Hey, I'm Winnie

Let's reflect on the latest scientific research, challenge the issues facing global communities, and use technology to empower expansive reformation.

My research lies at the intersection of generative models, probabilistic inference, and natural language understanding. My goal is to build interpretable and reliable generalist systems through the incorporation of useful inductive biases and development of powerful learning / inference schemes. Towards this, I explore ways to inject classical algorithms with differentiable components, build efficient methods exploiting intermediate representations of stochastic processes, and improve reasoning in large language models via modularity.

I'm a Student Researcher at Facebook AI Research (Meta AI), also collaborating closely with friends at Stanford StasML.
Previously, I interned with Stefano Ermon and was a Student Researcher at Google Brain with Igor Mordatch (Brain Robotics) / David Dohan (Generative Models).
I was fortunate to begin my AI research journey with David Duvenaud (Vector Institute) where I worked on latent variable models and neural differential equations.

I majored in Artifical Intelligence Computer Science, Statistics and Math at the University of Toronto. During my undergrad, I spent time at Brain/Tensorflow, NVIDIA Research, OATML, and Co:here. In earlier pre-med days, I studied biology and computational genomics with Michael Hoffman at Princess Margaret Cancer Center.

Check out my research / projects to see what I've been up to, and reach out winniexu@cs.toronto.edu if you'd like to chat!

 /   /   /   /   /   / 


2019 xwinxu's Github chart

Winnie Xu 2022.