avery (hee-woon) ryoo 🦖

Hey! I'm Avery, a CS PhD student at Mila and Université de Montréal, where I work with Guillaume Lajoie and Matt Perich.

I am primarily interested in deep generative models, especially in their potential for few-shot reasoning and adaptation. I aim to use ideas from test-time training, compositionality, and dynamical systems theory to design generative frameworks that are faster and more intelligent — a crucial step in mitigating the widening resource disparity in an era of increasingly large models. I am also broadly interested in their applications, particularly in scientific discovery and medicine.

In another life, I studied biomedical engineering at the University of Waterloo, during which I completed several internships in data science, computer vision research, and brain-computer interfaces. Outside of research, I enjoy watching Toronto sports teams, bouldering, and cooking for friends.