Research & Education

really-awesome-gan is a comprehensive, open-source resource maintained by Holger Caesar, offering a curated list of papers and other materials focused on Generative Adversarial (Neural) Networks. This GitHub repository provides an extensive collection for anyone interested in GANs, from theoretical foundations to applied vision and other applications. While the maintainer stopped adding new papers in November 2017 due to GANs becoming mainstream, the existing list remains a valuable archive. It includes recommendations, tutorials, workshops, blogs, videos, and code examples, making it an excellent starting point for understanding and exploring GAN technology.

reinforcement_learning_course_materials offers comprehensive lecture notes, tutorial tasks including solutions, and online videos for a reinforcement learning course. Originally hosted at Paderborn University and now transferred to the University of Siegen, this open-source material is licensed under a Creative Commons Attribution 4.0 International Public License. It is designed for both self-learning students and lecturers looking to set up their own courses. The content covers a wide range of topics from introduction to reinforcement learning, Markov decision processes, dynamic programming, Monte Carlo methods, and various policy gradient methods, all with accompanying video lectures and practical exercises based on Python 3.12.

Awesome-Federated-Learning is a curated list of federated learning publications, primarily re-organized from Arxiv. Hosted on GitHub, it serves as a valuable resource for researchers and practitioners interested in the field of federated learning. The repository includes a wide range of papers categorized by research areas such as statistical challenges, trustworthiness, system challenges, models and applications, and benchmarks. It highlights publications from top-tier conferences like ICML, NeurIPS, ICLR, CVPR, ACL, AAAI, and KDD, detailing their venue, year, targeting problem, and method. The latest updates and ongoing research are now maintained on the FedML repository, ensuring the list remains current and comprehensive.

Insight Monk is a global deep tech market intelligence platform and expert community, powered by BIS Research. It offers users access to curated market intelligence and the ability to connect with industry experts. The platform allows users to sign up for free or choose from various annual subscription plans, catering to different levels of access and features. It serves as a central hub for professionals seeking in-depth insights and networking opportunities within the deep tech sector, providing a comprehensive resource for market analysis and expert consultation.

Splatt3R is the official implementation of a research project focused on zero-shot Gaussian Splatting from uncalibrated image pairs. This feed-forward model is designed to directly predict 3D Gaussians from standard images, eliminating the need for complex calibration processes. It is particularly useful for computer vision and 3D graphics applications where rapid 3D scene reconstruction from minimal input is critical. The tool provides an initial codebase, a research paper, a project webpage, and a Gradio demo for easy experimentation. Users can set up an Anaconda environment, compile CUDA kernels, and utilize pretrained models and data from ScanNet++ to train their own models or generate 3D scene representations.

stable-baselines3-contrib is an open-source contrib package for Stable-Baselines3, designed to host experimental reinforcement learning (RL) algorithms and tools. It aims to maintain the simplicity, documentation, and style of Stable-Baselines3 while allowing for the inclusion of less matured implementations, such as those from recent publications. This repository addresses the need for a flexible space where the community can contribute niche utilities, environment wrappers, extended support, and new learning algorithms that might not fit directly into the main Stable-Baselines3 repository. It currently features RL algorithms like Augmented Random Search (ARS), Quantile Regression DQN (QR-DQN), MaskablePPO, RecurrentPPO, Truncated Quantile Critics (TQC), Trust Region Policy Optimization (TRPO), and CrossQ, alongside Gym Wrappers like the Time Feature Wrapper.

The 'State of Open Source AI' is a comprehensive guide presented as an ebook, designed to bring clarity to the rapidly evolving landscape of open-source AI. It covers a wide range of topics, from model evaluations to deployment strategies, serving as a valuable resource for anyone looking to understand current innovations and avoid FOMO in the fast-paced AI world. The project is hosted on GitHub, encouraging community contributions to keep the content up-to-date. It also provides resources for discussion, including a dedicated Discord channel, Twitter, and a newsletter, fostering engagement within the open-source AI community.

Structure_knowledge_distillation is an open-source repository providing the official code for the paper 'Structured Knowledge Distillation for Semantic Segmentation' (CVPR 2019 ORAL) and its extension to other dense prediction tasks. This tool facilitates the transfer of structured knowledge from a larger, more complex teacher model to a smaller, more efficient student model. It includes implementations for pixel-wise, pair-wise, and holistic distillation methods, demonstrating improved performance on tasks like semantic segmentation, object detection, and depth estimation. The repository offers pre-trained models and detailed instructions for compiling and running tests, making it a valuable resource for researchers and practitioners in the field of computer vision.

tensorflow-deepq offers a foundational demonstration of deep Q-learning principles implemented with Google TensorFlow. This open-source project provides a basic framework for understanding and experimenting with reinforcement learning tasks, particularly focusing on how a DeepQ controller can learn strategies within a simulated environment. Users can define custom controllers and simulations, observe states, collect rewards, and perform actions. While the repository is noted as obsolete by its maintainer, with a more complete implementation available from OpenAI, it still serves as a valuable educational resource for those looking to grasp the core concepts of deep Q-learning and its application using TensorFlow. It includes functionalities for creating GIF animations of learned strategies.

Kippy Language Tutor is an advanced AI language tutor designed to help learners achieve fluency faster through speaking practice. It moves beyond traditional grammar lessons, focusing on real-world conversations and scenarios. The tool provides detailed feedback on pronunciation, grammar, and fluency, and allows users to track their progress over time. Kippy supports 10 languages and offers features like instant translation, guided conversations, and a personal phrasebook. It's ideal for those looking to supplement other learning methods like Duolingo or private tutors, providing a safe space to practice speaking without fear of judgment.

Onri is an innovative platform designed to streamline the learning process, acting as a "Google Map of knowledge" to guide users along the shortest path to mastering any subject. It empowers individuals to set clear learning goals and leverage their existing knowledge as a foundational starting point. The tool then intelligently crafts a personalized learning journey, breaking down complex topics into bite-sized concepts. Onri curates relevant study materials, enabling users to learn at their own pace and efficiently achieve their educational objectives. This approach ensures a focused and effective learning experience, making complex subjects more accessible and manageable.

Probable offers real-time probability tracking for 16 major global events across various domains including geopolitics, markets, climate, health, energy, and cybersecurity. The platform provides three smart predictions per topic, which are updated live every 5 seconds, ensuring users have access to the most current information. It leverages AI to offer insights and predictions, making it a valuable resource for monitoring world signals and potential future developments. Probable is designed to be free forever, making it accessible to a wide audience interested in tracking global trends and risks.

GenForge provides a dual experience, allowing users to either dive into a collection of instant online games or explore its AI ecosystem. The games are designed to be fast, lightweight, and require no account, offering quick entertainment with titles like 2048, Minesweeper, and Connect Four. Beyond gaming, GenForge introduces an AI ecosystem, including sites like MCPBundles, and offers educational content on its Model Context Protocol (MCP). This platform aims to bridge AI and human interaction through various tools and resources, catering to both casual gamers and those interested in AI advancements.

Gizmo is an AI-powered learning platform designed to make studying more engaging and effective. It transforms diverse learning materials, including YouTube videos, PDFs, notes, and PowerPoint presentations, into interactive AI flashcards. The platform leverages proven educational techniques like spaced repetition and active recall to enhance memory retention and make learning addictive. Students can quiz themselves in a gamified environment, making the study process enjoyable and leading to improved academic performance. Gizmo aims to simplify studying and help users achieve better grades across various subjects.

Total-Text-Dataset is a comprehensive, word-level based English curve text dataset designed to facilitate research in text detection and recognition. It comprises 1555 images featuring more than three different text orientations: horizontal, multi-oriented, and curved, making it unique among existing datasets. The dataset is regularly updated with detection and recognition leaderboards, showcasing the performance of various methods. It also provides an updated guided annotation toolbox for scene text image annotation and includes pixel-level and text-level ground truth data. Researchers can leverage this dataset for training and benchmarking models, particularly for arbitrary-shaped text reading tasks, and it has been extended into the larger ArT dataset.

Vision Papers is a Hugging Face Space designed to help users conveniently explore summaries of vision papers. This tool allows researchers and students to quickly grasp the key points of academic research in the field of computer vision and vision language models. By browsing through the left tab, users can discover more resources and stay up-to-date with the latest advancements. The platform aims to make complex research papers more accessible, saving time and effort for those looking to understand cutting-edge AI developments.

