Jae Hyun Lim
PhD candidate in CS @ Mila, Université de Montréal

I’m a final-year Ph.D. student in Computer Science at Mila, Université de Montréal, advised by Chris Pal. My research focuses on approximate inference in deep generative models and deep reinforcement learning, with a particular interest in diffusion and flow-based models. I received my B.S. in Bio and Brain Engineering and my M.S. in Electrical Engineering from KAIST.
email | google scholar | github | linkedin | xnews
Oct 15, 2021 | I’m selected to receive a NeurIPS 2021 Outstanding Reviewer Award (the top 8% of reviewers)! |
Sep 29, 2021 | Our paper A Variational Perspective on Diffusion-Based Generative Models and Score Matching is accepted to NeurIPS 2021 and selected as a spotlight! |
Jan 2, 2021 | Our paper Bijective-Contrastive Estimation is accepted to AABI symposium 2021! (selected for a contributed talk) |
Jun 11, 2020 | Our paper AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation is accepted to ICML2020! |
projects




-
Neural Multisensory Scene Inference In Advances in Neural Information Processing Systems 2019 [project page] [code] [pdf]