Trending Projects

Automatically translate and dub videos using AI-powered text-to-speech and subtitle synchronization.

A curated list of resources for everything related to deepfakes and face-swapping technology.

Example code and machine learning models for the Teachable Machine web-based AI training tool.

PaddleVideo is a powerful toolkit for video understanding tasks like action recognition, localization, and detection.

OpenMLDB is an open-source machine learning database that provides a feature platform for training and inference.

A research project exploring the use of transformers in robotics applications.

A dataset and tools for the Project CodeNet dataset, hosted in the DAX platform, for AI-focused developers.

A curated list of awesome AI, ML, and DL resources, including code, tutorials, and study notes.

A Python-based tool for generating subtitles using OpenAI's Whisper speech recognition model.

A curated list of resources for developing applications using large language models (LLMs) with the Retrieval Augmented Generation (RAG) pattern.

A collection of pre-trained models for the dlib computer vision and machine learning library.

DomainBed is a suite to test domain generalization algorithms for machine learning models.

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

A JavaScript library that provides a powerful geometric algebra generator for various languages.

High-performance PyTorch implementation of the SSD (Single Shot MultiBox Detector) for object detection.

Automated deep learning algorithms implemented in PyTorch for AI-driven developers.

A fast symbolic computation library for robotics, with capabilities like code generation and nonlinear optimization.

An AI-powered companion tool for reading and understanding academic research papers.

An AI-powered tool that extracts knowledge and generates summaries from PDF books, page by page.

An open-source framework for detecting, highlighting, and correcting grammatical errors in natural language text.

A collection of edge/contour/boundary detection papers and toolbox for computer vision tasks.

A Python library for training and deploying image-based captcha recognition models.

A high-performance, autoregressive model for generating high-resolution images from text prompts.

A Python library that provides a wrapper for the ComfyUI AI-powered video generation tool.

A JavaScript library for generating and manipulating images using Telegraph, an AI-powered image editor.

A project that integrates text-to-SQL dataset, solutions, and research papers for developers working with AI tools.

A full Python interactive 3D Gaussian Splatting viewer for real-time editing and analyzing.

DeepRant is an AI-powered game chatting tool for developers who build with AI tools.

An open-source framework for building autonomous cognitive agents using Python and AI tools.

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

Code repository for a book on feature engineering for machine learning

Non-official implementation of the CBAM paper, a convolutional block attention module for neural networks.

A knowledge graph-based question answering system for medical diagnosis using Python.

The VS Code Jupyter extension provides a powerful interface for data science and machine learning workflows in VS Code.

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

A curated list of resources for interpreting and understanding large language models (LLMs).

A simple and efficient alternative to Retrieval-Augmented Generation (RAG) models for large language models.

Open-source foundational library for training deep learning models with PyTorch.

Unified-Modal Speech-Text Pre-Training for Spoken Language Processing

A novel Multimodal Large Language Model (MLLM) architecture for structurally aligning visual and textual embeddings.

A Python library implementing various multi-robot path-planning algorithms.

Fastest text 'uwuifier' written in Rust, targeting vibe coders who use AI tools.

A PyTorch toolbox for domain generalization, domain adaptation and semi-supervised learning.

A Facebook Messenger Bot with voice recognition, NLP, and features like restaurant search and memo transcription.

A library that provides seamless model explainability for transformers models in just 2 lines of code.

A simple image captioning model built using the CLIP neural network for generating captions for images.

An optimized library for running sub-billion parameter language models on mobile and edge devices.

WebThinker is a powerful framework for building large language models with deep research capabilities.

Python code to fuse multiple RGB-D images into a TSDF voxel volume for 3D reconstruction.

A collection of small projects related to Neural Networks and Deep Learning with a focus on computer vision.