VQVAE(image level) - 《Neural Discrete Representation Learning》2017 Google Deepmind
C-VIVIT (video level) - 《PHENAKI》2023 ICLR Goole Brain
MaGViT2（video level）-《LANGUAGE MODEL BEATS DIFFUSION》 2024 ICLR Google
TECO (video level) - 《Temporally Consistent Transformers for Video Generation》 2023 ICLR UC Berkley