Abhinav Shrivastava

Evolutionary Caching to Accelerate Your Off-the-Shelf Diffusion Model

NeRV-Diffusion: Diffuse Implicit Neural Representation for Video Synthesis

Growing Visual Generative Capacity for Pre-Trained MLLMs

LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior

Efficient Continuous Video Flow Model for Video Prediction

Utilization of Neighbor Information for Image Classification with Different Levels of Supervision

Accelerate High-Quality Diffusion Models with Inner Loop Feedback