Yanming Shao

Adversarial Posture Regularization transforms piano-playing robots from awkward automatons into fluid, human-like performers using minimal human data.

Learning dexterous manipulation from monocular videos could redefine how robots acquire complex skills without costly teleoperation data.

Achieving 86.4% grasp stability and 83.3% real-world success, SynManDex bridges the gap between human dexterity and robotic manipulation.

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.