2026-10论文中文摘要
SoRoMoX：快速、可微分且可并行化的软体机器人模型
SoRoMoX: Fast, Differentiable, and Parallelizable Soft Robot Models
arXiv 2608.06650 · 2026-10-01无需维度参数的多对数量子影子层析成像：基于序贯优良测量
Dimension-Free Polylogarithmic Quantum Shadow Tomography
arXiv 2608.06345 · 2026-10-01SPT-3G D1：用于原初引力波搜寻的前景鲁棒引力透镜模板
SPT-3G D1: Foreground-Robust Lensing Templates for Primordial Gravitational Wave Searches
arXiv 2608.06343 · 2026-10-01带条件查询的假设检验：可学习性与交互的价值
Hypothesis Testing with Conditional Queries: Learnability and the Value of Interaction
arXiv 2608.06262 · 2026-10-01通过最优症候测量时序实现量子存储器中指数级的逻辑错误降低
Exponential logical-error reduction in quantum memories via optimal syndrome-measurement timing
arXiv 2608.06242 · 2026-10-01EnvACE：通过世界预演内化环境动态以实现智能体强化学习
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
arXiv 2608.06197 · 2026-10-01区间的施赖尔集、超级施赖尔集与卡特兰数
Schreier Sets of Intervals, Super-Schreier Sets, and Catalan Numbers
arXiv 2608.06076 · 2026-10-01单一排序，任意预算：用于长视频理解的套娃式证据到上下文帧选择框架
One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding
arXiv 2608.05707 · 2026-10-01omni-macos：在Apple Silicon上运行的端侧全模态搜索系统
omni-macos: On-Device Omni-Modal Search on Apple Silicon
arXiv 2608.05543 · 2026-10-01渐进式适应中的最优训练时间缩放
Optimal Training-Time Scaling in Gradual Adaptation
arXiv 2608.04927 · 2026-10-01防御性悲观主义：增长、文化与证据的存续
Defensive Pessimism: Growth, Culture, and the Survival of Evidence
arXiv 2608.04787 · 2026-10-01结合前缀树约束的令牌预测与层级感知语义对齐的HS编码预测
Trie Constraints and Hierarchy-Aware Semantic Alignment for HS Code Prediction with Small Language Models
arXiv 2608.04464 · 2026-10-01LegalPincite：多级法律信息检索数据集
LegalPincite: Multi-level Legal Information Retrieval Dataset
arXiv 2608.03756 · 2026-10-01GPTKB 2.0：从大语言模型直接构建消歧知识库
Constructing Disambiguated Knowledge Bases from Large Language Models at Scale
arXiv 2608.03729 · 2026-10-01AccelNet：通过笛卡尔矩分解实现多项式角度描述符的精确后向兼容加速
AccelNet: Exact backward-compatible acceleration of polynomial angular descriptors through Cartesian moment factorization
arXiv 2608.03280 · 2026-10-01关系先验作为基于大语言模型的多智能体系统中的收敛压力
Relational Priors as Convergence Pressure in LLM-Based Multi-Agent Systems
arXiv 2608.03239 · 2026-10-01三次超曲面的Oka补空间
Elliptic complements of cubic hypersurfaces
arXiv 2608.02413 · 2026-10-01RamanPFN：基于表格基础模型学习拉曼光谱结构
RamanPFN: learning from Raman spectral structure with a tabular foundation model
arXiv 2608.02157 · 2026-10-01基于空间掩码与通道融合的深度多模态融合检测
Deep Multimodal Fusion Detection through Spatial Mask and Channel Competition
arXiv 2608.02092 · 2026-10-01一个QK通道，多个源：防范低精度注意力崩溃
One QK Channel, Many Sources: Tracing Low-Precision Attention Collapse
arXiv 2608.02091 · 2026-10-01AGNI：面向磁约束聚变装置的可微分理想磁流体动力学（MHD）稳定性求解器与优化器
AGNI: A differentiable MHD stability solver & optimizer for magnetic confinement fusion devices
arXiv 2608.01750 · 2026-10-01年轻重复快速射电暴周围超新星遗迹环境的传播诊断 I. 源局域色散量的流体动力学演化
Propagation Diagnostics of Supernova Remnant Environments around Young Repeating Fast Radio Bursts. I. Hydrodynamic Evolution of the Source-local Dispersion Measure
arXiv 2608.01342 · 2026-10-01HP-JEPA：用于多分辨率图联合嵌入预测学习的层次划分方法
HP-JEPA: Hierarchical Partitioning for Multi-Resolution Graph Joint-Embedding Predictive Learning
arXiv 2608.00491 · 2026-10-01四元数Kittaneh数值半径不等式
Quaternionic Kittaneh Numerical Radius Inequalities
arXiv 2608.00020 · 2026-10-01带奇异激活函数的无限宽神经网络的Radon测度表示
