Recently working on:
- LLM Agent
- Reinforcement learning from human feedback (RLHF)
- Retrieval-Augmented Generation (RAG)
My interesting codes:
- LLM-tools: Tool codes for LLM development. (Recently started)
- kdd99_feature_extractor: A forked project which can extract more features from network flow.
- ftp-server-client: FTP client and server by C and Qt.
- PokemonFight: A Qt-based C++ game.
-
Master of Artificial Intelligence, 2022-2025
Institute of Automation, Chinese Academy of Sciences, Beijing, China
-
Bachelor of Software Engineering, 2017-2022
School of Software, Tsinghua University, Beijing, China
- Python
- C/C++
- Go, Java
- JavaScript, TypeScript...
- Git
- Linux
- Frontend Development (Vue.js, ElementPlus)
- Backend Development (Flask, FastApi)
- Deployment (nginx, Docker)
- PyTorch, TensorFlow
- Large Language Model
- Reinforcement learning
- Natural Language Processing
- Intrusion detection