Diffusion Models

Diffusion Models is a generative modeling framework that belongs to the class of probabilistic latent variable models, distinguished by its sequential process of gradually transforming data into noise through a forward diffusion process and subsequently learning to reverse this process for data generation.

2.4K

Publications

205.9K

Citations

7.5K

Authors

1.8K

Institutions

Publications per year

2017–2026

1.3K

Authors

7.5K

  1. SE
    Stefano Ermon

    Stanford University, United States

    15 publications · 2.4K citations

    14

    h-index

  2. JC
    Jong Chul Ye

    Korea Advanced Institute of Science and Technology, South Korea

    14 publications · 1.6K citations

    13

    h-index

  3. WP
    Wilton Pereira da Silva

    Universidade Federal de Campina Grande, Brazil

    14 publications · 481 citations

    12

    h-index

  4. TS
    Tim Salimans

    Google (United States), United States

    13 publications · 7.6K citations

    12

    h-index

  5. JS
    Jiaming Song

    Stanford University, United States

    12 publications · 1.2K citations

    12

    h-index

1–5 of 7.5K

Venues

  1. arXiv (Cornell University)

    Repository · 375 publications · 32.7K citations

    64

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 29 publications · 1.9K citations

    21

    h-index

  3. The Journal of Chemical Physics

    22 publications · 1.7K citations

    17

    h-index

  4. IEEE Transactions on Medical Imaging

    16 publications · 1.4K citations

    15

    h-index

  5. Technological Forecasting and Social Change

    15 publications · 905 citations

    14

    h-index

1–5