Trending Projects

A PyTorch tutorial for building an image captioning model using the Show, Attend, and Tell technique.

A comprehensive collection of papers and datasets for 3D point cloud processing, useful for developers working on autonomous driving and computer vision.

A curated list of awesome resources for anomaly detection using machine learning and deep learning techniques.

An efficient, neural-network-free 3D radiance field renderer for virtual view synthesis and reconstruction.

High-performance vector graph neural network database in Rust for real-time AI inference and graph ML.

A survey and analysis of various large language model (LLM) agents and their capabilities.

A Python library that enables creating web demos using OpenAI's GPT-3 API with just a few lines of code.

Official Python SDK for ElevenLabs text-to-speech API with voice synthesis & audio generation.

A curated collection of survey papers summarizing advances in deep learning, NLP, CV, and other ML domains.

A Python library that uses Tensorflow and convolutional neural networks to recognize character-based image captchas.

Corrects OCR errors via LLM post-processing, smart chunking & markdown formatting for PDFs

A lightweight and generalist NER model for extracting entities from text, with support for prompt-tuning.

This is a code repository for learning deep learning with PyTorch, a popular machine learning library.

A PyTorch library for meta-learning research, enabling few-shot, fine-tuning, and other advanced ML techniques.

A high-performance, auto-diff neural network library for 3D and 4D sparse tensor computations.

AI-powered manga translator with OCR & bubble detection for Japanese comics to Chinese

Deep learning model for extracting & analyzing table structures from PDFs and images with datasets.

Official Python SDK for Claude API—LLM wrapper for building AI apps with Anthropic's models

Swift SDK for OpenAI API integration with type-safe wrappers and modern concurrency support.

A MATLAB library for joint face detection and alignment using multi-task cascaded convolutional neural networks.

An open-source project that explores the use of world models for reinforcement learning in diverse domains like Minecraft.

A general-purpose machine learning library for Python, useful for a variety of AI and ML tasks.

Pointcept is a codebase for point cloud perception research, featuring the latest works on 3D computer vision.

A C++ library for distributed large language model inference, allowing developers to build powerful AI applications with a cluster of home devices.

Implementation of 17+ agentic architectures for practical use across AI system development.

Family fitness app with AI health coaching, food tracking, and self-hosted deployment.

This repository provides guidance on optimizing algorithms for CUDA, a framework for parallel computing on NVIDIA GPUs.

OneTrainer is a comprehensive solution for training Diffusion models, including fine-tuning, LORA, and more.

This Python library provides a preview of computer usage data, potentially useful for AI coding tools.

A JavaScript library for enhancing the functionality and user experience of the ComfyUI tool for AI art generation.

A secure and interoperable platform for AI-driven payments, catering to the needs of vibe coders.

This repository provides examples and utilities for fine-tuning large language models (LLMs) using the PEFT library.

A repository for quantitative analysis, strategies, and backtests for algorithmic trading and finance research.

An open-source library for local feature matching using Transformers, useful for 3D vision and pose estimation tasks.

A curated list of robotics libraries and software for developers working on robotic applications.

A portable accelerated SQL query, search, and LLM-inference engine for data-grounded AI apps and agents.

A library for single- and multi-modal speaker verification, recognition, and diarization.

Code for a demo of the OpenAI Speech API, allowing developers to explore and build speech-enabled applications.

A real-time dense SLAM system with 3D reconstruction priors, built for computer vision and robotics applications.

A free API that provides access to the DeepSeek-V3 and R1 large language models, enabling developers to build AI-powered chatbots and applications.

A Python/C library and toolkit for automatically synchronizing audio and text (forced alignment).

A curated list of 100+ libraries and frameworks for AI engineers building with large language models (LLMs).

RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.

Instant AI Face Swap, a TypeScript library for developers to easily add AI-powered face swapping to their projects.

An open-source large-scale manipulation platform for scalable and intelligent robotic systems.

A lightweight, self-contained Rust library for running Tensorflow and ONNX models with no dependencies

A unified library for parameter-efficient and modular transfer learning in NLP with BERT, LoRA, and Transformers.

A comprehensive AI content generation and publishing system for WeChat, supporting multi-source data collection, intelligent analysis, and automated publishing.

HiPlot is a TypeScript library that makes understanding high-dimensional data easy for developers.

Comprehensive review of top solutions for NLP competitions, focused on the NLP domain.