Latent Dynamics Models

Latent Dynamics Models is a type of dynamics model in robot learning that represents environment transitions in a compressed, unobserved (latent) state space, enabling efficient and accurate prediction of future states by capturing essential physical or behavioral patterns while filtering out sensory redundancies.

187

Publications

11.3K

Citations

665

Authors

303

Institutions

Publications per year

2017–2026

136

Authors

665

  1. LE
    Lee E. Miller

    Northwestern University, United States

    5 publications · 277 citations

    5

    h-index

  2. MG
    Matthew G. Perich

    Northwestern University, United States

    3 publications · 211 citations

    3

    h-index

  3. YC
    Youngsoo Choi

    Lawrence Livermore National Laboratory, United States

    3 publications · 122 citations

    3

    h-index

  4. MJ
    Mehrdad Jazayeri

    McGovern Institute for Brain Research, United States

    3 publications · 352 citations

    3

    h-index

  5. MS
    Maneesh Sahani

    University College London, United Kingdom

    3 publications · 98 citations

    3

    h-index

1–5 of 665

Venues

  1. arXiv (Cornell University)

    Repository · 35 publications · 1.8K citations

    20

    h-index

  2. bioRxiv (Cold Spring Harbor Laboratory)

    Repository · 5 publications · 106 citations

    5

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 4 publications · 100 citations

    4

    h-index

  4. Nature Communications

    4 publications · 363 citations

    4

    h-index

  5. Structural Equation Modeling A Multidisciplinary Journal

    SEM · 4 publications · 325 citations

    4

    h-index

1–5