Trending Projects

High-fidelity performance metrics for generative models in PyTorch

A general object foundation model for computer vision tasks in images and videos at scale

Open-source COVID-19 detection tool using chest radiography images and deep learning models.

An open-source text-to-speech library built using Transformer-based neural networks for high-quality speech synthesis.

A voice-powered AI assistant that can answer questions about any application, in context and in audio.

A high-quality lip sync tool using deep learning techniques like GFPGAN and Wav2Lip.

An open-source machine learning framework for developers to build AI-powered applications.

A comprehensive collection of deep learning paper reviews and code practices for AI developers.

A Python library for building recommender systems using deep learning techniques.

A comprehensive resource for machine learning and deep learning research and enthusiasts.

An AI chatbot for small and medium-sized teams, supporting popular AI models like Deepseek, OpenAI, and Claude.

Analyzes computation-communication overlap in V3/R1 for vibe coders building with AI tools.

A powerful and easy-to-use toolkit for implementing various computer vision tasks on Android, including text recognition, barcode scanning, image labeling, face detection, and object detection.

ONNXMLTools enables conversion of machine learning models to the ONNX format, supporting Keras, Scikit-learn, and other frameworks.

Gaussian-SLAM is a Python library for photo-realistic 3D reconstruction and SLAM using Gaussian splatting.

An AI-powered podcast generator that creates bilingual episodes in multiple languages, an alternative to NotebookLLM.

A C++ library for calibrating LiDAR-IMU systems without using special targets.

A neural network-based OCR library for JavaScript, useful for building document scanning and text extraction features.

A collection of research papers from the Computer Vision and Pattern Recognition (CVPR) conference in 2024.

A curated list of NLP resources focused on Transformer networks, attention mechanism, and large language models.

Attention-based OCR library for building vision AI apps that extract text from images.

A TensorFlow-based rotation detection benchmark for computer vision and AI models.

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.

A Python and PyTorch-based AI voice assistant for hackers, with features like speech recognition and generation.

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.

A tool for structurally pruning large language models like LLaMA, BLOOM, and Vicuna to reduce their size and inference time.

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

A smaller subset of 10 easily classified classes from Imagenet, and a little more French

Mitsuba is a highly customizable, research-oriented renderer that provides a rich and flexible programming interface.

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

PyTorch re-implementation of DeepLab v2 for semantic segmentation on COCO-Stuff and PASCAL VOC datasets.

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 real-time speech recognition server built with the Kaldi toolkit and GStreamer framework.

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.

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

A powerful open-world object detection model for computer vision tasks, leveraging the DINO framework.

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

A real-time, expressive chatbot using LLM and TTS, with support for QQ robot and various media types.

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

This is a library for solving partial differential equations using neural networks.

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.

RStan is an R interface to the Stan probabilistic programming language, used for Bayesian data analysis and inference.

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

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

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