Teacher-Evolution Self-Distillation improves on-policy model training
TESD evolves self-teachers with task rewards to provide reliable guidance and down-weights unreliable samples.
1 stories, newest first · one card per story
TESD evolves self-teachers with task rewards to provide reliable guidance and down-weights unreliable samples.
Today 1.5K readers · 2.4K views · 754 reads · all time 189K views