Conference

KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Control
In IEEE International Conference on Robotics & Automation(ICRA), 2026
We present VMS, a unified whole-body controller that enables humanoid robots to learn diverse and dynamic behaviors within a single policy through hybrid tracking and orthogonal mixture of experts.
Jinrui Han , Weiji Xie , Jiakun Zheng , Jiyuan Shi , Weinan Zhang , Ting Xiao , Chenjia Bai✉
PDF Cite Code Project
KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Control
Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance
In International Conference on Learning Representations (ICLR), 2026
We propose Align-Then-stEer (ATE), a framework that adapts VLAs to novel robots and tasks through unified latent guidance. ATE can handle significant domain shifts without compromising performance and compatible to Pi0, RDT, and etc.
Yang Zhang , Chenwei Wang , Ouyang Lu , Yuan Zhao , Yunfei Ge , Zhenglong Sun , Xiu Li , Chi Zhang , Chenjia Bai✉ , Xuelong Li✉
PDF Cite Code Project 公众号
Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance