Yuanqi Du

Yuanqi Du is a PhD candidate in Computer Science at Cornell University. His research focuses on developing principled and efficient probabilistic and geometric modeling methods that are inspired by, and accelerate, discovery in the natural sciences, spanning chemistry, physics, and biology. His work has appeared at leading machine learning venues (NeurIPS, ICML, ICLR) and in scientific journals including Nature, Nature Machine Intelligence, Nature Computational Science, and the Journal of the American Chemical Society, with three cover articles. His research has been featured by Nature, Science, Chemistry World, Nature Computational Science (Five-Year Anniversary), MIT News, among many others. As a passionate community builder, he has organized over 20 events including conferences, workshops, and seminar series on topics ranging from AI for Science, probabilistic machine learning, and learning on graphs. He also leads an educational initiative AI for Science 101.

Join our vibrant AI for Science slack community with more than 1700 researchers here!

Feel free to send me en email if you are interested in collaborating or working on exciting research projects with me!

Research Interests

• Probabilistic Machine Learning: Generative Models, Large Language Models, Measure Transport, Stochastic Control, Sampling, Bayesian Inference, Reinforcement Learning
• Structure and Geometry: Neural Architectures (e.g. Graphs and Sets), Equivariance, Symmetry, Tensor Networks
• AI for Science: Physical Chemistry, Drug Discovery, Materials Science

Additional topics I am interested in include: (Mechanistic) Interpretability, Science of Science, and Societal Impact of AI.

News & Upcoming Events

• Join our Generative Modeling & Sampling Seminar at MSR NE (in-person attendance is available)!
• Check out my new blog Scientific Knowledge Emerges in LLMs and YOU CAN Access It!