The fundamental package for scientific computing with Python.

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

ImageBind One Embedding Space to Bind Them All

High accuracy RAG for answering questions from scientific documents with citations

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

Model interpretability and understanding for PyTorch

Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans

Vector (and Scalar) Quantization, in Pytorch

High-Performance Symbolic Regression in Python and Julia

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

Mastering Diverse Domains through World Models

TensorLy: Tensor Learning in Python.

Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch

Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA

Code base for MinD-Vis

Constrained optimization toolkit for PyTorch

Library for Jacobian descent with PyTorch. It enables the optimization of neural networks with multiple losses (e.g. multi-task learning).

[ICLR2025] Halton Scheduler for Masked Generative Image Transformer

Official Implementation of Semantic Image Synthesis via Diffusion Models

PyTorch implementation of VQ-VAE-2 from "Generating Diverse High-Fidelity Images with VQ-VAE-2"

[NeurIPS2022] Mind Reader: Reconstructing complex images from brain activities

PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning