Latent Space Models

Latent Space Models is a type of probabilistic model in latent variable analysis that represents observed data as generated from unobserved (latent) variables structured within a geometric space, where the spatial relationships encode similarities or interactions among entities.

1.2K

Publications

95.8K

Citations

4K

Authors

1K

Institutions

Publications per year

2017–2026

872

Authors

4K

  1. EP
    Eric P. Xing

    Carnegie Mellon University, United States

    9 publications · 306 citations

    9

    h-index

  2. DC
    Daniel Cohen‐Or

    Tel Aviv University, Israel

    9 publications · 629 citations

    9

    h-index

  3. RR
    Robin Rombach

    Ludwig-Maximilians-Universität München, Germany

    8 publications · 15.1K citations

    8

    h-index

  4. AB
    Andreas Blattmann

    Ludwig-Maximilians-Universität München, Germany

    7 publications · 15.1K citations

    7

    h-index

  5. SL
    Sergey Levine

    University of California, Berkeley, United States

    6 publications · 215 citations

    6

    h-index

1–5 of 4K

Venues

  1. arXiv (Cornell University)

    Repository · 171 publications · 9.4K citations

    40

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 29 publications · 2.2K citations

    19

    h-index

  3. 14

    h-index

  4. IEEE Transactions on Pattern Analysis and Machine Intelligence

    TPAMI · 13 publications · 3.1K citations

    13

    h-index

  5. ACM Transactions on Graphics

    TOG · 15 publications · 1.1K citations

    13

    h-index

1–5