Research & Education

Learn_Computer_Vision offers a comprehensive, open-source curriculum designed to teach computer vision, based on a YouTube series by Siraj Raval. The program is structured over eight weeks, with daily study recommendations, and covers topics from low-level image processing to modern deep learning techniques like GANs. Each week includes video lectures, reading assignments, and practical projects using tools like Python, OpenCV, and TensorFlow. The curriculum aims to equip learners with the skills necessary to pursue careers in computer vision, whether through startups, consulting, or full-time employment. Prerequisites include basic Python, Calculus, and Linear Algebra.

Packback is an Instructional AI platform designed to enhance student engagement, strengthen writing skills, and improve retention in both higher education and K-12 settings. It offers three core products: Packback Discussions for inquiry-based student discussions with AI coaching, Packback Writing for real-time, formative writing feedback and AI-assisted evaluation, and Originality for proactive plagiarism prevention that empowers students to revise before submission. The platform aims to reduce faculty workload by handling routine feedback, allowing instructors to focus on mentorship. Packback's proprietary Instructional AI engine, built on pedagogical principles, provides actionable feedback without generating content for students, ensuring academic integrity and responsible AI use.

Pangea is a fully open multilingual multimodal LLM developed by NeuLab at LTI/CMU, supporting 39 languages. It is designed for research and development in multilingual AI, offering a simple interface for text translation. Users can input text, select source and target languages, and receive a translated version. The tool is available as a Hugging Face Space, making it accessible for experimentation and integration into various projects. Its open-source nature under the Apache 2.0 license encourages diverse language applications and collaborative development within the AI community.

MODULABS is a comprehensive platform dedicated to AI and SW education, offering a variety of programs designed for practical, real-world application. The platform provides bootcamps like AI Engineer and AI Researcher courses, national support education, and tailored corporate training solutions. MODULABS emphasizes community-driven learning, fostering research communities and offering resources like 'LAB' for open research and 'MODUMOIM' for collaborative growth. It also features online courses, free seminars, and a blog with the latest AI content, making it a versatile hub for individuals and organizations looking to advance their AI and software skills.

ml-glossary is an open-source, community-maintained machine learning glossary designed to provide clear and accessible explanations of ML terms and concepts. It aims to present content in the most accessible way possible, with a heavy emphasis on visuals, interactive diagrams, code snippets (Python/Numpy), and equations formatted with Latex. The project encourages contributions from the community, allowing users to submit pull requests or raise issues to correct errors or add new content. It also provides a style guide for contributions, ensuring consistency and quality across entries. The glossary is a valuable resource for anyone looking to understand or contribute to machine learning knowledge.

ML_for_Hackers is a GitHub repository that hosts all the code examples accompanying the book "Machine Learning for Hackers" (2012). This resource is designed for individuals looking to gain practical experience with machine learning algorithms. The repository includes code for various topics such as Introduction, Exploration, Classification, Ranking, Regression, Regularization, Optimization, PCA, MDS, Recommendations, SNA, and Model Comparison. Users can get started by installing necessary R libraries, including RCurl and XML, using the provided `package_installer.R` script. While the code may have minor modifications since publication, it remains a valuable tool for learning and applying machine learning techniques.

mlbook is a free online book titled "Machine Learning from Scratch" available as a GitHub repository. This resource offers a comprehensive guide to understanding machine learning concepts and algorithms, making it accessible for self-study. The repository includes the full book content, a PDF version, and encourages community contributions through pull requests to the gh-pages branch. It's an excellent resource for individuals looking to delve into machine learning fundamentals, providing both theoretical knowledge and practical insights through its open-source nature and Jupyter Notebook content.

Machine-learning-open-source is a GitHub repository that provides a monthly curated list of the top 10 open-source machine learning projects. Mybridge AI, which ranks articles by shares, minutes read, and its own machine learning algorithm, selects these projects. Each month, 100 to 300 new or major release open-source projects in Machine Learning are compared, with only the 10 finest being picked. Users can subscribe to email notifications for new releases by starring or watching the repository. The project also publishes similar monthly lists for other categories like JavaScript, Python, and Web Development, alongside annual compilations of amazing open-source projects.

Machine-learning-specialization-andrew-ng is a comprehensive repository offering notes and practical implementations of machine learning algorithms, directly aligned with Andrew Ng's renowned machine learning specialization. This resource is structured around three core courses: Supervised Machine Learning (Regression and Classification), Advanced Learning Algorithms, and Unsupervised Learning, Recommenders, and Reinforcement Learning. It includes programming assignments completed using Jupyter Notebooks and Python, with clearly marked code sections for easy modification. The repository also provides detailed notes, high-level overviews, practical tips, and mathematical concept walkthroughs, making it an invaluable study aid for anyone delving into machine learning.

