2026-10论文中文摘要
MedicalHarness：医疗任务上LLM与智能体框架的受控评估
MedicalHarness: A Controlled Evaluation of LLMs and Agent Harnesses on Medical Tasks
arXiv 2610.05778 · 2026-10-06从生产轨迹中挖掘智能体技能
Mining Agent Skills from Production Traces
arXiv 2610.05777 · 2026-10-06关于 Kimberling 关于数组 $\lfloor k\varphi^n\rfloor$ 的三个猜想
On three conjectures of Kimberling concerning the array $\lfloor kφ^n\rfloor$
arXiv 2610.05776 · 2026-10-06InteractionBench：流式视频系统的实时交互基准
InteractionBench: A Real-Time Interaction Benchmark for Streaming Video Systems
arXiv 2610.05775 · 2026-10-06AdaSpark: 具有在线学习的自适应DSpark用于树验证与N-gram填充
AdaSpark: Adaptive DSpark with Online Learning for Tree Verification and N-gram Fill
arXiv 2610.05774 · 2026-10-06视觉假体在虚拟现实中的智能导航：基于优先级的场景翻译与路径引导的端到端框架
Smart Navigation for Visual Prostheses in Virtual Reality: An End-to-End Framework for Priority-Based Scene Translation and Path Guidance
arXiv 2610.05772 · 2026-10-06可控道路标线生成
Controllable Road Marking Generation
arXiv 2610.05771 · 2026-10-06自由形态灯罩的计算设计
Computational Design of Free-Form Lampshades
arXiv 2610.05770 · 2026-10-06关系合成：面向拟音与检索增强音频生成的结构介导拼接合成
Relational Synthesis: Structure-Mediated Concatenative Synthesis for Foley and Retrieval-Augmented Audio Generation
arXiv 2610.05768 · 2026-10-06参数单调非线性与神经逼近的全局误差估计器
Global error estimators for parametric monotone nonlinearities and neural approximations
arXiv 2610.05767 · 2026-10-06基于能量约束的对抗量子敌手的认证随机性生成
Certified Randomness Generation against Quantum Adversaries via Energy Constraints
arXiv 2610.05766 · 2026-10-06零样本语义通信在软件定义无线电上的实现
Implementation of Zero-shot Semantic Communication on Software Defined Radio
arXiv 2610.05764 · 2026-10-06理想流体能量-动量张量的度规变分及其在宇宙学和中子星中的应用
Metric Variation of the Energy-Momentum Tensor of a Perfect Fluid and Its Applications to Cosmology and Neutron Stars
arXiv 2610.05763 · 2026-10-06二维圆柱-翼型相互作用中基于同步理论自编码器的振荡死亡研究
Studying oscillation death in two-dimensional cylinder-airfoil interactions with synchronization-theoretic autoencoder
arXiv 2610.05762 · 2026-10-06镜像约束下的非对称金光栅光学霍尔整流：Edelstein转换与相位种子Kerr四波混频不稳定性
Mirror-Constrained Optical Hall Rectification in Asymmetric Gold Gratings:\\ Edelstein Conversion and a Phase-Seeded Kerr Four-Wave Mixing Instability
arXiv 2610.05761 · 2026-10-06关于${\cal N}=8$超引力中天体软对称代数的进一步研究
More on the Celestial Soft Symmetry Algebra in the ${\cal N}=8$ Supergravity
arXiv 2610.05760 · 2026-10-06一类保持函数性质的神经网络算子及其在调制信号去噪中的应用
A Class of Function-Preserving Neural Network Operators with Applications to Modulated Signal Denoising
arXiv 2610.05759 · 2026-10-06一种用于稀疏点云补全的三维反向投影方法及其在高速列车车头重建中的应用
A Three-Dimensional Reverse-Projection Method for Sparse Point Cloud Completion and Its Application to High-Speed Train Nose Reconstruction
arXiv 2610.05758 · 2026-10-06人机协同神经符号漂移预判用于可靠视觉SLAM
Human-in-the-Loop Neuro-Symbolic Drift Anticipation for Reliable Visual SLAM
arXiv 2610.05757 · 2026-10-06建筑工地安全帽合规检测的视觉赋能系统
Vision-enabled detection of safety helmet compliance in construction zones
arXiv 2610.05756 · 2026-10-06带相互作用的路径空间最优输运：动力学方程与程函结构
Path-Space Optimal Transport with Interactions: Kinetic Equations and Eikonal Structure
arXiv 2610.05754 · 2026-10-06有界Lipschitz区域上分数阶Dirichlet问题的最优全局Sobolev估计
Optimal Global Sobolev Estimates for Fractional Dirichlet Problems in Bounded Lipschitz Domains
arXiv 2610.05753 · 2026-10-06一种基于哈密顿量的高效量子算法用于对称群的特征标
An efficient Hamiltonian-based quantum algorithm for characters of the symmetric group
arXiv 2610.05752 · 2026-10-06物理驱动的目标条件深度波束形成用于平面波超声成像中的自适应分辨率-对比度控制
Physics-Grounded Objective-Conditioned Deep Beamforming for Adaptive Resolution-Contrast Control in Plane-Wave Ultrasound Imaging
arXiv 2610.05751 · 2026-10-06超越语义相似性：面向复杂任务的智能体检索的性能与成本
Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks
arXiv 2610.05750 · 2026-10-06一种融合地标识别与深度学习技术的跌倒检测系统新设计
A new design of a fall detection system integrating landmark identification and deep learning techniques
arXiv 2610.05749 · 2026-10-06MOLT：面向LLM服务的机会式微调细粒度GPU内存共享系统
MOLT: A Fine-Grained GPU Memory Sharing System for LLM Serving with Opportunistic Fine-Tuning
arXiv 2610.05748 · 2026-10-06未过期计划：加速扩散策略的免费监视器
The Unexpired Plan: A Free Monitor for Accelerated Diffusion Policies
arXiv 2610.05747 · 2026-10-06学习用神经网络和序列二次规划细化求解混合整数非线性规划
Learning to Solve Mixed-Integer Nonlinear Programming with Neural Networks and Sequential Quadratic Programming Refinement
arXiv 2610.05746 · 2026-10-06超越分布内保持：通过脆弱性导向微调恢复量化VLA的泛化能力
Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented Tuning
arXiv 2610.05745 · 2026-10-06CIPHER-MoE：在万亿级MoE训练中平衡效率与路由保真度
CIPHER-MoE: Balancing Efficiency and Routing Fidelity in Trillion-Scale MoE Training
arXiv 2610.05744 · 2026-10-06稳健局部优化的正确实现
Robust Local Optimization Done Right
arXiv 2610.05743 · 2026-10-06一种用于极大单调包含问题的非精确 Halpern 加速预条件广义近端点算法
An Inexact Halpern-accelerated Preconditioned Generalized Proximal Point Algorithm for the Maximal Monotone Inclusion Problem
arXiv 2610.05742 · 2026-10-06精确多元分布信度的Dirichlet混合成员模型
A Dirichlet Mixed-Membership Model for Exact Multivariate Distributional Credibility
arXiv 2610.05741 · 2026-10-06HLA-WM：用于长时程视频世界模型的混合线性注意力
HLA-WM: Hybrid Linear Attention for Long-Horizon Video World Models
arXiv 2610.05739 · 2026-10-06三变量正态乘积分布的降维：一种基于条件期望的高效数值算法
Dimension Reduction for the Trivariate Normal Product Distribution: An Efficient Numerical Algorithm via Conditional Expectation
arXiv 2610.05738 · 2026-10-06Hamilton-Jacobi 方程的病理粘性解
Pathological viscosity solutions of Hamilton--Jacobi equations
arXiv 2610.05736 · 2026-10-06稀疏典型相关分析的最小最大与自适应迁移学习
Minimax and Adaptive Transfer Learning for Sparse Canonical Correlation Analysis
arXiv 2610.05735 · 2026-10-06FreeSpeed：生成式机器人策略的无训练速度控制
FreeSpeed: Training-Free Speed Control for Generative Robot Policies
arXiv 2610.05734 · 2026-10-06PACMI：面向长期LLM智能体的溯源感知级联内存失效机制
PACMI: Provenance-Aware Cascading Memory Invalidation for Long-Term LLM Agents
arXiv 2610.05732 · 2026-10-06T-JEPA：一种用于学习更好遥感表示的时间联合嵌入预测架构
T-JEPA: A Temporal Joint-Embedding Predictive Architecture for Learning Better Remote Sensing Representations
arXiv 2610.05731 · 2026-10-06离散选择LQG平均场博弈中的对称性破缺
Symmetry-breaking in a discrete-choice LQG mean field game
arXiv 2610.05730 · 2026-10-06测试$\Lambda$LTB作为动力学暗能量的替代方案
Testing $Λ$LTB as an alternative to dynamical dark energy
arXiv 2610.05729 · 2026-10-06从研究空白到理论机遇：面向理论导向的生成式AI用于研究机遇评估
From Research Gaps to Theoretical Opportunities: Theory-Oriented GenAI for Research Opportunity Evaluation
arXiv 2610.05728 · 2026-10-06Bakamjian--Thomas构造与赝标量跃迁中的光前零模：与协变Bethe--Salpeter模型的比较
Bakamjian--Thomas construction and light-front zero modes in pseudoscalar transitions: A comparison with the covariant Bethe--Salpeter model
arXiv 2610.05727 · 2026-10-06FreSia：面向多元时间序列分析的频率-语义实例化与对齐
FreSia: Frequency-Semantic Instantiation and Alignment for Multivariate Time Series Analysis
arXiv 2610.05726 · 2026-10-06理想光滑集合与实数积和指数的显式上界
Ideal-Smooth Sets and an Explicit Upper Bound for the Real Sum-Product Exponent
arXiv 2610.05725 · 2026-10-06使用量化数据的线性系统数据驱动控制
Data-driven control of linear systems using quantized data
arXiv 2610.05724 · 2026-10-06利用物理约束注意力神经算子从不完整观测中推断含未知参数的耦合系统中的物理场
Inferring physical fields in coupled systems with unknown parameters from incomplete observations using physics-constrained attentive neural operators
arXiv 2610.05723 · 2026-10-06正则图生成森林数量的一个尖锐上界
A sharp upper bound on the number of spanning forests of regular graphs
arXiv 2610.05722 · 2026-10-06
