Open Models Almanac
Methodsmodel architecturemultimodal architecture

single mention · model architecture

SigLIP2 vision encoder with dynamic tiling and token reduction

Combines a SigLIP2 vision encoder with dynamic image tiling and visual-token reduction.

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