Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
Paper • 2604.12002 • Published • 8
Yinghui He
yinghuihe
·
AI & ML interests
Natural Language Processing, Machine Learning Theory
Recent Activity
upvoted a paper 4 days ago
Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision submitted a paper 4 days ago
Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision upvoted a paper 6 months ago
Skill-Targeted Adaptive TrainingOrganizations
submitted a
paper to Daily Papers 4 days ago
authored a
paper about 1 year ago