Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation
Anhao Zhao, Junlong Tong, Yingqi Fan +3
Standard on-policy distillation (OPD) for large language models estimates the reverse-KL objective using student-sampled tokens, yielding an unbiased single-sample Monte Carlo esti…
cs.LG2026
Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation
Anhao Zhao, Haoran Xin, Yingqi Fan +3
Knowledge distillation is central to LLM post-training, yet its design space remains poorly understood, especially alongside reinforcement learning (RL). We show that the prevailin…