Research & Education

deep-research-web-ui is an AI-powered research assistant designed for iterative, deep research across various topics. It integrates search engines, web scraping, and large language models to provide comprehensive insights. Key features include real-time AI response streaming, a tree-structure visualization of the research process, and support for multiple languages. The tool ensures safety and security by processing all configurations and API requests locally in the browser. It also allows for exporting final research reports as Markdown or PDF and supports a wide range of AI providers like OpenAI compatible, DeepSeek, and Ollama, as well as web search providers like Tavily and Firecrawl. It can be deployed in a server mode with environment variables or client mode where users configure their own API keys.

Deep Architecture Genealogy is an open-source project dedicated to mapping the vast and rapidly evolving landscape of deep learning architectures. It provides a comprehensive genealogy, illustrating the relationships and progression of various models such as CNNs (AlexNet, VggNet, ResNet), Generative Models (GANs, VAEs), Reinforcement Learning Algorithms (A3C, DARLA), and RNNs (LSTM, GRU, Transformer). The project is community-maintained, encouraging contributions via pull requests to its text-based genealogy file. This resource is invaluable for researchers, students, and practitioners seeking to understand the historical development and interconnections of deep learning models, offering both a visual mindmap and a detailed text version of the architectural lineage.

World Summit AI is the world's leading AI summit, bringing together key players who shape how AI is researched, governed, and deployed globally. Since its launch in Amsterdam in 2017, it has become a critical meeting point for enterprise leaders, big tech, startups, researchers, policymakers, investors, and ethical experts. The summit, now in its 10th anniversary edition, sets the global AI agenda by spotlighting real-world applications, emerging technologies, and the risks, benefits, and opportunities of artificial intelligence. It is renowned for hosting influential voices in AI and fostering meaningful collaboration across industries and sectors, serving as the anchor of World AI Week.

Make Custom Voices With KokoroTTS is a web-based tool hosted on Hugging Face Spaces, designed for creating unique voice profiles. It enables users to select from several pre-made voices, fine-tune their individual strengths using intuitive sliders, and then blend them together to form a single, custom voice. Once a custom voice is created, users can input any text, and the application will read it aloud using their newly mixed voice. This tool is ideal for experimenting with voice synthesis and exploring different vocal textures and tones.

Music Genre Classifier is an AI-powered tool hosted on Hugging Face Spaces, designed to analyze and classify the genre of music tracks. Users can upload short MP3 files, ideally under 15 seconds, and choose from various pre-trained models. The tool processes the audio by converting it into visual spectrograms, which are then fed into a neural network for analysis. It provides the most likely genre classification, making it useful for music analysis, data labeling, and potentially for building music recommendation systems. This web-based application offers a straightforward interface for quick genre identification.

Embedded-Neural-Network is a comprehensive collection of research papers and tutorials focused on optimizing deep neural networks for embedded applications. The repository curates works aimed at reducing model sizes and developing specialized ASIC/FPGA accelerators for machine learning. It covers various techniques including network compression, parameter sharing, teacher-student mechanisms (distilling), fixed-precision training, sparsity regularizers & pruning, tensor decomposition, and conditional (adaptive) computing. Additionally, it provides resources on hardware accelerator benchmarks and platform analysis, with a specific focus on Recurrent Neural Networks and Convolutional Neural Networks. This collection is an invaluable resource for researchers and engineers working on efficient deployment of AI models.

AI4Culture is a platform designed to support cultural heritage institutions by offering a suite of AI-powered tools. These tools facilitate various tasks, including multilingual text recognition, which helps in digitizing and understanding diverse textual content. The platform also provides subtitle generation capabilities, making audio-visual cultural assets more accessible. Furthermore, it offers image enrichment features and machine translation services, aiming to improve the discoverability and reusability of cultural content. The overarching goal of AI4Culture is to foster data sharing and integration within the European Data Space for Cultural Heritage, enabling institutions to leverage AI for better preservation and dissemination of their collections.

The Multi-agent Deep-research System is an AI-powered tool designed to streamline the research process by generating comprehensive reports. It leverages multiple AI agents to perform web searches, gather relevant information, and analyze the collected data. Users initiate the process by providing a research question, and the system then autonomously conducts the necessary steps to produce a detailed report. This tool is particularly useful for anyone needing to quickly synthesize information from various online sources and gain deep insights into a specific topic, requiring API keys for web search and other functionalities.

HEBO is an open-source library developed by Huawei Noah's Ark Lab, focusing on Bayesian optimization, reinforcement learning, and generative model research. It offers official implementations for a wide range of algorithms, including Heteroscedastic Evolutionary Bayesian Optimisation (HEBO), a framework for Combinatorial and Mixed-variable Bayesian Optimization (MCBO), and End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes (NAP). The library also covers high-dimensional Bayesian optimization with random decompositions (RDUCB) and applications in antibody design (AntBO) and logic synthesis (BOiLS). Additionally, HEBO supports research in reinforcement learning, such as enhancing agents with local guides and safe reinforcement learning, and generative models like EM-LLM for episodic memory in LLMs. It serves as a comprehensive resource for researchers and developers in these advanced AI fields.

