Cross-Commutator on $N_η$-type Quotient Modules in Polydisc
arXiv 2610.02692 · 2026-10-05DeltaWorld：通过动作条件潜在增量学习实现物理一致的交互式世界模拟器
DeltaWorld: Physically Consistent Interactive World Simulators via Action-Conditioned Latent Increment Learning
arXiv 2610.02691 · 2026-10-05簇的Grothendieck环与特征处的数值不变量
Grothendieck ring of varieties and at-the-characteristic numerical invariants
arXiv 2610.02690 · 2026-10-05中间小平维数的 $3$ 维流形的尖锐 Noether 型不等式
Sharp Noether-type inequalities for $3$-folds of intermediate Kodaira dimensions
arXiv 2610.02689 · 2026-10-05创伤知情培训对性别暴力倡导者应对技术辅助虐待的启示
Lessons from Trauma-Informed Training on Technology-Facilitated Abuse for Gender-Based Violence Advocates
arXiv 2610.02688 · 2026-10-05有限维连续数据同化中灵敏度的渐近逼近及其在参数估计中的应用
Asymptotic approximation of sensitivities in finite dimensional continuous data assimilation with application to parameter estimation
arXiv 2610.02686 · 2026-10-05带界漂移的定量抛物型衰减
Quantitative Parabolic Decay With Bounded Drift
arXiv 2610.02685 · 2026-10-05大型语言模型在患者证据演变过程中表现出不可靠的临床判断更新
Large language models exhibit unreliable updating of clinical judgment as patient evidence evolves
arXiv 2610.02684 · 2026-10-05RAOA：具有可编程无线电传播的交替算子神经计算
RAOA: Alternating-Operator Neural Computation with Programmable Radio Propagation
arXiv 2610.02683 · 2026-10-05布尔因子模型中的可辨识性刻画
Characterizing Identifiability in Boolean Factor Models
arXiv 2610.02682 · 2026-10-05远离Turán图的图的正差异
Positive discrepancy of graphs far from Turán graphs
arXiv 2610.02681 · 2026-10-05连续时间多参数最优控制的进展：时变有效约束的作用
Advances in Continuous-Time Multiparametric Optimal Control: The Role of Time-Varying Active Constraints
arXiv 2610.02680 · 2026-10-05DataWeave：面向探索性结构化数据分析的人机协同分析部署
DataWeave: Deploying Human-LLM Analytics for Exploratory Structured Data Analysis
arXiv 2610.02679 · 2026-10-05将教师令牌用在关键之处：成功参照的在线策略蒸馏
Spend Teacher Tokens Where They Matter: Success-Referenced On-Policy Distillation
arXiv 2610.02678 · 2026-10-05Ia型超新星爆燃中的中尺度湍流 II：基于拉格朗日分析的火焰热膨胀导致燃料预热证据
Mesoscale Turbulence in Type Ia Supernova Deflagrations II. Evidence for Fuel Preheat Due to Flame Thermal Expansion from Lagrangian Analysis
arXiv 2610.02677 · 2026-10-05FDP：现代NVMe SSD的数据放置承诺
FDP: The Data Placement Promise of Modern NVMe SSDs
arXiv 2610.02676 · 2026-10-05一个光子，多个世界：单光子相机的后验与预测
One Photon, Many Worlds: Posteriors and Predictions with Single-Photon Cameras
arXiv 2610.02675 · 2026-10-05基于BESS虚拟输电线路的发电与输电扩展规划
Generation and Transmission Expansion Planning with BESS-Based Virtual Transmission Lines
arXiv 2610.02674 · 2026-10-05Asterism：探索与综合分散观察为基于文献的假说与理论
Asterism: Exploring and Synthesizing Scattered Observations into Literature-Grounded Hypotheses and Theories
arXiv 2610.02673 · 2026-10-05利用矩方程从含噪Allen-Cahn电影推断本构力
Inferring constitutive forces from noisy Allen-Cahn movies with moment equations
arXiv 2610.02672 · 2026-10-05LATHE：面向基于假设的晶体编辑的语言驱动工具包
LATHE: LAnguage-driven Toolkit for Hypothesis-based crystal Editing
arXiv 2610.02671 · 2026-10-05LEAP：为LLM智能体学习高效动作提案
LEAP: Learning Efficient Action Proposals For LLM Agents
arXiv 2610.02670 · 2026-10-05从个体基模型到一般随机反应扩散方程
From Individual-Based Models to General Stochastic Reaction Diffusion Equations
arXiv 2610.02669 · 2026-10-05一种用于自动化液体处理工作站物理状态验证的被动式AI系统
A Passive AI System for Verifying Physical State on Automated Liquid Handlers
arXiv 2610.02668 · 2026-10-05区分宇宙双折射的起源：暗能量、暗物质和中微子不对称性
Distinguishing the origin of cosmic birefringence: dark energy, dark matter, and neutrino asymmetry
arXiv 2610.02667 · 2026-10-05CHASE-VLA：面向视觉-语言-动作模型的块感知尺度估计后训练量化框架
CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale Estimation
arXiv 2610.02666 · 2026-10-05大型语言连续扩散模型
Large Language Continuous Diffusion Models
arXiv 2610.02665 · 2026-10-05长时程智能体中的GHOST：跨轮次被忽视的安全约束引发的治理危害
A GHOST in Long-Horizon Agents: Governance Hazard from Overlooked Safety Constraints across Turns
arXiv 2610.02664 · 2026-10-05注意细化差距：当安全的高层机器人计划产生不安全的执行时
Mind the Refinement Gap: When Safe High-Level Robot Plans Produce Unsafe Executions
arXiv 2610.02662 · 2026-10-05AIGS：面向非平稳数据流在线表示学习的自适应增量门控系统
AIGS: Adaptive Incremental Gating System for Online Representation Learning in Non-Stationary Data Streams
arXiv 2610.02661 · 2026-10-05注释驱动的CUDA程序迁移至Tenstorrent Blackhole
Annotation-Driven Migration of CUDA Programs to Tenstorrent Blackhole
arXiv 2610.02658 · 2026-10-05旋转坐标中的光子量子化与传播子
Photon Quantization and Propagator in Rotating Coordinates
arXiv 2610.02656 · 2026-10-05数学图解：证明、直觉与人工智能
Mathematical Illustration: Proof, Intuition and AI
arXiv 2610.02655 · 2026-10-05一致性驱动的信念形成与LLM智能体中的传染人口动力学
Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents
arXiv 2610.02654 · 2026-10-05旋转中子星热X射线脉冲轮廓的改进解析扁球-施瓦西模型
A Refined Analytic Oblate--Schwarzschild Model for Thermal X-Ray Pulse Profiles of Rotating Neutron Stars
arXiv 2610.02653 · 2026-10-05RaBitQ-SSD：面向SSD驻留向量搜索的分裂码与流水线I/O
RaBitQ-SSD: Split Codes and Pipelined I/O for SSD-Resident Vector Search
arXiv 2610.02652 · 2026-10-05用于电子密度预测的等变流匹配
Equivariant Flow Matching for Electron Density Prediction
arXiv 2610.02651 · 2026-10-05
