Research & Education

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.

Augura Space delivers next-generation AI solutions for comprehensive space weather intelligence. Leveraging 3TB of daily space weather data, cutting-edge AI models, and advanced sensor fusion techniques, the platform provides historical analysis, real-time monitoring, and predictive forecasts. This intelligence is crucial for the aerospace, energy, and telecommunications sectors to enhance resilience, optimize operations, and secure critical infrastructure against space weather phenomena. Augura Space also offers custom expert consulting services and will feature sector-specific dashboards and seamless API integration.

This GitHub repository, Hands-On-Machine-Learning-for-Algorithmic-Trading, accompanies a book published by Packt. It offers a comprehensive collection of code examples and resources for individuals interested in applying machine learning techniques to algorithmic trading. The repository covers implementing various supervised, unsupervised, and reinforcement learning models, leveraging market, fundamental, and alternative data for alpha factor research, and optimizing portfolio risk and performance using Python libraries like pandas, NumPy, and scikit-learn. It also includes guidance on integrating machine learning models into live trading strategies. The content is structured into chapters, making it easy to follow along with the book's curriculum.

Hands-On-Machine-Learning-with-CPP is a comprehensive code repository accompanying a Packt publication, designed to guide users through implementing various machine learning and deep learning algorithms using C++. It covers fundamental to advanced concepts, offering practical, easy-to-follow examples. Users will learn to preprocess diverse data types, employ key machine learning algorithms with C++ libraries, and optimize models using grid-search. The repository also includes methods for anomaly detection, improving collaborative filtering, and managing model structures. It provides a C++ program for image classification tasks with LeNet architecture, making it suitable for data analysts, data scientists, and machine learning developers looking to implement models in production.

ClassMind is an AI workspace designed for teachers, students, schools, and districts to enhance teaching and accelerate learning. It offers over 40 AI tools specifically for educators, including planning tools for lesson and unit plans, assessment tools for quizzes and rubrics, and content generation tools for presentations and vocabulary lists. The platform also provides text processing tools like rewriters and summarizers, communication tools for professional emails, and feedback tools for report card comments. ClassMind supports major global curriculum frameworks and allows for content customization to align with specific standards and student needs, saving educators significant time on preparation and grading.

GraphRAG Local Ollama is an open-source adaptation of Microsoft's GraphRAG, designed to leverage local models via Ollama for LLM and embedding extraction. This tool eliminates the dependency on costly OpenAPI models, offering a cost-effective solution for knowledge graph implementations. It supports a variety of local models such as Llama3, Mistral, Gemma2, and Phi3, and integrates with Ollama for both language models and embedding models like nomic-embed-text. The setup process is straightforward, involving conda environment creation, Ollama installation, repository cloning, and specific `pip install` commands. Users can easily configure models and run indexing and querying operations, with options to visualize generated graphs using tools like Gephi or a provided Python script.

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.

h2o-tutorials is a comprehensive repository offering tutorials and training materials specifically designed for the H2O Machine Learning Platform. It serves as an invaluable resource for individuals looking to learn and understand the functionalities of H2O-3, covering a wide array of machine learning topics. The repository includes tutorials for both R and Python users, detailing subjects like H2O Grid Search & Model Selection, Deep Learning, Stacked Ensembles, and AutoML. It also provides historical event-specific training materials, ensuring users can access relevant content for different H2O releases. This platform is ideal for those seeking practical guidance and examples to effectively utilize the H2O Machine Learning Platform.

Particle Accelerator Simulation is an AI-powered tool available on Hugging Face, developed by the AI Coding Autonomous Agent MOUSE-I. This application provides a 3D environment where users can generate and interact with particles, set against a matrix rain background. Key functionalities include adjusting particle speed, energy, and power, as well as introducing additional particles or dark matter into the simulation. While the tool offers an engaging way to visualize and experiment with particle dynamics, it is currently paused on Hugging Face Spaces, requiring users to request a restart from the author to access its features.

Improved-diffusion is an open-source codebase developed by OpenAI for working with Improved Denoising Diffusion Probabilistic Models. This repository provides the necessary tools and scripts for researchers and developers to train and sample from these powerful generative AI models. Users can prepare their own image datasets, including options for class-conditional training by naming files with labels. The codebase supports various hyperparameters for model architecture, diffusion processes, and training flags, allowing for flexible experimentation. It also facilitates distributed training across multiple GPUs and offers different sampling strategies, including DDIM. Pre-trained model checkpoints and their corresponding hyperparameters are provided for several common tasks, such as unconditional ImageNet-64 and CIFAR-10 generation, class-conditional ImageNet-64, and LSUN bedroom models.

KAG is an open-source logical form-guided reasoning and retrieval framework built upon the OpenSPG engine and large language models (LLMs). It specializes in creating logical reasoning and factual Q&A solutions for professional domain knowledge bases, effectively addressing the limitations of traditional RAG vector similarity calculations and GraphRAG noise. KAG supports logical reasoning and multi-hop factual Q&A, offering superior performance compared to current state-of-the-art methods. Its core features include knowledge and chunk mutual indexing, conceptual semantic reasoning for knowledge alignment, schema-constrained knowledge construction, and logical form-guided hybrid reasoning and retrieval.

CT Read is an AI-powered tool designed to revolutionize medical imaging analysis, making complex interpretations accessible to non-medical users. It accurately interprets X-rays, CT scans, MRI, and ultrasound images, supporting both DICOM files and common formats like JPG and PNG. Users receive instant, accurate, and clear reports powered by AI, which include key findings, recommendations, and easy-to-understand summaries. The platform offers multi-modality analysis, advanced anomaly detection, and a user-friendly interface, allowing for comprehensive body analysis across various parts like the brain, chest, abdomen, and bones. It's ideal for individuals seeking to understand their medical images without medical jargon.

Physics Playground is an AI simulation tool created by an AI Coding Autonomous Agent named MOUSE. This Hugging Face Space allows users to explore and experiment with fundamental physics principles in a virtual environment. Users can set parameters such as mass and initial speed for various objects, then add these objects with a simple click to observe their motion. The app features adjustable gravity, air resistance, and elasticity, providing a dynamic platform for understanding how these forces influence object behavior. It is suitable for educational purposes, allowing students and enthusiasts to visualize physics concepts, and for AI coding experiments, offering a sandbox for testing simulations.

PhotoSolve is an AI-powered educational tool designed to help students efficiently complete assignments and understand complex topics. Users can scan questions from assignments, textbooks, or notes using the mobile app or browser extension, and PhotoSolve's AI provides accurate solutions and detailed explanations. Beyond direct problem-solving, the platform includes 'Tutoor.com' for personalized learning, allowing users to upload materials like notes, websites, and textbooks for AI analysis, summarization, and interactive Q&A. It also offers features like customizable quizzes, flashcard generation, and a homework solver that leverages multiple AI models for enhanced accuracy. PhotoSolve aims to improve academic performance by offering accessible, on-demand learning support.

IntroNeuralNetworks is an open-source Python project designed to introduce beginners to neural networks and demonstrate their application in stock price prediction. It guides users through the entire machine learning workflow, from data acquisition and preprocessing to model training and backtesting. The project includes implementations of Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM) models, explaining their relevance for time-series data like stock prices. While not intended for live trading, it serves as an educational template for understanding neural network fundamentals and can be extended for more sophisticated trading strategies. The project emphasizes the importance of data quality and provides a clear, step-by-step approach to building and evaluating predictive models.

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.

Isaac Lab is a GPU-accelerated, open-source framework designed to unify and simplify robotics research workflows, including reinforcement learning, imitation learning, and motion planning. Built on NVIDIA Isaac Sim, it combines fast and accurate physics and sensor simulation, making it an ideal choice for sim-to-real transfer in robotics. The framework provides developers with essential features for accurate sensor simulation, such as RTX-based cameras, LIDAR, and contact sensors. Its GPU acceleration enables faster complex simulations and computations, crucial for iterative processes like reinforcement learning. Isaac Lab supports over 16 robot models and more than 30 ready-to-train environments, compatible with popular reinforcement learning frameworks like RSL RL, SKRL, RL Games, and Stable Baselines. It can run locally or be distributed across the cloud, offering flexibility for large-scale deployments.

kg-gen is an AI tool designed for generating knowledge graphs from diverse text inputs. It can process both small and large texts, offering chunking capabilities for extensive documents, and effectively handles conversational messages while preserving role information and message order. The tool supports a wide range of API-based and local model providers through LiteLLM, including OpenAI, Ollama, Anthropic, and Gemini, and utilizes DSPy for structured output generation. Key features include clustering similar entities and relations, aggregating multiple graphs, and extracting relationships between concepts and speakers in conversations. It's ideal for creating graphs to assist with RAG, generating synthetic data, structuring text, and analyzing conceptual relationships.

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.

EduSignal is a K-12 district intelligence platform designed specifically for EdTech sales teams. It consolidates public education data, including enrollment trends, demographics, test scores, per-pupil spending, and accountability metrics, into instant, searchable district profiles. This eliminates the need for sales reps to spend time researching multiple sources, providing all necessary information in one place. The platform also features AI-powered sales analysis, generating personalized talking points and opportunity assessments based on specific products and district data. EduSignal aims to streamline the sales process by offering detailed district context and actionable insights, helping teams identify and engage with the most relevant school districts.

Panna Resume Builder is an AI-powered tool designed to help job seekers create professional and ATS-friendly resumes. It simplifies the resume creation process by allowing users to parse job descriptions, integrate relevant keywords, and apply ATS-friendly formatting. The platform also features an AI-powered rewriting capability to enhance resume content and offers instant job match analysis to help users tailor their applications effectively. This ensures resumes are optimized to pass initial screening and stand out to recruiters, increasing the chances of getting shortlisted for interviews.

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.