Danyal Rehman
Visiting Researcher
About
Danyal is a Banting Postdoctoral Researcher at Mila – Québec AI Institute (advised by Yoshua Bengio) and a visiting researcher with the group, developing diffusion-, flow-, and autoregressive generative models for AI for science. He completed his PhD at MIT, with recent work on Boltzmann generators for molecular sampling (RegFlow, FALCON, Autoregressive Boltzmann Generators).
Specialization
Primary supervisor
Yoshua Bengio
Publications
-
Autoregressive Boltzmann Generators
Danyal Rehman, Charlie B. Tan, Yoshua Bengio, Joey Bose, Alexander Tong
In ICML 2026 (Spotlight)
July 2026
-
FALCON: Few-step Accurate Likelihoods for Continuous Flows
Danyal Rehman, Tara Akhound-Sadegh, Artem Gazizov, Yoshua Bengio, Alexander Tong
In ICLR 2026 (Oral)
May 2026
-
FORT: Forward-Only Regression Training of Normalizing Flows
Danyal Rehman, Oscar Davis, Jiarui Lu, Jian Tang, Michael Bronstein, Yoshua Bengio, Alexander Tong†, Avishek Joey Bose†
ICML GenBio Best Paper Award 2025
July 2025