2026-07论文中文摘要
分布偏移何时会破坏图神经网络的校准？
When does distribution shift break graph neural networks calibration?
arXiv 2607.10804 · 2026-07-14Q学习实验室：通过学习者生成的轨迹分析教授强化学习
Q-Learning Lab: Teaching Reinforcement Learning Through Learner-Generated Trace Analysis
arXiv 2607.10802 · 2026-07-14非可逆马尔可夫过程的弛豫时间
Relaxation times of non-reversible Markov processes
arXiv 2607.10801 · 2026-07-14h-Flow：通过杜布h变换实现基于灵活流的图像编辑
h-Flow: Flexible Flow-based Image Editing via Doob's h-Transform
arXiv 2607.10800 · 2026-07-14城域规模光纤网络中的量子增强物理层威胁检测
Quantum-enhanced physical-layer threat detection in metropolitan-scale fiber networks
arXiv 2607.10799 · 2026-07-14融合前的信任：用于受污染多模态RAG的QIMG-7和源感知分辨率
Trust Before Fusion: QIMG-7 and Source-Aware Resolution for Polluted Multimodal RAG
arXiv 2607.10798 · 2026-07-14用于从视频理解复杂装配动作的组合上下文微调视觉语言模型
Compositional Context Fine-Tuning Vision-Language Model for Complex Assembly Action Understanding from Videos
arXiv 2607.10797 · 2026-07-14大型视觉语言模型中的认知专家混合体
Mixture of Cognitive Experts in Large Vision-Language Models
arXiv 2607.10796 · 2026-07-14STEC：开放域多跳问答中深度搜索的证据压缩
STEC: Evidence Compression for Deep Search in Open-domain Multi-Hop QA
arXiv 2607.10795 · 2026-07-14水印技术能帮助防止大语言模型被盗用吗？
Can Watermarking Techniques Help Prevent LLM Model Stealing?
arXiv 2607.10794 · 2026-07-14分层贝叶斯求积法
Hierarchical Bayesian Quadrature
arXiv 2607.10793 · 2026-07-14MAC-Splat：用于高保真稀疏视图重建的多属性一致性
MAC-Splat: Multi-Attribute Consistency for High-Fidelity Sparse-View Reconstruction
arXiv 2607.10792 · 2026-07-14成像101：在科学计算成像上对大语言模型编码智能体进行基准测试
Imaging-101: Benchmarking LLM Coding Agents on Scientific Computational Imaging
arXiv 2607.10789 · 2026-07-14静态预充电半缓冲器异步电路中的软错误特性及加固权衡
Soft-Error Characterization and Hardening Trade-offs in Static PCHB Asynchronous Circuits
arXiv 2607.10788 · 2026-07-14检测人工智能生成的视频：视觉-语言双视角综述
Detecting AI-Generated Video: A Vision-Language Dual-View Survey
arXiv 2607.10787 · 2026-07-14构造具有规定弱轨迹的有限D'Angelo型有界伪凸域
Constructing bounded pseudoconvex domains of finite D'Angelo type with prescribed weak loci
arXiv 2607.10785 · 2026-07-14LSTrans：用于轻量级和自动心电图分类的高效知识转移
LSTrans: Efficient Knowledge Transfer for Lightweight and Automated ECG Classification
arXiv 2607.10784 · 2026-07-14仅使用低倍率组织病理学图像实现高效弱监督语义分割
Toward Efficient Weakly Supervised Semantic Segmentation Using Only Low-Magnification Histopathological Images
arXiv 2607.10783 · 2026-07-14泊松导数与泊松幂零代数的上同调
Poisson derivations and cohomology of Poisson nilpotent algebras
arXiv 2607.10782 · 2026-07-14你所需要的只是能量引导吗？用于驱动世界模型的无训练规范注入
Is Energy Guidance All You Need? Training-Free Norm Injection for Driving World Models
arXiv 2607.10781 · 2026-07-14独著作者的回归：生成式人工智能时代科学领域劳动分工的变化
Return of the solo author: The changing division of labor in science in the age of generative AI
arXiv 2607.10780 · 2026-07-14RED-Sphere：用于跨人群眼底疾病领域泛化的超球面残差边缘去偏
RED-Sphere: Hyperspherical Residual Edge Debiasing for Cross-Population Fundus Disease Domain Generalization
arXiv 2607.10777 · 2026-07-14具有变指数的适配序列空间的实插值
Real interpolation for adapted sequence spaces with variable exponents
arXiv 2607.10776 · 2026-07-14通过模式分析理解CoNiV中的化学短程有序
Understanding Chemical Short-Range Order in CoNiV via Mode Analysis
arXiv 2607.10775 · 2026-07-14考克斯特码的最小距离与译码
Minimum distance and decoding of Coxeter codes
arXiv 2607.10774 · 2026-07-14通过量子幅度估计展示二次蒙特卡罗加速：核工程示例
Demonstrating Quadratic Monte Carlo Speedup via Quantum Amplitude Estimation: Nuclear Engineering Examples