Hedwig is an open-source repository offering PyTorch deep learning models specifically designed for document classification tasks. Developed by the Data Systems Group at the University of Waterloo, it includes implementations of several prominent models such as DocBERT, Reg-LSTM, XML-CNN, HAN, Char-CNN, and Kim CNN. Each model directory contains a detailed README.md for further information. The project is designed for Python 3.6 and PyTorch 0.4, with clear instructions for environment setup using Anaconda and installation of dependencies. It also provides options for downloading necessary datasets like Reuters, AAPD, and IMDB, along with word2vec embeddings, making it a comprehensive resource for document classification research and application.

How-to-learn-Deep-Learning offers a comprehensive, practical, and top-down guide for individuals looking to master AI, Deep Learning, and Machine Learning. The resource emphasizes a hands-on approach, starting with high-level frameworks and progressing to more complex concepts. It outlines a structured learning path, including familiarization with tools like Python and Jupyter notebooks, workflow development from data acquisition to model deployment, and building an intuitive understanding of deep learning models. A significant portion of the guide is dedicated to portfolio building, offering strategies and scoring metrics for creating impactful projects that appeal to potential employers in Machine Learning Engineering, Applied Machine Learning Research, and Research Scientist roles. It also provides a curriculum for understanding deep learning theory, recommending key books and resources for a well-rounded education.

Hunyuan-A13B is an innovative and open-source large language model (LLM) developed by Tencent Hunyuan, featuring a fine-grained Mixture-of-Experts (MoE) architecture. With 80 billion total parameters and only 13 billion active parameters, it delivers high performance while maintaining optimal resource efficiency. Key features include hybrid reasoning support with both fast and slow thinking modes, ultra-long context understanding up to 256K tokens, and enhanced agent capabilities. The model is optimized for efficient inference using Grouped Query Attention (GQA) and supports multiple quantization formats like FP8 and INT4, making it suitable for resource-constrained environments. It is ideal for researchers and developers seeking powerful yet computationally efficient AI solutions.

Heretic is an open-source tool designed for the fully automatic removal of censorship, also known as "safety alignment," from transformer-based language models. It achieves this without requiring expensive post-training processes, utilizing an advanced implementation of directional ablation combined with a TPE-based parameter optimizer powered by Optuna. This approach allows Heretic to automatically find high-quality ablation parameters by co-minimizing refusal rates and KL divergence from the original model, ensuring the decensored model retains as much original intelligence as possible. The tool supports most dense and many multimodal models, including various MoE architectures. It also offers research features for interpretability studies, such as plotting residual vectors and printing residual geometry details.

The Hong Kong Centre for Logistics Robotics (HKCLR) is an InnoCentre established in May 2020 by The Chinese University of Hong Kong (CUHK). Its core mission is to advance robotics and AI technologies with direct applications in the logistics industry, a critical economic pillar for Hong Kong. HKCLR addresses the challenges faced by Hong Kong as a major logistics hub through its research and development efforts. The center's research topics include component technologies like robust 3D imaging sensors and versatile soft robot hands, embodied AI focusing on vision foundation models and AI for robot manipulation, and integrated robot systems such as next-generation collaborative arms and high-precision self-driving logistics vehicles.

gym-pybullet-drones offers PyBullet Gymnasium environments specifically designed for single and multi-agent reinforcement learning in quadcopter control. This tool is a minimalist refactoring of its original repository, ensuring compatibility with Gymnasium, Stable-Baselines3 2.0, and Betaflight/Crazyflie-firmware SITL. It provides examples for PID control, downwash effect simulation, and reinforcement learning using SB3's PPO algorithm. Researchers and developers can use this environment to train and test control policies for drones, facilitating advancements in robotics and autonomous systems. The project also includes examples for integrating with Betaflight SITL and pycffirmware Python bindings.

ir-sim is an open-source, Python-based lightweight robot simulator specifically designed for navigation, control, and learning applications. It offers a simple and user-friendly framework that includes built-in collision detection, making it ideal for academic and educational use. The simulator allows for rapid prototyping of robotics and learning algorithms in custom scenarios with minimal coding and hardware requirements. Key features include the ability to simulate various robot platforms with diverse kinematics and sensors, quick scenario configuration using straightforward YAML files, and visualization of simulation outcomes with a naive visualizer for immediate debugging. It also supports multi-agent/robot learning projects.

