About Me
I’m an Assistant Professor of Computer Science at York University, a Faculty Affiliate at the Vector Institute and an Adjunct Professor in the University of Toronto Department of Computer Science. I am a member of the Centre for Vision Research and core member of the Vision: Science to Application (VISTA) program. I currently serve as an Associate Editor for IET Computer Vision and have been an Area Chair for a number of conferences.
I was a Researcher Director (2018-2020) at Borealis AI where I continue to work as an Academic Advisor. I am also a co-founder and advisor of Structura Biotechnology (makers of cryoSPARC), one of the original contributors to Stan and was a Research Associate at Cadre Research Labs (makers of TopMatch-GS). I studied at the University of Toronto where I received my PhD in 2011. I also did postdocs at the Toyota Technological Institute at Chicago and the University of Toronto. See my CV for more details.
Research Interests
I am interested in building rich, detailed models which capture fundamental relationships between the world and our observations of it. Such models ultimately enable us to measure and predict sometimes surprising details.
Most recently I have been focusing on probabilistic generative models, specifically normalizing flows. My research has been exploring theoretical aspects of normalizing flows and their applications. I also have an interest on the problem of estimating the 3D structure of biological molecules such as proteins and viruses with Cryo-EM. Beyond those current focuses, I have also worked on vehicle localization for robotics, physically realistic models of human motion, probabilistic programming languages, Bayesian methods, MCMC and forensic ballistics.
Prospective Students
Interested in joining my group? I’m also on the look out for exceptional students and colleagues to work with. More information is available here.
Recent News
Differential Privacy Tutorial (Part 2)
The second part of my tutorial on differential privacy is now available. The first part was a basic introduction to DP, while part II focuses on using differential privacy in the context of machine learning.
Paper Accepted for CVPR 2021
HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms with Michael Brown and Mahmoud Afifi has been accepted at CVPR 2021. Congratulations and thanks to the student, Mahmoud Afifi, and his supervisor Michael Brown for the fruitful collaboration!
Differential Privacy Tutorial (Part 1)
I recently wrote a tutorial on differential privacy. The first part is available now and the second part is coming soon.
Normalizing Flows Tutorial at CVPR 2021
Happy to announce that Ullrich Koethe and I will be again running our tutorial on Normalizing Flows and Invertible Neural Networks in Computer Vision at CVPR 2021. This will be an updated version of the tutorial we presented at ECCV 2020. The introductory video from that offering is available here. Feel like something should have been presented differently? Want to see more about some other topics? Let me know, feedback is welcome!
Faculty Affiliate at the Vector Institute
Happy to announce that my Faculty Affiliate status at the Vector Institute has been renewed!
Introduction to Normalizing Flows
This summer I presented a tutorial at ECCV 2020 on normalizing flows with Ullrich Koethe and Carsten Rother. I’ve finally uploaded my lecture which provides an introduction to normalizing flows. Feedback is welcome!
Paper and Code for Wavelet Flow
The code and paper for our NeurIPS 2020 paper, Wavelet Flow: Fast Training of High Resolution Normalizing Flows, is now available. The code is availble through the Wavelet Flow GitHub Project. The paper can be found on arXiv. All of this, and additional image results, can be found on the Wavelet Flow Project Page. If you have questions, feel free to get in touch or check us out at our poster session at NeurIPS 2020.
Two Papers Accepted for NeurIPS 2020
Two papers on normalizing flows have been accepted at NeurIPS 2020. Congratulations and thanks to the students, Jason and Ruizhi, and my excellent collaborators!
- Wavelet Flow: Fast Training of High Resolution Normalizing Flows with Jason Yu and Konstantinos Derpanis (arxiv preprint to come)
- Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows with Ruizhi Deng, Bo Chang, Greg Mori and Andreas Lehrmann
Launch of New Website
I’ve finally launched a new website based on GitHub Pages. This should make it easier for me to maintain and add content. Keep an eye on things over the coming weeks as I work to expand and improve its contents. My old York EECS website is still availble here and my ancient UofT DCS website is still available here, although I am planning to take down my DCS page soon.
Area Chair for CVPR 2021 and AAAI 2021
I’m happy to announce that I’ll be serving as an Area Chair at CVPR 2021 and AAAI 2021.
ICML 2020 Paper on Tail Behaviour of Normalizing Flows
Our paper on the “Tails of Lipschitz Triangular Flows” has been accepted for publication at ICML 2020. If you’re attending, be sure to stop by and chat.
Review article on Normalizing Flows
I recently co-authored a review article (preprint version) on Normalizing Flows which will be published in IEEE Transactions of Pattern Analysis and Machine Intellgience. Normalizing Flows is a topic that I’m excited about and looking to work more on in the future. If you’ve not seen it before, please check it out.
Return to Academia
I have returned full time to academia! At the moment I am working on expanding my lab and restarting my research program. Watch this space for updates in the near future!
For more news see here.