Open Models Almanac
Methodsmodel architecturemultimodal architecture

single mention · model architecture

Vision encoder and multimodal aligner

Includes a vision encoder and an aligner in the multimodal inference pathway.

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

Also called vision encoder and aligner.

Filed under model architecture › multimodal architecture