Research & Education

Fundamentals-of-Deep-Learning-Book serves as the official code companion for the O'Reilly "Fundamentals of Deep Learning, Second Edition" book. This GitHub repository offers practical, PyTorch-based implementations of all algorithms presented in the book, making it an invaluable resource for those looking to apply deep learning concepts. The code is primarily provided as Google Colab notebooks, allowing users to run examples directly from the repository without extensive setup. Additionally, some examples include .py files for more convenient execution. It also archives code from the first edition, ensuring comprehensive coverage for different versions of the book. This resource is ideal for students and practitioners aiming to deepen their understanding of deep learning through hands-on coding.

UnSAMv2 is an AI-powered tool designed for precise object segmentation in both images and videos. Users can upload their media files and interactively define areas of interest by adding clicks, which the tool then uses to generate detailed segmented masks. This capability is ideal for applications requiring fine-grained object separation and analysis. The tool is particularly useful for computer vision research and AI-assisted image analysis, enabling a deeper understanding of visual data at any granularity. Its intuitive interface allows for efficient and accurate segmentation, making it a valuable asset for tasks that demand high precision in visual data processing.

EMAGE is an AI tool designed for co-speech 3D gesture generation, allowing users to create moving characters that mimic speech from a short audio clip. Users can select from different models, including DisCo, CaMN, or EMAGE, to generate the desired animation. The application can produce a fast 2D video of the character's body and offers the option to include 2D face landmarks. This tool is built using Gradio and was featured at CVPR 2024, making it suitable for animation and research purposes where synchronized speech and gesture are required.

Text2Human is an official PyTorch implementation for text-driven controllable human image generation, as presented in the SIGGRAPH 2022 paper. This open-source tool enables users to create human images by providing text descriptions that specify clothing shapes and textures. It includes a comprehensive framework for training and sampling, utilizing a large-scale, high-quality DeepFashion-MultiModal Dataset with rich multi-modal annotations. Researchers and developers can leverage its capabilities for tasks like generating images from parsing maps or human poses, and it offers a user interface for interactive text-to-human image generation. The project also provides pretrained models and detailed installation instructions, making it a valuable resource for AI research in computer graphics.

foldingdiff is an open-source research tool developed by Microsoft that utilizes diffusion models to generate novel protein backbone structures. It employs trigonometry and attention mechanisms, as detailed in its preprint on arXiv. The tool provides a trained model on HuggingFace spaces and SuperBio, allowing users to generate protein structures directly from a browser. It supports installation via conda and pip, and offers scripts for training custom models, downloading necessary data, and sampling protein backbones. Additionally, foldingdiff includes functionalities for evaluating designability through inverse folding with ProteinMPNN or ESM-IF1, and structural prediction using OmegaFold or AlphaFold2.

Microsoft Reading Coach is a free AI-powered reading practice tool designed to help individuals build their literacy skills. It leverages artificial intelligence to generate engaging stories and offers a library of leveled passages from ReadWorks, ensuring content matches learners' abilities and interests. The tool keeps users motivated by allowing them to unlock new characters and settings, practice their most challenging words, and monitor their progress over time. It is particularly beneficial for learners who already know how to decode words, providing a supportive environment for improving reading fluency and comprehension.

Openlang is an open-source language-learning platform providing hundreds of free games with human-like speech across more than 60 languages, from Arabic to Yiddish. It emphasizes accessibility with no registration, no ads, and an MIT license. Users can easily install apps on mobile devices for offline use and benefit from customizable app generation, allowing them to create tailored learning experiences. The platform leverages AI for design and code generation, JavaScript for core logic, and React for UI rendering. It also supports threatened languages like Belarusian, Irish, Navajo, Welsh, and Yiddish, promoting language revitalization efforts. The open-source nature allows anyone to download source prompts, modify them, and produce fully functional customized games.

BreeAI is an all-in-one AI study assistant designed to help students learn more efficiently. It can instantly convert various forms of content, including text, PDF documents, and even photos of textbook pages, into structured study tools. Users can generate smart notes, interactive quizzes, and digital flashcards from their materials. The platform also supports the creation of visual diagrams, making complex information easier to understand and retain. BreeAI aims to streamline the study process, allowing students to transform raw information into actionable learning resources quickly and effectively, ultimately helping them to study smarter, not harder.

