This is the official repo for Gradient Agreement Filtering (GAF).

A family of state-of-the-art Transformer-based audio codecs for low-bitrate high-quality audio coding.

A library for fast and efficient mLSTM Kernels.

Minimalist ML framework for Rust

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…

Repository containing experimentation platform on how to train, infer on wav2vec2 models.

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

[ICLR 2020] A repository for extremely fast adversarial training using FGSM

Solve puzzles. Learn CUDA.

This repository implements SummaryMixing, a simpler, faster and much cheaper replacement to self-attention for automatic speech recognition (see: https://arxiv.org/abs/2307.07421). The code is read…

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

[Mamba-Survey-2024] Paper list for State-Space-Model/Mamba and it's Applications

Implementation of gradient-based adversarial attack(FGSM,MI-FGSM,PGD)

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

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Denoising Masked Autoencoders Help Robust Classification.

PyTorch implementation of adversarial attacks [torchattacks]

A challenge to explore adversarial robustness of neural networks on MNIST.

TRADES (TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization)

Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]

Uses WiFi signals 📶 and machine learning to predict where you are

Neural Networks: Zero to Hero

Gemini is a modern LaTex beamerposter theme 🖼

An implementation of soft-DTW divergences.