Pengyu Cheng

Linear95

·

AI & ML interests

None yet

Recent Activity

authored a paper 17 days ago

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

upvoted a paper 20 days ago

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

upvoted a paper 2 months ago

GD^2PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization

View all activity

Organizations

New activity in Quark-LLM/SSP 8 months ago

Add task category and improve dataset card

#3 opened 8 months ago by

docs: update readme

#2 opened 8 months ago by

New activity in Quark-LLM/SSP 9 months ago

feat: upload training and evaluation data

#1 opened 9 months ago by