I am a machine learning researcher and computer programmer. I am currently a Research Engineer at Facebook AI Research.

My career interests have been defined by two sets of work: machine learning platforms, research in machine learning

Machine Learning Platforms

I love open-source communities and advocate for open research. I have a lazy and simplistic attitude to programming, and I like fast prototyping of ideas, even at the cost of shady engineering practices.

With this perspective, I’ve helped build the machine learning platform PyTorch and maintained Torch-7, EBLearn and several open-source projects in the ML space.

I think deeply about the cultural aspects and social dynamics of open-source software. Some of these thoughts formed the basis for building vibrant and large communities of users and contributors around PyTorch and Torch. I am proud to have maintained Torch at it’s peak, when three large companies were using it (Deepmind, Twitter, Facebook), and I am proud to co-maintain PyTorch with hundreds of companies, research labs and individuals using it.

I learned interesting things while maintaining a large project written in a niche language (Torch was written in Lua). If you ask me about it, I’ll tell you fun stories.

I also like helping people with their questions, and have answered thousands of questions across the PyTorch and Torch forums. Unfortunately, this responsiveness doesn’t extend to my email, and I’m often really slow to respond to email.

Research in Machine Learning

My primary interest is to build a household robot that helps me with all kinds of chores. To help this robot reason well, I want to build a world simulator. To build this world simulator, I’ve been interested in multi-modal models (that combine vision, speech, text, robots), generative models (for vision and speech) and efficient representations for encoding the human-centric world. Because of these ambitions, I often try to avoid toy or hypothetical problems, even as proxies.

My secondary interests are in research that intersects between Computer Systems and Machine Learning, partly motivated by my work on Machine Learning Platforms.

I’ve made some progress on exploring my research interests.

In the past, I’ve worked on robotics, object and human detection, generative modeling of {images, videos}, AI for video games, ML systems research. Some of my most cited work is on Generative Adversarial networks (GANs), where I co-authored three well-cited papers: LAPGANdemo, DCGANcode/demo and Wasserstein GAN.

You can see a full list of my peer-reviewed or pre-print manuscripts on my Google Scholar page.