Xujie Si

简介

Xujie Si is an Assistant Professor and Canada CIFAR AI Chair in the School of Computer Science at McGill University and at Mila - Quebec AI Institute. His research interests span programming languages, software engineering, security, and artificial intelligence, focusing on deep learning and reinforcement learning techniques for program reasoning challenges such as verification, synthesis, and testing. He also designs logic-inspired neural architectures and neuro-symbolic systems for interpretable and data-efficient learning.

教育经历

• Ph.D. Computer and Information Science, University of Pennsylvania, 2020
• M.S. Computer Science, Vanderbilt University, 2014
• B.E. (with Honors), Nankai University, 2011

代表成果

• Identifying different student clusters in functional programming assignments: From quick learners to struggling students
• Learning for SAT and #SAT (Model Counting)
• Language models for novice type error diagnosis
• Code2Inv: A deep reinforcement learning framework for program verification
• Meta-learning for syntax-guided program synthesis
• Learning-aided reasoning
• SG-SANet: Symbol grounding for learning and reasoning over raw pixels
• Scallop: Neuro-symbolic reasoning over raw pixels and knowledge bases
• APISan: Inferring API specifications from big code
• Improving static analysis accuracy by learning from user feedback