Yash Kant is a research scientist and PhD graduate from the University of Toronto with a decade of experience building large-scale diffusion and vision models for industry leaders including Netflix, Meta, and Snap. He specializes in high-resolution and HDR video diffusion, controllable video models for reshooting and editing, and extending diffusion techniques to 3D and novel view synthesis. His work spans both foundational research—published at CVPR, SIGGRAPH Asia, ECCV and ICCV—and product-facing systems, such as Reality Labs’ first 1K diffusion model trained on billions of human images. Based in Los Angeles, he bridges academic rigor with production at-scale engineering, often focusing on practical training strategies and dataset design that enable next-generation content creation. An understated strength is his track record of moving prototype research into high-resolution, studio-grade models used in real-world creative pipelines.
10 years of coding experience
2 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Vision, Doctor of Philosophy - PhD, Computer Vision at Department of Computer Science, University of Toronto
Contributions:29 commits, 3 pushes, 1 comment in 2 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.