Hi!👋 I'm a research scientist at Luma working on video generation research. I'm also finishing up my last year of undergrad at UCLA studying math and statistics. I'm super interested in generative video models and the representations they learn of the world.
A generative text-to-video and image-to-video model scaled to a large pre-training dataset. We explore the impact of different data-filtering and synthetic captioning techniques to train powerful foundation video models.
Projects
Video2dataset
Maciej Kilian, Romain Beaumont, Daniel Mendelevitch, Sumith Kulal, Andreas Blattmann
(blogpost)
A tool to easily create large-scale video datasets from urls.