Open Models Almanac
Methodsmodel architecturemultimodal architecture

single mention · model architecture

Dedicated visual and audio encoders with lightweight projectors

Connects dedicated pretrained visual and audio encoders to the language backbone through lightweight projectors.

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.

Filed under model architecture › multimodal architecture