A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models
GitHub repository with 320 stars and 7 forks.
Topics: on-policy-distillation, awesome, llm, rl, opd, awesome-list, distillation, gkd, knowledge-distillation, llm-distillation
Trending score 1.93, activity score 0.05, stars gained +11, forks gained +1.
2026-06-13: 320 stars and 7 forks.
A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models
GitHub repository with 320 stars and 7 forks.
Trending score: 1.93; stars gained: +11; forks gained: +1.
Topics: on-policy-distillation, awesome, llm, rl, opd, awesome-list
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
GitHub repository with 542 stars and 28 forks.
Trending score: 0.98; stars gained: +8; forks gained: +1.
Language: Python
Topics: llms, mechanism, on-policy-distillation
Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"
GitHub repository with 22 stars and 1 forks.
Trending score: 0.61; stars gained: +3; forks gained: +0.
Language: Python
Topics: large-language-models, llm, on-policy-distillation, opsd, reinforcement-learning, self-distillation
A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models
GitHub repository with 320 stars and 7 forks.
Trending score: 1.93; stars gained: +11; forks gained: +1.
Topics: on-policy-distillation, awesome, llm, rl, opd, awesome-list
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
GitHub repository with 542 stars and 28 forks.
Trending score: 0.98; stars gained: +8; forks gained: +1.
Language: Python
Topics: llms, mechanism, on-policy-distillation
Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"
GitHub repository with 22 stars and 1 forks.
Trending score: 0.61; stars gained: +3; forks gained: +0.
Language: Python
Topics: large-language-models, llm, on-policy-distillation, opsd, reinforcement-learning, self-distillation