Research & Education

GNNs-for-NLP is a comprehensive resource offering code examples and tutorial materials for applying Graph Neural Networks (GNNs) to Natural Language Processing (NLP) tasks. Originating from presentations at EMNLP 2019 and CODS-COMAD 2020, this GitHub repository provides practical implementations using PyTorch 1.x and TensorFlow 1.x, compatible with Python 3.x. It features simplified GCN model implementations, extensions for relation extraction and word embeddings, and additional resources like theoretical write-ups and recent GNN papers. This tool is ideal for researchers and students looking to understand and implement graph-based deep learning methods in NLP.

langchain4j-aideepin (AIDEEPIN) is an AI-based productivity tool designed to enhance efficiency for enterprises and teams. It offers a comprehensive suite of features including multi-session chat with various roles, AI-powered image generation (text-to-image, image editing, image-to-image), and robust knowledge base capabilities utilizing large language models (RAG), vector search, and graph search. The tool also integrates AI workflows, a MCP service marketplace, and advanced ASR (Automatic Speech Recognition) and TTS (Text-to-Speech) functionalities with customizable voice options. Users can benefit from long-term memory features and flexible input/output formats, including text-to-text, text-to-speech, speech-to-text, and speech-to-speech. It supports various model platforms like Lingji, OpenAI, Silicon Base Flow, Ollama, DeepSeek, and Qianfan, making it a versatile solution for diverse AI-driven tasks.

machine-learning-deep-learning-notes provides a comprehensive learning path and knowledge summary for machine learning and deep learning, designed for modern AI development. It advocates a "practice first, then theory" approach, encouraging users to build projects and then delve into underlying principles as needed. The resource covers core concepts in mathematics, Python libraries like NumPy and Pandas, and practical applications of machine learning algorithms. It also delves into deep learning frameworks such as PyTorch and TensorFlow, with a strong focus on large language models (LLMs), multimodal AI, and AI agents. The guide includes structured learning paths for beginners and advanced users, emphasizing rapid skill acquisition and practical project building.

LLMBook-zh.github.io is an open-source project providing a comprehensive Chinese textbook titled "大语言模型" (Large Language Models). Authored by Zhao Xin, Li Junyi, Zhou Kun, Tang Tianyi, and Wen Jirong, this book aims to popularize and disseminate the latest advancements in large model technology. It offers a systematic framework and roadmap for LLM technologies, making it ideal for beginners with a background in deep learning. The project includes PDF courseware, code snippets on GitHub, and related teaching videos on Bilibili, serving as a valuable resource for both academic study and practical application. The content covers essential topics such as pre-training, fine-tuning, alignment, and prompt engineering, drawing from the authors' extensive research and practical experience in developing large models.

LLMs_interview_notes is an open-source repository designed to help algorithm engineers prepare for interviews related to Large Language Models (LLMs). The resource compiles learning notes and materials based on personal interview experiences, covering a wide array of LLM topics. It includes detailed sections on LLM fundamentals, advanced attention mechanisms, transformer operations, loss functions, similarity functions, generative LLMs, fine-tuning strategies, LangChain, and Retrieval-Augmented Generation (RAG). This comprehensive collection aims to provide a structured approach to understanding and answering common interview questions in the rapidly evolving field of LLMs.

llm-cookbook is an open-source project offering a comprehensive, developer-focused introduction to Large Language Models (LLMs). It translates, reproduces, and optimizes content from Andrew Ng's LLM course series, making it highly accessible for Chinese developers. The curriculum spans essential topics from Prompt Engineering to RAG development and model fine-tuning, guiding learners through practical applications. It includes both foundational 'required' courses for core skills and 'elective' courses for specialized areas like Gradio for AI application building, evaluating generative AI, and advanced RAG techniques. The project also provides translated code examples, online reading materials, and PDF downloads, with a focus on adapting content for the Chinese linguistic context.

Crane is an AI-powered Chrome extension designed to function as a personal knowledge base. It automatically tracks what you read across various sources like websites, articles, and documents, then generates a daily newsletter summarizing the key information from the previous day. This feature helps users improve knowledge retention, stay updated on industry news, and efficiently organize their personal knowledge for future reference. Crane uses AI to extract crucial information and create concise summaries, making it an effective tool for anyone looking to manage and synthesize their daily reading.

MLTO: Machine Learning Toronto is a vibrant community dedicated to AI and machine learning enthusiasts within the Greater Toronto Area. It serves as a central hub for professionals, researchers, and individuals passionate about artificial intelligence to connect, share knowledge, and stay updated on the latest advancements. The community regularly hosts events, fostering an environment for networking and collaborative learning. MLTO is committed to building a strong local ecosystem for machine learning, supported by its members and sponsors, and provides guidelines and a code of conduct to ensure a positive and inclusive experience for all participants.

