Open Models Almanac
Methodsmodel architecturemultimodal architecture

specific method · filed under model architecture

Joint multimodal decoding in a shared hidden space

Projects all modalities into a shared hidden space and processes them jointly in the decoder.

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.

sources
3
model
1
lab adopt it
1
strongest
core

Documented in

Thinking Machines Lab

Evidence

3 quotes from 3 sources, one card per model, each opening with its strongest.

How sources treat it
core 3

Inkling

Thinking Machines Labadopted3 sources

with all modalities projected into a shared hidden space and processed jointly by the decoder

coremodel architecturein InklingThinking Machines Lab
2 more from this model

with all modalities projected into a shared hidden space and processed jointly by the decoder

coremodel architecturein InklingThinking Machines Lab

with all modalities projected into a shared hidden space and processed jointly by the decoder

coremodel architecturein InklingThinking Machines Lab

Further reading

Picked by hand, not extracted: where to read more, not evidence for anything on this page.

↑