When to Follow the Teacher: Advantage-Based On-Policy Distillation
Online Policy Distillation (OPD) often outperforms offline methods such as Supervised Fine-Tuning (SFT) by training on trajectories sampled directly from the student.
By Mahdi Sabbaghi, George Pappas, Hamed Hassani, Adel JavanmardarXiv - stat.ML
Read the full story
Originally published by arXiv - stat.ML on Oct 23, 2026.
Comments
Sign in to join the discussion.