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

作者：Seungjae Lee, Yoonkyo Jung, Inkook Chun, Yao-Chih Lee, Zikui Cai, Hongjia Huang, Aayush Talreja, Tan Dat Dao, Yongyuan Liang, Jia-Bin Huang, Furong Huang · 单位：University of Maryland, College Park, New York University · 会议/期刊：CVPR 2026 · 日期：2025-11-26 · 来源：Low-Level Learning-Based Action Modelling / Learning Strategy / Vision-Grounded Goal Extraction / Visual Trace