A Python framework for GPU-accelerated simulation, robotics, and machine learning.
-
Updated
Oct 5, 2026 - Python
A Python framework for GPU-accelerated simulation, robotics, and machine learning.
Pytorch-based framework for solving parametric constrained optimization problems, physics-informed system identification, and parametric model predictive control.
Hardware accelerated, batchable and differentiable optimizers in JAX.
Comprehensive optical design, optimization, and analysis in Python, including GPU-accelerated and differentiable ray tracing via PyTorch.
Robot kinematics implemented in pytorch
Differentiable Finite Element Method with JAX
torchbearer: A model fitting library for PyTorch
TorchOpt is an efficient library for differentiable optimization built upon PyTorch.
Code for our NeurIPS 2022 paper
[ICLR 2021 top 3%] Is Attention Better Than Matrix Decomposition?
PyNeuraLogic lets you use Python to create Differentiable Logic Programs
Differentiable Computational Lithogrpahy Framework
S2FFT: Differentiable and accelerated spherical transforms
A unified end-to-end learning and control framework that is able to learn a (neural) control objective function, dynamics equation, control policy, or/and optimal trajectory in a control system.
A probabilistic programming language for metacognitive modeling
A JAX-based research framework for writing differentiable numerical simulators with arbitrary discretizations
Universal components for differentiable scientific computing. 📦
GPU accelerated differentiable finite elements for solid mechanics with PyTorch
A differentiable bridge between phase space and Fock space
A library for soft differentiable relaxations of common JAX functions.
To associate your repository with the differentiable-programming topic, visit your repo's landing page and select "manage topics."