Research & Education

Awesome-LLM-based-Text2SQL is a comprehensive repository dedicated to large language model-based text-to-SQL (LLM-based Text-to-SQL). It serves as a curated list of research papers, benchmarks, and open-source projects in this rapidly evolving field. The repository includes content from the survey paper "Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL" and is regularly updated to reflect the latest advancements and notable contributions from the text-to-SQL community. It categorizes resources into trends, surveys, benchmarks (including BIRD, Spider 1.0, Spider 2.0, BIRD-CRITIC, BIRD-INTERACT), datasets (original and post-annotated), and a taxonomy covering in-context learning and fine-tuning methods. This makes it an invaluable resource for researchers and developers working on natural language interfaces for databases.

awesome-llm-json is a comprehensive, open-source resource list dedicated to leveraging Large Language Models (LLMs) for generating structured outputs, primarily JSON. This curated collection encompasses various categories such as hosted and local LLM models, Python libraries, blog articles, videos, Jupyter notebooks, and leaderboards. It clarifies terminology like Function Calling, JSON Mode, Tool Usage, and Guided Generation, which are often used interchangeably. The list details specific models from providers like Anthropic, OpenAI, and Mistral that support structured output, as well as local models like Hermes 2 Pro. Python libraries such as DSPy, Instructor, LangChain, and Pydantic are highlighted for their roles in constrained generation and data validation. This resource is invaluable for developers and researchers looking to implement or understand structured output generation with LLMs.

Clevered is an online e-learning platform specializing in Artificial Intelligence and coding courses for students aged 6 to 18. The curriculum, developed by professors from institutions like MIT, Oxford, and IIT, focuses on practical skills in coding, data science, and AI. Programs include Junior Data Scientist, Young Coder, and AI Internship, offering live interactive sessions with expert mentors. Students gain hands-on experience through projects, receive certifications from Google, IBM, and Microsoft, and can participate in internships with opportunities for letters of recommendation from Oxford researchers or former NASA Chief Scientists. Clevered emphasizes a unique pedagogy that prepares students for real-world applications and future careers.

CausalNLP_Papers is a curated, open-source reading list hosted on GitHub, dedicated to papers exploring causality within natural language processing (NLP). This repository serves as an invaluable resource for researchers, academics, and practitioners seeking to understand and apply causal inference methods to NLP problems. It categorizes papers into sections such as Causality Basics, Causality Applied to General NLP, and Causality for Various Applications, including persuasion, psychology, economics, and healthcare. The list also features toolboxes for causal discovery and effect estimation, as well as resources from prominent labs like Schoelkopf's and Bengio's, making it a comprehensive guide for systematic learning and exploration in causal NLP.

Category_Theory_Machine_Learning is a GitHub repository that curates a list of academic papers exploring the intersection of machine learning and category theory. The repository organizes papers by various fields such as Deep Learning, Equivariance, Graph Neural Networks, Differentiable Programming, Probability Theory, Bayesian/Causal Inference, Topological Data Analysis, and more. It also includes theses and blog posts related to the subject. This resource is designed for researchers, academics, and enthusiasts interested in the theoretical foundations of machine learning, offering a structured overview of relevant publications and encouraging community contributions through pull requests or issue submissions.

The HKUST(GZ) Information Hub, part of The Hong Kong University of Science and Technology (Guangzhou), is dedicated to advancing information science and technology through innovative education and research. It emphasizes a cross-disciplinary approach, integrating various fields to address complex challenges. The hub focuses on key areas such as Artificial Intelligence, Data Science, Internet of Things (IoT), and Computational Media, aiming to cultivate forward-looking talents with a global vision. Through its academic structure, which includes various Hubs and Thrust Areas, HKUST(GZ) seeks to promote higher education reform and accelerate collaboration between Hong Kong and Mainland China, contributing significantly to the development of the Greater Bay Area.

Software-Engineer-Coding-Interviews is a comprehensive GitHub repository designed to help software engineers prepare for technical interviews. It covers essential topics such as Data Structures and Algorithms, System Design (including Generative AI and Machine Learning System Design), Machine Learning, and DevOps. The repository offers a curated collection of interview practices, notes, and resources from various reputable sources like ByteByteGo, Educative, and Princeton University's Algorithm courses. It includes detailed markdown notes, PDF notes, and references to books like "Beyond Cracking the Coding Interview" and "Coding Interview Patterns," making it a valuable self-study guide for aspiring and experienced engineers.

deepLearningBook-Notes offers an in-depth resource for understanding the Deep Learning book by Ian Goodfellow, Yoshua Bengio, and Aaron Courville (2016). This GitHub repository provides detailed notes, intuitive explanations, visual drawings, and practical Python code examples to clarify complex mathematical theories, especially linear algebra concepts crucial for deep learning and machine learning. It's designed to help beginners and advanced beginners grasp the underlying principles, offering a structured syllabus that mirrors the book's chapter on linear algebra. The resource emphasizes hands-on learning through Python notebooks, enabling users to experiment with abstract mathematical notions and visualize linear transformations, making it an invaluable aid for data science skill development.