Radon Measure Representations for Infinite-Width Neural Networks with Singular Activations
arXiv 2607.29258 · 2026-10-01关于信用归属与研究软件：来自格点量子色动力学的案例研究
On credit attribution and research software: A case study from lattice QCD
arXiv 2607.28444 · 2026-10-01超越改写：书籍级组织提升训练中合成教科书数据的质量
Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training
arXiv 2607.28109 · 2026-10-01AgentSnare：学习延迟、转移和瓦解自主渗透智能体
AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents
arXiv 2607.26998 · 2026-10-01随机超图匹配的稳定性 II：加权匹配、路由与批量到达
Stability in stochastic hypergraph matching II: weights, batch arrivals, and continuous time
arXiv 2607.26894 · 2026-10-01对称构型与实值函数的HRT猜想
The HRT Conjecture for Symmetric Configurations and Real-Valued Functions
arXiv 2607.26878 · 2026-10-01用于多量子比特最优控制中高效梯度评估的解析级数展开
Analytical Series Expansion for Efficient Gradient Evaluation in Multi-Qubit Optimal Control
arXiv 2607.26867 · 2026-10-01基于反对称化分子动力学研究$^{29}$Cl与$^{29}$Mg之间由入侵者驱动的镜像能量差
Intruder-driven mirror energy differences between $^{29}$Cl and $^{29}$Mg studied with antisymmetrized molecular dynamics
arXiv 2607.26546 · 2026-10-01关于NIP群及其Ellis群的若干结果
Some results on NIP groups and their Ellis groups
arXiv 2607.26265 · 2026-10-01关于边围长序列的可实现性
On the Realizability of Edge-Girth Sequences
arXiv 2607.25629 · 2026-10-01ARCHER：用于可执行法规的智能规则与合规框架
ARCHER: Agentic Rule and Compliance Harness for Executable Regulations
arXiv 2607.25566 · 2026-10-01用三路径分数量子霍尔干涉仪测试边缘手性
Probing quantum Hall edge chirality and the anyonic exchange angle with a three-path interferometer
arXiv 2607.24451 · 2026-10-01随机超图匹配中的稳定性I：充要条件
Stability in stochastic hypergraph matching I: necessary and sufficient criteria
arXiv 2607.23778 · 2026-10-01多变量阿尔 - 萨拉姆 - 卡尔itz 多项式的双线性生成函数及其应用
Bilinear generating functions of the multivariable Al-Salam-Carlitz polynomials and applications
arXiv 2607.23104 · 2026-10-01个性化多模态大语言模型中的群体偏好崩溃
Group Preference Collapse in Personalized Multimodal Large Language Models
arXiv 2607.22603 · 2026-10-01Al-Zn合金晶界扩散对烧结NdFeB磁体磁性和微结构的影响
Effect of Al-Zn alloy wafer grain boundary diffusion on the magnetism and microstructure of sintered NdFeB magnets
arXiv 2607.21870 · 2026-10-01环肽集合上的图学习：分子集合建模研究
EnsembleEGNN: Set-Based Graph Learning for Thermodynamic Ensembles of Cyclic Peptides
arXiv 2607.21561 · 2026-10-01零流双样本检验
Zero-Flow Two-Sample Tests
arXiv 2607.21542 · 2026-10-01骨架弦性
Skeleton Chordalities
arXiv 2607.21166 · 2026-10-01具有恒定谱隙的随机酉电路
Random unitary circuits with constant spectral gap
arXiv 2607.20919 · 2026-10-012024年爆发期间Be/X射线双星SXP 5.05中的星际盘与X射线变异性
Circumstellar Disc and X-ray Variability in the Be/X-ray Binary SXP 5.05 During its 2024 Outburst
arXiv 2607.19373 · 2026-10-01利用社交属性增强关系建模以进行社交媒体人气预测
Enhancing Relation Modeling with Social Attributes for Social Media Popularity Prediction
arXiv 2607.19200 · 2026-10-01对比策略蒸馏
Contrastive On-Policy Distillation
arXiv 2607.19046 · 2026-10-01使用微调的语言模型识别英国警方事件日志中的脆弱性指标
Using Fine-Tuned LLMs to Identify Indicators of Vulnerability in UK Police Incident Logs
arXiv 2607.18446 · 2026-10-01RoboHarness：用于长期规划的异构机器人策略的内存驱动编排
RoboHarness: Memory-Driven Orchestration of Heterogeneous Robot Policies for Long-Horizon Planning
arXiv 2607.18060 · 2026-10-01关于两步幂零洛伦兹自然约化李群的结构
On the structure of $2$-step nilpotent Lorentzian naturally reductive Lie groups
arXiv 2607.18017 · 2026-10-01
