UW Data Science Seminar: Yuanqi Du

Title: Scientific Knowledge Emerges in LLMs and You Can Extract It

Abstract: The emerging capabilities of large language models (LLMs) are opening new frontiers in scientific research, including experiment operation, literature retrieval, and molecular design. A central question, however, is whether LLMs truly encode scientific knowledge—and if so, how this knowledge can be systematically extracted. In this talk, I will present an affirmative answer to this question, supported by strong quantitative and empirical evidence. I will begin by framing knowledge extraction as a search problem with a computational verifier. I will illustrate through three problems: molecular optimization, crystal structure generation, and retrosynthesis. In all three cases, LLMs demonstrate impressive performance compared to state-of-the-art computational approaches. I will conclude by reflecting on analogous discoveries in other scientific domains and highlighting key questions for future exploration.


Biography: Yuanqi Du is a PhD candidate in Computer Science at Cornell University, where he studies the intersection of artificial intelligence and scientific discovery. His research centers on developing principled, efficient probabilistic and geometric models that are inspired by—and accelerating—discovery in the natural sciences. Yuanqi’s work has appeared in leading machine learning venues (NeurIPS, ICML, ICLR) and top-tier scientific journals, including Nature, Nature Machine Intelligence, Nature Computational Science, and JACS. As a passionate community builder, Yuanqi has organized over 20 community events, including conferences, workshops, and seminars across AI for Science, geometric deep learning and probabilistic machine learning.

#ai #science #research #datascience