Showing 2024Show all
2 papers · 1 filter
cs.CV2024
VidTwin: Video VAE with Decoupled Structure and Dynamics
Yuchi Wang, Junliang Guo, Xinyi Xie +3
Recent advancements in video autoencoders (Video AEs) have significantly improved the quality and efficiency of video generation. In this paper, we propose a novel and compact vide…
cs.CL2024
Can bidirectional encoder become the ultimate winner for downstream applications of foundation models?
Lewen Yang, Xuanyu Zhou, Juao Fan +2
Over the past few decades, Artificial Intelligence(AI) has progressed from the initial machine learning stage to the deep learning stage, and now to the stage of foundational model…