Trending Projects

A minimal tensor processing unit (TPU) for AI and machine learning workloads, inspired by Google's TPU V2 and V1.

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

A Python-based platform that uses LLMs to track and extract websites, RSS feeds, and social media for developers.

A visual-inertial calibration toolbox for cameras and IMUs, enabling precise sensor fusion.

H2O LLM Studio is a no-code GUI framework for fine-tuning large language models (LLMs) like GPT-3, LLAMA, and ChatGPT.

A Python module for automatic summarization of text documents and HTML pages.

The fast.ai course notebooks, a resource for developers to learn deep learning and machine learning using the fastai library.

A collection of books, papers, and documents for developers working with AI tools and technologies.

Open-source library for training and running inference with ColVision models for vision-language retrieval and generation.

AI-powered film production tool supporting batch video generation from scripts with Sora 2.0 integration

A JavaScript-based Gobang (Five-in-a-Row) AI game, built using the Alpha-Beta pruning algorithm.

A toolkit for easier and faster deployment of YOLO (You Only Look Once) object detection models using NVIDIA TensorRT.

A collection of TensorFlow 2.0 examples for deep learning, computer vision, and more.

RoboVerse is a unified platform, dataset, and benchmark for scalable and generalizable robot learning.

Declarative way to run AI models in React Native on device, powered by ExecuTorch.

Efficient implementations of Native Sparse Attention, a key component in large language models.

JARVIS connects LLMs with ML community for task automation and research.

Chinese version of CLIP for cross-modal retrieval and representation generation

An open-source, camera-only framework for autonomous driving perception tasks like 3D object detection and semantic map segmentation.

A line drawing colorization tool built using the Chainer deep learning framework.

A text detection library using the CTPN model, supporting ID card detection and robust reading.

A curated list of resources and projects related to quantum machine learning, algorithms, and frameworks.

A Python library for representing, sending, storing, and searching multimodal data in AI and ML applications.

A Ruby library that provides a powerful set of tools for building LLM-powered applications.

Experimental spaced repetition platform for exploring ideas in memory augmentation and programmable attention

A Chinese Natural Language Toolkit for various NLP tasks written in Python.

A visual debugging tool for machine learning models that provides a model-agnostic approach.

A demo for running neural networks across different deep learning frameworks

LAVIS is a comprehensive library for multimodal deep learning, including image captioning, visual question answering, and more.

This repository provides a roadmap and code samples for machine learning, deep learning, and related AI technologies.

Unofficial implementation of Animate Anyone, a tool for generating animations from text prompts.

This repository contains samples for the MediaPipe framework, a cross-platform and customizable ML solution for live and batch media processing.

A comprehensive collection of research on knowledge graphs, covering various applications and techniques.

A PyTorch implementation of the PWC-Net, a CNN-based optical flow estimation model for computer vision tasks.

This repository provides a model pruning technique for the YOLOv3 object detection model on the Oxford Hand dataset.

A low-level C++ library for building AI accelerator kernels and operators for Tenstorrent's METAL platform.

A Python library for building AI-powered visual agents and tools for developers focused on AI coding workflows.

A Python library for discovering and exploiting image scaling attacks for multi-modal prompt injection.

Deep learning implementation of Dive into Deep Learning using PyTorch

BertViz is a Python library for visualizing attention in transformer models like BERT, GPT-2, and RoBERTa.

AI suite with advanced AI/AGI functions, including personas, multi-model chats, text-to-image, voice, and more.

A Python-based library for solving visual understanding tasks using reinforced visual-linguistic models (VLMs).

A comprehensive AI-powered computer vision library for face detection, tracking, recognition, and more.

A production-ready reinforcement learning AI agent library for building AI-powered applications.

Run AI models like LLaMA locally on your machine with Node.js bindings for llama.cpp and enforce JSON schema on the output.

Manifold is a C++ geometry library focused on topological robustness for AI-powered applications.

GPT-2 multi-language pre-trained models, including a 1.5B parameter Chinese model, for text generation and NLP tasks.

Chat with your PDFs using AI, allowing you to easily extract information from documents.

An open-source annotation tool for machine learning practitioners to label data for training models.

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions.