Wenzhao Lian

HALOMI bridges the human-to-humanoid gap, achieving 85% success in complex loco-manipulation tasks by leveraging active perception from human demonstrations.

FAWAM achieves a 36.25% boost in success rates for robotic manipulation tasks by fully leveraging force signals to enhance action modeling and execution.

Human-in-the-loop chunk-wise residual adaptation closes the reality gap for dexterous robot manipulation, boosting success rates by up to 43% compared to offline imitation learning.