Julian Shun

Julian Shun is an associate professor in the Department of Electrical Engineering and Computer Science (EECS) and a member of the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT. Shun designs efficient algorithms and data structures with strong theoretical guarantees and good empirical performance, and high-level programming frameworks that make it easier for programmers to write efficient parallel code. His recent areas of interest include graph analytics, spatial and graph clustering, computational geometry, and financial applications. Shun received a PhD and MS in computer science from Carnegie Mellon University and a BA in computer science from the University of California, Berkeley.

Selected Publications

• Wang, S., Lin, J., Guo, X., Shun, J., Li, J., & Zhu, Y. (2025). Reasoning of large language models over knowledge graphs with super-relations. In Proceedings of the International Conference on Learning Representations (ICLR).
• Lin, J., Guo, X., Zhang, S., Zhou, D., Zhu, Y., & Shun, J. (2024). UnifiedGT: Towards a universal framework of transformers in large-scale graph learning. In Proceedings of the 2024 IEEE International Conference on Big Data (BigData) (pp. 1057–1066).
• Lin, J., Guo, X., Zhu, Y., Mitchell, S., Altman, E., & Shun, J. (2024, November). FraudGT: A simple, effective, and efficient graph transformer for financial fraud detection. In Proceedings of the 5th ACM International Conference on AI in Finance (ICAIF). 

Media

• October 4, 2024: MIT News, Modeling relationships to solve complex problems efficiently
• September 10, 2024: MIT News, School of Engineering faculty and staff receive awards in spring 2024
• July 1, 2024: MIT News, The tenured engineers of 2024