On-Policy Distillation with Negative-Policy Rollouts
NP-OPD improves on-policy distillation by using weaker-model rollouts as an explicit negative signal.
Stories per day · 30 days
1 stories, newest first · one card per story
Stories tagged #np-opd
1 stories, newest first · one card per story
NP-OPD improves on-policy distillation by using weaker-model rollouts as an explicit negative signal.
Today 252 readers · 272 views · 20 reads · all time 108K views