Machine-learning-visualized is an open-source project offering a Jupyter Book filled with Jupyter Notebooks. These notebooks meticulously implement and mathematically derive various machine learning algorithms from first principles, making complex concepts accessible. A key feature includes Interactive Notebooks built with Marimo, allowing users to dynamically observe how weight adjustments impact loss functions. Each notebook's output visualizes the machine learning algorithm's training phase, demonstrating its convergence to optimal weights. The project is structured such that this repository configures and builds the Jupyter Book, while individual machine learning algorithms reside in separate GitHub repositories, which are downloaded via a provided script.

This open-source curriculum, `mcp-for-beginners`, introduces the core concepts of Model Context Protocol (MCP) using practical, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust, and Python. Designed for developers, it focuses on building modular, scalable, and secure AI workflows from session setup to service orchestration. The curriculum includes hands-on labs, clear explanations, and guidance on integrating AI models with various tools and services. It covers essential background concepts like protocols and client-server relationships, security best practices, and deployment strategies, aiming to empower developers to build their own MCP servers and integrate them with popular AI platforms.

MachineLearningNote is an open-source GitHub repository dedicated to providing comprehensive notes and practical code examples for various machine learning algorithms. Primarily utilizing the Sklearn library in Python, this resource covers a wide array of topics including Logistic Regression, Decision Trees, K-Nearest Neighbors, Naive Bayes, K-Means & DBSCAN, Ensemble Learning, One-Class SVM, PCA, LDA, EM (GMM), SVM, XGBoost, Isolation Forest, Random Forest, LOF, and SVD. Each algorithm is accompanied by detailed explanations and code implementations, often linking to external blog posts for deeper understanding. It serves as an excellent reference for students and practitioners looking to enhance their knowledge and practical skills in machine learning with Python and Sklearn.

MathsDL-spring18 is an open-source repository offering comprehensive materials for the 'Mathematics of Deep Learning' topics course, taught at NYU in Spring 2018. It provides detailed logistics, instructor information, and a full syllabus covering geometric aspects of deep learning, optimization, and generalization. The repository includes lecture slides, references, and outlines for parallel curricula focusing on topics like Dynamic Programming, Policy Learning, and Monte-Carlo Tree Search, with specific readings and questions for each session. This resource is invaluable for students and researchers interested in the theoretical and mathematical foundations of deep learning, offering a structured approach to complex concepts and open problems in the field.

matrixcalc is an open-source GitHub repository hosting the materials for the MIT IAP short course, "Matrix Calculus for Machine Learning and Beyond." Taught by Professors Alan Edelman and Steven G. Johnson, this resource extends traditional calculus to matrix functions and arbitrary vector spaces, crucial for modern applications like machine learning and large-scale optimization. It covers topics such as derivatives as linear operators, multidimensional chain rules, automatic differentiation, and adjoint methods. The course emphasizes matrices as holistic objects and includes practical aspects like numerical computations using the Julia language, making it a valuable resource for those looking to deepen their understanding of advanced calculus in a computational context.

MatterSim is a deep learning atomistic model developed by Microsoft, designed for simulating materials across a wide range of elements, temperatures, and pressures. It enables researchers and scientists to predict and analyze material behavior using advanced deep learning techniques. The tool offers two pre-trained models, MatterSim-v1.0.0-1M and MatterSim-v1.0.0-5M, based on the M3GNet architecture, with the larger version providing higher accuracy. Users can install MatterSim via PyPI or from source, and it supports finetuning on custom datasets. While primarily for bulk materials, it can be fine-tuned for specific applications like surfaces or interfaces.

3D2cut SA offers comprehensive digital vine pruning training solutions designed to improve vineyard health and productivity. Co-founded with Simonit & Sirch, the platform provides short video lessons and interactive exercises, including pruning cut simulations, to teach various pruning methods in multiple languages. It also features manager dashboards for tracking progress and an innovative AI/AR pruning guidance system, which uses augmented reality glasses to suggest optimal cut zones. This tool addresses challenges like inconsistent pruning quality, high training burdens for new crews, and the increasing complexity of modern viticulture, making expert knowledge accessible and repeatable.

