2026-08论文中文摘要
分界面的生成式学习
Generative Learning of Separatrices
arXiv 2608.14743 · 2026-08-18PandasCorpus：真实世界Pandas工作流与使用模式资源
PandasCorpus: A Resource of Real-World Pandas Workflows and Usage Patterns
arXiv 2608.14742 · 2026-08-18用于稀疏脑磁图源定位的二次无约束二元优化
Quadratic Unconstrained Binary Optimization for Sparse Magnetoencephalography Source Localization
arXiv 2608.14738 · 2026-08-18系统综述LLM筛选中的类别不平衡与批次效应
Class Imbalance and Batch Effects in LLM-Based Screening for Systematic Reviews
arXiv 2608.14737 · 2026-08-18不够离散：关于离散可信平台模块（dTPMs）在测量启动中的固有安全性问题
Not Discrete Enough: On the Inherent Insecurity of dTPMs for Measured Boot
arXiv 2608.14736 · 2026-08-18AccretionLink：针对属性推断的暴露控制攻击的设备端审计
AccretionLink: On-Device Auditing of Exposure-Control Attacks on Attribute Inference
arXiv 2608.14735 · 2026-08-18通过可解释神经网络揭示纳米晶体合成的尺寸决定机制
Unraveling the Size Determination Mechanism of Nanocrystal Synthesis via Interpretable Neural Networks
arXiv 2608.14734 · 2026-08-18一种用于求解偏微分方程的新型傅里叶特征网络
A Novel Fourier Feature Network for Solving Partial Differential Equations
arXiv 2608.14733 · 2026-08-18gmsEDA：基于矩阵分离的皮肤电活动信号分解
gmsEDA: Decomposition of Electrodermal Activity Signals Using Matrix Separation
arXiv 2608.14732 · 2026-08-18面向阿尔茨海默病特定识别的迁移学习的涌现：一种前瞻性方法
Emergence of Transfer Learning towards Specific Identification of Alzheimer's Disease A Prospective Approach
arXiv 2608.14731 · 2026-08-18视觉生成AI时代的知识产权保护：一项综述
IP Protection in the Era of Visual Generative AI: A Survey
arXiv 2608.14730 · 2026-08-18卷积神经网络（CNNs）是否在内部对真实图像与虚假图像的表示存在差异？隐藏层分析
Do CNNs Internally Represent Real and Fake Images Differently? A Hidden-Layer Analysis
arXiv 2608.14729 · 2026-08-18感知长尾的Top-k在线策略蒸馏
Tail-Aware Top-$k$ On-Policy Distillation
arXiv 2608.14728 · 2026-08-18边缘端低成本两阶段织物缺陷检测
Low Cost Two-Stage Fabric Defect Detection at the Edge
arXiv 2608.14727 · 2026-08-18卡萨-阿尔韦罗猜想的下降集障碍
A descent-set obstruction for the Casas-Alvero conjecture
arXiv 2608.14726 · 2026-08-18用于因果充分可解释性的空间注意力噪声掩码
Spatial Attention Noise Masking for Causally Sufficient Interpretability
arXiv 2608.14725 · 2026-08-18面向吉隆坡城市交通的隐私保护数据集构建：结合空间车辆上下文过滤的接地视觉-语言检测
Privacy-Preserving Dataset Curation for Kuala Lumpur Urban Traffic: Grounded Vision-Language Detection with Spatial Vehicle-Context Filtering
arXiv 2608.14724 · 2026-08-18一种用于多临床站点基于心电图检测左心室收缩功能障碍的视觉Transformer
A Vision Transformer for ECG-Based Detection of Left Ventricular Systolic Dysfunction Across Multiple Clinical Sites
arXiv 2608.14723 · 2026-08-18用于多视角视网膜眼底成像中卒中检测的编织视觉Transformer
Braided Vision Transformer for Stroke Detection in Multi-view Retinal Fundus Imaging
arXiv 2608.14722 · 2026-08-18AeroGround：用于空-地协同推理的综合基准
AeroGround: A Comprehensive Benchmark for Aerial-Ground Collaborative Reasoning
arXiv 2608.14721 · 2026-08-18基于多智能体闭环推理的多模态光谱有机结构解析
Multi-Agent Closed-Loop Reasoning for Organic Structure Elucidation from Multimodal Spectra
arXiv 2608.14720 · 2026-08-18DeCo-MIL：面向长尾全幻灯片图像分析的去偏反事实推理
DeCo-MIL: Debiased Counterfactual Reasoning for Long-Tailed Whole Slide Image Analysis
arXiv 2608.14719 · 2026-08-18VideoGAIA：面向通用人工智能助手的智能体视频理解基准
VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understanding
arXiv 2608.14718 · 2026-08-18共享集合解码器中的局部增益与固定分配集合损失
Local Gains and Fixed-Assignment Set Losses in Shared Set Decoders
arXiv 2608.14717 · 2026-08-18用于分岔和速率诱导 tipping 的 Koopman 早期预警信号
Koopman early warning signals for bifurcation and rate-induced tipping
