Can We Trust the Teacher? Decoupled Credit Direction-Magnitude for Self-Distillation
A new self-distillation method separates credit direction from magnitude and beats prior RL baselines.
1 stories, newest first · one card per story
A new self-distillation method separates credit direction from magnitude and beats prior RL baselines.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views