Research & Education

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.

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.

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.

CosyVoice Gpu is an AI tool designed for voice synthesis, providing users with the capability to generate speech. Hosted on Hugging Face Spaces, it leverages a provided model for its functionality. The tool is built with Gradio, indicating a user-friendly web interface for interaction. It operates under the MIT license, suggesting it is open-source and potentially allows for modification and distribution. While the current live website indicates a runtime error, its core purpose is to facilitate speech generation, making it relevant for various audio and content creation tasks.

Prismer AI is an AI-powered learning platform designed to help users master any topic quickly and deeply. It leverages concept maps and Feynman challenges to facilitate active recall and build real understanding from various sources like PDFs, academic papers, or videos. The platform features an intelligent auto-suggestion system that learns from user interactions, refining its recommendations over time. Users can build structured courses from any topic, generating syllabi with slides, audio lectures, and quizzes. Prismer AI is suitable for students, professionals, and curious minds seeking to go beyond surface-level answers and engage in smarter, more personalized learning.

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.

squeezeDet is an open-source project providing a TensorFlow implementation of SqueezeDet, a convolutional neural network specifically designed for real-time object detection. This tool is particularly optimized for autonomous driving applications, emphasizing a unified, small, and low-power architecture. It allows users to train and evaluate object detection models using datasets like KITTI, supporting various network backbones such as SqueezeNet, ResNet50, and VGG16. The repository includes scripts for installation, demo execution, training, and validation, making it a comprehensive resource for researchers and developers working on efficient object detection in resource-constrained environments.

spark-py-notebooks is a comprehensive collection of IPython/Jupyter notebooks designed to educate users on various Apache Spark concepts using Python (pySpark). The tutorials range from fundamental to advanced topics, focusing on Big Data Analysis and Machine Learning. Users can learn about RDD creation, basic RDD operations like map, filter, and collect, sampling, set operations, and data aggregations. The collection also delves into working with key/value pair RDDs and introduces MLlib for basic statistics, exploratory data analysis, logistic regression, and decision trees. Additionally, it covers Spark SQL for structured processing with DataFrames and includes applications like building a movie recommendation web service.

Sloth is an open-source tool specifically designed for labeling image and video data, primarily catering to the needs of computer vision research. It enables researchers and data scientists to efficiently annotate visual data, which is crucial for training machine learning models. The tool supports various annotation tasks, making it a versatile solution for creating high-quality labeled datasets. Its open-source nature means it can be freely used and adapted by the community, fostering collaboration and customization in computer vision projects. Sloth aims to simplify the often complex and time-consuming process of data annotation, facilitating the development of robust AI applications.

Bade Achhe Lagte Hain is a delightful brain training application specifically designed for Indian elders. This tool focuses on enhancing cognitive health by offering engaging and simple brain games. Users can sharpen their memory and math skills, with content available in both Hindi and English, making it accessible to a wider audience. The app aims to prevent cognitive decline and is designed to be free and easy to use, providing a joyful experience for senior citizens. It serves as a valuable resource for families looking to support their elders in maintaining mental sharpness and overall well-being.

Setup-NVIDIA-GPU-for-Deep-Learning is a comprehensive, open-source guide designed to assist users in setting up their NVIDIA GPUs for deep learning tasks. It outlines a clear, step-by-step process, starting with the installation of the latest NVIDIA GPU drivers. The guide then proceeds to cover essential software components such as Visual Studio with C++ support, Anaconda/Miniconda for package management, the CUDA Toolkit, and cuDNN. Finally, it provides instructions for installing PyTorch and includes a script to test the GPU setup, ensuring all components are correctly configured for optimal deep learning performance. This resource is invaluable for deep learning practitioners and AI researchers looking to streamline their development environment setup.

VitalMinute AI is a powerful meeting assistant designed for professionals and teams, enabling users to record any meeting and instantly receive structured minutes within 60 seconds. A key differentiator is its privacy-first approach, offering an On-Device Mode for complete data isolation where audio never leaves the phone, and designed for HIPAA compliance with strict encryption. The tool also boasts offline functionality, processing sessions locally without internet access for maximum security. It supports over 100 languages, providing perfectly structured summaries globally. VitalMinute can generate various formats, including Clinical SOAP Notes, Class Study Guides, and Meeting Highlights, making it versatile for different professional needs. It operates on a simple pay-as-you-go pricing model with credits that never expire, avoiding subscriptions or hidden fees.

Stanford-CS-221-Artificial-Intelligence is a comprehensive resource offering VIP cheatsheets for Stanford's CS 221 Artificial Intelligence course. This repository aims to consolidate all crucial notions covered in the course, including cheatsheets for each artificial intelligence field and an ultimate compilation of concepts. The material is accessible on a dedicated website, ensuring readability across various devices. Authored by Afshine Amidi and Shervine Amidi, it serves as an invaluable study aid for students and anyone interested in understanding core AI principles. The cheatsheets are available in English, French, and Turkish, making it accessible to a broader audience.

tf-gnn-samples is a GitHub repository offering TensorFlow implementations of various Graph Neural Network (GNN) architectures. It serves as the code release for an article introducing GNNs with feature-wise linear modulation (GNN-FiLM). The repository includes implementations for Gated Graph Neural Networks (GGNN), Relational Graph Convolutional Networks (RGCN), Relational Graph Attention Networks (RGAT), Relational Graph Isomorphism Networks (RGIN), GNN-Edge-MLP, and Relational Graph Dynamic Convolution Networks (RGDCN). It provides scripts for training and evaluating models on tasks such as citation networks (Cora, Pubmed, Citeseer), protein-protein interaction (PPI), quantum chemistry prediction (QM9), and variable misuse detection (VarMisuse). The code allows users to reproduce experimental results presented in the accompanying research paper, making it a valuable resource for researchers and developers working with GNNs.

A-dapt brings Emotion AI into LegalTech, providing lawyers with human-centered tools for scalable, privacy-first witness preparation and emotionally intelligent litigation training. Its TestMyWitness platform uses Emotional AI to prepare confident and credible witnesses by focusing on people, not paperwork. Key features include viewer emotion analysis, real-time emotional feedback during witness preparation, dynamic emotion labels, and "move the dot" coaching to improve composure. The platform also offers a transcript and annotation workspace with auto-generated Q&A, emotion tags, and sharable notes for follow-up coaching. It flags risk signals like hostility or low confidence, supporting legal teams in enhancing witness credibility before court or interviews. The system is designed for privacy, reduced bias, and eco-friendliness.

Abzu is a biotechnology company leveraging explainable AI to innovate in the field of RNA therapeutics. The company specializes in developing best-in-class RNA drugs, including siRNAs, ASOs, and anti-miRs, for significant medical needs. Their AI-guided design platform, powered by the QLattice®, allows for the in silico exploration and prioritization of vast sequence spaces, evaluating over 100,000 design variants to predict efficacy and developability properties. This approach significantly reduces experimental cycles, lowers costs, and shortens the time to candidate selection. Abzu also focuses on RNA-based delivery systems, developing targeted aptamers for cell-specific uptake of therapeutic RNA, offering a modular platform for precision delivery beyond the liver. The team combines deep RNA biology, AI-driven design, and drug development experience to create a closed learning loop where data refines models and models improve molecules.