2026-07论文中文摘要
滑动级主动学习减轻苏木精-伊红染色图像的标注负担
Slide-Level Active Learning Reduces Annotation Burden in H&E images
arXiv 2607.09831 · 2026-07-14利用自学习视觉特征跟踪间歇性粒子
Tracking Intermittent Particles with Self-Learned Visual Features
arXiv 2607.09829 · 2026-07-14锥束CT在具有挑战性的采集设置下的可微变移位FBP的鲁棒性和稳定性分析
Robustness and Stability Analysis of Differentiable Shift-Variant FBP for Cone-Beam CT under Challenging Acquisition Settings
arXiv 2607.09828 · 2026-07-14TDSal：基于任务的自上而下显著度预测模型
TDSal: Task-Based Top-Down Saliency Prediction Model
arXiv 2607.09827 · 2026-07-14迈向客观书写障碍检测：一种用于在线手写分析的多分支深度学习方法
Towards Objective Dysgraphia Detection: A Multi-Branch Deep Learning Approach for Online Handwriting Analysis
arXiv 2607.09826 · 2026-07-14更多结构，而非更多容量：用于视觉运动模仿学习的以对象为中心的表示
More Structure, Not More Capacity: Object-Centric Representations for Visuomotor Imitation Learning
arXiv 2607.09825 · 2026-07-14纠缠产生时空：度规、引力或拓扑的出现
Spacetime from Entanglement: The Emergence of Metric, Gravity, or Topology
arXiv 2607.09823 · 2026-07-14用于相机优先视觉智能体的内存条件工具调用
Memory-Conditioned Tool Calling for Camera-First Visual Agents
arXiv 2607.09822 · 2026-07-14医学图像分析中局部和非局部相似性度量的聚类算法性能基准测试与优化
Performance Benchmarking and Optimisation of Clustering Algorithms for Local and Non-Local Similarity Measure in Medical Image Analysis
arXiv 2607.09821 · 2026-07-14学习用于决策聚焦的分布鲁棒优化的预测模糊集
Learning Predictive Ambiguity Sets for Decision-Focused Distributionally Robust Optimization
arXiv 2607.09820 · 2026-07-14新《逻辑哲学论》计划：量子力学、反极权本体论与意识
The New Tractatus Program: Quantum Mechanics, Anti-Totalitarian Ontology, and Consciousness
arXiv 2607.09819 · 2026-07-14TS-Mask VLA：用于视觉-语言-动作模型的具有有效桥接的二维时空掩码
TS-Mask VLA: 2D Temporal-Spatial Masking for Vision-Language-Action Model with Effective Bridging
arXiv 2607.09818 · 2026-07-14具有面板数据的马尔可夫链选择模型的估计、预测和商品组合优化
Estimation, Prediction, and Assortment Optimization for Markov Chain Choice Models with Panel Data
arXiv 2607.09817 · 2026-07-14网络的桥接距离
Bridge distances for networks
arXiv 2607.09813 · 2026-07-14Detangled：一个用于创建、编辑和推理具有丰富特征的发丝的框架
Detangled: A Framework for Creating, Editing, and Inferencing Feature Rich Hair Strands
arXiv 2607.09811 · 2026-07-14用于视网膜 OCT 分类的校准混合 CNN-Transformer
Calibrated Hybrid CNN-Transformer for Retinal OCT Classification
arXiv 2607.09809 · 2026-07-14ACT代表尴尬的宇宙学理论
ACT stands for Awkward Cosmology Theories
arXiv 2607.09808 · 2026-07-14一种使用时空变换器的高精度无心电图动态冠状动脉造影统一模型
A Unified Model for Highly Accurate ECG-Free Dynamic Coronary Roadmapping Using Spatio-Temporal Transformers
arXiv 2607.09805 · 2026-07-14简单提示重构绕过谷歌MedGemma-4B中的安全护栏
Trivial Prompt Reframing Bypasses Safety Guardrails in Googleś MedGemma-4B
arXiv 2607.09804 · 2026-07-14自回归生成中自我修正盲点的频谱起源
Spectral Origins of the Self-Correction Blind Spot in Autoregressive Generation
arXiv 2607.09803 · 2026-07-14配额市场：用于高效分配机器学习训练资源的动态定价
Quota Marketplace: Dynamic Pricing for Efficient Allocation of ML Training Resources
arXiv 2607.09802 · 2026-07-14在强迫物理系统中发现潜在响应规律
Discovering Latent Response Laws in Forced Physical Systems
arXiv 2607.09801 · 2026-07-14仿射单值性与有限域上的精确值分布
Affine monodromy and exact value distributions over finite fields
arXiv 2607.09799 · 2026-07-14用于人工智能原生6G的联合嵌入预测架构：预测表示与开放挑战
JEPA for AI-Native 6G: Predictive Representations and Open Challenges
arXiv 2607.09798 · 2026-07-14基于大型多模态模型的环境感知移动性管理
Large Multimodal Model-Based Environment-Aware Mobility Management
arXiv 2607.09795 · 2026-07-14通过自我发现的规范进行智能体上下文学习
Agentic Context Learning with Self-Discovered Specification
arXiv 2607.09794 · 2026-07-14关于索菲热尔曼循环数的科恩次可加性猜想的一个反例
