2026-07论文中文摘要
影响你论文的影响力有多难？
How Hard Is It to Impact the Impact of Your Paper?
arXiv 2607.22737 · 2026-07-28评估领域差距：视频胶囊内镜领域转移下的模型选择不稳定性
Benchmarking the Domain Gap: Model Selection Instability Under Domain Shift in Video Capsule Endoscopy
arXiv 2607.22736 · 2026-07-28用于30米晴空陆地表面温度无间隙重建的快速傅里叶卷积生成对抗网络
Fast Fourier Convolutional GAN for 30 m Clear-Sky Land Surface Temperature Gap-Free Reconstruction
arXiv 2607.22734 · 2026-07-28用于脑电图运动想象分类的生成式增强：具有循环一致解码器优化的类条件变分自编码器
Generative Augmentation for EEG Motor Imagery Classification: A Class-Conditional VAE with Cycle-Consistent Decoder Refinement
arXiv 2607.22733 · 2026-07-28大语言模型游戏智能体中的空间推理：因果上下文和多步规划的影响
Spatial Reasoning in LLM Game Agents: Impact of Causal Context and Multi-Step Planning
arXiv 2607.22732 · 2026-07-28室内环境下无校准的3D多摄像机人体跟踪
Calibration-Free 3D Multi-Camera People Tracking for Indoor Environment
arXiv 2607.22731 · 2026-07-28圆动力学磁输运中的四阶闭合阻碍与手征非局域性
Fourth-order closure obstruction and chiral nonlocality in circular kinetic magnetotransport
arXiv 2607.22730 · 2026-07-28睁开模型之眼：视频与上下文感知的多模态反馈预测
Open Your Model's Eyes: Video and Context-Aware Multimodal Backchannel Prediction
arXiv 2607.22729 · 2026-07-28CrossSpine：具有解剖学先验知识的多尺度跨序列注意力机制用于自动 Pfirrmann 分级
CrossSpine: Multi-scale Cross-sequence Attention with Anatomical Priors for Automated Pfirrmann Grading
arXiv 2607.22728 · 2026-07-28可信医学分割：临床图像退化下的不确定性感知U-Net评估
Trustworthy Medical Segmentation: Uncertainty-Aware U-Net Evaluation Under Clinical Image Degradation
arXiv 2607.22727 · 2026-07-28PCA：用于快速视频大语言模型的持久性感知压缩与聚合
PCA: Persistence-Aware Compression and Aggregation for Fast Video Large Language Models
arXiv 2607.22726 · 2026-07-28基于深度学习的激光散斑材料分类中结构保持对数据增强的控制
Structural Preservation Governs Data Augmentation in Deep Learning-Based Laser Speckle Material Classification
arXiv 2607.22725 · 2026-07-28用于长期代理任务的进度条件分组策略优化
Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks
arXiv 2607.22724 · 2026-07-28通过分类引导的大型视觉语言模型从文档中提取视觉信息
Visual Information Extraction from Documents via Classification-Guided Large Vision-Language Models
arXiv 2607.22723 · 2026-07-28一种新型对抗样本：衡量人类与模型的差距及其与分布外检测的关系
A New Kind of Adversarial Example: Measuring the Human-Model Gap, and Its Relationship to OOD Detection
arXiv 2607.22722 · 2026-07-28用于精神分裂症认知康复的交互式视觉语言平台
An Interactive Vision Language Platform for Cognitive Remediation in Schizophrenia
arXiv 2607.22721 · 2026-07-28γ-桥：一种外观参数化扩散桥
$γ$-Bridge: A Look-Parametric Diffusion Bridge
arXiv 2607.22719 · 2026-07-28DAMamba-UNet3D：一种用于3D医学图像分割的参数高效的Mamba状态空间U-Net，采用动态自适应扫描
DAMamba-UNet3D: A Parameter-Efficient Mamba State Space U-Net with Dynamic Adaptive Scan for 3D Medical Image Segmentation
arXiv 2607.22718 · 2026-07-28TOM-GS：通过静态3D高斯的时间不透明度调制实现可编辑视频表示
TOM-GS: Editable Video Representation via Temporal Opacity Modulation of Static 3D Gaussians
arXiv 2607.22717 · 2026-07-28视觉令牌压缩增强多模态大语言模型的鲁棒性
Visual Token Compression Enhances Robustness of MLLMs
arXiv 2607.22716 · 2026-07-28面向儿童的AIGC视频风险审查：一个基准和知识支持的迭代推理框架
Child-Oriented AIGC Video Risk Reviewing: A Benchmark and Knowledge-Supported Iterative Reasoning Framework
arXiv 2607.22715 · 2026-07-28用于嵌入式汽车系统的优化RetinaNet架构的实时语义分割
Real-Time Semantic Segmentation with Optimized RetinaNet Architectures for Embedded Automotive Systems
arXiv 2607.22714 · 2026-07-28CORVUS：通过底层同步实现大语言模型编码代理的上下文优化与缩减
CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents
arXiv 2607.22711 · 2026-07-28StepX-Edge：一种通过架构-训练-部署协同设计的端侧用户界面视觉语言模型
StepX-Edge: An On-Device UI Vision-Language Model via Architecture-Training-Deployment Co-Design
arXiv 2607.22708 · 2026-07-28LowAux-RDNet：用于单图像反射去除的具有场景平衡真实世界训练的低通残差监督
