2 papers
cs.RO2025
VITA-E: Natural Embodied Interaction with Concurrent Seeing, Hearing, Speaking, and Acting
Xiaoyu Liu, Chaoyou Fu, Chi Yan +15
Current Vision-Language-Action (VLA) models are often constrained by a rigid, static interaction paradigm, which lacks the ability to see, hear, speak, and act concurrently as well…
cs.RO2025
HiLo: Learning Whole-Body Human-like Locomotion with Motion Tracking Controller
Qiyuan Zhang, Chenfan Weng, Guanwu Li +2
Deep Reinforcement Learning (RL) has emerged as a promising method to develop humanoid robot locomotion controllers. Despite the robust and stable locomotion demonstrated by previo…