Open Models Almanac
Methodsmodel architecturemultimodal architecture

single source · model architecture

Depth-aware perception tokens

Uses depth perception tokens as a representation for spatially grounded action reasoning.

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 Depth perception tokens.

Filed under model architecture › multimodal architecture