Trending Projects

Build, enrich, and transform datasets using AI models with no code

A curated list of papers and resources on text style transfer, a task in natural language processing.

A symbolic programming library for high-performance, parallel, and symbolic computing in Julia.

Code repository for a book on feature engineering for machine learning

A curated collection of impactful AI prompts across various domains for developers working with large language models.

An implementation for detailed localized image and video captioning using large multimodal models.

An extensive collection of resources for developers interested in talking face synthesis using AI tools.

A scalable system for training large language models (LLMs) with a focus on efficiency and performance.

An open-source robotics operating system (ROS) with support for speech recognition, semantic understanding, visual control, and Gazebo simulation.

A research framework for easy and efficient training of Generative Adversarial Networks (GANs) based on PyTorch.

Mip-Splatting is a novel 3D Gaussian splatting algorithm for alias-free novel view synthesis.

A tool for segmenting 3D objects in scenes using AI-powered computer vision techniques.

A PyTorch implementation of the DeepLab v3+ semantic segmentation model, allowing developers to train their own models.

LangChat is a Java-based framework that supports multiple AI providers and helps developers build AI-powered applications quickly.

A speech recognition server based on Vosk and Kaldi libraries, supporting WebSocket, gRPC, and WebRTC protocols.

A curated list of resources on large language models and foundation models for time series, spatiotemporal, and event data analysis.

A PyTorch implementation of a Scene Graph Generation method, with visualization and extraction capabilities.

Matterport3D is a dataset for RGB-D machine learning tasks, especially 3D reconstruction and semantic scene understanding.

A fast, differentiable tensor library in JavaScript and TypeScript with Bun and Flashlight support.

A point-based neural radiance field for 3D reconstruction and rendering from multi-view images.

A Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL, useful for AI coding tools.

Official implementation of SAM-Med2D, a tool for medical image segmentation using transformers.

A deep reinforcement learning library for training robotic agents to plan pushing and grasping actions for manipulation tasks.

This repository contains information about digital humans, likely focused on computer graphics and visualization.

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

AnomalyGPT is a powerful tool for detecting industrial anomalies using large vision-language models.

Repository for the AdaBelief Optimizer, a NeurIPS 2020 Spotlight paper on an adaptive optimizer for AI/ML models.

A curated list of papers on trajectory and motion prediction, a key topic in computer vision and robotics.

Strategies for pre-training graph neural networks for better performance on graph-based machine learning tasks.

A real-time pix2pix implementation for Unity, a popular game engine, enabling AI-powered image-to-image translation.

A Python library that provides a wrapper around various speech quality metrics for audio processing and analysis.

A Python framework for developing complex video analysis and series-processing applications.

A flexible and efficient DNN compiler that generates high-performance executable from DNN models.

An open-source platform for building and deploying ML pipelines with a focus on MLOps

A lightweight Chinese OCR library that supports vertical text recognition and NCNN/MNN/TNN inference with a small model size.

A Python library for explaining the predictions of any machine learning classifier.

Large World Model -- Modeling Text and Video with Millions Context, a powerful AI tool for developers.

An open framework for building powerful AI agents with blockchain-powered skills and capabilities.

An open-source voice interface for desktop, mobile, and embedded devices, focused on developers building with AI tools.

An instruction-tuned LLM with Chinese medical knowledge for AI-powered healthcare applications.

A simple reinforcement learning training library for reasoning tasks.

An advanced multimodal AI model series for vision-language reasoning, developed by Skywork AI.

An open-source project for tracking and segmenting any objects in videos using AI models like SAM and AOT.

.NET library for interacting with the OpenAI API, enabling developers to build AI-powered applications.

A PyTorch implementation of the TabNet paper, a novel deep learning architecture for tabular data.

Native multimodal model for high-quality image generation with text-to-image capabilities

An efficient video loader for deep learning with smart shuffling, easy to use in AI/ML projects.

Official implementation of a library for representing functions using periodic activation functions

This repository contains code for the MADDPG algorithm, a multi-agent actor-critic method for cooperative-competitive environments.

A scalable image generation model based on the Llama language model, outperforming diffusion models.