Research & Education

Socrates is an advanced AI tool designed for comprehensive document analysis, enabling users to unlock complete and accurate answers from PDFs, DOCXs, EPUBs, and text files. Its standout "Deep Dive" feature intelligently breaks down lengthy documents, creating multiple search indexes for thorough analysis. Users can also build custom AI workflows with "Flow AI" and compare multiple documents using "Table AI." A key differentiator is its support for local LLMs, allowing for document analysis without sending data to the cloud, which is ideal for users prioritizing data privacy and security. Socrates also offers the ability to ask questions across multiple documents, search specific pages, and save frequently used prompts, making it a versatile solution for researchers and professionals.

DataDepot is an AI-powered research platform designed to streamline the research process and personalize access to insights for every decision. It allows users to discover a variety of research assets from leading providers, all in one centralized location, helping to eliminate information overload and uncover valuable insights. The platform features a trusted marketplace where users can explore providers offering diverse content types. Dynamic displays allow for tailoring the view to show essential research, further streamlining workflows. DataDepot leverages AI to uncover vital insights from research, enhancing decision-making with ease and precision. It also offers providers the opportunity to join, connect with a global audience, and empower others with their insights, with no upfront cost or listing fees.

Claude Scholar is an AI companion designed to help students succeed academically by offering customized support throughout their learning process. This Chrome extension assists with research, writing, and exam preparation. Leveraging advanced AI capabilities, it helps generate ideas for essays and research papers, analyzes requirements, suggests relevant topics, outlines, and source materials. Additionally, Claude Scholar provides valuable feedback on writing, identifying grammar mistakes and strengthening arguments, making it an essential tool for academic success.

Algorithm Audit is a European knowledge platform dedicated to fostering responsible AI through public knowledge building. It brings together data scientists, lawyers, and ethicists to address value-based questions in AI, bridging the gap between policy initiatives, academic insights, and real-world case experiences. The platform provides open-source tools for validating algorithmic systems, offers independent validation and advice, and translates knowledge into action. Key offerings include sociotechnical evaluation of generative AI, AI Act implementation support, bias analysis, non-discrimination assessments, and auditing for legal compliance. They also provide an open-source AI and Algorithms Qualification Toolkit (AI AQT) to help organizations identify and categorize AI systems based on risk.

awesome-persian-nlp-ir is a comprehensive, curated list dedicated to Persian Natural Language Processing (NLP) and Information Retrieval (IR) tools and resources. This GitHub repository serves as a central hub for researchers, developers, and enthusiasts interested in the field, segmenting its content into five main categories: Tools, Datasets, Models, Repositories, and Papers and Books. It aims to consolidate various research efforts and practical applications related to Persian NLP, making it easier for users to discover and utilize relevant resources. The repository encourages community contributions to ensure its continued growth and relevance, providing guidelines for new submissions.

awesome-quantum-machine-learning is a comprehensive, curated list designed to provide a deep dive into the world of quantum machine learning. It covers fundamental concepts such as quantum mechanics and quantum computing, alongside advanced topics like quantum algorithms, quantum neural networks, and quantum statistical data analysis. The resource includes detailed descriptions of various quantum machine learning algorithms, study materials, and a collection of relevant libraries and software. It also features sections on quantum programming languages, tools, and hot topics in the field, making it an invaluable resource for anyone looking to explore or advance their knowledge in quantum machine learning, from basic principles to cutting-edge research.

Awesome-Efficient-LLM is a comprehensive, curated list of resources focused on efficient large language models (LLMs). This open-source project provides researchers and engineers with a centralized hub for papers and projects related to optimizing LLMs. The list is organized into various sub-areas, including Network Pruning / Sparsity, Knowledge Distillation, Quantization, Inference Acceleration, Efficient MOE, Efficient Architecture of LLM, KV Cache Compression, Text Compression, Low-Rank Decomposition, Hardware / System / Serving, Efficient Fine-tuning, Efficient Training, Survey or Benchmark, and Reasoning Model. Users can easily navigate through these categories to find relevant papers, with recent additions highlighted on the main page. The project also encourages community contributions, allowing users to submit new papers or update existing details via pull requests or email, ensuring the list remains current and comprehensive.

LongBench is an open-source evaluation tool designed to rigorously assess the capabilities of Large Language Models (LLMs) in processing and reasoning over extensive contexts. LongBench v2, the latest iteration, features context lengths ranging from 8k to 2M words, presenting a significant challenge even for human experts. It covers six major task categories including single-document QA, multi-document QA, long in-context learning, long-dialogue history understanding, code repo understanding, and long structured data understanding. The benchmark consists of 503 challenging multiple-choice questions, ensuring reliable evaluation. Data is collected from nearly 100 highly educated individuals, undergoing both automated and manual review to maintain high quality and difficulty. LongBench aims to provide a reliable standard for developing future superhuman long-context AI systems.

