Research & Education

TensorFlow Federated (TFF) is an open-source framework designed for machine learning and other computations on decentralized data. It specifically supports Federated Learning (FL), an approach where a shared global model is trained across many participating clients while their sensitive training data remains local. This framework enables developers to utilize included federated learning algorithms with their existing TensorFlow models and data, or to experiment with novel algorithms. TFF provides both a high-level Federated Learning (FL) API for applying federated training and evaluation, and a lower-level Federated Core (FC) API for expressing new federated algorithms. It includes a single-machine simulation runtime for experiments, making it suitable for researchers and developers exploring privacy-preserving machine learning.

NetNewsWire 7 is a free and open-source RSS reader designed for Mac, iPhone, and iPad, offering a streamlined way to consume news and blog content. It allows users to subscribe to their favorite blogs and news sites via RSS feeds, consolidating articles into a single, easy-to-manage interface. The application tracks read articles, ensuring users don't miss new content and can easily pick up where they left off. Key features include a Safari extension for adding feeds, syncing capabilities with various services like iCloud, Feedbin, and Feedly, customizable article themes, and a reader view. It also supports easy keyboard navigation, dark mode, starred articles, smart feeds, and background refreshing, providing a fast, stable, and accessible reading experience.

MonBotAchat is an AI-powered online shopping assistant designed to simplify the purchasing process for consumers. It offers personalized product recommendations, allowing users to discover innovative products tailored to their preferences. The platform provides intuitive price comparisons across a wide range of categories, including high-tech, fashion, beauty, and leisure, ensuring users find the best deals. MonBotAchat aims to deliver an intuitive and natural shopping experience, offering exceptional offers, current fashion trends, and gift ideas. Its features include easy and fast search capabilities, coupled with personalized advice to enhance the overall shopping journey.

PearAI aims to be a comprehensive inventory that curates leading, cutting-edge AI tools in one centralized location. It provides a unified interface, allowing users to seamlessly switch between different AI solutions without the need to constantly search for alternatives. The project is a conglomeration of several repositories, including `pearai-app` for VSCode integration and editor functionalities, `pearai-submodule` for AI chat features, `pear-landing-page` for the website, and `pearai-documentation` for user guides. It also includes `pearai-server` for optional convenience, allowing users to avoid using their own API keys. PearAI is built using TypeScript/Electron.js for the app, Next.js/React for the landing page, and a Python FastAPI server for the backend, utilizing Supabase for authentication and database management.

Quizi AI is a mobile application designed to revolutionize the way students study by converting any text-based material into interactive quizzes using advanced AI. Users can simply snap a photo of textbooks, notes, PDFs, presentations, or even whiteboards, and the AI instantly extracts the text to create personalized quiz questions. The tool supports over 100 languages, making it highly versatile for international students and language learners. It offers features like detailed analytics to track learning progress and performance insights, helping students study smarter. Quizi AI leverages Google's ML Kit for accurate text recognition and processes images locally on the device for enhanced privacy.

Freshman is an AI-powered study companion designed to enhance learning and memory retention through active recall and spaced repetition. It converts various study materials, including handwritten notes (from photos), PDF textbooks, PowerPoint slides, and digital text files, into scientifically designed active recall questions, quizzes, flashcards, and full mock exams. The tool helps students identify knowledge gaps, practice with interactive MCQ tests generated from past papers, and receive immediate feedback with detailed explanations. Freshman aims to move beyond passive study methods, offering a daily stream of bite-sized revision prompts and concept refreshers tailored to individual progress, making revision as simple as swiping.

RoseTTAFold is a deep learning model and script package designed for the accurate prediction of protein structures and interactions. This tool is an official implementation of the RoseTTAFold architecture, which employs a 3-track neural network to achieve its predictions. It is primarily intended for research in computational biology, enabling scientists to model complex protein structures and protein-protein interactions (PPIs). The package includes scripts for installation, dependency management, and running predictions for both monomer structures and complex modeling. It also features a faster 2-track version for PPI screening, making it a versatile tool for advanced biological research.

BrainDeck is an AI-powered flashcard and spaced repetition study app designed to help users memorize content more effectively. It allows for the generation of flashcards from various sources, including uploaded notes, documents, images, or simple text prompts. The app emphasizes daily, focused study sessions and incorporates spaced repetition to optimize knowledge retention. Users can track their progress, view performance insights, and set study reminders to maintain consistency. BrainDeck also offers access to a library of pre-made flashcard decks and supports importing flashcards from other apps or CSV formats, making it a versatile tool for students and anyone looking to improve their memorization skills.

