Research & Education

obsidian-text-extractor is an Obsidian plugin designed to extract text from images, PDFs, and office documents using OCR technology. It acts as a "companion" plugin, primarily useful when integrated with other Obsidian plugins like Omnisearch, but can also be used independently for quick text extraction. The plugin supports various image formats, PDFs, and office documents (.docx, .xlsx). It processes text locally but requires an internet connection to download language files for the underlying Tesseract OCR library. Extracted texts are cached as local JSON files, which can be synced across devices, allowing mobile users to access cached texts even though direct extraction doesn't work on mobile.

PDF Summarizer is an AI-powered tool designed to streamline document analysis by summarizing long PDFs. Users can upload documents and engage in multi-file chats, allowing them to ask questions across multiple documents simultaneously, which is ideal for research projects. The system provides detailed or short summaries, extracts key points, and can even create notes, flashcards, and quizzes. A standout feature is its ability to translate any PDF into a preferred language instantly. The tool also offers a side-by-side view, linking questions directly to specific parts of the PDF for easy source checking and deeper exploration without losing context. It supports PDF files up to 50MB and 500 pages, ensuring data security with SOC2 Type II certification.

The Groq Emulator is a project designed to explore Groq-like static dataflow computation, characterized by deterministic, pre-scheduled execution where computation graphs are compiled ahead of time without dynamic branching. It offers three main functionalities: a DNN Runner for configuring and running forward passes of neural networks, a Cellular Automata section for simulating 2D stencil computations with various rules, and a Kernel editor for writing custom operations using an emulator API. This tool provides insights into core abstractions like Buffers, Nodes, and Graphs, and demonstrates the difference between iterative and unrolled computation. It's a valuable resource for understanding the performance characteristics and potential optimizations achievable with Groq's technology, built with LLM assistance.

ebooks is an open-source GitHub repository offering a comprehensive collection of high-quality IT ebooks. This resource is specifically curated for programmers, students, and technology enthusiasts, providing valuable learning materials across numerous technical domains. The collection includes books on AI, Machine Learning, LLM, Algorithms, C/C++, C#, Competitive Programming, Computer Networks, Databases, Full-Stack Development, Java, Interview preparation, Python, R Programming, ReactJS, System Design, and more. Users can access these materials for free, making it an excellent resource for self-study and skill development in information technology. Contributions are welcome, allowing the community to expand and improve the collection.

Concise AI is an AI-powered platform designed for markets and finance analytics, offering a unified view of global and local developments in finance, economics, government, and society. It provides real-time AI-compiled research reports that add context to world events and the macro investing landscape, seamlessly combining insights and data from various sources with citations. The platform features an AI-powered deep search to expedite financial research, allowing users to search investor materials, financial news, earnings transcripts, and industry publications. Additionally, it offers equity and ETF analysis using natural language, global market analysis, and tools to track special situations like mergers and acquisitions, breaking down deal structures and regulatory risks. The AI-enhanced research and reporting tools allow users to save, share, and publish reports within an AI-augmented environment.

Emotion-recognition-neural-networks is an open-source project developed for emotion recognition using deep neural networks, specifically with TensorFlow. It employs convolutional neural networks (CNNs) for mood recognition, utilizing the FER-2013 Faces Database which contains 28,709 pictures across 7 emotional expressions. The project provides scripts for data transformation from CSV to NumPy, and supports training models using architectures like AlexNet. While the repository notes that the code might not be actively maintained or fully functional, it serves as a foundational academic project for those interested in exploring DNN-based emotion recognition.

EmotiVoice is a powerful and modern open-source text-to-speech engine available at no cost. It supports both English and Chinese, offering over 2000 distinct voices. A key feature is its emotional synthesis, allowing users to generate speech with a wide range of emotions like happy, excited, sad, and angry. The tool provides an easy-to-use web interface for interactive use and a scripting interface for batch generation. Recent updates include support for tuning voice speed, an app for Mac, an HTTP API with free calls, and voice cloning capabilities. EmotiVoice prioritizes community input and plans to support more languages in the future.

KEATH.ai is an award-winning, intelligent AI marking suite designed for educational assessment. This platform streamlines the grading process, offering rapid evaluation of academic work such as EPQ evaluations, essays, and custom assignments. Beyond just grading, KEATH.ai provides hyper-personalized learning feedback to students, aiming to enhance their educational experience. The tool focuses on delivering unbiased assessment and supporting academic tutoring. It is built to assist educators in efficiently managing their assessment workload while ensuring students receive tailored insights for improvement.