LLM-scientific-feedback is an open-source project that leverages large language models, specifically GPT-4, to provide comprehensive feedback on research papers. The tool offers an automated pipeline to analyze full PDF documents of scientific papers and generate comments. Empirical analysis has shown that the overlap between GPT-4's feedback and human peer reviewer feedback is comparable to the overlap between two human reviewers. It is particularly beneficial for researchers, especially those who are junior or in under-resourced settings, to receive timely feedback. While it excels in certain areas like suggesting additional experiments, it also has limitations, such as struggling with in-depth critique of method design. The project includes Python source code and instructions for setting up PDF parsing and LLM feedback servers.

awesome-2vec is a comprehensive, curated list of 2vec-type embedding models, hosted as an open-source project on GitHub. This repository serves as a central hub for researchers and developers to discover and explore a wide array of embedding models, including popular ones like word2vec, doc2vec, and node2vec, as well as more specialized models such as tweet2vec, image2vec, and mol2vec. Each entry typically includes links to the original research paper and available code implementations in languages like Python, Java, and C++. It's an invaluable resource for anyone working with embeddings in natural language processing, graph analysis, and other machine learning domains, facilitating the discovery of relevant models and their implementations.

awesome-adversarial-machine-learning is a curated list of resources focused on adversarial machine learning, hosted on GitHub. It serves as a valuable starting point for individuals interested in this specialized area of AI. The repository organizes information into categories such as blogs, academic papers, and talks, covering topics like general adversarial examples, attacks on image classification, reinforcement learning, and speech recognition, as well as defense mechanisms. While the maintainer notes that the list is no longer updated with the latest papers, it remains a strong reference for foundational knowledge in adversarial machine learning. This open-source project is ideal for researchers and students looking to explore the field.

awesome-llm-books offers a meticulously curated list of books specifically focused on Large Language Models (LLMs), designed for engineers and developers. The list is compiled through a rigorous process including reviewing blurbs, tables of contents, star ratings, and social media discussions to ensure relevance and quality. Each book entry provides details such as authors, publisher, publication year, and star ratings from Amazon and Goodreads, along with direct links to purchase or learn more. This resource aims to simplify the discovery of high-quality educational materials for those looking to deepen their understanding and practical skills in LLM development.

Awesome-LLM-KG is a comprehensive collection of academic papers and resources dedicated to the integration of Large Language Models (LLMs) and Knowledge Graphs (KGs). This repository aims to provide researchers and practitioners with a clear roadmap and understanding of how to leverage the strengths of both LLMs, known for their generalizability, and KGs, valued for their structured factual knowledge. It categorizes research into three main frameworks: KG-enhanced LLMs, LLM-augmented KGs, and Synergized LLMs + KGs, detailing involved techniques and applications. The project is actively updated with new research, including recent papers accepted at major conferences like ICML, NeurIPS, and ACL, making it a valuable resource for staying current in the field.

Awesome-LLMs-for-Video-Understanding is a comprehensive, open-source GitHub repository dedicated to the rapidly evolving field of video understanding using Large Language Models (Vid-LLMs). It serves as a vital resource for researchers, academics, and engineers by curating the latest papers, associated code, and relevant datasets. The repository features a detailed survey on Vid-LLMs, covering various techniques, training strategies, tasks, datasets, benchmarks, and evaluation methods. It also introduces novel taxonomies for Vid-LLMs based on video representation and LLM functionality, making it easier to navigate the complex landscape of this domain. Regular updates ensure the content remains current, including new models, benchmarks, and redesigned figures and tables for clarity.

awesome-ml-courses offers a comprehensive, curated list of free machine learning and artificial intelligence courses, all featuring high-quality video lectures from renowned AI researchers and educators. This resource goes beyond just videos, linking to course websites that provide detailed lecture notes, supplementary readings, and practical assignments. It caters to both beginners, with introductory lectures requiring some knowledge of linear algebra, calculus, and probability, and advanced learners, offering courses that delve into specialized topics like deep unsupervised learning, graph neural networks, and advanced reinforcement learning. The platform serves as an excellent starting point for anyone looking to deepen their understanding of AI and ML concepts.

Basic-Mathematics-for-Machine-Learning is an open-source GitHub repository designed to help individuals overcome the mathematical challenges associated with Machine Learning, Deep Learning, and other AI fields. The repository provides foundational knowledge in key mathematical areas such as Algebra, Calculus, Statistics, and Probability. It includes practical code examples, primarily in Python notebooks, demonstrating the application of these concepts using essential libraries like NumPy, Pandas, and Matplotlib. The resource emphasizes the importance of mathematics for selecting algorithms, choosing parameter settings, understanding bias-variance tradeoffs, and estimating confidence intervals. It covers topics like Linear Algebra, Probability Theory, Statistics, Multivariate Calculus, and Algorithms, making it a comprehensive guide for those looking to strengthen their mathematical background for AI.

