3 papers
cs.RO2026
PRICE the Action Chunks: Physical Relational Credit Assignment for Embodied Reinforcement Learning
Yangang Zou, Jiajun Lu, Weitao Zhou +6
Outcome-based reinforcement learning (RL) post-trains vision--language--action policies using terminal success signals, but assigns the same trajectory-level advantage to every act…
cs.RO2026
UMI-Bridge: Action-Anchored Latent Alignment across Human and Robot Manipulation Data
Haiyi Liu, Jinming Ma, Jingming Ma +13
Real-robot demonstrations are limited, motivating the use of human manipulation data collected without robots, including egocentric videos and handheld Universal Manipulation Inter…
cs.RO2026
EMoG: Emotion-Modulated Gait Generation for Expressive Humanoid Locomotion
Yi Lu, Tianhao Jiang, Honglong Tian +6
Existing humanoid locomotion systems primarily focus on stability and task execution, while integrating expressiveness with explicit locomotion control remains challenging. We prop…