Weak-to-Strong Generalization via Direct On-Policy Distillation

By Shiyuan Feng · Paper · cs.LG

Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because the target model must generate many rollouts during training. As models scale, post-training itself b

Cs.lg

View original

HomeResourceLoading…