MiniGPT-4 is an open-source initiative dedicated to advancing vision-language understanding by integrating advanced large language models. The project offers open-sourced code for both MiniGPT-4 and its successor, MiniGPT-v2, enabling researchers and developers to explore and build upon state-of-the-art vision-language capabilities. It functions as a unified interface, facilitating multi-task learning across various vision and language domains. The project provides detailed instructions for installation, preparation of pretrained LLM weights (including Llama2 Chat and Vicuna), and model checkpoints. Users can launch local demos for both MiniGPT-v2 and MiniGPT-4, with options to optimize GPU memory usage. Training and finetuning details are also provided, making it a comprehensive resource for those working with vision-language models.

Melting Pot is an open-source suite of test scenarios specifically designed for multi-agent reinforcement learning (MARL). Developed by Google DeepMind, it offers researchers a robust platform to train and evaluate AI agents in complex social situations. The tool includes over 50 multi-agent games (substrates) and more than 256 unique test scenarios, allowing for the assessment of generalization to novel social interactions like cooperation, competition, and trust. It is built on DeepMind Lab2D and provides tools for interactive play, evaluation of trained models, and example training scripts using frameworks like RLlib. Melting Pot aims to become a standard benchmark for MARL research, with ongoing development to expand its coverage of social interactions and generalization scenarios.

Mallet is an open-source, Java-based package designed for statistical natural language processing and machine learning applications to text. It provides sophisticated tools for document classification, including efficient text-to-feature conversion, various algorithms like Naïve Bayes and Maximum Entropy, and performance evaluation metrics. Beyond classification, Mallet supports sequence tagging for tasks such as named-entity extraction using algorithms like Hidden Markov Models and Conditional Random Fields. Its topic modeling toolkit offers efficient, sampling-based implementations of Latent Dirichlet Allocation and Hierarchical LDA. The package also includes routines for transforming text documents into numerical representations through a flexible system of "pipes" for tokenizing, stopword removal, and count vector conversion. Mallet is ideal for researchers and practitioners working with large text datasets.

DGL-LifeSci is an open-source Python package built on DGL (Deep Graph Library) specifically designed for deep learning applications in life sciences using graph neural networks. It provides a comprehensive suite of tools for researchers and developers, including methods for constructing and featurizing molecular graphs and biological networks, evaluating models, and offering various model architectures. The package also includes training scripts and pre-trained models to accelerate research and development. DGL-LifeSci supports applications such as molecular property prediction and reaction prediction, making it a valuable resource for advancing drug discovery and bioinformatics.

DIG (Dive into Graphs) is a comprehensive open-source library designed for graph deep learning research. Unlike basic graph deep learning libraries, DIG offers a unified testbed for advanced, research-oriented tasks such as graph generation, self-supervised learning on graphs, explainability of Graph Neural Networks, deep learning on 3D graphs, and graph out-of-distribution. It provides unified implementations of data interfaces, common algorithms, and evaluation metrics, allowing researchers to easily implement their own methods and compare them against baseline methods using common datasets and metrics without extensive effort. The library supports various research directions including Graph Augmentation and Fair Graph Learning, and is built on PyTorch Geometric (PyG).

DeepLearningVideoGames is a project focused on applying deep Q-networks to develop AI agents capable of learning optimal control patterns from visual input in video games. Utilizing reinforcement learning, specifically Q-learning with convolutional neural networks, the system processes raw pixel values from game screens to approximate future expected rewards for actions. The project successfully trained an AI to achieve better than human performance in Pong and is actively working on Tetris. It highlights the potential of deep learning for generalizable high-level control schemes in gaming, demonstrating how AI can learn complex strategies without explicit knowledge of game rules.

deep_learning_curriculum offers an advanced, open-source curriculum designed for individuals seeking to understand the latest developments in deep learning, with a particular emphasis on large language model alignment. It is hosted on GitHub and is intended for those with a strong quantitative background who are already familiar with the fundamentals of deep learning. The curriculum is structured into nine chapters covering topics like Transformers, Scaling Laws, Optimization, Reinforcement Learning, and Alignment. Each chapter includes recommended reading, optional reading, and suggested exercises to facilitate hands-on learning. While challenging, it provides a comprehensive pathway for self-study or mentored learning in this rapidly evolving field.

ChatGPT Continuer is a Chrome extension designed to improve the user experience with ChatGPT by automating the "Continue Generating" button. When ChatGPT's responses stop mid-sentence, this tool automatically clicks the button, allowing the conversation to flow seamlessly without requiring manual intervention. This eliminates the frustration of interrupted responses and ensures a more enjoyable and efficient interaction with the AI. It's particularly useful for users who engage in long conversations or generate extensive content, as it prevents the need to constantly monitor and click to continue the output. The developer has stated that it does not collect or use user data, prioritizing privacy.