A counterexample to a subadditivity conjecture of Cohen for Sophie Germain cyclic numbers
arXiv 2607.09793 · 2026-07-14具身视觉与语言导航的全面综述与系统真实世界评估
A Comprehensive Survey and Systematic Real-World Evaluation of Embodied Vision-and-Language Navigation
arXiv 2607.09792 · 2026-07-14语义漂移与推理类决策支持系统中操作员控制的稳定性
Semantic Drift and the Stability of Operator Control in Reasoning-Class Decision Support Systems
arXiv 2607.09790 · 2026-07-14PHITSBench：用于使用自然语言生成人工智能辅助的PHITS辐射传输输入的执行评分基准
PHITSBench: an execution-scored benchmark for AI-assisted PHITS radiation-transport input generation using natural language
arXiv 2607.09789 · 2026-07-14MVMGNN；用于基于结构磁共振成像的阿尔茨海默病诊断的多视图掩码图神经网络
MVMGNN;Multi-View Masked Graph Neural Network for Alzheimer's Disease Diagnosis using Structural MRI
arXiv 2607.09788 · 2026-07-14用于激光雷达距离图像合成的对抗引导扩散
Adversarially Guided Diffusion for LiDAR Range Image Synthesis
arXiv 2607.09787 · 2026-07-14终身表示：视觉模型持续自监督学习综述
Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models
arXiv 2607.09785 · 2026-07-14噪声锚定扩散反演中的压缩不对称性与轨迹绑定
Compression Asymmetry and Trajectory Binding in Noise-Anchored Diffusion Inversion
arXiv 2607.09784 · 2026-07-14在发表后研究评估中，评审者比论文更重要
Judges matter more than papers in post-publication research assessment
arXiv 2607.09783 · 2026-07-14从模式到迷宫结构：基于SMT的路径合成与二维/三维构建
From Patterns to Maze Structures: SMT-Based Path Synthesis and 2D/3D Construction
arXiv 2607.09781 · 2026-07-14迈向现实世界的可穿戴运动重建
Towards Real-World Wearable Motion Reconstruction
arXiv 2607.09780 · 2026-07-14一种用于合成孔径雷达自动目标识别的广义深度非负矩阵分解方法
A Generalized Deep Non-negative Matrix Factorization Approach for SAR Automatic Target Recognition
arXiv 2607.09779 · 2026-07-14BDFlow-3DRM：通过双动态流匹配构建高度相干的3D无线电地图
BDFlow-3DRM: Height-Coherent 3D Radio Map Construction via Bi-Dynamical Flow Matching
arXiv 2607.09778 · 2026-07-14时间印记：在多模态知识图谱中学习时间感知表示
Time Imprint: Learning Time-Aware Representations in Multi-Modal Knowledge Graphs
arXiv 2607.09777 · 2026-07-14WINT：一种具有改进误差特性的新型加权整数表示法
WINT: A Novel Weighted Integer Representation with Improved Error Characteristics
arXiv 2607.09775 · 2026-07-14幻觉检测器：一种用于在AtomGPT.org上检测科学文献中幻觉的混合大语言模型和语义学者工具调用
Hallucination Detector: A hybrid LLM and Semantic Scholar tool calling for detecting hallucination in scientific literature on AtomGPT.org
arXiv 2607.09774 · 2026-07-14一种用于自动驾驶安全验证的风险场增强闭环数字孪生框架
A Risk-Field Enhanced Closed-Loop Digital Twin Framework for Autonomous Driving Safety Validation
arXiv 2607.09772 · 2026-07-14科学的支柱：论文与其来源之间的引用网络分析
The backbone of science: analysis of citation networks between papers and their sources
arXiv 2607.09771 · 2026-07-14新兴多参考特征下酶促过渡态模拟中的挑战
Challenges in the simulation of enzymatic transition states with emerging multireference character
arXiv 2607.09769 · 2026-07-14基于RISC-V多核MCU的视觉系统上的低功耗车牌检测与识别
Low-Power License Plate Detection and Recognition on a RISC-V Multi-Core MCU-Based Vision System
arXiv 2607.09768 · 2026-07-14倾听特征：基于信号重构的内容嵌入匹配驱动的语音匿名化
Listen to the Features: Voice Anonymization Driven by Content Embedding Matching over Signal Reconstruction
arXiv 2607.09767 · 2026-07-14人工智能代理的规范执行：在多智能体系统中稳健塑造行为
Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems
arXiv 2607.09766 · 2026-07-14正确性的代价是多少？弱多智能体群体中强校正器的预算放置
How Much Does Correctness Cost? Budgeted Placement of Strong Correctors in a Weak Multi-Agent Swarm
arXiv 2607.09765 · 2026-07-14OmniSCS：通过完全可编辑的驾驶世界实现自动驾驶的全场景安全关键场景合成
OmniSCS: Omni Safety-Critical Scenario Synthesis for Autonomous Driving via a Fully Editable Driving World
arXiv 2607.09764 · 2026-07-14