ENACOM Group specializes in developing and regionalizing advanced computational methods for various engineering applications. The company's core expertise lies in areas such as multiobjective optimization, machine learning, and data mining. ENACOM is committed to fostering technological development within Brazil, actively supporting research initiatives, and facilitating the transfer of technology to practical applications. While specific features are not detailed on their website, their focus suggests a strong emphasis on scientific and statistical analysis, likely catering to technical professionals in engineering and research fields.

Mapwise is an AI-powered learning assistant designed to transform various study materials into structured, step-by-step learning roadmaps. Users can upload notes, PDFs, and videos, which Mapwise then processes to extract topics, structure concepts, and generate milestones. The platform offers a comprehensive suite of study tools, including AI-generated flashcards with spaced repetition, interactive AI quizzes, and voice tutor sessions directly tied to the learning roadmap. This integrated approach helps students, professionals, and self-learners break down complex topics, track progress, and reinforce learning effectively. Mapwise aims to provide a single solution for organized and adaptive study, eliminating the need to juggle multiple apps.

EnCodec is a state-of-the-art deep learning-based audio codec developed by Facebook Research. It offers high-fidelity neural audio compression for both mono 24 kHz audio and stereo 48 kHz audio. The tool provides two multi-bandwidth models: a causal model for 24 kHz monophonic audio and a non-causal model for 48 kHz stereophonic audio, trained on music-only data. Users can compress audio to various bitrates, ranging from 1.5 kbps to 24 kbps, depending on the model. EnCodec also includes pre-trained language models for further compression without quality loss and can be integrated with Hugging Face Transformers for scalable use. It supports direct command-line usage for compression, decompression, and extracting discrete audio representations.

Wordage AI is an AI-powered writing tool specifically designed for founders and professionals to streamline their LinkedIn content creation. The platform enables users to input their initial ideas or rough thoughts, which are then transformed into polished, publish-ready drafts. This workflow aims to boost confidence in publishing on LinkedIn by providing high-quality, refined content. Wordage AI focuses on efficiency, allowing users to quickly move from an initial concept to a complete post, making it an ideal solution for those who need to maintain a strong professional presence on social media without extensive manual writing effort. The tool is tailored to enhance the writing process for professional networking and thought leadership.

e3nn is an open-source, modular framework designed to facilitate the development of neural networks with Euclidean symmetry. It provides fundamental mathematical operations such as tensor products and spherical harmonics, essential for building E(3) equivariant neural networks. The library is under active development, with breaking changes indicated by version number increments. It is recommended to install using pip, and users can contribute to its development or seek help through discussions and bug reports on GitHub. The framework is backed by research papers on Euclidean Neural Networks and e3nn itself, with BibTeX entries available for citation.

mPLUG-Owl is a family of multi-modal large language models (MLLMs) designed to enhance language models with multimodality through a modular approach. The project includes several iterations: mPLUG-Owl, mPLUG-Owl2, and mPLUG-Owl3, each building upon the previous version to offer improved capabilities. mPLUG-Owl2, for instance, was accepted by CVPR 2024 as a Highlight, and mPLUG-Owl2.1 provides a Chinese-enhanced version. The latest iteration, mPLUG-Owl3, focuses on long image-sequence understanding. The source code and weights for these models are available on HuggingFace, making them accessible for researchers and developers to integrate and experiment with.

Strella is an AI-powered customer research platform designed to help product, design, and marketing teams gain customer insights 10x faster. It leverages AI to run in-depth, moderated interviews and provides real-time synthesis of responses, significantly reducing the time required for customer research. The platform can generate unbiased discussion guides, recruit participants from an 8M global panel, and analyze key themes across responses. Strella supports various research types including market research, usability testing, and concept testing, and offers features like AI-powered probing, instant highlight reels, and multi-language support across 46+ languages.

mteb (Massive Text Embedding Benchmark) is an open-source Python library designed for comprehensive evaluation of text and multimodal embeddings. It offers a standardized framework to benchmark the performance of different embedding models across a wide array of tasks, including classification, clustering, semantic textual similarity (STS), retrieval, and reranking. The tool supports both monolingual and multilingual evaluations, with a focus on reproducibility and ease of use. Developers and researchers can use mteb to select models, define custom models, run evaluations, and analyze results, contributing to an interactive leaderboard that tracks the state-of-the-art in embedding performance. Its modular design allows for easy integration of new models, datasets, and benchmarks.

