News
Graduated with my PhD in Computer Science from the University of Toronto. 🎓
We announced SIMA 2, a Gemini-powered generalist agent that plays, reasons, and learns with you in virtual 3D worlds.
LMAct, our benchmark for in-context imitation learning with long multimodal demonstrations, appeared at ICML 2025.
We announced Genie 2, a large-scale foundation world model that generates playable 3D environments.
Projects
SIMA 2
A Gemini-powered generalist agent that plays, reasons, and learns alongside you across many virtual 3D worlds.
Google DeepMind
Genie 2
A large-scale foundation world model that turns a single image into a playable, action-controllable 3D environment.
Google DeepMindResearch
World models
Foundation models that learn to simulate rich, interactive environments you can act inside, explore, and generate on the fly.
General agents
Agents that perceive, plan, and act across many worlds, following language and generalizing to tasks they were never trained on.
Learning from language and interaction
How agents learn from instructions, demonstrations, and feedback, spanning reinforcement learning, imitation, and multimodal foundation models.
Selected publications
All publications
About
I'm a research scientist at Google DeepMind working on world models and general agents. I completed my PhD in Computer Science at the University of Toronto as part of the Machine Learning Group, co-supervised by Prof. Jimmy Ba and Prof. Sheila McIlraith. During my MSc, I was co-supervised by Prof. Sanja Fidler and Prof. Jimmy Ba.
Along the way I've done research internships at Google DeepMind (with Vlad Mnih), Google Brain Robotics (with Ted Xiao), Google Research, Google Brain Toronto (with William Chan and Jamie Kiros), and Borealis AI. More details are in my CV.
Outside of research, I'm a speedcuber. 🧩
Background
- Google DeepMindResearch Scientist, world models & general agents
- Research internshipsGoogle DeepMind, Google Brain (Robotics & Toronto), Google Research, Borealis AI
- PhD & MSc, Computer ScienceUniversity of Toronto, Machine Learning Group
- IndustryIntel PSG (OpenCL usability), Qualcomm (video processing)
- BASc, Engineering ScienceUniversity of Toronto, ECE major; thesis with Prof. Deepa Kundur
Teaching
- CSC413/2516 Neural Networks & Deep Learning · Winter 2020–2022 (Head TA, Co-Head TA)
- CSC311 Introduction to Machine Learning · Fall 2019/2020
- ECE421 Introduction to Machine Learning · Winter 2019
- MIE324 Introduction to Machine Intelligence · Fall 2018
- CSC321 Introduction to Neural Networks · Winter 2018
- CSC411 Introduction to Machine Learning · Fall 2017
Talks
- Closing the generalization gap in stochastic optimization through Fisher gradient noise · Vector Institute, Toronto · Feb 2018
- More presentations →