LowAux-RDNet: Low-Pass Residual Supervision with Scene-Balanced Real-World Training for Single-Image Reflection Removal
arXiv 2607.22707 · 2026-07-28MPR-CiteG：通过多组合检索和引用基础生成增强RAG
MPR-CiteG: Enhancing RAG with Multi-Portfolio Retrieval and Citation-Grounded Generation
arXiv 2607.22706 · 2026-07-28EditCLEVR：用于以对象为中心表示的组合忠实性的配对场景干预基准测试
EditCLEVR: A Paired-Scene Intervention Benchmark for Compositional Faithfulness of Object-Centric Representations
arXiv 2607.22705 · 2026-07-28托卡马克偏滤器中中性粒子发射断层扫描的可见光成像诊断：基于高效Transformer的替代模型
Visible-Light Imaging Diagnosis of Neutral Particle Emission Tomography in the Tokamak Divertor: An Efficient Transformer-based Surrogate Model
arXiv 2607.22704 · 2026-07-28MIME：多模态交互式运动编码器
MIME: Multimodal Interactive Motion Encoder
arXiv 2607.22702 · 2026-07-28非线性期刊声望归一化生产力：定义与度量
Nonlinear Journal Prestige Normalized Productivity: Defining and Measuring It
arXiv 2607.22701 · 2026-07-28RoleMix：通过语义令牌化统一顺序和非顺序特征以进行点击后转化率预测
RoleMix: Unifying Sequential and Non-Sequential Features via Semantic Tokenization for Post-Click Conversion Rate Prediction
arXiv 2607.22700 · 2026-07-28FogDrive：用于分级雾天感知的多模态合成驾驶数据集
FogDrive: A Multi-Modal Synthetic Driving Dataset for Perception under Graded Fog
arXiv 2607.22698 · 2026-07-28测试时覆盖：用于部署感知学习的测试条件数据管理
Test-Time Coverage: Test-Conditioned Data Curation for Deployment-Aware Learning
arXiv 2607.22697 · 2026-07-28MegaSlide-DiT：用于高效视频扩散的以内存为中心的自适应和可变形局部注意力
MegaSlide-DiT: Memory-Centric Adaptation and Deformable Local Attention for Efficient Video Diffusion
arXiv 2607.22696 · 2026-07-28全景监控：基于个人身份信息的自然主义输出令牌集合，用于研究大语言模型上下文窗口内的隐私泄露
PANOPTICON: A PII-Based Assemblage of Naturalistic Output Tokens for Investigating Privacy Leakage Within LLM Context Window
arXiv 2607.22695 · 2026-07-28贝叶斯重复惩罚：一种用于扭转自回归语言模型中注意力崩溃的有原则的相邻条件框架
Bayesian Repetition Penalty: A Principled Adjacent-Conditional Framework for Reversing Attention Collapse in Autoregressive Language Models
arXiv 2607.22694 · 2026-07-28生成式人工智能心理健康支持的风险治理：一种多轮安全架构
Risk Governance for Generative AI Mental Health Support: A Multi-Turn Safety Architecture
arXiv 2607.22692 · 2026-07-28HiLLTS：用于可持续交通的零样本分层大语言模型引导的交通信号控制
HiLLTS: Zero-Shot Hierarchical LLM-Guided Traffic Signal Control for Sustainable Transportation
arXiv 2607.22691 · 2026-07-28超越顺序交互：GUI 智能体并行执行与协调的基准测试
Beyond Sequential Interaction: Benchmarking Parallel Execution and Coordination for GUI Agents
arXiv 2607.22689 · 2026-07-28协同控制：大语言模型智能体的控制与模型权重协同进化
Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents
arXiv 2607.22688 · 2026-07-28图中的超级联盟数
Super Coalition Number in Graphs
arXiv 2607.22686 · 2026-07-28基于物理信息神经网络的格罗斯-皮塔耶夫斯基方程和非线性薛定谔方程孤子解框架
PINN-Based Framework for Soliton Solutions of Gross Pitaevskii and Nonlinear Schrodinger Equations
arXiv 2607.22685 · 2026-07-28迈向关联分数：元数据缺口限制学术人工智能归因
Towards Nexus-Score: Metadata Gaps Limit Scholarly AI Attribution
arXiv 2607.22684 · 2026-07-28Imprompt：一种用于提示编程的语言框架
Imprompt: A Language Framework for Prompt Programming
arXiv 2607.22683 · 2026-07-28多智能体自动研究系统的词汇表
A Vocabulary for Multi-Agent Automated Research Systems
arXiv 2607.22682 · 2026-07-28从同行评审细微差别到最佳实践
From peer review nuances to best practices
arXiv 2607.22681 · 2026-07-28DOSA：一种用于长文档结构分析的树引导自回归框架
DOSA: A Tree-Guided, Self-Regressive Framework for Long Document Structure Analysis
arXiv 2607.22679 · 2026-07-28凸化平均场控制：一种占用测度和弗兰克 - 沃尔夫方法
Convexifying Mean-Field Control: An Occupation-Measure and Frank-Wolfe Approach
arXiv 2607.22678 · 2026-07-28SetGo：科学人工智能数据集的元数据就绪性
SetGo: Metadata Readiness for Scientific AI Datasets
arXiv 2607.22677 · 2026-07-28基于二次无约束二进制优化的自动取款机现金补充调度优化框架
A QUBO-Based Optimization Framework for ATM Cash Replenishment Scheduling
arXiv 2607.22675 · 2026-07-28