The Hugging Face Evaluation Guidebook is a comprehensive resource for understanding and implementing Large Language Model (LLM) evaluation. It provides both practical insights and theoretical knowledge, drawing from the experience of managing the Open LLM Leaderboard and designing the lighteval framework. The guidebook covers various evaluation methods, including automatic benchmarks, human evaluation, and LLM-as-a-judge approaches. It offers guidance on designing custom evaluations, troubleshooting common issues, and provides tips and tricks for both beginner and advanced users. Additionally, it includes sections on general LLM knowledge, such as model inference and tokenization, making it a valuable resource for anyone looking to ensure their LLM performs effectively.

DyNet is a powerful open-source neural network library, primarily developed by Carnegie Mellon University, with contributions from many others. Written in C++ and offering Python bindings, it's engineered for efficiency on both CPU and GPU architectures. A key differentiator is its ability to handle dynamic neural network structures, which can adapt and change for each training instance. This makes DyNet particularly well-suited for complex natural language processing tasks, where it has been successfully applied to build state-of-the-art systems for syntactic parsing, machine translation, and morphological inflection. The toolkit provides comprehensive documentation, tutorials for both C++ and Python, and examples to help users get started with its auto-batching feature and other functionalities.

DropoutUncertaintyExps is an open-source project containing the experimental code for the paper "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning." The repository provides a framework for researchers to replicate and build upon the uncertainty experiments, with adaptations reflecting community feedback and bug fixes. It is based on José Miguel Hernández-Lobato's work on probabilistic backpropagation for scalable learning of Bayesian Neural Networks. The code utilizes datasets from the UCI machine learning repository, with specific data splits to ensure comparability of results. It details the methodology for hyperparameter tuning using grid-search and reports RMSE and log-likelihood metrics for various datasets, offering a valuable resource for academic research in deep learning uncertainty.

MiniSearch is a minimalist web-searching application that integrates an AI assistant directly into your browser. Designed for quick and efficient information retrieval, it allows users to type in questions or topics and receive relevant information and AI-generated responses. The tool aims to provide a streamlined search experience, making it easy for users to find what they need without navigating through multiple pages. Its browser-based nature ensures accessibility and convenience for anyone looking for fast answers and AI-powered insights.

finetrainers is a work-in-progress library from Hugging Face designed for scalable and memory-optimized training of diffusion models. It provides support for various commonly used training algorithms, including DDP, FSDP-2, HSDP, and CP. Key features include LoRA and full-rank finetuning, conditional control training, and memory-efficient single-GPU training. The library also supports multiple attention backends like flash, flex, sage, and xformers, along with auto-detection of common dataset formats. It's built to handle combined image/video datasets, multi-resolution bucketing, and offers memory-efficient precomputation. finetrainers is recommended for use with PyTorch 2.5.1 or above for optimal performance and reproducibility.

fastai_deeplearn_part1 is an open-source repository offering comprehensive notes and resources for the fast.ai deep learning course. It serves as a valuable educational aid, providing structured outlines for different versions of the deep learning and machine learning courses, ranging from Fall 2016 to Spring 2020. The repository includes helpful resources such as a directory of fastai and deep learning terms, solutions for common errors, FAQs for beginners, and best practices. Additionally, it features technical tools and tips for working with platforms like AWS, Kaggle CLI, and Jupyter Notebooks, making it a practical guide for students and developers engaging with deep learning concepts. The content is primarily in Markdown format, making it easily accessible and reviewable.

ExLlamaV3 is an inference library specifically designed for running Large Language Models (LLMs) locally on modern consumer-class GPUs. Its headline feature is the new EXL3 quantization format, which is based on QTIP from Cornell RelaxML, allowing for efficient model conversion in a single step. The library supports flexible tensor-parallel and expert-parallel inference setups, and provides an OpenAI-compatible server via TabbyAPI for local or remote inference. It also includes features like continuous, dynamic batching, HF Transformers plugin support, speculative decoding, and 2-8 bit cache quantization. ExLlamaV3 aims to make advanced quantization techniques more accessible and less resource-intensive, enabling users to run large models like Llama-3.1-70B with minimal VRAM.

The PatchCamelyon (PCam) benchmark is a challenging image classification dataset designed for deep learning in medical imaging. It comprises 327,680 color images (96 x 96px) extracted from histopathologic scans of lymph node sections. Each image is annotated with a binary label indicating the presence of metastatic tissue, making it ideal for training and evaluating machine learning models for metastasis detection. PCam is larger than CIFAR10 but smaller than ImageNet, allowing models to be trained on a single GPU within a few hours. It serves as a valuable resource for fundamental machine learning research on topics such as active learning, model uncertainty, and explainability, particularly within the medical domain. The dataset is provided in gzipped HDF5 files and includes training, validation, and test sets with balanced positive and negative examples.