Sionna: An Open-Source Library for Research on Communication Systems

[ICLR 2022] Accelerated Policy Learning with Parallel Differentiable Simulation

Reinforcement learning in differentiable multiphysics simulation with NVIDIA Warp.

Sionna RT: The Ray Tracing Package of Sionna

A library for soft differentiable relaxations of common JAX functions.

Symbolic differentiation. C++ code generation. JIT compilation. Global assembly. Non-linear optimization.

We compare the gradients calculated by different differentiable contact model implementations.

Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control

[Siggraph 2024] Differentiable solver for time-dependent deformation problems with contact

A curated list of 100+ AI-ready tools for Computer-Aided Engineering, ranked by an AI-Readiness Score (agent-callability: MCP, Python API, CLI, pip). CFD, FEA, SPH, DEM, differentiable simulation, neural operators, PINNs, MCP servers.

This repo contains the differentiable physics simulation module in "PPR: Physically Plausible Reconstruction from Monocular Videos". ICCV 23.

Code for "Evolution and learning in differentiable robots", Strgar et al., Proceedings of Robotics: Science and Systems (RSS) 2024

PyTorch3D-based differentiable drone simulator — train vision-based flight policies end-to-end via gradient descent. Extends DiffPhysDrone with CMA-ES, multi-sensor fusion, and 10 policy architectures.

PyTorch and Taichi implementations of our paper on improving gradient computation

A Python based framework for differentiable power system simulation and dynamic optimization

[ICML 2026] DLO-Lab: Benchmarking Deformable Linear Object Manipulations with Differentiable Physics

A differentiable multibody dynamics simulator for computational design of rigid-flexible robot

Code for "Accelerated co-design of robots through morphological pretraining", Strgar & Kriegman, Proceedings of the International Conference on Learning Representations (ICLR) 2026

"Differentiable Simulations" tutorial presented at the 5th MaLAPA workshop at CERN in April 2025

Inverse parameter estimation for the viscous Burgers equation: a differentiable solver-adjoint, PINNs (JAX/PyTorch), and an amortized flow-matching posterior, packaged as swappable Tesseract components.