NakedTensor serves as a foundational resource for understanding machine learning concepts within TensorFlow. It presents simplified, bare-bones examples, focusing on fitting straight lines to data through gradient descent. The project is structured to introduce users to TensorFlow's mechanics, starting with a serial processing example, then progressing to tensor operations for parallel computation, and finally demonstrating how to handle large datasets using placeholders and data sampling. This approach makes complex topics like error definition, optimization, and distributed computing accessible, providing a clear pathway for beginners to grasp the core principles of machine learning with TensorFlow.

OmniIsaacGymEnvs offers a robust platform for developing and testing reinforcement learning agents within the Omniverse Isaac Gym ecosystem. It leverages PPO from the rl_games library and is built upon Isaac Sim's omni.isaac.core and omni.isaac.gym frameworks. Users can train policies, load pre-trained models for inference, and run simulations in both graphical and headless modes for optimized performance. The tool supports various tasks, from Cartpole to complex robotic simulations like Humanoid and ShadowHand, and provides extensive configuration options via Hydra. It also integrates with Docker for streamlined deployment and offers livestreaming capabilities for real-time visualization.

Paper-List is an open-source GitHub repository curated by Yanjie Ze, offering a comprehensive collection of research papers across the domains of robotics, learning, and computer vision. The list is meticulously organized by publication year and conference, including prominent venues like RSS, CVPR, ICLR, NeurIPS, CoRL, ICCV, ICML, and SIGGRAPH. It features papers on topics such as humanoid robots, dexterous manipulation, 3D robot learning, and robot foundation models. The repository also highlights 'Best Papers' and 'Recent Random Papers,' providing direct links to arXiv preprints, official websites, and other resources, making it an invaluable resource for researchers and academics to track cutting-edge advancements in these fields.

pytorch_diffusion offers a PyTorch reimplementation of Denoising Diffusion Probabilistic Models, complete with checkpoints converted from the original TensorFlow implementation. This tool allows users to load diffusion models with pretrained weights for various datasets like CIFAR-10, LSUN-bedroom, LSUN-cat, and LSUN-church. It provides a quickstart guide for running a Streamlit demo, making it accessible for immediate use. Users can also instantiate and configure the U-Net model for denoising independently. The repository includes instructions for producing samples, evaluating results against TensorFlow models, and converting TensorFlow checkpoints to PyTorch, making it a comprehensive resource for researchers and developers working with diffusion models.

Model Medicines is an AI-driven company dedicated to building better medicines by innovating at the intersection of data science, biology, and drug development. The platform utilizes AI to model chemistry and human biology, accelerating the discovery and development of life-changing drugs. With 192 compounds and 67 validated assets in disease-relevant cellular models across 12 therapeutic targets, Model Medicines focuses on areas such as virology, oncology, inflammation, and longevity. Their proprietary GALILEO™ and AmesNet™ technologies enable ultra-large virtual screening and agentic AI breakthroughs, leading to the identification of best-in-class potential therapeutics, such as MDL-001, a direct-acting, broad-spectrum antiviral.

PINNpapers is a comprehensive, open-source repository maintained by the IDRL lab, dedicated to curating essential research papers on Physics-Informed Neural Networks (PINNs). Since PINNs have gained significant traction in scientific computing, this resource serves as a valuable collection of representative works in the field. The repository categorizes papers across various aspects of PINNs, including foundational models, parallel computing approaches, acceleration techniques, model transfer and meta-learning, probabilistic PINNs, uncertainty quantification, and diverse applications. It also lists relevant software libraries like DeepXDE and SciANN, providing links to papers and code where available. Researchers and practitioners can use this resource to stay updated on the latest advancements and foundational concepts in PINN research.

pysc2-examples offers a collection of Deep Reinforcement Learning examples specifically designed for StarCraft II. Built upon Deepmind's pysc2, OpenAI's baselines, and Blizzard's s2client-proto, it provides a robust framework for developers and researchers. The project leverages TensorFlow 1.3 and includes examples for tasks like 'CollectMineralShards' using Deep Q Networks and A2C algorithms. Users can quickly set up the environment, install necessary libraries like pysc2 and baselines, download StarCraft II maps, and then train and enjoy their AI agents. It supports various parameters for training, including algorithm choice (deepq, a2c), total timesteps, exploration fraction, and options for prioritized replay or dueling networks.

SnakeFusion is an AI project that leverages genetic algorithms and neural networks to train virtual snakes within a game environment. The core concept involves training five individual snakes, which can then be fused together to create a single, more advanced 'ultimate snake'. This project serves as a practical demonstration of applying evolutionary algorithms and AI in game development. Built using Processing, it provides a hands-on approach to understanding how AI can learn and adapt. Users can interact with the system by adjusting mutation rates, saving trained snakes, and initiating the fusion process to observe the creation of a 'super snake'.