Trending Projects

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

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.

An AI-powered research assistant that helps developers discover and organize research papers using GPT language models.

A dataset and pretrained model for detecting safety helmet wearing, useful for computer vision projects.

An open-source deep reinforcement learning library that combines several state-of-the-art improvements.

Simple samples for TensorRT programming, a powerful GPU-accelerated inference optimization library from NVIDIA.

Automated machine learning for analytics & production use cases powered by popular ML libraries.

A collection of reference environments for offline reinforcement learning in Python.

The google-research/pegasus repository is a Python library for training and using the PEGASUS language model for abstractive text summarization.

Quark Agent is an AI-powered Android APK analyzer that helps developers and security researchers detect vulnerabilities in Android apps.

Estimates dense, flicker-free, geometrically consistent depth from monocular video for computer vision applications.

The Pile is a large, diverse language model training dataset for use in AI research and development.

A collection of modular datasets generated by GPT-4 for AI code generation and prompt engineering.

A diffusion-based model for generating realistic talking portrait videos.

Official PyTorch implementation of Magic123, a tool for generating high-quality 3D objects from a single image using 2D and 3D diffusion priors.

Open academic research on improving the LLaMA language model to state-of-the-art performance.

A Python-based multimodal OCR tool for efficient offline processing of LaTeX, ZhEn, and tables on Windows.

A Jupyter Notebook-based tool for generating AI-powered NFT images.

A PyTorch-based framework for reproducible deep learning studies with 26 knowledge distillation methods.

Open-source implementations of machine learning algorithms from scratch in Python.

A large language model from Tencent's Hunyuan project, potentially useful for AI-powered coding tools and applications.

A TypeScript-based open-source project for building AI-powered group chat applications.

A PyTorch implementation of the Non-local Block, a key component in computer vision models.

A C++ library that enables deploying the YOLOv5 object detection model on mobile devices using the NCNN framework.

Official implementation of a composable, controllable, and creative image synthesis model.

DeepSeek-Math-V2 is a Python library for AI-powered math analysis and computation.

A Python library for probabilistic time series forecasting using large language models like LLaMA.

A collection of notes and resources for quickly developing OpenAI/GPT-based applications for Chinese developers

ChatArena is a multi-agent language game environment for developing communication and collaboration capabilities of AI models.

A Python implementation of the neural algorithm for artistic style transfer.

Official TensorFlow implementation of the Noise2Noise: Learning Image Restoration without Clean Data paper.

Official repo for Pai-Megatron-Patch, a large language model and visual language model training framework developed by Alibaba Cloud.

A Python library for turning Chinese natural language into structured data for chatbots and NLP applications.

Official codebase for Alibaba DAMO Conversational AI, a deep learning-powered dialog system.

A curated collection of must-read papers on knowledge representation learning (KRL) and knowledge embedding (KE) for AI/ML developers.

A PyTorch implementation of OpenAI's pre-trained transformer language model for fine-tuning and inference.

A library of 200+ deep learning architecture diagrams and figures for use in blog posts, presentations, and papers.

A Python library for channel and layer pruning of YOLOv3 and YOLOv4 models, with support for knowledge distillation.

A Transformer-based sensor fusion model for end-to-end autonomous driving.

A curated list of resources for Document Understanding (DU) related to machine learning and natural language processing.

Code repository for examples in the book 'Generative Deep Learning' focused on AI and ML topics.

Official implementation of a paper on a unified Transformer-based framework for object detection and segmentation.

A PyTorch implementation of Deformable Convolution Networks V2 (DCNv2), a powerful computer vision technique.

Phantom is a subject-consistent video generation tool that aligns text and video via cross-modal alignment.

A one-stop Transformer library for state-of-the-art code language models and AI-powered code understanding.

A curated collection of datasets, papers, and books on the intersection of AI and finance.

A machine learning platform and recommendation engine built on Kubernetes for deployment on cloud platforms.

A curated collection of NLP paper summaries for developers interested in natural language processing.

A PyTorch library that provides Vision Transformer (ViT) adapters for dense prediction tasks like object detection and semantic segmentation.