Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Library for reading and processing ML training data.

Efficient Triton Kernels for LLM Training

Flax is a neural network library for JAX that is designed for flexibility.

Scenic: A Jax Library for Computer Vision Research and Beyond

Pretrained deep learning models for Jax/Flax: StyleGAN2, GPT2, VGG, ResNet, etc.

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

A collection of resources regarding the interplay between differential equations, deep learning, dynamical systems, control and numerical methods.

Code for the paper: Rotating Features for Object Discovery

A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods

Matplotlib style sheets to nicely format figures for scientific papers, thesis and presentations while keeping them fully editable in Adobe Illustrator.

🚀 A powerful library for efficient training of Neural Fields at scale.

Repository for Deep Structural Causal Models for Tractable Counterfactual Inference

Code for the paper: Complex-Valued Autoencoders for Object Discovery

CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning

[AAAI 2020 Oral] Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution

Contrastive Learning of Structured World Models