Tensors and Dynamic neural networks in Python with strong GPU acceleration

Face recognition with deep neural networks.

A Python-embedded modeling language for convex optimization problems.

Sequence modeling benchmarks and temporal convolutional networks

Tutorials and implementations for "Self-normalizing networks"

[NeurIPS'19] Deep Equilibrium Models

A fast and differentiable QP solver for PyTorch.

OptNet: Differentiable Optimization as a Layer in Neural Networks

[ICLR'19] Trellis Networks for Sequence Modeling

JAX implementation of MeanFlow

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

Provable adversarial robustness at ImageNet scale

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

PyTorch wrapper for FFTs

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

A differentiable LCP physics engine in PyTorch.

A Newton ADMM based solver for Cone programming.

Code for minimum-entropy coupling.