# REViT-v2: Hierarchical Windowed Roto-reflection Equivariant ViT for Equivariant Feature Extraction

arXiv: https://arxiv.org/abs/2610.07585 · HTML: https://mlsanity.com/paper/2610.07585/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 12 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 1 of 1)

- [REViT: Roto-reflection Equivariant Convolutional Vision Transformer](https://mlsanity.com/paper/2606.25318/) (2026)

## Abstract (arXiv)

We propose a scalable roto-reflection-group-equivariant vision transformer based on windowed group-convolutional self-attention and a hierarchical feature architecture. We demonstrate that our approach can be scaled to group-equivariant vision transformers (ViTs) with millions of parameters and large datasets with practically sized images, i.e., ImageNet. The code and pretrained weights for the proposed Hierarchical Windowed Roto-reflection Equivariant ViTs (REViT-v2) are available at https://github.com/kc-ml2/revit.