Trending Projects

A comprehensive music transcription library that can detect beat, chord, drum, vocal, and instrument components.

Unsupervised text tokenizer for neural network-based text generation and natural language processing.

A multi-purpose OCR tool for image-to-text, translation, read-aloud, formula/table extraction, and more.

A Python library that provides a simple way to view and summarize PyTorch models.

A comprehensive compendium of resources for machine learning and deep learning development.

An open-source library that enhances document layout analysis using diverse synthetic data and adaptive perception.

A curated list of resources for leveraging visual information in large vision-language models (LVLMs) for complex reasoning, planning, and generation.

Neva is a dataflow programming language and compiler that enables parallel computing with static typing.

Lab materials for an introductory course on deep learning from MIT, covering computer vision, music generation, and more.

An open-source Python library for democratizing deep learning in drug discovery, quantum chemistry, materials science, and biology.

A library for single- and multi-modal speaker verification, recognition, and diarization.

An imbalanced dataset sampler for PyTorch that oversamples low-frequency classes and undersamples high-frequency ones.

AI-powered PowerPoint presentation generation tool that supports complex features like charts, animations, and 3D effects.

NVIDIA DLSS is a deep learning neural network that boosts frame rates and generates sharp images for games.

PixelLib is a Python library for image and video segmentation using deep learning models like Mask R-CNN, DeepLab, and PointRend.

VideoGPT is a Jupyter Notebook-based project for generating videos from text prompts using AI models.

Porcupine is an on-device wake word detection library powered by deep learning, enabling hands-free voice activation in AI apps.

A Python project that enables natural, spoken conversations with AI using real-time voice chat.

A flexible AutoML framework with learning guarantees for building high-performance AI models.

A tutorial course for building AI-powered applications using Stable Diffusion and PyTorch.

A comparative framework for building multimodal recommender systems using collaborative filtering and matrix factorization.

A recurrent neural network for audio noise reduction, useful for building audio processing tools.

A lightweight C++ library for portable low-level GPU computation using WebGPU.

A Python library for applying artistic styles to images using neural networks.

Democratizing internet-scale financial data for developers through natural language processing.

A Python-based GUI tool for simulating VHS video effects, popular among vibe coders and AI enthusiasts.

Open source audio fingerprinting library in C# for building acoustic recognition applications.

A Chinese tutorial for getting started with LangChain, a framework for building AI/ML applications.

All-in-one WebUI for AI generative image and video creation, captioning and processing

Learning embeddings for classification, retrieval and ranking.

A collection of pre-trained AI models for the ROCK Chip AI accelerator

This repository contains code for a paper on automatic image colorization using joint learning of global and local image priors.

Perception and AI components for autonomous mobile robotics.

A markup language for orchestrating and managing prompts for large language models (LLMs) and AI tools.

An open-source enterprise-level AI knowledge base and management platform for chatbots and LLM applications.

An autoregressive character-level language model for generating text in a variety of styles.

Curated tutorials and resources for large language models, text-to-SQL, and related AI-powered development tools

FoundationStereo is a CVPR 2025 Best Paper Nomination project for zero-shot stereo matching using AI.

A simple, powerful, and efficient API for building deep learning models in Python.

Practical course on using Large Language Models (LLMs) with tools like LangChain, HuggingFace, and PEFT.

Voyager is an interactive RGBD video generation model that supports real-time 3D reconstruction from camera input.

This repository provides a comprehensive guide and implementation for reinforcement learning algorithms in Python.

Practical algorithm for real-world face restoration using GANs and deep learning.

A comprehensive collection of research papers on automatic speech recognition, speech synthesis, and related topics.

A tutorial series for developers to learn how to use large language models (LLMs) from zero to hero.

This repository is a Jupyter Notebook focused on the Google Health GEMMA project, which is not clearly defined.

A PyTorch implementation of Prototypical Networks for Few-Shot Learning, a powerful technique for training AI models on small datasets.

PaddleDetection is an open-source object detection toolkit based on the PaddlePaddle deep learning framework, supporting various computer vision tasks.

A JavaScript library for deep learning and reinforcement learning, with applications in areas like self-driving cars.

AllenAI's open-source post-training codebase for building AI models and agents.