4 papers
WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time
Yusen Feng, Bingchen Han, Jiangran Lyu +13
Steering robot foundation models (RFMs) toward new task variants or user-preferred behaviors remains challenging, often requiring additional robot demonstrations, task-specific fin…
MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots
Yusen Feng, Xiang Wang, Heyuan Yao +7
This paper presents MuGen, a data-driven framework for learning and deploying multi-skill locomotion on humanoid robots. MuGen enables a robot to perform expressive motions like hu…
ProAct: A Dual-System Framework for Proactive Embodied Social Agents
Zeyi Zhang, Zixi Kang, Ruijie Zhao +3
Embodied social agents have recently advanced in generating synchronized speech and gestures. However, most interactive systems remain fundamentally reactive, responding only to cu…
OpenDance: Multimodal Controllable 3D Dance Generation with Large-scale Internet Data
Jinlu Zhang, Zixi Kang, Libin Liu +4
Music-driven 3D dance generation offers significant creative potential, yet practical applications demand versatile and multimodal control. As the highly dynamic and complex human…