Deepgaze is an open-source computer vision library designed for human-computer interaction, providing advanced capabilities for analyzing human behavior through visual data. It leverages Convolutional Neural Networks (CNNs) for precise head pose and gaze direction estimation, which is crucial for understanding a person's focus of attention, even when eyes are obscured or far from the camera. Beyond CNN-based estimation, Deepgaze incorporates features like skin detection via backprojection, robust motion detection and tracking, and saliency map generation using the FASA algorithm. Built on OpenCV and TensorFlow, it offers optimized, state-of-the-art algorithms, making complex implementations accessible with just a few lines of code for both beginners and advanced users in computer vision and machine learning.

Outline AI is an AI-powered tool designed to simplify the outline creation process. Users can generate comprehensive outlines by simply inputting their desired content or by providing source material such as websites, PDFs, images, and audio files. The tool leverages the latest AI technology to summarize information and structure it into a clear, organized outline. It is highly beneficial for brainstorming, academic writing, research structuring, preparing presentations, and organizing notes, offering a streamlined approach to content organization and idea development. The platform aims to enhance productivity by automating the initial structuring phase of various projects.

Ask Teacher: AI Study Tutor is a free AI-driven online education platform designed to provide expert solutions and guidance across a wide range of subjects. It acts as a real-time, comprehensive online teacher, offering instant solutions and expertly curated modules. The platform combines AI with education to create a smart learning experience, aiming to shape the future where technology and knowledge work hand-in-hand. It supports all subjects with an intensive training mode, providing professional support and streamlining the learning journey for maximum academic success. Students can enjoy personalized learning and rapid academic progress through its AI integration.

summarize.site is a browser extension designed to efficiently summarize web page content using OpenAI ChatGPT. Available for Chrome and Edge, this tool helps users quickly grasp the main points of articles and web content, making reading and research more efficient. It allows for local installation or building from source, offering flexibility for users. The extension also provides options to customize the summary prompt, including configurations for different languages like Chinese, enabling users to tailor the output to their specific needs, such as brevity, outline form, or translation. This makes it a versatile tool for anyone looking to condense information quickly.

ReviseMate is an AI-powered study coach designed to help students master any topic and excel in their exams. It allows users to instantly transform their notes into comprehensive study guides, streamlining the revision process. The platform provides 24/7 AI tutoring, offering on-demand assistance and explanations for various subjects. Additionally, ReviseMate features smart flashcards that adapt to individual learning patterns, enhancing memorization and deep understanding. With personalized learning paths and practice tests, ReviseMate aims to provide a comprehensive and effective study solution for students seeking to improve their academic performance.

Federated-Learning-PyTorch provides an open-source implementation of the vanilla federated learning paradigm, as described in the paper 'Communication-Efficient Learning of Deep Networks from Decentralized Data'. This tool is built using PyTorch and allows researchers and developers to conduct experiments on popular datasets such as MNIST, Fashion MNIST, and CIFAR10. It supports both independent and identically distributed (IID) and non-IID data distributions, with options for equal or unequal data splits among users. The implementation focuses on simple models like MLP and CNN to illustrate the effectiveness of federated learning, making it a valuable resource for understanding and experimenting with this distributed machine learning approach.

Calculus Solver - Math Answers is an AI-powered mobile application designed to assist students and individuals with their math homework and problem-solving needs. The app allows users to easily snap a photo of any math equation using its AI camera, crop the image to fit the problem, and then quickly access solutions. A key feature is its smart AI tool, which provides step-by-step solutions, making complex algebra and calculus problems easier to understand and master. This tool is particularly useful for those seeking immediate assistance and detailed guidance for their mathematical challenges, transforming how users approach and solve various math problems.

Auriko is an engaging educational gaming platform designed for K-8 students, aiming to make learning fun and interactive. It features over 1 million questions covering core subjects such as math, reading, and coding, presented within four magical worlds. Students can participate in battles with friends, earn rewards, and collect over 50 badges, fostering a sense of achievement and continuous engagement. The platform is kid-friendly, completely ad-free, and COPPA safe, ensuring a secure learning environment. Parents have access to a dashboard to monitor their child's progress, while teachers can manage classrooms and create student accounts without requiring individual emails. Auriko offers a free 2-hour trial to explore its features.