World Labs is a spatial intelligence company focused on developing advanced AI models capable of perceiving, generating, reasoning, and interacting with the 3D world. Their primary product, Marble, allows users to create spatially consistent, high-fidelity, and persistent 3D environments from multimodal inputs like text, images, videos, or 360 panoramas. Users can precisely control 3D layouts, interactively edit specific elements, and expand or combine worlds to build larger, more immersive experiences. The platform supports versatile outputs, enabling downloads and exports in various 2D and 3D formats for seamless integration into existing workflows in fields such as art, film, gaming, AR/VR, robotics, and architecture.

Paligemma Doc is an AI tool designed for comprehensive document understanding. Users can upload various image types, including documents, infographics, diagrams, and images containing text, and then pose questions to receive detailed answers. This functionality makes it suitable for extracting information, analyzing content, and gaining insights from visual data. The tool leverages the power of PaliGemma for its document understanding capabilities, offering a versatile solution for tasks that involve interpreting and querying information embedded within images.

Hibay is a mobile application designed to enhance English speaking proficiency through engaging AI-powered conversations. The tool provides a judgment-free environment for users to practice their English across more than 100 realistic scenarios, ranging from everyday discussions to specialized business English and IELTS preparation. Users benefit from immediate feedback on their pronunciation, grammar, and vocabulary, which helps in identifying areas for improvement. Additionally, Hibay offers tailored learning plans, enabling users to build confidence and fluency at their own pace. This comprehensive approach makes it an effective solution for anyone looking to significantly improve their spoken English.

Music Descriptor is an AI-powered application hosted on Hugging Face that offers comprehensive music analysis. Users can upload audio files or record live music to receive detailed insights into its characteristics. The tool identifies various aspects of music, including genres, instruments present, and the emotional content conveyed. It then provides a breakdown of top predictions for each category, making it a valuable resource for understanding musical compositions. This tool is designed for anyone interested in a deeper analysis of music, from casual listeners to professionals.

Learn Languages AI is an innovative tool designed to help users achieve conversational fluency in various languages by interacting with an AI teacher directly on Telegram. This platform facilitates language learning through engaging activities like speaking, texting, and playing, making the process interactive and accessible. It supports a diverse range of languages including German, Polish, Spanish, Italian, French, Dutch, Brazilian Portuguese, Hindi, and Chinese. The tool emphasizes a user-friendly experience, requiring no account to start learning and offering a free trial. It's built to help users reach their language learning goals efficiently and effectively.

Score Jacobian Chaining is a technique designed for analyzing the sensitivity of machine learning models. This tool is invaluable for AI researchers and machine learning engineers seeking to understand the intricate relationship between model inputs and outputs. By providing insights into how changes in input data propagate through a model, it facilitates effective debugging and optimization. This understanding is crucial for improving model performance, ensuring robustness, and gaining deeper insights into model behavior. While the current live website indicates a runtime error, the underlying concept is highly relevant for academic research and practical application in machine learning development.

Video Summarize for Youtube is an iOS mobile application designed to streamline video content consumption by leveraging AI to generate summaries of YouTube videos. This tool is particularly useful for individuals who need to quickly grasp the main points of long videos without watching them in their entirety. By simply pasting a YouTube link, users can receive instant, concise, and actionable highlights, making it an efficient solution for busy learners and professionals. The app aims to save significant time by distilling complex or lengthy video content into easily digestible summaries, enhancing productivity and learning.

The RWKV-8 ROSA-QKV-1bit Demo is a Hugging Face Space designed by Jellyfish042, offering a platform to explore and interact with the RWKV-8 language model, specifically focusing on the ROSA-QKV-1bit architecture. This tool is particularly useful for individuals interested in understanding the mechanics and performance of this specific AI model. It serves as a visualizer, allowing users to observe how the model processes information and generates responses. The demo is ideal for educational purposes, research, and for developers or students looking to test and experiment with advanced language models in a live environment.

