Research & Education

spacy-models offers a collection of pre-trained models specifically designed for use with the spaCy Natural Language Processing (NLP) library. These models are essential for data scientists and machine learning engineers who are building applications that require advanced text processing capabilities. The models support a wide range of NLP tasks, including efficient text analysis, named entity recognition, and dependency parsing. By leveraging these pre-trained models, users can significantly accelerate their NLP development workflows, reducing the need for extensive custom training. The integration with spaCy ensures high performance and ease of use for various linguistic tasks.

PySlowFast is an open-source video understanding codebase developed by FAIR, designed to provide high-performance, lightweight PyTorch implementations of state-of-the-art video backbones. It supports various video understanding research tasks, including classification and detection, and is built for rapid implementation and evaluation of novel video research ideas. The repository features implementations of methods like SlowFast Networks, Non-local Neural Networks, X3D, Multiscale Vision Transformers (MViTv1 and MViTv2), Reversible Vision Transformers (Rev-ViT and Rev-MViT), and supports advanced techniques such as Multigrid Training, MAE for Video, and MaskFeat. It also includes a comprehensive model zoo with pre-trained models and baselines, along with visualization tools for analysis and inference.

ReMind is an AI memory agent designed to capture, index, and summarize your digital activities directly on your device. It records screenshots, audio, and other digital interactions, then transcribes text from captured screenshots. Utilizing advanced AI models and vector databases, ReMind indexes this information, provides detailed summaries of daily activities, and allows users to interact with the application via a chat interface to query their digital history. This tool is ideal for individuals seeking to effortlessly manage and recall their digital footprint, offering a personalized and local artificial memory solution.

siggraph2016_colorization is an open-source tool offering code for automatic image colorization, leveraging deep learning techniques. It specifically implements a method for joint end-to-end learning of global and local image priors, allowing for nuanced and context-aware colorization. A key feature is its ability to perform simultaneous classification during the colorization process of grayscale images, which can enhance the accuracy and quality of the output. This tool is ideal for researchers, developers, and enthusiasts interested in computer vision and image processing, providing a foundational codebase for further experimentation and application in image restoration and enhancement.

Scholarcy is an AI-powered research assistant designed to simplify academic research by transforming complex texts into concise, interactive summary flashcards. It allows users to summarize any paper, article, textbook, or even videos, highlighting key information and enabling quick comprehension. The tool offers features like enhanced summaries, spotlighting key findings, and critical analysis tools to evaluate research quality. Users can organize their knowledge by saving flashcards to a personal library, adding notes, and exploring related concepts. Scholarcy also supports synthesizing insights by exporting summaries to various formats compatible with research and productivity apps like Zotero, Notion, and Excel, and can generate one-click bibliographies.

TensorFlow-VAE-GAN-DRAW is an open-source collection of generative methods implemented using TensorFlow. This repository offers implementations of Deep Convolutional Generative Adversarial Networks (DCGAN), Variational Autoencoders (VAE), and DRAW: A Recurrent Neural Network For Image Generation. It allows users to experiment with and run these different generative models, providing a foundation for research and development in image generation. The project highlights that DCGANs produce decent results after 10 epochs with default parameters and outlines future enhancements like more complex data integration and replacing the current attention mechanism with a Spatial Transformer Layer.

SocratiQ is an AI-powered learning platform designed to deliver personalized, social, and self-driven educational experiences. It leverages artificial intelligence to create adaptive learning paths that cater to the unique needs of each student. The platform supports a wide range of educational settings, from individual learners seeking self-paced study to large-scale institutional implementations. SocratiQ aims to enhance engagement and effectiveness in learning by providing tailored content and interactive tools, making education more accessible and impactful across various domains and user groups.

TTS is a comprehensive open-source library developed by Mozilla for advanced Text-to-Speech generation. It leverages the latest research to provide a balance of ease-of-training, speed, and quality, making it suitable for various applications. The library includes pretrained models and tools for measuring dataset quality, supporting over 20 languages. It features high-performance deep learning models for Text2Spec tasks like Tacotron and Glow-TTS, as well as various vocoder models such as MelGAN and WaveRNN. TTS supports multi-speaker TTS, efficient multi-GPU training, and the ability to convert PyTorch models to Tensorflow 2.0 and TFLite for inference. It also provides a demo server for model testing and notebooks for extensive benchmarking.

UniPic is an open-source multi-image editing model developed by SkyworkAI, focusing on image editing, generation, and understanding tasks. The tool is built around three distinct modeling paradigms, offering flexibility and advanced capabilities for manipulating and interpreting images. It is particularly well-suited for AI researchers and developers who are actively working on or interested in multimodal models, providing a robust platform for experimentation and application development in the field of artificial intelligence and computer vision.

BMInf (Big Model Inference) is an open-source toolkit designed to facilitate efficient inference for large-scale pretrained language models (PLMs). It enables the execution of models with over 10 billion parameters, even on low-resource hardware like a single NVIDIA GTX 1060 GPU. The tool offers significant performance improvements over existing PyTorch implementations, particularly for GPUs like V100 or A100. BMInf 2.0.0 introduced compatibility with any transformer-based model, making it a versatile solution for researchers and developers working with big AI models. It provides methods for automatic model conversion using `bminf.wrapper` or manual replacement of modules like `torch.nn.ModuleList` and `torch.nn.Linear` for optimized performance.

ETM (Topic Modeling in Embedding Spaces) is a research tool designed to perform topic modeling by representing words and topics within a unified embedding space. This approach allows for the likelihood of a word under ETM to be modeled as a Categorical distribution, derived from the dot product between the word embedding and its assigned topic's embedding. ETM is particularly effective as a document model, capable of learning interpretable topics and word embeddings. Its design makes it robust against large vocabularies, including those with rare words and stop words, which is a significant advantage in natural language processing. The tool provides scripts for data preprocessing, training, and evaluation, supporting various datasets like 20NewsGroup and New York Times.

ViZDoom is an open-source platform designed for developing AI bots that play the classic 1993 game Doom using only visual information from the screen buffer. It is primarily intended for research in machine visual learning and deep reinforcement learning. The tool offers a robust API for Python (including Gymnasium/Gym wrappers) and C++, supporting multi-platform deployment on Linux, macOS, and Windows. Key features include high performance (up to 7000 frames/steps per second), lightweight footprint, and easy creation of custom scenarios with visual editors and a powerful scripting language. Researchers can leverage its async and sync single-player/multiplayer modes, customizable rendering, access to depth and audio buffers, object labeling, and in-game data for advanced AI experimentation. ViZDoom is reinforcement learning friendly, suitable for learning from demonstration, apprenticeship learning, and inverse reinforcement learning.

Shiken is an AI-powered learning platform designed to help individuals and teams learn faster and more effectively. It allows users to create voice-powered learning content, including courses, microlearning quizzes, and notes, often in minutes. The platform features an AI Knowledge Assistant to enhance creativity and productivity, along with AI role-playing scenarios for interactive training. Shiken supports various use cases such as sales enablement, onboarding, compliance training, and customer education. It aims to reduce content creation time by up to 70% using AI, offering an all-in-one solution for engaging and personalized learning experiences.

MaterialSearch is an open-source semantic search tool designed to help users efficiently find local photos and videos using natural language queries. The tool offers robust features including text-based image search, image-based image search, text-based video search (providing matching video clips), and image-based video search (searching for video segments based on screenshots). Its core logic is separated into a standalone pip package, materialsearch-core, facilitating easier version control and distribution. MaterialSearch can be deployed via Windows bundles or Docker, supporting GPU acceleration. It is particularly useful for organizing and retrieving media from large local collections.

xlstm is the official GitHub repository for the xLSTM, a new Recurrent Neural Network architecture based on the original LSTM. This tool provides the necessary code and resources for researchers and practitioners to implement and experiment with this novel LSTM variant. xLSTM utilizes Exponential Gating with appropriate normalization and stabilization techniques, along with a new Matrix Memory, to overcome the limitations of traditional LSTMs. It demonstrates promising performance in Language Modeling compared to Transformers or State Space Models. The repository includes a 7B parameter xLSTM Language Model trained on 2.3T tokens, optimized for fast and efficient inference, and offers detailed instructions for installation and usage.

Lyrebird Health is an AI medical scribe designed for Australian GPs, Specialists, and Allied Health professionals. It securely listens to patient consultations in the background and intelligently generates comprehensive clinical notes, letters, and other documents tailored to the practitioner's style. The tool aims to automate the entire administrative burden, allowing clinicians to focus more on patient care. It integrates deeply with EMRs like Best Practice and Genie/Gentu, enabling direct workflow within the existing medical record system. Lyrebird Health supports various documentation needs, including CCMPs, MHTPs, and NDIS PDFs, and ensures patient data is processed and stored onshore in Australia with bank-level encryption, without using data to train AI models.

