Previously, I developed models for automated valuations and other high stakes algorithmic decision making at Opendoor, did research on transfer learning in AI/robotics at OpenAI, and led deep learning efforts to build a collaborative human-machine intelligence system at Clara Labs. I’ve also worked on speech synthesis and computational neuroscience for brain-computer interfaces, built the Apple Design Award winning app Mosaic, and founded a mobile behavioral analytics company through Y Combinator.
You can see some of my side projects on Instagram. Lately I’ve been doing a lot of research on novel view synthesis. There are so many incredible applications of comprehensive, high resolution novel view synthesis - the holy grail is what we call total scene capture - can you capture the entirety of a scene to be shared/remembered later? One day we’ll be able to do that with the devices we hold in our pockets, and the world we know and love, in all its ephemeral beauty that simply resists description, needn’t be described. In the meantime, check out my app Vidi for a sneak preview of that future, and ask me about some of the applications for a better teleconferencing experience.
This blog is a compressed version of me. If you want to get in touch with the real me, feel free to email me at xzvf AT tarzain DOT com