Biography
I’m a Research Engineer at Google DeepMind where I’ve been since 2017. I’m interested in representation learning, scene understanding, and generative models. Back in the day, I trained for the Indian National team for the Informatics Olympiad (‘09, ‘10), and represented the UAE at the World Robot Olympiad (Taiwan ‘07, Japan ‘08).
Fun fact: I have lived in every country whose name begins with “United.”
Interests
- Visual Perception
- Multimodal Learning
- Analysis by Synthesis
- Causality
Education
PhD in Computer Science, 2023-present
University College London
MSc in Applied Statistics, 2015
University of Oxford
BS in Computer Science (Minor in Mathematics), 2014
Massachusetts Institute of Technology
Recent Posts
Recent Publications
Quickly discover relevant content by filtering publications.
(2026).
COBALT: Censored Optimization and Bayesian Active Learning Techniques.
UAI 2026.
(2026).
Video Generation Models are General-Purpose Vision Learners.
ECCV 2026.
(2026).
A Mixed Diet Makes DINO An Omnivorous Vision Encoder.
arXiv.
(2026).
How to Spin an Object: First, Get the Shape Right.
CVPRW 2026.
Contact
Please reach out if you’re interested in any of my work.