co-me-tokens/CoMe

Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers

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

A place to store reusable transformer components of my own creation or found on the interwebs

[CVPR 2026 Hightlight] OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer

🐍 Geometric Computer Vision Library for Spatial AI

Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on high-res images

Collection of common code that's shared among different research projects in FAIR computer vision team.

Hackable and optimized Transformers building blocks, supporting a composable construction.

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data