• Skip to primary navigation
  • Skip to content
  • Skip to footer
    Seunghoon Paik

    Seunghoon Paik

    Stat PhD @ UC Berkeley

    Diffusion

    On this page

    • Prelude: VAE
    • Text-to-image
    • Text-to-video
    • Text-to-text? Diffusion in LM

    Diffusion Part 2: From Text, to Image, Video, and … Text?

    Progress of diffusion models in text-to-image, text-to-video, and non-autoregressive language models, focusing more on key idea and model design.

    Continued from Part 1.


    Coming soon.


    Prelude: VAE


    Text-to-image


    Text-to-video


    Text-to-text? Diffusion in LM

    This website looks best in dark mode. Toggle light/dark mode in the top left corner.
    © 2025 Seunghoon Paik. Powered by Jekyll & Minimal Mistakes. This site uses Google Analytics.