Banting Postdoctoral Researcher @ Mila – Québec AI Institute ·· Ph.D. @ MIT
I'm a Banting Postdoctoral Researcher at Mila – Québec AI Institute, advised by Yoshua Bengio on the development of diffusion/flow-based and autoregressive generative models for AI for Science. I also hold visiting research appointments at both the Broad Institute of MIT & Harvard and AITHYRA.
Previously, I completed my Ph.D. from the Massachusetts Institute of Technology (MIT). During that time, I was awarded research fellowships from the Martin Family Society of Fellows for Sustainability and the Abdul Latif Jameel (J-WAFS) World Water and Food Systems Lab. Prior to that, I completed my undergraduate degree from the University of Toronto with High Honours.
My Ph.D. focused on the development of physics-informed deep learning methods and accelerated partial differential equations (PDEs) solvers for physics-based applications. Examples include neural differential equation models for molecular/ion transport phenomena (under John Lienhard) and self-supervised learning (SSL) methods with Lie point symmetries for PDEs (under Yann LeCun). More recently, my interests have extended to generative modelling for applications to AI for Science.
Recent Highlights
Selected Publications
Autoregressive Boltzmann Generators.
Danyal Rehman, Charlie B. Tan, Yoshua Bengio, Avishek Joey Bose, Alexander Tong.
Coming soon.
FALCON: Few-step Accurate Likelihoods for Continuous Flows.
Danyal Rehman, Tara Akhound-Sadegh, Artem Gazizov, Yoshua Bengio, Alexander Tong.
Published at ICLR (2026) (Oral). Presented at NeurIPS – Machine Learning for Structural Biology Workshop (2025).
Efficient Regression-based Training of Normalizing Flows for Boltzmann Generators.
Danyal Rehman, Oscar Davis, Jiarui Lu, Jian Tang, Michael Bronstein, Yoshua Bengio, Alexander Tong, Avishek Joey Bose.
Published at ICLR (2026). Received the Best Paper Award at the ICML Generative AI for Biology Workshop (2025).
A Generative Deep Learning Approach to De Novo Antibiotic Design.
Aarti Krishnan, Melis N. Anahtar, Jacqueline A. Valeri, ..., Danyal Rehman, ..., Felix Wong, James J. Collins.
Published in Cell (2025).
Physics-informed Deep Learning for Multi-species Membrane Transport.
Danyal Rehman and John H. Lienhard.
Published in Chemical Engineering Journal (2024). Presented at ICLR – Physics for Machine Learning Workshop (2023).
Self-supervised Learning with Lie Symmetries for Partial Differential Equations.
Grégoire Mialon, Quentin Garrido, Hannah Lawrence, Danyal Rehman, Yann LeCun, Bobak T. Kiani.
Published at NeurIPS (2023). Presented at NeurIPS – AI for Science Workshop (2023).