arXiv 2608.14716 · 2026-08-18基于格林函数方法的、在(μ,ν)-二分下具无界非线性项的光滑非自治拓扑等价问题
A Green Function Approach to Smooth Nonautonomous Topological Equivalence with Unbounded Nonlinearities under $(μ,ν)$--Dichotomies
arXiv 2608.14715 · 2026-08-18SpotlessGS：面向机器人感知的动态光照下可重光照三维高斯溅射技术
SpotlessGS: Relightable 3D Gaussian Splatting under Dynamic Illumination for Robotic Perception
arXiv 2608.14713 · 2026-08-18你的注意力指标回答的是哪个问题？注意力行作为组成数据
Which Question Is Your Attention Metric Answering? Attention Rows as Compositional Data
arXiv 2608.14712 · 2026-08-18超越Pass@k：衡量智能体代码生成的可靠性与安全性
Beyond Pass@k: Measuring Reliability and Security of Agentic Code Generation
arXiv 2608.14711 · 2026-08-18Path2ST：面向空间转录组学的基于细胞-组织层级的跨模态转换方法
Path2ST: Hierarchical Cell-Tissue Grounded Cross-Modal Translation for Spatial Transcriptomics
arXiv 2608.14710 · 2026-08-18用于实时5G信道估计的硬件在环相位感知CNN
Hardware-in-the-Loop Phase-Aware CNN for Real-Time 5G Channel Estimation
arXiv 2608.14709 · 2026-08-18PE-CSNet：一种具有可学习基于块的稀疏表示的等变网络架构
PE-CSNet: An equivariant network architecture with learnable patch-based sparse representation
arXiv 2608.14708 · 2026-08-18分层多智能体系统中基于语义不确定性的协调策略
Semantic Uncertainty-Guided Orchestration in Hierarchical Multi-Agent Systems
arXiv 2608.14707 · 2026-08-18均衡强迫：无需噪声条件的自适应视频生成
Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning
arXiv 2608.14706 · 2026-08-18深度学习图像分类器超参数优化的交叉验证方法研究
On Cross-Validation for Hyperparameter Optimization of Deep Learning Image Classifiers
arXiv 2608.14705 · 2026-08-18保持邻近性的神经细分（Proximity-Preserving Neural Subdivision）
Proximity-Preserving Neural Subdivision
arXiv 2608.14704 · 2026-08-18引力场中宇称不守恒的证据
Evidence for parity violation in gravitational fields
arXiv 2608.14703 · 2026-08-18Deep Analog：基于参考条件3D LUT的开放集胶片模拟
Deep Analog: Open-Set Film Emulation with Reference-Conditioned 3D LUTs
arXiv 2608.14702 · 2026-08-18眼周软生物特征：综述及其在多媒体取证与虚假信息检测中的应用
Periocular Soft Biometrics: A Survey and Applications to Multimedia Forensics and Disinformation Detection
arXiv 2608.14701 · 2026-08-18Xemo-Talker：为音频驱动的说话人像合成显式解锁情感
Xemo-Talker: Unlock Emotions Explicitly for Audio-Driven Talking Portrait Synthesis
arXiv 2608.14700 · 2026-08-18COLCS流形上哈密顿系统的可积性
Integrability of Hamiltonian systems on COLCS Manifold
arXiv 2608.14699 · 2026-08-18用于环境监测和嵌入式太阳能预测的低成本物联网设备，具备设备端增量学习功能
A Low-Cost IoT Device for Environmental Monitoring and Embedded Solar Forecasting with On-Device Incremental Learning
arXiv 2608.14698 · 2026-08-18同步对数几率调控：面向真实场景的隐写术
Synchronized Logit Steering: Real-world Steganography
arXiv 2608.14697 · 2026-08-18可精确求解的胜率模型中的校准-杠杆权衡
The Calibration-Leverage Tradeoff in Exactly Solvable Win-Probability Models
arXiv 2608.14696 · 2026-08-18面向AI原生6G网络的无线基础模型综合综述
A Comprehensive Survey of Wireless Foundation Models for AI-Native 6G Networks
arXiv 2608.14694 · 2026-08-18基于指令微调的自然语言规则的领域无关文本脱敏
Domain Agnostic Text Redaction from Natural Language Rules using Instruction Tuning
arXiv 2608.14693 · 2026-08-18识别个性化生成式AI系统中的危害需要在交互层面开展以用户为中心的审计
Identifying Harm in Personalized, Generative AI Systems Requires User-Centered Auditing at the Interaction Level
arXiv 2608.14692 · 2026-08-18量子捷径：复相态动力学减少序列模型的优化步数
The Quantum Shortcut: Complex Phase-State Dynamics Reduce the Optimization Steps of Sequence Models
arXiv 2608.14691 · 2026-08-18若干图运算的双服务器控制数
The Dual-Server Domination Number of Some Graph Operations
arXiv 2608.14690 · 2026-08-18非等变格罗莫夫环面的存在性
The Existence of Non-Equivariant Gromov Tori
arXiv 2608.14688 · 2026-08-18
