Co-founder & Co-CEO, Dotmo
I’ve worked on video generation since before it worked, starting with MoCoGAN in 2017. At Snap I founded the Creative Vision research team and grew it to more than 20 people, hosting about 30 interns a year. Together we became one of the most prolific research teams in generative AI, spanning video, images, 3D and 4D. Along the way we developed four generations of the Snap Video model family and the on-device image models SnapFusion and SnapGen. Our work went into Snapchat’s AI video clips and its ML, 3D and 4D Lenses, along with much of the technology behind Snap’s most engaging products, which reach hundreds of millions of people every day.
Now the core of that team is building Dotmo, and we’re hiring researchers, engineers and designers.
At Dotmo we’re building a new platform for games and social experiences. At its core is a foundational layer of playable models: generative models you play, not just watch or steer a camera through. Everything on the platform, from 3D worlds to 2D games and puzzles, is generated live, follows real rules, reacts to what each player does, and can be shared by many players at once.
The idea goes back to 2021, when we introduced playable video generation and showed that game-like controls can be learned automatically from unlabeled videos.
Since 2018, we have invented and kept improving the core technology behind Snapchat’s Gen AI Lenses, from the first real-time generative networks on the phone to fast, scalable Lenses generated on the server. Many teams built the Lenses themselves on top of our technology. Snap co-founder Bobby Murphy said that “our popular gender and age transformation lenses, our anime lens, our cartoon lens… have become incredible viral hits”.
I’ve published more than 100 papers at top venues including CVPR, NeurIPS, ICLR, ICML, ICCV, ECCV, SIGGRAPH, TPAMI and IJCV, and hold more than 50 granted US patents, with dozens more pending.


Selected works. 17,000+ citations, h-index 56. Full record on Google Scholar.







