今日从 arXiv 订阅中筛选 10 篇论文。
⚡ Learning from the Unseen: Generative Data Augmentation for Geometric-Semantic Accident Anticipation
⚡ Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling

⚡ Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning

⚡ An End-to-End Decision-Aware Multi-Scale Attention-Based Model for Explainable Autonomous Driving

⚡ Thinking in Text and Images: Interleaved Vision-Language Reasoning Traces for Long-Horizon Robot Manipulation

⚡ Scaling Video Understanding via Compact Latent Multi-Agent Collaboration

⚡ Online Self-Calibration Against Hallucination in Vision-Language Models

⚡ Robust Fusion of Object-Level V2X for Learned 3D Object Detection

⚡ Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs

⚡ Time-series Meets Complex Motion Modeling: Robust Motion Predictor for Multi-object Tracking

自动生成于 2026-05-04 · 基于 arXiv Daily Digest