- Website: https://www.cs.toronto.edu/~duvenaud/
- Scholar: https://scholar.google.com/citations?user=ZLpO3XQAAAAJ
I’m an associate professor at the University of Toronto. My research focuses on AGI governance, evaluation, and mitigating catastrophic risks from future systems. I recently finished an extended sabbatical on the Alignment Science team at Anthropic. My past research focused on constructing deep probabilistic models to help predict, explain and design things. Some past highlights:
- Neural ODEs, a kind of continuous-depth neural network,
- Automatic chemical design using generative models,
- Gradient-based hyperparameter tuning,
- Structured latent-variable models for modeling video,
- and Convolutional networks on graphs.
Before Toronto, I was a postdoc in the Harvard Intelligent Probabilistic Systems group with Ryan Adams. I did my Ph.D. at the University of Cambridge, where my advisors were Carl Rasmussen and Zoubin Ghahramani. My M.Sc. advisor was Kevin Murphy at the University of British Columbia. I’m also a founding member of the Vector Institute, a Sloan Research Fellow, and held a Canada Research Chair in Generative Models.