Trending Projects

A deep learning-based library for classifying the genre of audio files.

A curated list of resources for realistic image composition and object insertion using AI and computer vision techniques.

A tightly coupled GNSS-Visual-Inertial system for smooth and consistent state estimation in complex environments.

Offline Russian voice assistant with plugin-based skills for developers working with AI tools.

This project is a deformation inpainting network for realistic face visually dubbing on high resolution video.

This repository provides tools and models for training LoRA (Low-Rank Adaptation) for large language models like LLaMA and ChatGLM, enabling AI-powered code generation and assistance.

Official implementation of a paper on watermarking images with localized messages for AI-assisted image editing.

A fast and robust feature matching library for computer vision tasks like SfM and SLAM.

A Python benchmark suite for evaluating text-to-3D generation models and techniques.

Automatically generate programs using AI and genetic algorithms, with tutorials and examples.

AI Group is a mobile app that integrates multiple AI services to provide an intelligent interaction experience.

A powerful document AI question-answering tool that connects to your local Ollama models.

A library for accelerating deep neural networks through channel pruning, a model compression technique.

A C++ library for real-time, rotation-invariant face detection using progressive calibration networks.

A Python-based tool that helps developers solve SQL issues in real-world applications using LLM-powered pathways.

An open-source AI-powered face swap tool, focused on the Chinese market.

A simple Python script demonstrating the backpropagation algorithm for training a neural network.

A PyTorch implementation of Temporal Segment Networks (TSN) for video understanding and action recognition.

Aria is an open-source multimodal AI framework for building vision and language models.

Rotary Transformer, a Python library for Transformer models that incorporates rotary position encoding.

A desktop application that allows you to chat with your local documents using large language models.

AIConfig is a config-based framework to build generative AI applications using Python.

An implementation of Graph Transformer Networks, a neural network architecture for graph-structured data.

Code for high-fidelity 3D human avatar modeling using animatable Gaussians, a novel approach for pose-dependent 3D reconstruction.

Code for reproducing key results in the paper 'InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets'

A curated list of SLAM (Simultaneous Localization and Mapping) resources for developers working in computer vision and robotics.

Open-source code for a NeurIPS 2018 paper on multi-task learning as multi-objective optimization

An open-source app that allows users to search, read, bookmark, and summarize academic papers from arXiv using AI-powered features.

Open-source digital stylus using camera tracking and inertial measurements for vibe coders.

A deep learning-based library for efficient lane detection, using self-attention distillation.

Implementations of selected inverse reinforcement learning algorithms.

An open-source Chinese medical multimodal model that can summarize chest radiographs.

A Python library for less-is-more reasoning with large language models, focused on the COLM 2025 conference.

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

A comprehensive guide for developers to stay up-to-date with the latest advancements in AI, ML, DL, and computer vision.

A C++ implementation of Stable Diffusion, supporting txt2img and img2img, optimized for Android and other mobile devices.

A recurrent neural network trained on Kanye West's discography to generate new rap songs and lyrics.

A Python library that provides a Reinforcement Learning environment using the PyGame game engine.

A fast and powerful hierarchical vision transformer for computer vision tasks.

DepthAI is a high-performance, low-power embedded AI vision library for building computer vision and spatial AI applications.

A collection of 'black magic' tools, libraries, and resources for developers who build with AI tools.

An AI-powered tool for quickly generating character descriptions and biographies for creative writing projects.

A Python library for implementing reinforcement learning algorithms.

Open-source optical flow toolbox and benchmark for computer vision tasks powered by PyTorch.

A data repository for pre-trained NLP models and corpora to use in language processing projects.

Perception and AI components for autonomous mobile robotics.

A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery.

A PyTorch library for building CNN-based text classification models.

A flexible, extensible framework for gait recognition that allows designing and comparing models easily.

PubLayNet is a Jupyter Notebook library for parsing and analyzing layout and structure of scientific publications.