JAX implementation of MeanFlow

Code for minimum-entropy coupling.

[NeurIPS'19] Deep Equilibrium Models

Bridging deep learning and logical reasoning using a differentiable satisfiability solver.

Provable adversarial robustness at ImageNet scale

[ICLR'19] Trellis Networks for Sequence Modeling

Sequence modeling benchmarks and temporal convolutional networks

A differentiable LCP physics engine in PyTorch.

A method for training neural networks that are provably robust to adversarial attacks.

A Newton ADMM based solver for Cone programming.

Tutorials and implementations for "Self-normalizing networks"

A Python-embedded modeling language for convex optimization problems.

PyTorch wrapper for FFTs

Face recognition with deep neural networks.

A fast and differentiable QP solver for PyTorch.

OptNet: Differentiable Optimization as a Layer in Neural Networks

Tensors and Dynamic neural networks in Python with strong GPU acceleration

An intelligent block matrix library for numpy, PyTorch, and beyond.