A library for differentiable nonlinear optimization

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

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

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

Mathematical Programming in JAX

Safe robot learning

Official repo for the paper "SAGE: SLAM with Appearance and Geometry Prior for Endoscopy" (ICRA 2022)

Official code repository for ∇-Prox: Differentiable Proximal Algorithm Modeling for Large-Scale Optimization (SIGGRAPH TOG 2023)

A library for soft differentiable relaxations of common JAX functions.

A library for soft differentiable relaxations of common PyTorch functions.

Implementation and examples from Trajectory Optimization with Optimization-Based Dynamics https://arxiv.org/abs/2109.04928

[L4DC 2025] Automatic hyperparameter tuning for DeePC. Built by Michael Cummins at the Automatic Control Laboratory, ETH Zurich.

Differentiable curve and surface similarity measures.

Decision-Focused Learning (DFL) for day-ahead scheduling of Underground Pumped Hydro Energy Storage (UPHES).

Preliminary code for the paper "Learning Deterministic Surrogates for Robust Convex QCQPs".

Differentiable VLSI placer in Python/PyTorch: macro-aware density model, two-phase overlap-penalty ramp; 8.8% wirelength and 99.1% overlap-area reduction vs unoptimized baseline; CUDA-ready tensors, Docker + GitHub Actions CI, 6/6 pytest passing.

Differentiable PyTorch loss for partial point-cloud alignment and contact-aware 3D optimization.

Tutorial on Deep Declarative Networks

Differentiable stochastic-computing primitives for PyTorch: train neural networks natively SC-aware.

SILVA Networks is a Python package for extended deep equilibrium layers, fixed-point solvers, implicit differentiation, structured operators, diagnostics, and reproducible research notebooks.