Productive & portable high-performance programming in Python.

Swift for TensorFlow

10 differentiable physical simulators built with Taichi differentiable programming (DiffTaichi, ICLR 2020)

A general-purpose probabilistic programming system with programmable inference

High-performance automatic differentiation of LLVM and MLIR.

Hardware accelerated, batchable and differentiable optimizers in JAX.

Swift for TensorFlow Deep Learning Library

Compositional Differentiable Programming Library

torchbearer: A model fitting library for PyTorch

A high-fidelity 3D face reconstruction library from monocular RGB image(s)

Pytorch-based framework for solving parametric constrained optimization problems, physics-informed system identification, and parametric model predictive control.

🧩 Shape-Safe Symbolic Differentiation with Algebraic Data Types

TorchOpt is an efficient library for differentiable optimization built upon PyTorch.

Julia bindings for the Enzyme automatic differentiator

Code for our NeurIPS 2022 paper

[ICLR 2021 top 3%] Is Attention Better Than Matrix Decomposition?

Code repository for our paper DiffCloth: Differentiable Cloth Simulation with Dry Frictional Contact

PyNeuraLogic lets you use Python to create Differentiable Logic Programs

Experimental tensor-typed deep learning

Robot kinematics implemented in pytorch