Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Paper • 2604.13016 • Published • 87 •
6
Huanxin Sheng
HuanxinSheng
·
AI & ML interests
None yet
Recent Activity
upvoted a collection 1 day ago
Nemotron-Post-Training-v3 commentedon a paper 6 days ago
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe commentedon a paper 6 days ago
Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy DistillationOrganizations
commented 4
papers 6 days ago
Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
Paper • 2604.13010 • Published • 12 •
7
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Paper • 2604.13016 • Published • 87 •
6
Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
Paper • 2604.13010 • Published • 12 •
7