Super-gradients is an open-source training library designed to simplify the process of building, training, and fine-tuning state-of-the-art computer vision models. It provides ready-to-deploy pre-trained models, including the high-performance YOLO-NAS and YOLO-NAS-POSE architectures, which outperform other YOLO versions in accuracy and speed. The library supports various computer vision tasks such as classification, semantic segmentation, object detection, and pose estimation. Users can easily load and fine-tune models with validated hyper-parameters, and all models are production-ready, compatible with deployment tools like TensorRT and OpenVINO. Super-gradients also offers advanced features like Quantization Aware Training (QAT) and Knowledge Distillation, along with support for Distributed Data Parallel (DDP) for efficient multi-GPU training.

aTrain is a powerful GUI tool designed for offline transcription of speech recordings, leveraging state-of-the-art machine learning models for high accuracy and speed. Developed by researchers at the University of Graz, it features speaker diarization to identify different speakers in a recording. A key differentiator is its commitment to privacy, processing all data locally on your device without internet uploads, ensuring GDPR compliance. It supports transcription in 99 languages and offers compatibility with popular qualitative analysis tools like MAXQDA, ATLAS.ti, and nVivo. The tool can run on both CPU and NVIDIA GPUs, with GPU support significantly reducing transcription times.

StudyFlash AI is an AI-powered tool designed to simplify the study experience by enabling users to create and manage flashcards. The platform's core objective is to help individuals balance their academic commitments with other responsibilities by automating aspects of studying. By leveraging artificial intelligence, StudyFlash aims to make learning more efficient and effective, providing a streamlined approach to mastering new material. While the specific features are not detailed on the current website, the tool's focus on flashcard creation and management suggests it targets students and professionals seeking to optimize their learning processes. The platform emphasizes making studying less time-consuming and more productive.

Calcish is a versatile macOS application that integrates a programmable calculator, an enhanced JavaScript engine, AI capabilities, and an intuitive notebook into a single tool. It allows users to instantly solve complex math problems, work with big numbers, fractions, vectors, and matrices, and perform advanced scientific computing. The enhanced JavaScript engine, powered by QuickJS, supports arbitrary-precision integers and decimals, going beyond typical browser console limitations. Users can organize calculations, code, and AI chats in editable notebooks, with rich output and easy export options. AI integration supports both local and remote models for brainstorming, code generation, and data analysis, all accessible via a global hotkey for quick access.

autoTaskr is an AI-powered task helper designed to simplify daily life by providing clear, step-by-step guidance for a wide range of tasks. Users can describe any problem in plain English, and autoTaskr generates an actionable checklist in seconds. This tool is ideal for tackling everything from unblocking a sink and fixing tech issues to finding quick recipes and organizing the home. Key features include instant step generation, progress tracking, the ability to ask for more detail on any step, and a history function to revisit past tasks. Available on both iOS and Android, autoTaskr aims to help users get things done faster and more efficiently without wasted time.

PhyCV is the first Physics-inspired Computer Vision Python library developed by Jalali-Lab at UCLA. It introduces a new class of computer vision algorithms that simulate the propagation of light through physical mediums with diffractive properties, followed by coherent detection. Unlike traditional empirical algorithms, PhyCV leverages physical laws as blueprints, making these algorithms potentially implementable in real physical devices for fast and efficient computation. The library currently includes Phase-Stretch Transform (PST) for edge and texture detection, Phase-Stretch Adaptive Gradient-field Extractor (PAGE) for directional edge detection, and Vision Enhancement via Virtual diffraction and coherent Detection (VEViD) for low-light and color enhancement. Both CPU and GPU versions are available for each algorithm, with GPU versions depending on PyTorch and torchvision.

parameter_efficient_instruction_tuning is an open-source repository dedicated to the systematic comparison of various parameter-efficient fine-tuning (PEFT) methods for instruction tuning tasks. The project utilizes the SuperNI dataset as its primary benchmark for training and evaluation. Implementations of PEFT methods are adapted from well-known libraries such as adapter-transformers and peft. The repository includes bash scripts for running experiments, optimized for the hfai HPC platform, supporting features like experiment configuration, checkpoint management, and training state validation. It also addresses platform-specific considerations like PyTorch and CUDA compatibility, making it a valuable resource for researchers and developers working on efficient large language model fine-tuning.

Creative Minds Think Alike is an AI-powered platform designed to enhance creative collaboration and skill development. It offers tools for brainstorming, team collaboration, and project management, enabling users to work together effectively on creative projects. The platform also includes AI-powered skill assessments to help individuals understand and improve their creative capabilities. Users can leverage its features for creative development, fostering a community where ideas are shared, and projects are managed efficiently. It aims to connect individuals globally for meaningful creative work and skill enhancement.