Research & Education

Pubky is an open-source platform offering a suite of tools and protocols designed to build a decentralized, user-controlled internet. It leverages PKARR for decentralized routing and identity management, alongside Homeservers for interoperable and censorship-resistant hosting. The platform includes Pubky App, a decentralized social media application, and Pubky Core, which provides the underlying infrastructure and SDKs for developers. Key features include identity management with Pubky Ring, a mobile key manager, and developer tools like Pubky Docker for local environment setup. Pubky also explores concepts like a Semantic Social Graph for filtering and discovery, aiming to provide a credible exit strategy for users.

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.

DeepReinforcementLearningInAction is an open-source GitHub repository that serves as a companion to the 'Deep Reinforcement Learning in Action' book from Manning, Inc. It provides a comprehensive collection of code snippets, listings, and projects, all embedded within Jupyter Notebooks. The content is meticulously organized by chapter, allowing users to follow along with the book's concepts and immediately apply them. The repository also includes an Errata folder with updated notebooks to correct any discovered errors, ensuring users have access to the most accurate code. It requires the NumPy library and PyTorch to run many of the projects, with installation instructions provided via a `requirements.txt` file. This resource is ideal for those looking to practically implement deep reinforcement learning algorithms.

Exam 1 - Fundamentals of GRPO is an educational AI tool hosted on Hugging Face Spaces, designed for self-assessment and learning in the field of AI. It provides a quiz format for users to test their understanding of key concepts such as GRPO, TRL, RL, and Deepseek R1. Upon successfully passing the exam, users can earn a certificate, which can be shared on platforms like LinkedIn to showcase their knowledge. The tool encourages users to log in to start the quiz, answer questions, and claim their certificate, making it a valuable resource for students and professionals looking to validate or enhance their understanding of these specific AI topics.

Seamlessm4t Diarization VAD is an AI tool designed for advanced audio analysis, specifically focusing on speech diarization and voice activity detection. This tool helps in identifying who spoke when, and when speech occurred in an audio recording. Hosted on Hugging Face, it provides a free solution for users needing to process audio files for speaker separation and speech presence. While the current live website indicates a runtime error, the tool's core functionality is centered around these critical audio processing tasks, making it valuable for researchers, developers, and content creators working with spoken audio.

sidon_demo_beta is a speech restoration tool available as a Hugging Face Space, designed to enhance the clarity of audio recordings by effectively removing background noise. Users can easily upload their noisy speech audio files to the platform. The system then processes these files, applying advanced algorithms to produce a cleaner, more intelligible version of the original recording. This demonstration tool is ideal for individuals looking to explore speech enhancement techniques or for those who need to quickly clean up audio for various purposes, such as research or educational projects. Its straightforward interface makes it accessible for users without specialized audio engineering knowledge.

S2S-Arena is a specialized AI evaluation tool designed for assessing Speech-to-Speech (S2S) models. Hosted as a Hugging Face Space by FreedomIntelligence, it offers a platform where users can listen to audio samples generated by various S2S models. The primary function is to compare how effectively these models follow instructions and maintain semantic integrity during speech transformation. This tool is invaluable for researchers, developers, and anyone involved in the development and testing of S2S technologies, providing a direct way to evaluate and benchmark model performance against specific criteria. It helps in understanding the strengths and weaknesses of different S2S approaches.

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.

ShieldGemma2 VLM is a multimodal safety model designed to evaluate and test the safety of AI models by analyzing images. Users can upload an image and define specific safety policies using descriptive text. The tool then processes the image against these policies, returning a probability score for each policy, indicating the likelihood of the image complying or violating the defined safety guidelines. This functionality makes it a valuable resource for researchers and developers focused on AI safety, vulnerability assessment, and ensuring responsible AI deployment. It helps in identifying potential risks and non-compliance in visual content based on user-defined criteria.

AI Speak, part of the Monkey English suite, provides a fun and engaging platform for children aged 3-11 to master English pronunciation and communication. The tool utilizes proprietary M-Speak technology, which offers real-time speech recognition and syllable-level scoring to help young learners develop native-like pronunciation. Beyond pronunciation, it aims to build confidence in speaking English through interactive courses and activities. AI Speak is designed to be an accessible and effective supplementary learning product, complementing other Monkey English offerings like Monkey Junior and Monkey Stories, to create a comprehensive English learning pathway for children.

SmolLM3 WebGPU is a cutting-edge dual reasoning AI model developed by Hugging Face Smol Models Research. This innovative tool distinguishes itself by running entirely locally within a web browser, leveraging WebGPU technology. It provides a platform for AI enthusiasts and developers to directly interact with and experiment with advanced AI models without the need for complex setups or cloud infrastructure. The model's local execution ensures privacy and potentially faster response times, making it an ideal environment for testing new ideas and understanding AI behavior. As an open-source offering, it fosters community collaboration and allows for transparent development and customization.

4d-gaussian-splatting is an open-source implementation for real-time photorealistic dynamic scene representation and rendering, based on the ICLR 2024 paper "Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting." This tool allows users to model dynamic scenes using native 4D Gaussian primitives, offering a coherent integrated approach to space and time dimensions. It builds upon the principles of 3D Gaussian Splatting and provides a dedicated rendering pipeline. The project includes resources for data preparation using datasets like DyNeRF and DNeRF, and offers scripts for training models. It's ideal for researchers and developers working on advanced 3D and animation projects.

