Mickel Liu
PKU-Alignment / Peking University researcher; co-first author on PKU-SafeRLHF and BeaverTails safety dataset.
- Role
- researcher
- Currently at
- Peking University
- Unknown
- GitHub
- github.com/mickel-liu
- Scholar
- scholar.google.com/scholar
- Papers
- 4
Cite
Notes
Only stored in your browser.
4papers
Authored papers
4SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
arXiv 2025
BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset
NeurIPS
Baichuan 2: Open Large-scale Language Models
arXiv 2023
Safe RLHF: Safe Reinforcement Learning from Human Feedback
arXiv 2023
Affiliations
Previously
Frequent co-authors
10from 4 papers
Jiaming Ji
researcher
Ruiyang Sun
researcher
Xuehai Pan
grad-student
Ce Bian
researcher
Juntao Dai
researcher
Yaodong Yang
professor
Yizhou Wang
professor
Aiyuan Yang
Bin Xiao
Bingning Wang