Open Models Almanac
Methodsmodel architecturenormalization & residual

specific method · filed under model architecture

Adaptive Layer Normalization (AdaLN)

Injects conditioning information such as a diffusion or flow-matching timestep through adaptive layer normalization.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See normalization & residual for the methods filed beside it.

Also called adaptive layernorm (AdaLN), adaptive normalization layers (adaLN).

sources
3
models
2
labs adopt it
2
strongest
core

Documented in

Evidence

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

How sources treat it
used 2core 1

Xiaomi-Robotics-1

Xiaomiadopted2 sources

We leverage adaptive normalization layers (adaLN) [49, 48] to inject the flow-matching timestep condition into the DiT for action generation.

usedmodel architecturein Xiaomi-Robotics-0Xiaomi Robotics
1 more from this model

we leverage adaptive normalization layers (adaLN) [57] to inject the flow-matching timestep condition into the DiT for action generation.

usedmodel architecturein Xiaomi-Robotics-1Xiaomi
↑