William Chen
Co-first author of FRS paper, building research program around controllable and adaptable generalist policies at UC Berkeley RAIL Lab.
“FRS is an inference-time mechanism to unlock that latent knowledge without retraining the base model.”
Source→“up to 95% absolute task success rate boosts in under a minute of training (Abstract) on 10 trajectories — challenges the assumption that adaptation requires significant data collection infrastructure.”
Source→“Chen has prior work on training strategies for embodied reasoning (Reference 11) and steerable VLA policies (Reference 12). He is building a consistent research program around making generalist policies more controllable and adaptable.”
Source→“Authors: Andy Tang, William Chen, Andrew Wagenmaker, Chelsea Finn, Sergey Levine (Stanford + UC Berkeley). Date: June 2025. arXiv: 2606.13675.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.