Concept质量引导
quality steering
A training mechanism operating at the video or observation level that retains full supervision over rollouts of all quality levels, enabling the model to learn to predict the subsequent frame evolution of a trajectory even when the trajectory is a failure.
Timeline (last 90 days)
Oct 14
Quality steering operates at the video/observation level, retaining full supervision for rollouts of all quality levels; quality-weighted supervision operates at the action level, reweighting the imitation loss, so that successful segments receive higher action cloning weights, and failed segments have their share in the action loss reduced while retaining their contribution in the world modeling loss.
Unverified50%