Brian Zhengyu Li

About

I am a PhD Candidate in Computer Science at Georgia Institute of Technology advised by Professor Vijay Ganesh. I hold a Bachelor of Science in Mathematics from the University of Toronto and a master's degree in Computational Mathematics from the University of Waterloo.

I work on combining (logical) reasoning and (machine) learning to build automated reasoning systems that solve open Math and Physics problems. More concretely, one ongoing line of work combines SAT solvers' search capabilities with Computer Algebra Systems' mathematical domain knowledge to solve hard combinatorial problems.

Selected Publications

2026

• Preprint "MathConstraint: Automated Generation of Verified Combinatorial Reasoning Instances for LLMs", Viresh Pati, Zhengyu Li, Piyush Jha, Rahul Garg, Yatharth Sejpal, Vijay Ganesh.
• Preprint "SAT + NAUTY: Orderly Generation of Small Kochen-Specker Sets Containing the Smallest State-independent Contextuality Set", Zhengyu Li, Curtis Bright, Stefan Trandafir, Adán Cabello, Vijay Ganesh.

2025

• Published "Verified Certificates via SAT and Computer Algebra Systems for the Ramsey R(3,8) and R(3,9) Problems", Zhengyu Li, Conor Duggan, Curtis Bright, Vijay Ganesh. IJCAI 2025 (Acceptance Rate = 19.3%).
• Published "PokerBench: Training Large Language Models to Become Professional Poker Players", Richard Zhuang, Akshat Gupta, Richard Yang, Aniket Rahane, Zhengyu Li, Gopala Anumanchipalli. AAAI 2025 (Acceptance Rate = 23.4%).

2024

• Published "A SAT Solver and Computer Algebra Attack on the Minimum Kochen-Specker Problem", Zhengyu Li, Curtis Bright, and Vijay Ganesh. IJCAI 2024 (Acceptance Rate = 15%).
• Published "A SAT + Computer Algebra System Verification of the Ramsey Problem R(3, 8) (Student Abstract)", Conor Duggan, Zhengyu Li, Curtis Bright, and Vijay Ganesh. AAAI 2024.
• Published "A SAT Solver and Computer Algebra Attack on the Minimum Kochen-Specker Problem (Student Abstract)", Zhengyu Li, Curtis Bright, and Vijay Ganesh. AAAI 2024.
• Preprint "AlphaMapleSAT: An MCTS-based Cube-and-Conquer SAT Solver for Hard Combinatorial Problems", Piyush Jha, Zhengyu Li, Zhengyang Lu, Curtis Bright, and Vijay Ganesh.

2022

• Published "An SC-Square Approach to the Minimum Kochen–Specker Problem", Zhengyu Li, Curtis Bright, and Vijay Ganesh. SC-Square Workshop, Part of IJCAR 22.
• Published "Automatic quantification and classification of microplastics in scanning electron micrographs via deep learning", Shi, B., Patel, M., Yu, D., Yan, J., Li, Z., Petriw, D., ... & Howe, J. Y. (2022). Science of The Total Environment.

2021

• Published "In Tetracycles: a SET Deck Magic Trick", Parker Glynn-Adey, Zhengyu Li. Math Horizons.

News

• May 2026: Passed my PhD qualifier and became a PhD Candidate.
• Summer 2025: Applied Scientist Intern for the Automated Reasoning – NeuroSymbolic AI Team at Amazon Web Services in Boston. I led projects on heuristics generation in SAT solvers with Large Language Models and evolutionary algorithms, and combining LLM Tree of Thoughts with SAT solver feedback to discover new matrix multiplication algorithms.
• Summer 2023: Machine Learning Research Intern for Phenomic AI in Toronto, Canada. I led a project to enhance spatial gene expression analysis using deep learning.
• Summer 2022: Data Science and Advanced Analytics Intern for TD Insurance in Toronto, Canada. I implemented a predictive model using machine learning and PCA on large-scale customer data.

Awards and Honors (more in CV)

• IJCAI Travel Grant — 33rd International Joint Conference on Artificial Intelligence
• Student Travel Scholarship — 36th International Conference on Computer Aided Verification
• Resource Allocation Competitions ($18,841) — Digital Research Alliance
• Best Speaker Award for Master Project Presentation — University of Waterloo
• Ontario Graduate Fellowship — University of Waterloo
• Dean's List Scholar — University of Toronto
• Best VR/AR Application — HackWestern Hackathon 2020
• Best Machine Learning Application Award — Hack the Six Hackathon 2019
• Third Place — Scotiabank & University of Toronto Big Data & A.I. Competition 2019