drivelm-project

non-profit

https://huggingface.co/drivelm_project/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Thu-zqc submitted a paper 9 days ago

R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop

Thu-zqc authored a paper 15 days ago

R$^2$Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop

Thu-zqc authored a paper 16 days ago

Why On-Policy Distillation Sometimes Fails: Vanishing Learning Signals

View all activity

drivelm-project 's datasets

None public yet