chrisliu298/awesome-on-policy-distillation · AI Repo StatsCHchrisliu298/awesome-on-policy-distillation
A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models
LLM & foundation models CC0-1.0 42created 2026-03-22 #awesome#awesome-list#distillation#gkd#knowledge-distillation#llm#llm-distillation#llm-training#minillm#on-policy-distillation#opd#post-training#reinforcement-learning#rl#rlhf#self-distillation#speculative-decoding