Trending Projects

An open-source question-answering tool that leverages large language models to provide answers to any query.

ImageBind is a multimodal learning framework that learns a single embedding space to represent diverse modalities like images, text, and more.

A platform for discovering and sharing AI models, textual inversions, and other AI-powered creative tools.

Interactive 3D visualization framework for pre-trained deep learning models, supporting TensorFlow, Keras and TensorFlow.js.

OpenMMLab's toolbox and benchmark for advanced video understanding and action recognition.

A GUI for the faster-whisper library, which enables fast, open-source speech transcription using OpenAI's Whisper model.

A library that provides insights into the internals of Apple's Neural Engine for iOS developers.

Optax is a gradient processing and optimization library for JAX, a high-performance machine learning framework.

A collection of examples and demos for the Transformers.js library, which brings powerful AI models to JavaScript.

An innovative AI-powered document understanding and OCR platform from Alibaba Research.

A Python library for extracting data and LLM outputs from various document types with ease.

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

A lightweight and efficient virtual try-on diffusion model for fashion applications.

A comprehensive list of Implicit Representations and NeRF papers relating to Robotics/RL domain.

MultiAgentPPT is an AI-powered presentation generation system that leverages multi-agent collaboration and streaming concurrency.

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

Fast, modular reference implementation of Semantic Segmentation algorithms in PyTorch for vibe coders.

A state-of-the-art Python implementation of the unbounded / large-scale NeRF view synthesis technique.

commonsense/conceptnet-numberbatch is a Python library for integrating commonsense knowledge into AI/ML models.

Meridian is an MMM framework that enables advertisers to set up and run their own in-house models.

An AI-powered platform for creating virtual influencers and content creators on platforms like Bilibili and Douyin.

A Chinese legal dialogue language model for developers working with AI tools.

FateZero is a video editing tool that uses AI-powered text-driven video editing and style transfer.

AI-powered data enrichment tool that transforms emails into rich datasets with company profiles, funding data, tech stacks, and more.

An Elixir implementation of the LangChain framework for integrating Elixir projects with large language models.

A Python library for depth estimation and 3D/4D reconstruction using AI-powered prompts.

This repository provides optimized PyTorch models and inference tools for NVIDIA GPUs, aimed at vibe coders building with AI tools.

A PyTorch implementation of the UNet++ (Nested U-Net) architecture for image segmentation tasks.

Picasso is a CNN visualizer that helps developers understand and interpret convolutional neural networks.

ChatGLM-6B is an open-source bilingual dialogue language model with 6.2B parameters, optimized for Chinese and English conversations.

An open-source Chinese version of the LLaMA and Alpaca language models with 64K long context support for advanced NLP applications.

Stable Diffusion-based tool for real-time music generation and audio manipulation for developers.

A small package to create visualizations of PyTorch execution graphs for AI/ML developers.

MITIE is a C++ library and tools for information extraction, with support for Java and Python.

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

LLM model optimized for coding tasks and autonomous agent workflows

A repository that contains interview notes and questions related to large language models (LLMs) for algorithm engineers.

Turn any computer or edge device into a command center for your computer vision projects.

Deprecated Tinder automation tool using AI that has been redirected towards Bernie AI.

A generic U-Net implementation in TensorFlow for image segmentation tasks.

A curated collection of resources for learning and implementing AIOps, covering various aspects of AI/ML in operations.

The KDL document language specifications - a serialization format for vibe coders using AI tools.

A fully-automated AI assistant that helps with deep research, powered by large language models.

A robust, real-time LiDAR-inertial initialization method for robotics and SLAM applications.

An open-source medical AI language model focused on taming language models to be a doctor.

A reference BLEU implementation that auto-downloads test sets and reports a version string.

An open-source computer vision and deep learning library for analyzing League of Legends gameplay.

LakeSail is a Rust-based computation framework that unifies batch processing, stream processing, and AI workloads.

A Jupyter Notebook library for applying data augmentation techniques to improve object detection models.

A SQL-driven RAG engine that automatically builds a knowledge graph during querying, enabling knowledge-enhanced applications.