Article

EgoForesight: Scaling Policy Learning with Noisy Egocentric Action Data

EgoForesight is a vision-language-action framework that jointly leverages robot demonstration trajectories and noisy egocentric videos for policy learning, reducing the impact of unreliable action labels through reliability-conditioned corruption and reliability-weighted regression, and supplementing supervision from demonstrated outcomes via privileged-future representation distillation.

Part of the event: EgoForesight: Scaling Policy Learning with Noisy Egocentric Action Data

This page provides a summary and source link only.