Reverse Engineering the Abstraction and Reasoning Corpus

Implementation of ConvMixer for "Patches Are All You Need? 🤷"

Convolutions for Sequence Modeling

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Sequence modeling benchmarks and temporal convolutional networks

This repository contains the official implementation for the ECCV'22 paper, "SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks".

The most parameter efficient machine learning models on a few popular benchmarks

SAM: Sharpness-Aware Minimization (PyTorch)

Implementations of orthogonal and semi-orthogonal convolutions in the Fourier domain with applications to adversarial robustness

Pytorch library for fast transformer implementations

Semisupervised learning for adversarial robustness https://arxiv.org/pdf/1905.13736.pdf

A plugin for code generation in PyCharm/IntelliJ using tranX

A Closer Look at Accuracy vs. Robustness

A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.

Understanding and Improving Fast Adversarial Training [NeurIPS 2020]

Differentiable convex optimization layers

Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"

This project is the Torch implementation of our accepted AAAI 2018 paper : orthogonal weight normalization method for solving orthogonality constraints over Steifel manifold in deep neural networks…

Implementation of Methods Proposed in Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks (NeurIPS 2019)

🧠🗼

The Mixing method: coordinate descent for low-rank semidefinite programming

Implementation of the paper "Automatic Program Synthesis of Long Programs with a Learned Garbage Collector"

The Z3 Theorem Prover

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

Karel dataset for program synthesis and program induction

Collect and view OSS cryptocurrency development.