arxiv:2605.07396
zhepeihong
peregrine123
AI & ML interests
Post-training, On-policy Distillation
Recent Activity
submitted a paper about 7 hours ago
Rubric-based On-policy Distillation authored a paper about 14 hours ago
Rubric-based On-policy Distillation upvoted a paper about 15 hours ago
Rubric-based On-policy DistillationOrganizations
None yet