Trending Projects

A Python implementation of the Simhash algorithm for near-duplicate detection.

An end-to-end web agent built with large multimodal models, enabling AI-powered web browsing and automation.

A Python library that extends the Segment Anything Model (SAM) to enable zero-shot video segmentation with point-based tracking.

Xwin-LM is a powerful, stable, and reproducible LLM alignment library for Python developers.

TinyMaix is a tiny inference library for microcontrollers, enabling efficient AI/ML on resource-constrained devices.

A Python library for benchmarking generalized out-of-distribution detection algorithms.

An interpretability library for TensorFlow 2 Keras models, providing visualization and understanding of model behavior.

An open-source Chinese medical chatbot built on the ChatGLM language model.

Panda is an open-source large language model project for the Chinese language, aiming to drive innovation and collaboration in NLP.

A tutorial for learning the Python programming language, with a focus on the Microsoft Cognitive Toolkit (MCP).

A codebase for Time-series Generative Adversarial Networks (TimeGAN), a deep learning model for time series data generation.

FaceAPI is a powerful library for face detection, recognition, and emotion prediction in the browser and Node.js using TensorFlow/JS.

A small fast portable speech synthesis system written in C.

This is a Jupyter Notebook repository for the Stable Diffusion AI model, a powerful text-to-image generation tool.

A collection of notes and code for the Andrew Ng Deep Learning course, useful for learning AI and ML concepts.

A companion repository for the book 'GANs in Action: Deep learning with Generative Adversarial Networks'.

A PyTorch-based library for unsupervised learning of depth, disparity, and other visual features from monocular video.

A library that expands natural language instructions for use in AI/ML models and applications.

DynamicTanh (DyT) is a Python library that enhances the performance of neural networks by introducing a novel activation function.

torchview is a Python library for visualizing PyTorch models, helping developers understand and debug their neural networks.

DeepLab2 is a TensorFlow library for dense pixel labeling tasks, providing a state-of-the-art codebase for computer vision and AI.

A research paper on first-order meta-learning algorithms, with associated code in JavaScript.

A Google Assistant for single board computers like Raspberry Pi, with voice commands and control.

A Python library for working with mathematical models and algorithms.

A bottom-up object detection algorithm that groups extreme and center points to detect objects.

A fast and simple tool for resource-constrained learning of deep network structure.

Reinforcement learning environments for the Omniverse Isaac Gym, a robotics simulation platform.

Dynamiq is an orchestration framework for agentic AI and LLM applications, enabling developers to build advanced AI-powered tools.

An explainable GNN (Graph Neural Network) library for interpreting and understanding GNN models.

A PyTorch implementation of LightGCN, a graph convolutional network for recommender systems.

A PyTorch implementation of Stable Diffusion, a powerful AI-powered text-to-image generation model.

Minimal LLM inference in Rust, a lightweight library for running large language models.

A collection of Jupyter Notebook tutorials for accelerated tabular data machine learning in Python.

OpenWash is a format and specification for defining and sharing AI model deployment packaging.

Open-source, full-stack face recognition toolkit for developers building AI-powered apps.

An AI-powered computer vision library for developers to build advanced image and video processing applications.

A collection of must-read papers on neural relation extraction (NRE) for natural language processing researchers and engineers.

This repository provides optimized PyTorch models and inference tools for NVIDIA GPUs, aimed at vibe coders building with AI tools.

This GitHub repository provides in-depth analysis and code explanations for state-of-the-art VIO (Visual-Inertial Odometry) research papers.

Kuromoji is a Java-based Japanese morphological analyzer for natural language processing applications.

A PyTorch quantization backend for Optimum, a library for deploying and accelerating AI models.

A real-time motion tracking addon for Blender using MediaPipe and Rigify.

Official implementation of HyperStyle, a StyleGAN inversion method using hypernetworks for real image editing.

An open-source framework and context engine for Retrieval Augmented Generation (RAG) powered by Pinecone vector database.

Scalable, event-driven, deep-learning-friendly backtesting library for algorithmic trading strategies

A pure PyTorch implementation of the NVIDIA paper on Instant Training of Neural Graphics Primitives.

A Swift library for optical character recognition (OCR) of Chinese ID cards, using machine learning.

Fast and efficient Jax-based reinforcement learning implementations for developers building AI-powered applications.

JAX-based, hardware accelerated, batchable and differentiable optimizers for machine learning.

A minimal solution for high-speed hand motion capture from a single color camera.