Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
Paper • 2605.12483 • Published • 6
ab
Shenbixiaoxin
AI & ML interests
None yet
Recent Activity
upvoted a paper 27 days ago
TIP: Token Importance in On-Policy Distillation upvoted a paper 2 months ago
PACED: Distillation at the Frontier of Student CompetenceOrganizations
None yet