Yuanqi Du

Yuanqi Du

PhD Student, Cornell University

Yuanqi Du

Yuanqi Du is a PhD candidate in the Department of Computer Science at Cornell University, where he studies the intersection of artificial intelligence and scientific discovery. His research develops principled, efficient probabilistic and geometric models that both draw inspiration from and accelerate discovery in the physical sciences. His work has been published in premier machine learning venues such as NeurIPS, ICML and ICLR, as well as in top-tier scientific journals including Nature, Nature Machine Intelligence, Nature Computational Science and JACS. He has served as an area chair for NeurIPS and regularly reviews for flagship journals in the Nature, Science and ACS families. In the past, he spent time at AMLab at University of Amsterdam advised by Prof. Max Welling and Microsoft Research. He is also a passionate community builder, which he founded the series of AI for Science workshops, co-founded the Learning on Graphs conference and probabilistic inference workshops, and led an initiative AI for Science 101 building knowledge systems for AI for Science. He maintains a slack channel for communication and outreach about AI for Science (with 1300+ active researchers), feel free to join and say Hi to people here!

I am on the academic job market for positions that start from Fall 2026!

Research Interests

  • Probabilistic Machine Learning: Generative Models (includ. Large Language Models), Measure Transport, Stochastic Control, Sampling, Bayesian Inference
  • Structure and Geometry: Neural Architectures (e.g. Graphs and Sets), Equivariance, Symmetry, Tensor Networks
  • AI for Science: Molecular Design, Molecular Simulation (esp. Understanding Out-of-equilibrium Processes), Chemical Reaction and Synthesis

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

News & Upcoming Events