https://github.com/xuehaipan/xuehaipan
https://github.com/xuehaipan/xuehaipan
Last synced: 30 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/xuehaipan/xuehaipan
- Owner: XuehaiPan
- Created: 2021-06-04T14:42:55.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2025-03-21T17:30:35.000Z (about 1 month ago)
- Last Synced: 2025-03-21T18:30:35.944Z (about 1 month ago)
- Size: 3.91 KB
- Stars: 6
- Watchers: 2
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
### Hi there 👋 
Xuehai Pan (/ʃwɛˈhaɪ pæn/, 潘å¦æµ· in Mandarin, [[email protected]](mailto:[email protected])) is a final-year Ph.D. student in Applied Computer Science at Peking University.
His research interests lie in the intersection of **Reinforcement Learning**, **Multi-Agent Systems**, and **Distributed Computing**, with a focus on developing _scalable_ and _automated_ algorithms and exploring their theoretical and practical aspects.
He has a solid background in both research and engineering, having obtained a B.S. degree in _Physics_ with honors and a B.S. degree in _Computer Science_ (double major) from Peking University before pursuing his Ph.D. degree.
His academic journey is embellished with achievements such as winning gold medals in the Chinese Physics Olympiad (CPhO) and the [Asian Physics Olympiad (APhO)](https://en.wikipedia.org/wiki/Asian_Physics_Olympiad) during high school.
Xuehai is now working on pioneering research in the development of Large Language Models (LLMs) while ensuring they align with human intentions and values through AI Alignment techniques (essentially balancing between helpfulness and harmlessness).
Specifically, he is exploring automated data syntactic, red teaming, and evolutional training via multi-agent interaction and self-play.
The ultimate goal is to build a scalable and fully automated system, including training, evaluation, inference, and governance.
Beyond academia, Xuehai is an open-source enthusiast and an active contributor to influential projects such as [PyTorch](https://github.com/pytorch/pytorch), [CPython](https://github.com/python/cpython), [Ray](https://github.com/ray-project/ray), [Transformers](https://github.com/huggingface/transformers), [DeepSpeed](https://github.com/microsoft/deepspeed), [Gymnasium](https://github.com/Farama-Foundation/Gymnasium) (formerly [OpenAI Gym](https://github.com/openai/gym)), [PyBind11](https://github.com/pybind/pybind11) (C++ bindings for Python), [PyO3](https://github.com/PyO3/pyo3) (Rust bindings for Python), [Conda](https://github.com/conda/conda), [Homebrew](https://github.com/Homebrew/brew), etc.
He enjoys dedicating his spare time to helping people and sharing knowledge in the community, further enriching his impact beyond his research pursuits.
