Currently

At Google, I am working on models that understand the world around them. I'm in the Google Brain team. Current focus areas are video generation and prediction and using that for model-based reinforcement learning. I used to work on fast single-shot detection, image captioning, visual question-answering, as well as structured outputs for image understanding. Formerly, I was part of Google Photos, and built neural network models that understand all the images and photos on the web. Here's an overview from 2013 and 2015.

Previously

• I did my PhD at University of Montreal, on deep learning with Yoshua Bengio.
• In 2011-2012, I was at Yahoo Labs, where I improved Federated Search, the ranking of search results (web, news, movies, shopping etc.) on the Yahoo Search results page.

Publications

My up-to-date list of publications can be found on my Google Scholar or ResearchGate, which do a better job than me at indexing them.

Stuff

• Download my résumé
• Email:
• My wife, a research scientist at the Berkeley Lab.

Social

I'm on Facebook, Google+, LinkedIn, Mastodon, and Twitter.