s's picture

2 1 1

s

leosong

AI & ML interests

NLP

Recent Activity

commented on a paper about 1 month ago

Reinforcement Pre-Training

upvoted a paper about 2 months ago

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

updated a model 4 months ago

leosong/Qwen2.5-1.5B-GRDPO

View all activity

Organizations

None yet

commented a paper about 1 month ago

Reinforcement Pre-Training

Paper • 2506.08007 • Published Jun 9 • 247 •