Talk 1

Time and Venue

3 October 2025, 9 to 10 AM (ET)
Klaus 1116, Klaus Advanced Computing Building (KACB), Georgia Tech

Title and Abstract

At the Intersection of Reasoning and Learning: From Solvers to LLMs

From its inception, AI has had two broad sub-fields, namely, reasoning and learning, with little interaction between them. In recent years, there is a growing recognition that if our goal is to solve problems at the cutting-edge of AI (trustworthy AI, AI for Science, AI for Math, AI for Code), then we need to bring these sub-fields together. In this talk, I will present techniques and results showing how machine learning (ML) can be used in service of automated reasoning (a la, SAT/SMT solvers), and in the reverse direction, how symbolic reasoning engines can be used to improve LLMs. The key idea in both directions is the same: the ML model is viewed as a synthesizer that generates code/proofs/molecules/equations, while the reasoning engine acts as a verifier that provides corrective feedback to the model at various points (training, fine-tuning, or inference) in its life cycle.

Speakers

Vijay Ganesh

Professor,
School of Computer Science,
Georgia Tech

Dr. Vijay Ganesh is a professor of computer science at the Georgia Institute of Technology. He serves as the Associate Director of the IDEaS Institute and is affiliated with Tech AI. Prior to joining Georgia Tech in 2023, Vijay was a professor at the University of Waterloo in Canada from 2012 to 2023 and a research scientist at the Massachusetts Institute of Technology from 2007 to 2012. Vijay completed his PhD in computer science from Stanford University in 2007. 
Vijay’s primary area of research is the theory and practice of SAT/SMT solvers, and their application in AI, software engineering, security, mathematics, and physics. In this context, he has led the development of many SAT/SMT solvers, most notably, STP, Z3str4, AlphaZ3, MapleSAT, and MathCheck. He has also proved several decidability and complexity results in the context of first-order theories. More recently, he has started working on topics at the intersection of learning and reasoning, especially the use of machine learning for efficient solvers, and the use of solvers aimed at making AI more trustworthy, secure, and robust. For his research, Vijay has won over 30 awards, honors, and medals to-date, including an ACM Impact Paper Award at ISSTA 2019, ACM Test of Time Award at CCS 2016, and a Ten-Year Most Influential Paper citation at DATE 2008.

    David Sherrill

    Professor,
    School of Chemistry & Biochemistry,
    Georgia Tech

    Dr. C. David Sherrill is a Regents’ Professor with joint appointments in the School of Chemistry and Biochemistry and School of Computational Science and Engineering.  He obtained his B.S. in Chemistry from MIT  in 1992, and his Ph.D. in Chemistry from the University of Georgia in 1996.  Dr. Sherrill serves as Associate Director of the Institute for Data Engineering and Science at Georgia Tech.   He has published over 175 peer-reviewed articles on the development and application of new theoretical methods and new algorithms in computational quantum chemistry.  He is a Fellow of the American Association for the Advancement of Science (AAAS), the American Chemical Society, and the American Physical Society, and he has been Associate Editor of the Journal of Chemical Physics since 2009.  Dr. Sherrill has received a Camille and Henry Dreyfus New Faculty Award, the International Journal of Quantum Chemistry Young Investigator Award, an NSF CAREER Award, and Georgia Tech’s W. Howard Ector Outstanding Teacher Award. In 2017, he was named the Outreach Volunteer of the Year by the Georgia Section of the American Chemical Society for his many years of working with K-12 teachers during National Chemistry Week.