Xujie Si

Xujie Si is an Assistant Professor in the Department of Computer Science at the University of Toronto. He is also a faculty affiliate at the Vector Institute and an affiliate member at Mila - Quebec AI Institute, holding a Canada CIFAR AI Chair. Previously, he served as an Assistant Professor at McGill University's School of Computer Science.

Education:

• Ph.D., Computer and Information Science, University of Pennsylvania (advised by Mayur Naik)
• M.S., Computer Science, Vanderbilt University
• B.E. (with Honors), Nankai University

Research Focus: His work bridges AI and program reasoning, emphasizing the integration of statistical and logical methods. Key areas include:

• Static analysis and verification using deep learning/reinforcement learning
• Neuro-symbolic systems for urban simulation (e.g., LogiCity)
• Automated theorem proving via LLMs and symbolic reasoning
• Program repair and compiler fuzzing

Recent Article Trends: Recent work focuses on synergizing LLMs with symbolic reasoning (e.g., Olympiad inequality proving), advancing SAT solving with graph neural networks, and applying neuro-symbolic methods to Euclidean geometry formalization.

Awards:

• Canada CIFAR AI Chair (2023)

Lab/Teams: Leads research teams exploring program analysis, neuro-symbolic AI, and formal verification at the University of Toronto and Vector Institute.