Hello, there!
My name is Daiwei Chen (陈戴纬).
I'm a graduate student (Electrical and Computer Engineering PhD student) 🎓 @ UW-Madison.
Focus on AI alignment, Preference Learning, LLM Reliability, and interesting NLP applications 🤖.
Hello, there!
My name is Daiwei Chen (陈戴纬).
I'm a graduate student (Electrical and Computer Engineering PhD student) 🎓 @ UW-Madison.
Focus on AI alignment, Preference Learning, LLM Reliability, and interesting NLP applications 🤖.
The open-source repository for PAL: Sample-Efficient Personalized Reward Modeling for Pluralistic Alignment, which provides a general personalized preference learning modeling framework.
My minimal-style nvim configurations with tree structure (space + e) and some nice visualization configurations. Avoid all other unnecessary plugins.
Lua 1
Beautify Print is a lightweight Python package that makes it easy to beautifully format and display any output—such as LLM API responses or nested Python objects—directly in your terminal.
Python 1
My personal agent skills contains 1) the official obsidian-skills; 2) the personal knowledge base construction skills (follow the philosophy emphasized by Karpathy through `LLM-wiki`); 3) my own re…