Prompt-tutorial is a GitHub-based open-source resource dedicated to teaching prompt engineering for large language models (LLMs). It offers a structured series of lessons covering fundamental principles, advanced strategies, and common limitations in prompt creation. The tutorial emphasizes clear and explicit instructions, structured output requirements, and iterative prompt optimization. It includes practical examples for tasks like text summarization, inference, language translation, and content generation, making it suitable for individuals looking to enhance their skills in interacting with LLMs without requiring a technical background.

TautMore is an EdTech platform designed for K-12 schools, providing a comprehensive, one-stop solution for educational needs. The platform leverages advanced technologies such as Artificial Intelligence (AI), Machine Learning (ML), and Virtual Reality (VR) to create highly personalized learning experiences for students. Beyond technology, TautMore integrates principles of learner psychology to optimize educational outcomes. It combines essential school management functionalities, including a Learning Management System (LMS), Enterprise Resource Planning (ERP), and supply chain management services, into a single platform. Additionally, TautMore extends its offerings to include live classes and various extracurricular activities, aiming to provide a holistic educational environment.

tensorflow-nlp-tutorial is an open-source Deep Learning NLP repository built on TensorFlow 2.0+. It offers a comprehensive collection of tutorials covering various aspects of Natural Language Processing, from fundamental text preprocessing techniques to advanced models like Topic Models, BERT, GPT, and Large Language Models (LLMs). The repository details downstream tasks for these modern models, providing practical examples for students and developers. Each tutorial file includes a Colab link, enabling users to practice directly in a browser without needing a local Python installation. The content is based on an extensive 1,200-page e-Book, ensuring a strong theoretical foundation alongside practical application. Updates include recent additions for RAG, LLM, and VLM fine-tuning.

PyTorch-Tutorial-2nd is a comprehensive, open-source tutorial designed for individuals ranging from beginners to experienced deep learning engineers. It systematically covers PyTorch fundamentals, including environment setup, data handling, model building, optimization, and visualization. The tutorial delves into practical applications across computer vision (image classification, segmentation, object detection, GANs, Diffusion models), natural language processing (RNN, LSTM, Transformer, BERT, GPT models for text classification, machine translation), and large language models (Qwen, ChatGLM, Baichuan, Yi, GPT Academic). Furthermore, it provides in-depth guidance on industrial deployment, covering ONNX and TensorRT principles, model quantization (PTQ, QAT), and acceleration techniques, enabling users to master PyTorch for real-world project implementation.

SuperCLUE is a comprehensive benchmark designed for evaluating Chinese large language models (LLMs). It assesses LLMs across four primary capability quadrants: language understanding and generation, professional skills and knowledge, Agent intelligence, and safety, further breaking these down into 12 foundational abilities. The platform provides detailed rankings and reports, including a SuperCLUE total leaderboard, open multi-turn question leaderboard, and objective question leaderboard. It also features specific evaluations for AI Agent capabilities, focusing on tool use and task planning, which are critical for developing advanced AI assistants. SuperCLUE aims to provide a robust framework for researchers and developers to compare and improve Chinese LLMs.

system_prompts_leaks is a comprehensive, regularly updated GitHub repository that compiles extracted system prompts, system messages, and developer instructions from a wide array of popular AI chatbots and coding assistants. This includes models such as ChatGPT (GPT-5.4, GPT-5.3, Codex), Claude (Opus 4.6, Sonnet 4.6, Claude Code), Gemini (3.1 Pro, 3 Flash, CLI), Grok (4.2, 4), and Perplexity. The repository serves as a valuable resource for understanding how these advanced AI systems are instructed and behave, offering insights into their underlying configurations and personas. It is an open-source project, welcoming contributions from the community to expand its collection of prompts and models.

Tutorial, developed by InternLM, is an open-source learning platform designed for developers to master large language models (LLMs) and vision-language models (VLMs). It offers a structured curriculum through 'camps' with challenges, documentation, and video tutorials covering foundational topics like Linux, Python, and Git, as well as advanced concepts such as prompt engineering, RAG implementation, model fine-tuning with XTuner, and deployment with LMDeploy. The platform also includes practical applications like building intelligent agents with Lagent and multi-modal model deployment. Participants can earn computational resources and certificates upon completing advanced challenges, fostering a community-driven learning environment.

Bayuegua - Innovation Brain is a global patent search and analysis platform designed to provide comprehensive intellectual property services. It offers a one-stop solution for global patent search and analysis across 178 countries and regions. Key features include patent search, global patent retrieval, patent navigation, patent analysis and evaluation, and patent transaction services. The platform also provides free intellectual property analysis and evaluation consulting from experienced advisors and access to extensive patent search databases. It supports various search options like simple, advanced, semantic, image, instruction, and batch searches, utilizing AI assistants and knowledge graphs to enhance the process.

