Trending Projects

Official implementation of the RAVE model, a Realtime Audio Variational autoEncoder for generative audio AI.

JVector is an advanced embedded vector search engine written in Java, optimized for similarity search and machine learning applications.

A curated list of papers and source code for multi-object tracking, a computer vision task.

A repository of machine learning papers focused on proteins, useful for researchers and developers in the field.

Efficient visual geometry learning for AI-powered applications with permutation-equivariant representations.

A reverse-engineered ChatGPT proxy server built with Rust, allowing developers to integrate ChatGPT-like functionality into their applications.

Implements the 4 agentic patterns from scratch in a Jupyter Notebook for developers building with AI tools.

A Python library that allows you to fake your webcam background on Linux, with support for blurring, animations, and color effects.

A self-supervised video representation learning model for video understanding tasks.

A highly scalable distributed vector search engine for high-dimensional data and AI applications.

A curated collection of resources related to the Segment Anything model, a powerful image segmentation tool.

Graph4nlp is a library for easy use of Graph Neural Networks for Natural Language Processing (NLP) tasks.

A flexible, high-performance e-graph library written in Rust for developers working with AI tools.

A curated list of books on Large Language Models (LLMs) for developers interested in AI coding tools.

A Chinese Natural Language Toolkit for various NLP tasks written in Python.

A must-have resource for experimenting with and building on the OpenAI vision API.

PaddleVideo is a powerful toolkit for video understanding tasks like action recognition, localization, and detection.

Open-source eye tracking library for developers working on computer vision and augmented reality projects.

A collection of state-of-the-art video and single-image super-resolution architectures in TensorFlow.

A trainable PyTorch reproduction of the AlphaFold 3 protein structure prediction model.

Swift Core ML 3 implementations of popular transformer models like GPT-2, BERT for question answering.

A multi-threaded GOAP system for Unity game development, with support for AI-powered agents and behaviors.

Underthesea is a powerful Vietnamese NLP toolkit for developers working with natural language processing tasks.

A research project exploring the use of transformers in robotics applications.

A TypeScript-based Electron app that uses large language models to translate subtitles between languages.

A Python library that improves the stability and accuracy of convolutional neural networks (CNNs) in computer vision tasks.

A Python library for Chinese word segmentation, part-of-speech tagging, and named entity recognition.

OpenMLDB is an open-source machine learning database that provides a feature platform for training and inference.

Textbook on reinforcement learning from human feedback, focused on AI alignment research.

A lightweight OCR system based on PaddleOCR, with ultra-fast inference speed and decoupled from the PaddlePaddle deep learning framework.

A deep learning-based image denoising library that can handle a variety of denoising tasks like JPEG deblocking and super-resolution.

A comprehensive machine learning library for R, providing a unified interface to a wide range of algorithms.

This repository contains a collection of LLM (Large Language Model) interview questions asked at top tech companies.

A memory-efficient library for training large language models (LLMs) using gradient low-rank projection.

AI-powered image upscaling and restoration tool for developers working with anime, manga, and digital art

RoboVerse is a unified platform, dataset, and benchmark for scalable and generalizable robot learning.

A neurosymbolic perspective on large language models for AI-powered coding and development

Efficient context window extension for large language models, enabling faster and more accurate inference.

An open-source Chinese conversational AI model with tools for fine-tuning and optimizing the model for downstream tasks.

A PyTorch implementation of the YOLOv4 object detection model with support for various attention mechanisms and mobile models.

Real-time multi-person tracking using YOLO v3 and deep_sort with TensorFlow for computer vision applications.

This repository provides a model pruning technique for the YOLOv3 object detection model on the Oxford Hand dataset.

jiant is an NLP toolkit that provides pre-trained BERT models and tools for multi-task learning and transfer learning.

An open-source AI-powered drone location tracking system for developers.

Contextually-keyed word vectors for natural language processing and machine learning tasks.

A visual debugging tool for machine learning models that provides a model-agnostic approach.

An extensible and easy-to-use diffusion web UI for generating images with AI tools like Stable Diffusion.

MT3 is a Python library for multi-task multitrack music transcription, a powerful tool for audio analysis.

Nx-powered Neural Networks library for building deep learning models in Elixir

This is a Python library for audio tagging using a convolutional neural network model trained on the AudioSet dataset.