Sign inSign in
ConceptAI & ML

adaLN-zero

An initialization strategy for DiT blocks where scale, shift, and gating parameters are initialized to zero to represent identity functions initially.
as Sayak Paul defines itStanford 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.

Adaptive layer normalization1ResNet initialization1

Lecturers

1

    Connections

    2

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

    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.