The Cnr-Istituto di Linguistica Computazionale “Antonio Zampolli” is a research institute under the Consiglio Nazionale delle Ricerche (CNR) dedicated to computational linguistics. Its core activities encompass technology transfer and specialized training within strategic areas of computational linguistics. Key research domains include digital humanities, natural language processing (NLP), and the development of language resources. The institute contributes to scientific advancements through various projects, international collaborations, and public engagement initiatives, as evidenced by its participation in events like the International Book Fair and its contributions to climate change research methodologies.

DEEPNOID is an AI research company dedicated to improving quality of life by leveraging artificial intelligence technology. The company develops solutions across two main business areas: Medical AI and Industrial AI. In Medical AI, DEEPNOID offers DEEP:NEURO, an MRA-based AI solution for aneurysm detection and diagnosis assistance, and DEEP:CHEST, a CXR-based AI solution for multi-lung disease detection and diagnosis assistance. For Industrial AI, it provides SkyMARU:SECURITY and DEEP:SECURITY, both AI-powered automated X-ray screening solutions designed to enhance aviation and enterprise security, respectively. DEEPNOID aims to make life 'Wider, Bolder, and Clearer' through its innovative AI applications.

knowledge-distillation-papers is a GitHub repository dedicated to cataloging academic papers on knowledge distillation. It provides a structured collection of research, ranging from early foundational works on model compression and knowledge acquisition to more recent advancements in areas like adversarial distillation, self-distillation, and data-free knowledge transfer. The repository is organized chronologically and by specific techniques, making it easy for users to navigate and find relevant literature. It's an essential resource for anyone looking to understand the theoretical underpinnings and practical applications of knowledge distillation in deep learning.

Qwen3-TTS-Daggr-UI is an AI tool designed for advanced voice manipulation, offering capabilities for custom voice creation, voice design, and voice cloning. It integrates ASR (Automatic Speech Recognition) nodes to enhance its voice processing features. A unique aspect of this tool is its ability to generate interactive directed acyclic graphs (DAGs) from uploaded CSV or JSON files, which define nodes and their connections. Users can explore, zoom, rearrange, and export these graphs, making it suitable for researchers, AI enthusiasts, and voice designers who need to visualize and manage complex voice models and workflows. The tool runs on Hugging Face Spaces, indicating accessibility and a focus on community and open-source principles.

Lighting-the-Darkness-in-the-Deep-Learning-Era-Open is an open-source project offering a comprehensive platform and resources for low-light image and video enhancement (LLIE) using deep learning. It features LLIE-Platform, a user-friendly web interface covering 14 popular deep learning-based LLIE methods like Zero-DCE++ and EnlightenGAN, allowing users to produce enhancement results. The project also provides the LLIV-Phone dataset, containing 120 videos (45,148 images) captured by various phone cameras under diverse illumination conditions. Additionally, it collects and categorizes numerous deep learning-based LLIE methods, datasets, and evaluation metrics, making it a valuable resource for researchers and developers in the field.

LLaVA-Med is a Large Language-and-Vision Assistant for Biomedicine, developed by Microsoft, that aims to achieve multimodal GPT-4 level capabilities in the biomedical domain. It leverages visual instruction tuning and is continuously trained using a curriculum learning approach, starting with general-domain LLaVA and then specializing in biomedical concept alignment and instruction-tuning. The tool is open-sourced under the MSR release policy and is intended for research use only, specifically for advancing visual-language processing and visual question answering in biomedicine. It is expressly prohibited for use in clinical care or for any clinical decision-making purposes. LLaVA-Med is built upon the PMC-15M dataset, which comprises 15 million figure-caption pairs from biomedical research articles, covering diverse image types like microscopy, radiography, and histology.

Long-Context is an open-source repository from Abacus.AI designed to provide code and tooling for Large Language Model (LLM) context expansion. It offers a comprehensive suite of evaluation scripts and benchmark tasks specifically tailored to assess a model’s information retrieval capabilities within expanded contexts. The repository details various experimental results, including different positional encoding schemes like linear scaling and fine-tuning approaches, and provides instructions for reproducing and building upon these findings. It also shares weights for best-performing models, such as the scale 16 model, which is expected to perform well up to 16k context lengths. The project includes novel evaluation datasets like an extended LMSys dataset and WikiQA (Free Form QA and Altered Numeric QA) to rigorously test models across varying context lengths and answer locations, addressing potential issues like models answering from pre-trained knowledge rather than provided context.

Arxiv Digest is an AI research tool hosted on Hugging Face Spaces, developed by AutoLLM. It is specifically designed to summarize research papers found on Arxiv, making it easier for users to quickly understand the core content of academic articles. Built with Gradio, the tool aims to streamline the research process for academics, students, and other researchers by providing concise summaries. While the current live website indicates a runtime error, the tool's intent is to offer an accessible way to digest complex scientific literature, enhancing efficiency in academic pursuits.