Shengyu Feng
I am a third-year Ph.D. student in Language Technologies Institute, Carnegie Mellon University. I am fortunately advised by Prof. Yiming Yang. Before that, I received my M.S. in Computer Science from University of Illinois at Urbana-Champaign in 2022, and B.S.E in Computer Science from University of Michigan and B.S in Electrical and Computer Engineering from Shanghai Jiao Tong University in 2020.
Curriculum Vitae (Last updated July 2025)
Research Interest
My research focuses on developing artificial intelligence for mathematical problem solving (AI4Math), with an emphasis on methods that require minimal or no human supervision. I currently pursue two primary directions:
- Large Language Model (LLM)-based mathematical reasoning (FrontierCO, CO-Bench, TSMC4Math)
- Neural approaches for combinatorial optimization (FrontierCO, RLD4CO, SORREL)
In addition, I apply combinatorial optimization to real-world applications such as high-performance computing, computer vision, biology, and information extraction. My earlier work spans self-supervised graph representation learning and reinforcement learning.