arxiv:2306.05836
Jiarui Liu
Jerry999
AI & ML interests
None yet
Recent Activity
new activity 1 day ago
Jerry999/user-sim-eval:Add reward bench 2 eval data updated a model 1 day ago
Jerry999/Atomic2Compositional upvoted a paper 2 days ago
Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision