Library for reading and processing ML training data.

Efficient Triton Kernels for LLM Training

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

Code for the paper: Rotating Features for Object Discovery

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

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

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

Scenic: A Jax Library for Computer Vision Research and Beyond

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

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

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

Repository for Deep Structural Causal Models for Tractable Counterfactual Inference

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

Contrastive Learning of Structured World Models

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

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

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