[KongchangAI]
Model

MLP-Mixer

A vision architecture based on multilayer perceptrons (MLPs) that dispenses entirely with convolution and self-attention, mixing information by alternately applying MLPs along the spatial dimension and the channel dimension.

Timeline (last 90 days)

Nov 14

A developer has open-sourced a Graph HyperNetwork (GHN) project that can predict all weights in a single forward pass for previously unseen ResNet, MLP-Mixer, MobileNet and even Transformer architectures.

Unverified50%
Nov 13

The token mixing and channel mixing of EG-RL draw on the design philosophy of MLP-Mixer-style architectures, decoupling the two dimensions of the feature tensor for separate processing.

Unverified50%

All Facts (2)

Source Articles