Criov is an AI-powered quiz generator designed to simplify the creation of custom quizzes for various needs, particularly for HR teams and training. Users can quickly generate multiple-choice, true/false, fill-in-the-blanks, and short answer questions in minutes. The platform offers a drag-and-drop interface for easy quiz construction and allows for setting correct answers and scores. Advanced features include tracking and analyzing user performance, monitoring quiz pass rates, and viewing grade distributions. Criov also provides anti-cheat systems, question and answer randomization, time limits, and the ability to customize quiz appearances with branding and logos. Quizzes can be shared via public or private links with password protection.

Y2Doc is an AI-powered tool designed to convert YouTube video content into various structured document formats. Users can paste a YouTube link to instantly generate summaries, quizzes, and detailed notes, making it ideal for educational purposes or content analysis. The platform is powered by multimodal AI, ensuring secure, fast, and accurate conversions. Y2Doc also partners with FindTube.ai, allowing users to search across over 85 million educational videos curated by AI difficulty levels, providing a comprehensive solution for video-to-document transformation.

Alevels.ai is an AI-powered platform designed to assist A-Level students in their revision and exam preparation. It offers a comprehensive suite of curriculum-specific resources, ensuring that students have access to relevant materials tailored to their studies. A key feature is its AI tutor, which can mark student answers, provide immediate feedback, and guide them through challenging topics. This personalized support aims to help students understand complex concepts, improve their problem-solving skills, and ultimately boost their grades. The platform consolidates all necessary study materials in one place, streamlining the revision process for A-Level students.

The AI4Good Lab is an intensive 7-week summer program designed to introduce machine learning to women and gender-diverse individuals with some programming background. The program is split into a 4-week ML Bootcamp covering introductory machine learning and AI concepts, followed by 3 weeks of team projects where trainees develop AI/ML prototypes for social good issues. Hosted by Mila and supported by national AI institutes, the program emphasizes mentorship, professional networking, and a tuition-free model with stipends to ensure accessibility. It aims to open doors for underrepresented genders in the AI industry by providing a comprehensive learning experience and connections to the AI community.

Text-speech.net provides a free online text-to-speech (TTS) converter that transforms written text into natural-sounding voices. The tool boasts high-quality audio clarity and offers options to choose voice gender and accent. It features a simple user interface with four main buttons: Play, Stop, Copy, and Clear, making it easy to operate for anyone. The conversion process is designed for high speed, often taking less than a second, and the tool is lightweight, ensuring quick results even with slower internet connections. No login or signup is required, and it is compatible with most web browsers, including Microsoft Edge for more voice options, and is fully mobile-responsive.

WordlyWit.com is an AI-powered crossword generator designed for teachers, trainers, and puzzle enthusiasts. It enables users to create custom crossword puzzles from any topic by simply entering a theme or subject. The AI then generates clues, answers, and arranges them into a professional grid. Users can solve puzzles online for free without an account, while creating puzzles requires a free account, offering daily AI generations and the ability to download and share creations. WordlyWit supports various download formats including PDF for printing, SVG for high-quality graphics, and HTML for web embedding, all including an answer key. It's particularly useful for educators to create vocabulary, history, or science review puzzles.

AI Film Festa is an AI video generation tool powered by Dokdo Video Generation. It enables users to create videos, though the specific features for video creation are not detailed. The tool is hosted on Hugging Face Spaces by ginigen. Currently, the application is paused, and users interested in using it are directed to the community tab to request its restart from the author(s). The meta description indicates that the app allows running custom code provided in an environment variable, suggesting a flexible or programmable approach to video generation, where users input code to execute and deliver results.

ValgrAI is a non-profit foundation based in Valencia, Spain, dedicated to advancing Artificial Intelligence through education, research, and collaboration. It offers a range of specialized courses and master's programs in AI, catering to both individuals and organizations. The foundation aims to meet the technological needs of the business sector, foster new AI talent, and provide specialized training to professionals. ValgrAI is supported by the Valencian government, companies, and five public universities, coordinating efforts to drive innovation and contribute to the region's productive model. They also engage in various research projects and offer custom training solutions.

GPTWorld is an educational environment created to help users understand and master prompting techniques for language models. It provides a unique grid-world interface where users can issue instructions to an AI, which then generates code to control a game. This interactive approach allows for practical experimentation and observation of how language models interpret and execute commands in a grounded, simulated environment. The tool is particularly useful for testing the capabilities and limitations of AI in following complex instructions, making it an excellent resource for researchers, educators, and anyone interested in the practical application of large language models.