Gemma3n Visual (Audio) Question Answering is an AI tool that enables users to interact with images using audio queries. By uploading an image and speaking a question, users receive a text-based answer. This functionality makes it a valuable resource for multimodal AI research, allowing for exploration into how AI can process and respond to combined visual and auditory inputs. The tool is built as a Hugging Face Space, indicating its accessibility and potential for community-driven development and experimentation in the field of AI agents and automation.

The Arabic MMMLU Leaderborad is a platform designed for evaluating the performance of AI models specifically in Arabic language tasks. It offers a comprehensive leaderboard where users can view and compare various LLM evaluations. The tool allows for the submission of new models for evaluation, fostering a competitive environment for improving Arabic language AI. Users can customize their view by filtering and selecting specific columns to display detailed information about the models, making it easier to analyze and track progress. This resource is invaluable for researchers and developers focused on enhancing the accuracy and fluency of AI in the Arabic language.

Solving Inverse Problems with FLAIR is an AI tool available on Hugging Face that allows users to tackle common inverse problems in image processing. It provides functionalities for both inpainting and super-resolution. For inpainting, users can upload a photo and draw a mask over the areas they wish to replace. For super-resolution, the tool takes a low-resolution picture and enhances its detail. The platform also allows users to write a short description of their desired outcome, guiding the AI in its processing. This tool is suitable for anyone needing to restore or enhance images through AI-driven solutions.

Owlu is a free AI email agent designed for solo professionals, freelancers, and 1-person founders to streamline email management. It offers chat-driven workflows, allowing users to automate tasks like triaging alerts, summarizing reports, and managing attachments. The platform emphasizes a 'human-in-the-loop' approach, ensuring users review personalized drafts before sending. Owlu integrates with Gmail, enabling personalized mass emails and inbox triage with pre-summarized threads and suggested actions. It's built for those whose work revolves around their inbox, helping them decide faster, write with full context, and put repetitive tasks on autopilot.

Siwalu develops AI-based image recognition technology, primarily through mobile applications, to identify animal breeds. Their apps, including Dog Scanner, Cat Scanner, and Horse Scanner, allow users to quickly determine the breed of their pets or other animals by scanning images. This technology provides specific information about various characteristics and traits, offering a reliable statement about the breed within seconds, including mixed breeds. Siwalu aims to increase knowledge about global biodiversity through universal animal recognition. The platform has garnered over 26 million app downloads and identifies nearly 2 million animals per month, demonstrating its widespread adoption and utility.

Entelechy is a professional development platform designed to transform vague performance challenges into actionable insights by revealing the unseen drivers of behavior within a workforce. It utilizes a behavior-based methodology centered on 54 Human Qualities, which are foundational to in-demand soft skills. The platform offers personal insight tools to discover individual strengths and growth opportunities, alongside team insight features that help managers develop crucial human qualities like accountability and collaboration. Entelechy provides AI-supported coaching plans, structured reflections, and feedback mechanisms to foster continuous improvement and measurable behavior change, supporting leadership development and strengthening learning culture across organizations.

NV-Reason-CXR-3B Demo is an AI-powered tool developed by NVIDIA, hosted on Hugging Face, designed for analyzing chest X-ray images. Users can upload an X-ray and pose specific questions or prompts, such as "Find abnormalities." The application then processes the image and generates a detailed, written explanation of any identified findings, medical devices present, or provides suggestions for reports. This tool aims to assist medical professionals and researchers by offering an intelligent interpretation of radiological data, streamlining the diagnostic process and enhancing understanding of complex medical images.

Trancy is an AI-powered language learning assistant that enhances comprehension and speaking skills through bilingual subtitles and advanced translation features. It supports major streaming platforms like YouTube, Netflix, and Disney+, providing accurate bilingual subtitles in various viewing modes. Beyond video content, Trancy offers AI word and sentence translation for web pages, allowing users to select text or translate entire articles immersively. Key features include AI word lookup, grammar analysis, intelligent sentence segmentation, and listening/speaking practice tools. It also supports PDF bilingual translation and offers customizable translation engines, making it a comprehensive solution for language learners.