Yao Mu

BORA is an offline-to-online RL framework that enhances dexterous VLA models for real-world robotics by using an action-conditioned critic and a lightweight residual adaptation mechanism to correct execution errors.

The Implicit Drifting Policy (IDP) is a novel one-step action generation framework that implicitly enforces trajectory correction constraints by analyzing local expert action geometry, overcoming the difficulties of explicitly estimating a training-time drifting field.