AI Language Learning is an AI-powered Chrome extension designed to supercharge language acquisition. It offers real-time grammar checking and translations, enabling users to confidently practice and improve their new language skills. This tool is ideal for students, travelers, and professionals who want to enhance their language proficiency through practical application. By integrating AI assistance directly into the browser, it provides immediate feedback and support, making the learning process more efficient and effective for various language learners.

Algoryx specializes in high-fidelity physics simulation, offering physical AI and physics-based digital twins. Its core product, AGX Dynamics, is a powerful physics engine capable of real-time multibody dynamics simulation, handling frictional contacts, non-ideal joints, flexible objects, and more. Algoryx Momentum, a plugin for SpaceClaim CAD software, enables interactive design and rapid prototyping, with an extension for granular material handling. The company also provides AGX Dynamics for Unity and is developing a version for Unreal Engine, combining state-of-the-art visualization with industrial-grade simulations. Algoryx's solutions are crucial for developing autonomous systems, virtual prototyping, and creating accurate VR training simulators, ensuring reliable transfer of simulated data to real-world applications.

Easy English Vocabulary is an application designed to help users expand their English vocabulary with ease and enjoyment. It features vocabulary cards with native example sentences available in 19 languages, offering comprehensive support for diverse learners. The app leverages AI-powered insights and personalized study plans to tailor the learning experience. Users can explore diverse word lists, create AI-generated stories for contextual learning, and organize collections to track their progress. Additionally, it includes interactive games to make vocabulary acquisition engaging and provides comprehensive statistics to monitor learning achievements.

SmartPrep is an AI-powered platform designed to revolutionize lesson planning for educators. It instantly generates comprehensive lesson bundles, including free templates, Project-Based Learning (PBL) frameworks, Understanding by Design (UbD) structures, and a wealth of teaching resources. The tool significantly reduces the time spent on repetitive tasks by leveraging AI to scour the web for relevant content like webpages, images, videos, and academic materials. SmartPrep also offers limitless ready-to-use assessments, allowing teachers to produce customizable quizzes, MCQs, FRQs, essay prompts, and discussions in minutes. It aims to empower teachers by fostering creativity and providing more time to focus on actual teaching.

Exec's AI Roleplay platform helps teams practice critical conversations with realistic simulations and instant feedback. It allows for the creation of custom scenarios tailored to an organization's specific needs, leveraging AI characters with deep industry context and customizable traits. The platform supports voice-based interactions, screen sharing for presentations, and provides dynamic feedback, actionable tips, and an AI Coach debrief. Designed for sales, leadership, and support teams, Exec aims to accelerate onboarding, improve coaching, and enhance overall performance through unlimited practice sessions and measurable skill development.

AI-Resume-Analyzer is an open-source tool designed to assist job applicants and recruiters by parsing resume information using natural language processing. It extracts keywords, clusters them into relevant sectors, and offers recommendations, predictions, and analytics based on keyword matching. The tool can structure resume data into tabular formats and CSV for organizational analytics. It also provides applicants with insights to improve their resumes, including predicted job roles, course recommendations, and an overall score. For administrators, it offers features like viewing applicant data, downloading CSVs, and analyzing user feedback and ratings through pie charts.

Kidopedia AI is an innovative educational tool designed to support children's learning and emotional well-being. This v1.0.2 release introduces vision-powered homework assistance, allowing kids to get help with their assignments by simply showing them to the AI. It also features AI-generated story time tales, providing engaging and personalized narratives. The tool boasts an enhanced chat user experience and a polished UI, all while maintaining a fully offline-first approach, ensuring learning can continue without an internet connection. Kidopedia AI aims to connect learning with feelings through its features, making education more interactive and accessible.

UndercoverDevs is an AI-powered study assistant designed for students and researchers to enhance their learning experience. It offers a suite of tools including an AI Teacher that provides step-by-step explanations and answers questions, smart note-taking features with AI expansion, and a PDF simplifier and translator to make complex documents easy to understand. Users can generate quizzes and flashcards directly from their AI conversations or notes, create custom question papers for exam preparation, and even use a Mnemonic Maker to aid memorization. The platform aims to help students study faster, retain more information, and stay focused by breaking down complex topics and offering personalized study tools.