Siamak Ravanbakhsh

Siamak Ravanbakhsh is an Associate Professor at McGill University's School of Computer Science and a Canada CIFAR AI Chair at Mila. His research focuses on machine learning, particularly representation learning with an emphasis on geometry, symmetry, and probabilistic inference. He has held academic positions at the University of British Columbia and was a postdoctoral fellow at Carnegie Mellon University.

• Education:
  • B.Sc. in Computer Science, Sharif University of Technology
  • M.Sc. and Ph.D. in Computer Science, University of Alberta (supervised by Russ Greiner)
  • Postdoctoral Fellowship at Carnegie Mellon University (with Barnabás Póczos and Jeff Schneider)

His research interests span geometric deep learning, equivariant networks, reinforcement learning, and AI for scientific applications. Notable contributions include work on symmetry-aware models, diffusion processes, and equivariant representation learning.

Publications highlight advancements in causal abstraction, diffusion-based anomaly detection, and equivariant architectures for crystals and hierarchical structures. His work often bridges theory and application, emphasizing symmetry principles.

• Advising & Grants:
  • Supervised over 20 graduate students and postdocs, including recent PhD graduates Daniel Levy and Mehran Shakerinava
  • Active in mentoring M.Sc. and internship students

He contributes to academic leadership roles at Mila and McGill, fostering interdisciplinary collaborations in AI research.