Ma-Lab-Berkeley/CRATE

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation

Official PyTorch implementation of SegFormer

[CVPR 2026] [Best Paper Finalist] [Oral] Official repository of Vision Test-Time Training

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

A concise but complete full-attention transformer with a set of promising experimental features from various papers

Code implementation from my blog post: https://fkodom.substack.com/p/transformers-from-scratch-in-pytorch

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.