On-Policy Distillation is formalized as f-divergence minimization over student-sampled trajectories and organized along three design axes for LLM capability transfer.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Survey of On-Policy Distillation for Large Language Models
On-Policy Distillation is formalized as f-divergence minimization over student-sampled trajectories and organized along three design axes for LLM capability transfer.