About me
Hi, I’m Jarrid! I’m currently a PhD student at Mila and the Université de Montréal where I’m supervised by Yoshua Bengio. I am also a co-founder of Dreamfold where we try to improve protein design with structure based generative models. Before joining Mila, I completed my undergraduate studies at the University of Michigan where I was a member of Barzan Mozafari’s lab.
My research focuses on the application of machine learning to protein design. I am especially interested in the development of algorithms for efficiently sampling from Boltzmann densities, including things like GFlowNets and diffusion/flow matching models.
Publications
Note that publications may be out of date – refer to google scholar for an updated list.
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
Tara Akhound-Sadegh*, Jarrid Rector-Brooks*, Avishek Joey Bose*, Sarthak Mittal, Pablo Lemos, Cheng-Hao Liu, Marcin Sendera, Siamak Ravanbakhsh, Gauthier Gidel, Yoshua Bengio, Nikolay Malkin, Alexander Tong
Arxiv (2024) linkOn diffusion models for amortized inference: Benchmarking and improving stochastic control and sampling
Marcin Sendera, Minsu Kim, Sarthak Mittal, Pablo Lemos, Luca Scimeca, Jarrid Rector-Brooks, Alexandre Adam, Yoshua Bengio, Nikolay Malkin
Arxiv (2024) linkSe(3)-stochastic flow matching for protein backbone generation
Avishek Joey Bose, Tara Akhound-Sadegh, Kilian Fatras, Guillaume Huguet, Jarrid Rector-Brooks, Cheng-Hao Liu, Andrei Cristian Nica, Maksym Korablyov, Michael Bronstein, Alexander Tong
ICLR (2024) linkLearning Conditional Policies for Crystal Design Using Offline Reinforcement Learning
Prashant Govindarajan, Santiago Miret, Jarrid Rector-Brooks, Mariano Phielipp, Janarthanan Rajendran, Sarath Chandar
Digital Discovery (2024)Thompson sampling for improved exploration in GFlowNets
Jarrid Rector-Brooks, Kanika Madan, Moksh Jain, Maksym Korablyov, Cheng-Hao Liu, Sarath Chandar, Nikolay Malkin, Yoshua Bengio
ICML SPIGM Workshop (2023) linkMolecular fragment-based diffusion model for drug discovery
Daniel Levy, Jarrid Rector-Brooks
ICLR MLDD Workshop (2023) linkConditional Flow Matching: Simulation-Free Dynamic Optimal Transport
Alexander Tong, Nikolay Malkin, Guillaume Huguet, Yanlei Zhang, Jarrid Rector-Brooks, Kilian Fatras, Guy Wolf, Yoshua Bengio
TMLR (2023) linkMulti-Objective GFlowNets
Moksh Jain, Sharath Chandra Raparthy, Alex Hernandez-Garcia, Jarrid Rector-Brooks, Yoshua Bengio, Santiago Miret, Emmanuel Bengio
ICML (2023) linkLearning GFlowNets from Partial Episodes for Improved Convergence and Stability
Kanika Madan, Jarrid Rector-Brooks, Maksym Korablyov, Emmanuel Bengio, Moksh Jain, Andrei Nica, Tom Bosc, Yoshua Bengio, Nikolay Malkin
ICML (2023) linkBiological Sequence Design with GFlowNets
Moksh Jain, Emmanuel Bengio, Alex Hernandez-Garcia, Jarrid Rector-Brooks, Bonaventure F. P. Dossou, Chanakya Ekbote, Jie Fu, Tianyu Zhang, Micheal Kilgour, Dinghuai Zhang, Lena Simine, Payel Das, Yoshua Bengio
ICML (2022) linkRECOVER: Sequential Model Optimization Platform for Combination Drug Repurposing Identifies Novel Synergistic Compounds in vitro
Paul Bertin, Jarrid Rector-Brooks, Deepak Sharma, Thomas Gaudelet, Andrew Anighoro, Torsten Gross, Francisco Martínez-Peña, Eileen L. Tang, Suraj M S, Cristian Regep, Jeremy Hayter, Maksym Korablyov, Nicholas Valiante, Almer van der Sloot, Mike Tyers, Charles Roberts, Michael M. Bronstein, Luke L. Lairson, Jake P. Taylor-King, Yoshua Bengio
Cell Reports Methods (2023) linkDEUP: Direct Epistemic Uncertainty Prediction
Moksh Jain, Salem Lahlou, Hadi Nekoei, Victor Butoi, Paul Bertin, Jarrid Rector-Brooks, Maksym Korablyov, Yoshua Bengio
TMLR (2023) linkRevisiting Projection-Free Optimization for Strongly Convex Constraint Sets
Jarrid Rector-Brooks, Jun-Kun Wang, Barzan Mozafari
AAAI (2019) link
Misc
Besides work, I live with my brilliant partner, our dog Ella, and our cat Clementine. I love hiking, listening to music, drumming (I’m nostalgic for my college marching band days), and playing video games. If you’ve got any questions, or would just like to chat, don’t hesitate to reach out!