CRAFT: Adapting VLA Models to Contact-rich Manipulation via Force-aware Curriculum Fine-tuning

作者：Yike Zhang, Yaonan Wang, Xinxin Sun, Kaizhen Huang, Zhiyuan Xu, Junjie Ji, Zhengping Che, Jian Tang, Jingtao Sun · 单位：National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, Changsha, 410082, China. Yike, Beijing Innovation Center of Humanoid Robotics, Beijing, 102600, China, Department · 会议/期刊：arXiv · 日期：2026-02-13 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / Other Modalities / Force