Evaluating Language Models as Synthetic Data Generators Paper • 2412.03679 • Published 22 days ago • 43
STIV: Scalable Text and Image Conditioned Video Generation Paper • 2412.07730 • Published 16 days ago • 69
Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation Paper • 2412.06016 • Published 18 days ago • 20