Mingxuan (Adrian) Cao
RSS FeedPhD student in Data Science @ UChicago DSI and Research Aide @ Argonne National Laboratory. I work at the interface of AI & statistics—focusing on diffusion/SDE models, inference-time guidance, and reinforcement learning for purposeful generation. Current applications span protein/molecular design, functional genomics, and materials—with interpretable AI-for-Biology as a throughline.
Before UChicago, I completed my undergraduate and master's degrees in 4 years with highest distinction at WashU. Go Bears! 🐻
News
- Our paper, "MixUni: Joint Multi-Property Prediction for Chemical Mixtures with Physics-Informed Heads", has been accepted to NeurIPS 2026! An independent project led entirely by five PhD students—huge thanks to my great collaborators Qinan Huang, Weizhi Xue, Weizhou Wang, and Ian Su. 🎉
- My first paper, "Monte Carlo Tree Diffusion with Multiple Experts for Protein Design" (MCTD-ME), has been accepted as a poster at MLCB 2026! It was previously presented at the NeurIPS 2025 Workshop on AI for Virtual Cells and Instruments, where it sparked a lot of great discussion. 🎉
- Adrian’s site is available now! 🎉