SmolVLM realtime WebGPU is an innovative AI tool that leverages a vision-language model to provide real-time descriptions of visual input. Users can simply point their webcam at any object or scene, type a question or instruction, and the application will analyze the visual data to describe what it perceives. This tool operates locally within a web browser, utilizing WebGPU for efficient processing. It captures frames at user-defined intervals, making it highly interactive and responsive. Ideal for those interested in real-time AI vision applications and local model execution.

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.

SoloSpeech is an advanced AI tool designed for target speech extraction, enabling users to isolate and extract specific voices from audio recordings. By uploading an audio file containing multiple voices and a short sample of the desired speaker, the application processes the input to return a clean audio file with only the target speech. This state-of-the-art tool is particularly useful for tasks requiring precise voice isolation, such as enhancing audio quality, conducting speech processing research, or developing applications that rely on clean, isolated speech. Its intuitive interface on Hugging Face Spaces makes it accessible for various users looking to refine audio content.

SoloAudio is an innovative AI tool developed by OpenSound, available as a Hugging Face Space, designed to intelligently separate specific sounds from complex audio mixtures. Users can upload an audio file and then provide a text prompt describing the desired sound they wish to isolate. The application processes the input and generates a new audio file containing only the specified sound, effectively removing other elements from the original recording. This capability is highly beneficial for audio editing, sound design, and various research applications in audio processing, offering a streamlined approach to sound extraction.

Embodied_AI_Paper_List is an open-source repository maintained by HCPLab at SYSU and Pengcheng Laboratory, offering a comprehensive collection of papers and resources focused on Embodied AI. This resource is designed to serve as a foundational reference for researchers and practitioners, bridging the gap between cyberspace and the physical world through intelligent systems. The repository covers key areas such as embodied perception, interaction, agent development, and sim-to-real adaptation, including state-of-the-art methods, essential paradigms, and comprehensive datasets. It also explores the role of Multi-modal Large Models (MLMs) and World Models (WMs) in facilitating interactions for embodied agents, highlighting their significance in both digital and physical environments. The list is regularly updated with the latest advancements and includes a survey paper accepted by IEEE/ASME Transactions on Mechatronics.

awesome-contrastive-self-supervised-learning is an open-source GitHub repository offering a comprehensive and curated list of research papers focused on contrastive self-supervised learning. This resource is invaluable for academics, researchers, and students looking to stay updated with the latest advancements and foundational works in this rapidly evolving AI domain. The repository categorizes papers by year, ranging from 2010 to 2024, and includes surveys, reviews, and specific research contributions, often with links to associated code. It covers diverse applications such as medical image analysis, vision-language representation, graph representations, and natural language understanding, making it a central hub for exploring the theoretical and practical aspects of contrastive learning.

Voice Match is an AI tool hosted on Hugging Face that allows users to analyze English voice clips to find similar and dissimilar voices within a large dataset. By either recording or uploading an audio sample, the application processes the input and returns a list of matching audio clips, complete with associated sentences and a similarity score for each match. The tool leverages Rimecaster technology to perform its voice comparison, aiming to help users identify vocal characteristics. While the tool's live website currently indicates a runtime error, its core functionality is designed for voice analysis and matching.

Golden Record is an innovative audio recording platform designed to help individuals capture and preserve the voices, stories, and memories of their loved ones for generations. Users can easily record precious sounds and narratives using just a mobile device. The platform leverages AI to generate customizable story prompts and conversation starters, making the recording process engaging and straightforward. It supports collaboration, allowing users to invite friends or family to contribute to albums. Golden Record also offers the unique option to create physical keepsakes, such as custom lathe-cut vinyl records, from the audio recordings, transforming digital memories into timeless family heirlooms. The tool is accessible via both a mobile app and a website, ensuring broad usability.

paper-rec is an AI tool designed to recommend research papers, hosted on Hugging Face. It aims to assist users in discovering relevant academic articles, making it useful for literature reviews, academic research, and staying updated on new publications. While the tool's live website currently indicates a build error, its intended purpose is to streamline the process of finding academic content. The platform is created by bluebalam and is licensed under the MIT license, suggesting an open and accessible approach to its development.

VLM Object Understanding is an AI tool available on Hugging Face that provides capabilities for exploring object detection, visual grounding, and keypoint detection. Users can upload an image and select a task such as asking a question, generating a caption, or performing object detection. The application runs two distinct vision-language models, returning both a visual annotation and a textual response. This tool is ideal for researchers, developers, and enthusiasts interested in understanding and experimenting with advanced visual AI models for image analysis and object identification.

Ebook2audiobook is a versatile tool hosted on Hugging Face that transforms various ebook formats, including PDF, EPUB, TXT, and DOCX, into ready-to-play audio files. Users can upload their ebook, select from an extensive list of over 1107 supported languages, and even preview chapters before conversion. This application provides a convenient way for individuals to consume written content audibly, making books accessible in a new format. It's designed for ease of use, allowing for quick conversion and download of the audio output, catering to a wide range of linguistic preferences.

PaperList serves as a comprehensive platform designed for academics and researchers to streamline their engagement with scientific literature. It offers a centralized hub for discovering new papers, sharing insights with peers, and participating in discussions around published research. The tool enhances knowledge exchange by enabling users to effectively track specific authors and sources, ensuring they stay updated with relevant advancements in their fields. PaperList aims to simplify the research process, fostering a collaborative environment where users can easily access, organize, and interact with academic content, ultimately accelerating their research endeavors and facilitating deeper understanding of complex topics.