Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
Paper • 2604.12002 • Published • 10
Yang Yongjin
Dragonjinny
AI & ML interests
Few shot, Language Modeling, Meta Learning
Recent Activity
upvoted a paper 7 days ago
Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision updated a dataset 10 months ago
Dragonjinny/FiFA-pickapic-v2 published a dataset 10 months ago
Dragonjinny/FiFA-pickapic-v2Organizations
None yet
upvoted a paper 7 days ago