differentiable-programming

Productive, portable, and performant GPU programming in Python.

Swift for TensorFlow

A Python framework for accelerated simulation, data generation and spatial computing.

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.

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

Fast and embedded solvers for nonlinear optimal control and nonlinear model predictive control

Hardware accelerated, batchable and differentiable optimizers in JAX.

Swift for TensorFlow Deep Learning Library

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

torchbearer: A model fitting library for PyTorch

Robot kinematics implemented in pytorch

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

🧩 Shape-Safe Symbolic Differentiation with Algebraic Data Types

Julia bindings for the Enzyme automatic differentiator

Differentiable Finite Element Method with JAX

Comprehensive optical design, optimization, and analysis in Python, including GPU-accelerated and differentiable ray tracing via PyTorch.

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

Code for our NeurIPS 2022 paper