Summary
Raghav Goyal is a Senior Researcher specializing in video understanding and machine learning, with a decade of industry and academic experience spanning Samsung Research America, Google, Meta, and Twenty Billion Neurons. He completed an integrated M.Tech from IIT Delhi and pursued a PhD at UBC under Leonid Sigal, producing research at the intersection of long-video representation learning and unified video understanding (including MAE-style approaches). His internships and research roles reflect a pattern of tackling hard, large-scale video problems—action recognition, long-range temporal modeling, and cross-modal understanding—often bridging theory and practical system implementation. Comfortable in both industrial research labs and academic settings, he brings deep expertise in designing models that scale to real-world video data and a knack for translating state-of-the-art ideas into deployable prototypes.
10 years of coding experience
4 years of employment as a software developer
Indian Institute of Technology Delhi (IIT Delhi)
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at The University of British Columbia