Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Paper • 2604.13016 • Published • 116
Zixuan Fu
ZixuanFu
·
AI & ML interests
None yet
Recent Activity
authored a paper about 13 hours ago
Rethinking On-Policy Distillation of Large Language Models II: One Training Example authored a paper about 13 hours ago
MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement authored a paper about 13 hours ago
UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic EditingOrganizations
upvoted 2
papers about 19 hours ago