Open Models Almanac
Methodsmodel architecturenormalization & residual

single mention · model architecture

Learned depth gate on expert conditioning

Uses a learned gate to control depth-token conditioning on an action expert.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See normalization & residual for the methods filed beside it.

Also called Learned gating of depth-token conditioning.

Filed under model architecture › normalization & residual