Letrus is a pioneering educational technology program in Brazil that integrates artificial intelligence with pedagogical methods to significantly enhance reading and writing abilities for students in the final years of elementary school and throughout high school. The platform offers immediate feedback to students via AI, personalized learning paths based on data, and comprehensive assessment criteria aligned with textual genres and exam requirements like ENEM. For teachers, Letrus provides real-time performance data, engagement levels, and autonomy to complement AI-generated feedback, reducing correction time and allowing more focus on classroom instruction. School administrators benefit from performance reports, pedagogical support, and monitoring dashboards to track learning evolution across their networks. Recognized by UNESCO as a leading educational technology, Letrus has demonstrated proven efficacy, contributing to improved national exam rankings in states where it has been implemented.

The Gemma Cookbook is a comprehensive collection of guides and examples designed to help developers get started with and understand Google's Gemma family of open models. It covers a wide range of Gemma variants, including the core Gemma models for text generation, CodeGemma for coding tasks, FunctionGemma for function calling, MedGemma for medical text and image comprehension, and PaliGemma for vision language tasks. The cookbook also features models like ShieldGemma for safety evaluation and TxGemma for therapeutic development. While the repository is deprecated, it serves as a valuable resource for exploring the capabilities and applications of these generative AI models, built from the same research as Gemini.

The tensorflow_cookbook is a comprehensive GitHub repository that serves as a practical guide for implementing machine learning algorithms with TensorFlow. It accompanies the Tensorflow Machine Learning Cookbook by Nick McClure, offering code examples across a wide range of topics. Users can explore chapters dedicated to linear regression, support vector machines, nearest neighbor methods, neural networks, natural language processing, and convolutional neural networks. The repository details how to set up TensorFlow, work with tensors, variables, and operations, implement activation functions, and handle various data sources. It also covers advanced topics like computational graphs, loss functions, backpropagation, and taking TensorFlow models to production, making it an invaluable resource for both learning and applying TensorFlow in real-world scenarios.

torch-Video-Tutorials is a comprehensive collection of introductory video tutorials designed to guide users through the Torch ecosystem, a fast and flexible framework for Machine and Deep Learning. The resource aims to demystify the learning curve often associated with Torch by providing accessible video content. Each tutorial comes with accompanying slides, transcripts, and quizzes, which are available in the 'res' folder, along with notes on video creation. The tutorials cover fundamental concepts such as Lua and Torch's Tensor and image packages, delve into Artificial Neural Networks (feed-forward, backpropagation, and Torch's nn package), explore Convolutional Neural Networks (basics, internals, architectures, training, and loss functions), and introduce Recurrent Neural Networks (vectors, sequences, nngraph package, and training). Future content will include LSTM and training with the rnn package.

tiny-llm provides a comprehensive course for system engineers focused on learning LLM inference serving, specifically tailored for Apple Silicon. The curriculum guides users through building a tiny vLLM using MLX and Qwen, with a codebase primarily utilizing MLX array/matrix APIs. This approach allows participants to construct model serving infrastructure from scratch, gaining deep insights into optimizations. The course covers essential components like attention, RoPE, KV cache, and continuous batching, with a roadmap extending to advanced topics such as Paged Attention and Speculative Decoding. It's designed for those who want to understand the underlying techniques for efficiently serving large language models.

Porosheets is an AI-powered educational tool designed to significantly reduce lesson preparation time for teachers, parents, and students. It automates the creation of printable math, science, and ELA worksheets, rubrics, and lesson plans from a simple prompt. Users can specify topics, grade levels, and preferences, and the AI generates structured, ready-to-use content with mixed question types, real rubric criteria, and proper lesson timing. The platform includes answer keys, PDF export, and inline editing capabilities. Porosheets aims to free up educators to focus more on teaching by handling the repetitive tasks of resource creation, supporting multiple languages like French and Arabic.

EasyClass is an all-in-one AI platform specifically designed for K-12 teachers, offering over 60 AI tools to significantly reduce time spent on planning, grading, and communication. Educators can generate lesson plans, worksheets, rubrics, quizzes, exit tickets, and even parent newsletters in seconds. The platform includes specialized tools for AI grading, allowing teachers to provide rubric-aligned feedback on written student work quickly. EasyClass is built with student data privacy in mind, meeting FERPA and COPPA compliance standards, and is designed to be user-friendly for teachers without requiring technical or AI prompting skills. It offers a generous free plan with unlimited uses across its extensive toolset, with a Pro plan available for advanced features like AI grading and a comprehensive lesson planner with 18 formats.