Sign inSign in
ConceptAI & ML

V-JEPA

A JEPA architecture trained on video by predicting the representation of a full video from a partially masked or corrupted video.
as Yann LeCun defines itHarvard University
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

I-JEPA1Joint-embedding architectures1

Lecturers

1

    Connections

    2

    The lectures that define it or assume it, and the concepts next to it.

    Concept1

    1 lecturer. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.