Personalized Residuals for Concept-Driven Text-to-Image Generation
27:39
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
41:27
Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video
44:09
Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent
42:48
Generative Image Dynamics (CVPR2024 best paper award)
7:50
Scale AI CEO Alexandr Wang on U.S.-China AI race: We need to unleash U.S. energy to enable AI boom
24:13
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
48:40
Make It Count: Text-to-Image Generation with an Accurate Number of Objects
41:49