arxiv:2603.10178
Huanxin Sheng
HuanxinSheng
ยท
AI & ML interests
None yet
Recent Activity
commentedon a paper about 5 hours ago
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe commentedon a paper about 5 hours ago
Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation commentedon a paper about 23 hours ago
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe