Trending Projects

Magma is a foundation model for building multimodal AI agents, enabling next-gen AI applications.

An extremely simple tool for separating vocals and background music, completely localized for web operation.

This repository contains materials, slides, and notebooks for Andrew Ng's deeplearning.ai course on machine learning and AI.

The Wa Programming Language, a new language designed for AI-powered development workflows.

A Python framework for quick implementation of recommender systems using TensorFlow.

A PyTorch library for working with neural fields like NeRFs, NGLOD, instant-ngp, and VQAD.

A simple GUI for ByteDance's Piano Transcription with Pedals, built using the Nix programming language.

A collection of codes for Reconfigurable Intelligent Surface (RIS) research related to 6G and wireless communication.

WebThinker is a powerful framework for building large language models with deep research capabilities.

SpeechGPT is a Python library for building speech-based applications using large language models.

An open-source virtual assistant for Ubuntu-based Linux distributions, focused on speech recognition and natural language processing.

A point-based neural radiance field for 3D reconstruction and rendering from multi-view images.

A curated list of resources for building multi-modal GUI agents using large language models.

An open-source library for generating, editing, and working with DALL-E 2 images using the OpenAI API.

Open-source repository of pre-trained language models for various AI and NLP applications.

Large-scale Chinese natural language processing corpus for training and fine-tuning language models

A PyTorch implementation of a CIFAR10 model achieving 95.47% accuracy.

This is an AI-focused development platform for building with AI tools and services.

A Java proxy for the MidJourney Discord channel, allowing API-based access to its AI image generation capabilities.

A self-supervised learning framework for computer vision tasks with a focus on contrastive learning.

A PyTorch library for processing spatiotemporal graph data using neural machine learning models.

A YOLOv5-based object detection system for detecting safety helmets and restricted areas on construction sites.

A collection of leaked GPT prompts and tools to bypass subscription limits and try out AI models.

TorchIO is a Python library for efficient medical image preprocessing and data augmentation for AI applications.

A repository containing notebooks of posts on Medium, focused on AI, data science, and machine learning topics.

Cross-platform, GPU-accelerated Whisper speech recognition library for developers building AI-powered apps.

A PyTorch-based AI factory that enables easy configuration and running of complex AI recipes across various data domains.

A Python library that provides a wrapper for the ComfyUI AI model integration framework.

A general NeRF acceleration toolbox in PyTorch for efficient neural rendering and computer vision.

A curated list of awesome resources for model-based reinforcement learning.

A modular, high-performance noise generation library using SIMD, C++17, and templates for procedural content creation.

This Python tool accelerates the download of HuggingFace models from mirror sites for faster model training and deployment.

This is a workshop repository for the Google Brain Tokyo team, focusing on AI and machine learning topics.

A framework for data augmentation for 2D and 3D image classification and segmentation tasks.

NotaGen is an AI-powered tool for generating symbolic music by leveraging large language models.

Samples for Intel's oneAPI Toolkits, supporting a wide range of AI, HPC, and parallel computing use cases.

A PyTorch implementation of the Style-Based GAN architecture for generative adversarial networks.

A library of recommendation algorithms based on Graph Neural Networks for information retrieval and recommendation systems.

An open-source Python library for image augmentation in machine learning experiments.

An official PyTorch implementation of StyleGAN2-ADA, a state-of-the-art generative adversarial network for realistic image synthesis.

Deepchecks is an open-source solution for thorough testing of ML models and data from research to production.

TextAttack is a Python framework for adversarial attacks, data augmentation, and model training in NLP.

Automatic generation of visualizations and infographics using large language models.

Official implementation of a CVPR2020 paper for video-based 3D human pose and shape estimation.

Chunkr is a Rust-based vision infrastructure for turning complex documents into RAG/LLM-ready data.

A C++ SQLite extension that provides efficient vector search capabilities using the Faiss library.

A photorealistic synthetic dataset for holistic indoor scene understanding using machine learning.

A suite of GIMP plugins for texture synthesis, inpainting, and style transfer.

A curated list of resources for transfer learning and domain adaptation research and applications.

A package for the sparse identification of nonlinear dynamical systems from data