Open Models Almanac
Methodsmodel architecturemultimodal architecture

single mention · model architecture

Reusing image tokens for video frames

Uses the image token for video frames, with frame spans delimited by video start and end tokens.

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 reusing image token for video frames.

Filed under model architecture › multimodal architecture