Edde.ai empowers users to create their own digital twin using AI magic. By uploading 5-10 high-quality photos, users can train a personalized AI model that captures their unique features. This model then allows for the generation of stunning, photorealistic images in under 30 seconds, across a wide range of styles including photorealistic, artistic, anime, and vintage. The platform emphasizes privacy, ensuring photos and generated images are encrypted and never shared. It offers a responsive design for mobile optimization and continuously improving AI models for better results over time. Edde.ai is designed for ease of use, requiring no technical knowledge to transform users into any character or scenario.

Quizgecko is an AI-powered learning platform designed to transform various content types into interactive study materials. Users can upload PDFs, lecture slides, YouTube links, or handwritten notes, and the AI processes them to create custom courses. The platform generates interactive quizzes (multiple choice, true/false, short answer, fill-in-the-blank, matching), smart flashcards, study notes, and AI-generated podcasts. It allows users to tailor difficulty levels, track progress with real-time grading and analytics, and identify knowledge gaps. Quizgecko is ideal for students, teachers, and businesses looking to create assessments, training materials, and certification tests efficiently. It supports various file formats and offers customization options for all generated content.

Blue is a native macOS application that brings the power of ChatGPT directly to your desktop, allowing you to interact with AI models like GPT-4o and GPT-3.5 Turbo within any application. It features AppVision, which enables the AI to understand the context of what's on your screen, providing more relevant assistance without requiring you to copy and paste. Blue prioritizes user privacy, storing all data on-device, encrypting it with your Apple ID, and ensuring no data is used for model training. It is GDPR-compliant and designed for professional use, offering a secure and efficient way to leverage AI for tasks like coding, brainstorming, and report polishing.

LOTUS Depth is an AI tool designed for advanced depth estimation, allowing users to generate detailed depth maps from uploaded images or videos. The application supports two distinct modes: generative and discriminative. In generative mode, users can optionally provide a seed to influence the output. This tool is particularly useful for analyzing the spatial relationships and distances of objects within visual media. Hosted on Hugging Face, LOTUS Depth provides a accessible platform for researchers, developers, and enthusiasts interested in computer vision and 3D reconstruction tasks.

Kollegio AI is an AI-driven platform designed to assist students, schools, and colleges throughout the college application process. It provides personalized college recommendations by matching student profiles with thousands of institutions, eliminating guesswork. The platform also offers 24/7 AI essay support, helping students brainstorm ideas, structure their essays, and receive detailed feedback to make their applications stand out. Additionally, Kollegio AI includes a personalized financial aid AI that helps students discover and apply for scholarships that align with their needs. The tool aims to make college applications less stressful and more accessible, offering a comprehensive suite of features to support students from start to finish.

Uruky is a private search engine designed for users prioritizing privacy, an ad-free experience, and an EU-based service. Unlike many alternatives, Uruky is search-only, avoiding ecosystem sprawl and not incorporating AI into its stack. It offers personalized search results, allowing users to exclude or boost specific domains, and ensures no tracking or logging of search queries. A key differentiator is its commitment to data ownership, providing paying customers with a copy of the source code after 12 months. Uruky operates with EU servers, storage, and payment processing, utilizing EU search providers to maintain its privacy-centric and regional focus.

VLM_survey is an open-source repository offering a systematic survey of Vision-Language Models (VLMs) applied to diverse visual recognition tasks such as image classification, object detection, and semantic segmentation. It serves as a valuable resource for researchers, providing an extensive collection of academic papers, widely adopted datasets for VLM pre-training and evaluation, and categorized methodologies for VLM pre-training, transfer learning, and knowledge distillation. The repository also highlights recent advancements and future research directions in the field, making it an essential reference for anyone working with or studying VLMs.

Models Explorer is an AI tool hosted on Hugging Face Spaces, designed for discovering and exploring a wide array of AI models. It provides a platform for users to delve into model performance metrics, enabling detailed analysis and comparison of different AI models. This tool is particularly useful for individuals involved in AI research and development, offering a centralized hub to navigate the vast landscape of available models. It facilitates informed decision-making by presenting key metrics, making it easier to identify suitable models for specific applications or to benchmark existing solutions. The platform is freely accessible, promoting open exploration and collaboration within the AI community.