Open Models Almanac
Methodsmodel architecture

specific method · filed under model architecture

Mixture-of-Transformers (MoT)

An architecture organizing a model from multiple transformer components, with the evidence giving a vision-language model and a diffusion transformer as an example.

The sources on this page name it without explaining how it works. The line above is the extraction's one-line gloss. See model architecture for the methods filed beside it.

Also called Mixture-of-Transformers architecture, Mixture-of-Transformers (MoT) architecture.

sources
3
models
2
labs adopt it
2
strongest
core

Documented in

Robbyant (Ant Group)

Evidence

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

How sources treat it
core 3

Xiaomi-Robotics-1

Xiaomiadopted2 sources

Xiaomi-Robotics-1 adopts a Mixture-of-Transformers (MoT) architecture consisting of a pre-trained vision-language model (VLM) (i.e., Qwen3-VL [3]) and a diffusion transformer (DiT) [57].

coremodel architecturein Xiaomi-Robotics-1Xiaomi
1 more from this model

Xiaomi-Robotics-0 adopts a mixture-of-transformers (MoT) model architecture.

coremodel architecturein Xiaomi-Robotics-0Xiaomi Robotics
↑