Yuxiang Wei is a PhD student in Computer Science at UIUC with seven years of experience building and training code-focused large language models and agentic systems. He has held multiple research roles at Meta FAIR and Snowflake where he worked on CodeGen, code LLM pretraining, world models for code, and reinforcement learning for agentic code agents. His work blends rigorous academic research with production-scale model training, including self-play and world-model approaches to improve code generation and agent behavior. Based in Champaign, Illinois, he brings hands-on expertise in designing training pipelines and scaling LLMs for developer-centric tasks. Notably, his trajectory spans both research scientist positions and internships, indicating rapid progress from intern to core researcher on cutting-edge code intelligence projects. He combines deep technical focus with practical experience shipping large-model experiments in industry research environments.
7 years of coding experience
1 year of employment as a software developer
Bachelor of Engineering - BE, Computer Science, Bachelor of Engineering - BE, Computer Science at Tongji University
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of Illinois Urbana-Champaign
[NeurIPS'24] SelfCodeAlign: Self-Alignment for Code Generation
Contributions:3 reviews, 2 PRs, 68 pushes in 10 months
code-generationlarge-language-modelsllmllm4code
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.