Hey, I'm Christian.

M.S. Computer Science student at the University of Wisconsin–Madison. I work on trustworthy AI—safety evaluations, monitoring, and the robustness of ML systems and agents.

I'm pursuing my M.S. in Computer Science at UW–Madison (2024–2026, GPA 3.80) after graduating from UIUC with a B.S. in Computer Science (2020–2024, GPA 3.96). My research focuses on making AI systems more trustworthy through rigorous safety evaluations and monitoring, and on security and robustness for AI agents.

Some things I've worked on

  • Process reward models & reasoning: I contributed to work on synthetic chain-of-thought data for training process reward models, including VersaPRM (ICML 2025).
  • LLM behavior & safety: I've studied plagiarism in model outputs (NSF REU at Penn State) and stay active in the Wisconsin AI Safety Initiative as exec board and tech scholar.
  • Building & teaching: I've led and mentored student engineering efforts (e.g. Project Code), and I care about clear communication and solid engineering practice.

Selected publications

  • VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data — T. Zeng, S. Zhang, S. Wu, C. Classen, D. Chae, E. Ewer, M. Lee, H. Kim, W. Kang, J. Kunde, Y. Fan, J. Kim, H. Koo, K. Ramchandran, D. Papailiopoulos, K. Lee. International Conference on Machine Learning (ICML), 2025.
  • In-batch Ensemble Drafting: Robust Speculative Decoding for LVLMs — M. Lee, W. Kang, B. Ahn, C. Classen, M. Yan, H. Koo, K. Lee. ICLR 2025 SCOPE Workshop.

On this site

Browse Experience for research, leadership, and project history, Projects for software and portfolio work, and About for a fuller background and awards.