Open Models Almanac
Methodsmodel architecturemultimodal architecture

single mention · model architecture

Vision-language model with diffusion-transformer action head

Combines a vision-language foundation model with a diffusion-transformer head that denoises continuous actions.

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