Optimized Whisper models for streaming and on-device use

The benchmark of SOTA text-to-image diffusion models with a new benchmarking strategy based on MiniGPT-4, namely X-IQE.

Open-source models accelerated by TheStage AI ANNA: Automated NNs Accelerator

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

ConMamba for Automatic Speech Recognition

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

Solve different formulations of the portfolio optimization problem.

Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.

Constrained optimization toolkit for PyTorch

Neural network graphs and training metrics for PyTorch, Tensorflow, and Keras.

Ongoing research training transformer models at scale

Tensor library for machine learning

Stable Diffusion with Core ML on Apple Silicon

MLX: An array framework for Apple silicon

Yet another PyTorch implementation of Stable Diffusion (probably easy to read)

[CVPR 2022] Deep Equilibrium Optical Flow Estimation

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

A node-based image processing GUI aimed at making chaining image processing tasks easy and customizable. Born as an AI upscaling application, chaiNNer has grown into an extremely flexible and power…

Integral Neural Networks in PyTorch

An easy to use PyTorch to TensorRT converter

Accelerated deep learning R&D

A collection of easy-to-use image/video filter.