A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

Visualisations of data are at the core of every publication of scientific research results. They have to be as clear as possible to facilitate the communication of research. As data can have differ…

Generating 3D Hilbert curves

Domain adaptation toolbox compatible with scikit-learn and pytorch

TorchDR - PyTorch Dimensionality Reduction

A reactive Python kernel for Jupyter notebooks.

Python Library for Signal/Image Data Analysis with Transport Methods

JAX implementation of the JKOnet* architecture presented in "Learning Diffusion at Lightspeed".

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

ICLR22 "Fast Differentiable Matrix Square Root" and T-PAMI extension

Matrix square root with gradient support for PyTorch

BlackJAX is a Bayesian Inference library designed for ease of use, speed and modularity.

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Optimal transport tools implemented with the JAX framework, to get differentiable, parallel and jit-able computations.

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git.

Official Implementation for The Numerical Stability of Hyperbolic Representation Learning

Code for Supervised Word Mover's Distance (SWMD)

TorchCFM: a Conditional Flow Matching library

Hyperbolic Embeddings

This is the official GitHub repo for "Deep Optimal Transport for Domain Adaptation on SPD Manifolds"

Computations and statistics on manifolds with geometric structures.

About A collection of AWESOME things about information geometry Topics

Differentiable signal processing on the sphere for PyTorch

A package for Multiple Kernel Learning in Python

A Python library for variational inference with normalizing flow and annealing

An extension of the PyTorch library containing various tools for performing deep learning in hyperbolic space.