Awesome Robotics Manipulation · full_paper

TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos

CVPR 2026 · 2025-11-26 · Low-Level Learning-Based Action Modelling / Learning Strategy / Vision-Grounded Goal Extraction / Visual Trace

3D 表征视频规划跨本体世界模型感知机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos figure
AlphaXiv 中文论文页面（可滚动查看）