arXiv 2607.10772 · 2026-07-14使用Desbordante实现闪电般快速的匹配依赖发现
Lightning Fast Matching Dependency Discovery with Desbordante
arXiv 2607.10771 · 2026-07-14学习作为一种几何相变：深度网络中的重整化群流与各向异性对称性破缺
Learning as a Geometric Phase Transition: Renormalization Group Flow and Anisotropic Symmetry Breaking in Deep Networks
arXiv 2607.10770 · 2026-07-14Opti-Agent-Bench：在实际业务问题上对端到端优化研发智能体进行基准测试
Opti-Agent-Bench: Benchmarking End-to-End Optimization R&D Agents on Real-World Business Problems
arXiv 2607.10768 · 2026-07-14通过结合探测和对偶固定增强混合整数规划中的预求解
Enhancing Presolve in Mixed Integer Programming by Combining Probing and Dual Fixing
arXiv 2607.10767 · 2026-07-14M83 延伸紫外盘内的年轻星团
Young star clusters in the extended UV disk of M83
arXiv 2607.10766 · 2026-07-14李 - 杨哈密顿量的能隙
Spectral gap of Lee-Yang Hamiltonians
arXiv 2607.10765 · 2026-07-14一种用于具有空间干扰抑制的稀疏阵列近场波束聚焦的统一对偶框架
A Unified Dual Framework for Sparse-Array Near-Field Beam Focusing With Spatial Interference Suppression
arXiv 2607.10764 · 2026-07-14模乘法矩阵的秩
The rank of the modular multiplication matrix
arXiv 2607.10763 · 2026-07-14TOLiD：通过用于蒸馏的令牌提升弥合视觉基础模型与激光雷达预训练之间的架构差距
TOLiD: Bridging the Architecture Gap in Vision Foundation Model to LiDAR Pretraining via Token Lifting for Distillation
arXiv 2607.10762 · 2026-07-14用于漫游的三自由度切斯纳维奇模型：推导、相空间几何、NHIM 锚定分割面和漫游输运
A Three-Degree-of-Freedom Chesnavich Model for Roaming: Derivation, Phase-Space Geometry, NHIM-Anchored Dividing Surfaces, and Roaming Transport
arXiv 2607.10761 · 2026-07-14用于控制时延Kuramoto模型的高阶相互作用
Higher-order interactions for controlling time-delayed Kuramoto model
arXiv 2607.10759 · 2026-07-14用于批量蒙特卡罗中积分自相关时间预测的矩阵算子函数展开计数：二维散射链解析基准
Functional Expansion Tallies of Matrix Operators for Prediction for Integrated Autocorrelation Time in Batch Monte Carlo: an Analytic 2D Scattering Chain Benchmark
arXiv 2607.10758 · 2026-07-14奇偶性驱动的RKKY解耦与p波磁体中反常的1/R 迪拉克-莫利亚相互作用
Parity-driven RKKY decoupling and anomalous $1/R$ Dzyaloshinskii-Moriya interaction in $p$-wave magnets
arXiv 2607.10757 · 2026-07-14酉多对多市场中的医生最优稳定性
Doctor-Optimal Stability in Unitary Many-to-Many Markets
arXiv 2607.10756 · 2026-07-14当筛选产生误导时：用于可靠因果发现的稳健孟德尔随机化检验
When Screening Misleads: A Robust Mendelian Randomization Test for Reliable Causal Discovery
arXiv 2607.10755 · 2026-07-14三维激子偶极各向异性实现 CrCl₃ 中的超宽带偏振光探测
Three-dimensional excitonic dipole anisotropy enables ultrabroadband polarization photodetection in CrCl3
arXiv 2607.10752 · 2026-07-14通过拉东定理研究部分概念类的VC维数
The VC dimension of partial concept classes via Radon's theorem
arXiv 2607.10751 · 2026-07-14过滤有害行为是不够的：智能体自反决策函数中的幻影转移
Filtering Harmful Actions Isn't Enough: Phantom Transfer in Agentic SDF
arXiv 2607.10750 · 2026-07-14策略驱动的CT智能体：为临床一致的CT推理建模阶段感知诊断控制
Policy-Driven CT-Agent: Modeling Phase-Aware Diagnostic Control for Clinically Consistent CT Reasoning
arXiv 2607.10748 · 2026-07-14用于低开销多用户 MIMO 波束成形的特定站点学习
Site-Specific Learning for Low-Overhead Multi-User MIMO Beamforming
arXiv 2607.10746 · 2026-07-14超导量子比特 - 耦合器晶格中连通性引起的表面损耗代价
Connectivity-induced surface-loss penalty in superconducting qubit-coupler lattices
arXiv 2607.10743 · 2026-07-14无参数三次正则化牛顿法：精确复杂度与广义光滑性
Parameter-Free Cubic-Regularized Newton Method: Sharp Complexity and Generalized Smoothness
arXiv 2607.10741 · 2026-07-14具有最优传输注意力的多尺度卷积对多元时间序列的影响
Multi-Scale Convolution with Optimal Transport Attention Effect on Multivariate Time Series
arXiv 2607.10740 · 2026-07-14边传输不规则图
Edge transmission irregular graphs
arXiv 2607.10739 · 2026-07-14
