Preprint
Aug 2026
Simple-OPD: Demystifying Warm-up for On-policy Distillation
On-policy distillation (OPD) trains a student on its own rollouts with token-level supervision from teacher models, but its effectiveness can depend strongly on the warm-up stage before OPD. In this paper, we demystify warm-up for OPD from both data and training perspectives. For data, we find that effective warm-up re...
Tao Liu, Taiqiang Wu, Mao Zheng et al.
· 1 citation