Prompt-Engineering-Guide-zh-CN is an open-source, continuously updated guide to prompt engineering, specifically tailored for Chinese speakers. It serves as a comprehensive resource for understanding and optimizing prompts for large language models (LLMs). The guide covers various aspects of prompt engineering, including introductory concepts, basic and advanced prompting techniques, applications, and specific guidance for ChatGPT. It also compiles relevant papers, lectures, notebooks, and tools, making it an invaluable resource for researchers and developers looking to enhance their understanding and application of LLMs.

Spangli is an AI-powered Spanish learning platform designed to help users master the language through convenient and interactive methods. It delivers daily lessons directly via Telegram, making learning accessible in your pocket. Beyond structured lessons, Spangli offers interactive chat practice, allowing users to apply their knowledge and improve conversational skills in real-time. The platform also includes a suite of free Spanish learning tools such as a verb conjugator, a Ser vs Estar guide, an idioms translator, and a false cognates detector, catering to various aspects of language acquisition. Spangli aims to provide an effortless path to Spanish fluency for learners of all levels.

Voicefy is a text-to-speech platform that leverages neural voices to convert text into convincing human-like speech, primarily in Portuguese. It supports a wide range of applications, from producing audiobooks and podcasts without the need for recording studios to dubbing videos in 40 languages. The tool is also highly effective for e-learning, enabling automatic narration of courses, and for developing natural-sounding virtual assistants with low latency. Voicefy offers a free tier and boasts over 120 neural voices, making it a versatile solution for content creators, businesses, and developers seeking high-quality, automated voice narration.

WriteGPT is an open-source AI framework developed by Turing's Cat, primarily focused on generating argumentative essays. Built upon the GPT-2 model, it leverages advanced OCR and NLP techniques to produce human-like text. The tool is specifically finetuned for high school essays, particularly argumentative styles, and can generate articles that often meet passing grades. It integrates various modules including EAST for text detection, CRNN for text recognition, BERT for text summarization, and GPT-2 for text generation. WriteGPT is intended for academic exchange and popular science, offering features like end-to-end generation from exam paper recognition to answer sheet output, and an online text generation demo via Colab. While it aims for human-like output, the developers note that not all generated essays are perfect, and some may only barely pass or even fail.

SuperPrompt is an open-source project designed to engineer prompts that enhance understanding of AI agents, particularly large language models like Claude. It utilizes a unique approach involving 'holographic metadata' and XML tags to guide the LLM's thought process. The tool aims to encourage models to 'think outside the box' and explore areas usually left untouched, often leading to novel ideas, though sometimes resulting in hallucinations. SuperPrompt is not intended to create conscious AI but rather to force deeper cognitive engagement from the model. It adapts its meta-prompt based on the user's request, allowing for dynamic and context-aware prompt generation, making it a valuable resource for AI research and development.

Summarize YouTube Videos is a Chrome extension designed to provide quick and efficient summaries of YouTube videos using AI. This tool allows users to grasp the main points of any video without needing to watch it in its entirety, making it ideal for busy individuals, students, and researchers. It helps skip unnecessary content, save valuable time, and quickly identify the most important highlights. The extension is easy to use: simply install it, navigate to a YouTube video, and click the extension icon to generate a concise summary. This AI-powered solution analyzes video content to pinpoint key information, offering a streamlined way to consume video content.

Foundations-of-LLMs is an open-source book designed for readers interested in large language models, providing a systematic explanation of foundational knowledge and cutting-edge techniques. The author team is committed to monthly updates, incorporating suggestions from the open-source community and experts, aiming to create an easy-to-read, rigorous, and in-depth LLM textbook. Each chapter is accompanied by a relevant Paper List to track the latest advancements. The first edition covers traditional language models, LLM architecture evolution, prompt engineering, parameter-efficient fine-tuning, model editing, and retrieval-augmented generation. The book uses animal-themed examples to illustrate specific technologies, making complex concepts more accessible.

Andi is an innovative AI search engine designed for the next generation, moving beyond traditional link-based results to deliver direct answers. It leverages generative AI and large language models, combined with live data, to provide contextually rich and factual responses. The platform boasts an impressive 87% accuracy rate, outperforming established search engines like Google, as well as AI models like ChatGPT and Perplexity. Andi prioritizes user privacy by offering a free, private, and ad-free search experience, ensuring that searches are not tracked and cookies are not used. This focus on accuracy, privacy, and a conversational interface makes Andi a compelling alternative for users seeking a more intelligent and secure way to find information.