Overview

Introduction to the Educational Omics six-dimension framework and the Uedu platform. Hands-on experience with ClassroomGPT AI tutor, and interactive exploration of how PALM integrates wearable physiological data into AI tutoring.

Topics

The Educational Omics Framework

Educational Omics draws an analogy from biological omics, conceptualizing education as a complex system that requires multi-dimensional data integration. The framework encompasses six dimensions:

Hands-on: ClassroomGPT AI Tutor

ClassroomGPT is the core feature of Uedu Core, providing an LLM-powered conversational AI tutor for every classroom. Instructors can customize the System Prompt to define the AI's teaching style and behavioral guidelines. The AI tutor uses Socratic questioning to guide students' thinking rather than directly providing answers.

In this hands-on session, participants interact with ClassroomGPT on their own laptops, exploring Socratic dialogue and AI-powered quiz generation, and understanding how conversation trajectories generate Cognomics and Linguomics data.

PALM Live Demo: Physiological-Aware Language Model

PALM (Physiological-Aware Language Model) is the core concept of Uedu Mind. It augments LLM system prompts with real-time physiological data from wearable devices, enabling the AI tutor to adapt its teaching strategies based on learners' physiological states.

In this interactive demo, audience-driven scenarios let participants manipulate physiological input parameters and observe in real time how the AI tutor adjusts its response strategies.

When a learner's stress is elevated or sleep quality is poor, PALM reduces cognitive load—simplifying explanations and suggesting breaks. When the learner is in a good state, PALM can present more challenging, in-depth questions.

Related Research

• Chang & Li (2025). Designing an Educational Omics Data Lake: A Multimodal Infrastructure for Technology-Enhanced Learning. ICMET.
• Chang & Chien (2024). Enhancing Academic Performance with Generative AI-Based Quiz Platform. IEEE ICALT.
• Chen et al. (2025). Leveraging Knowledge Graphs and Large Language Models to Track and Analyze Learning Trajectories. LAK25.
• Yen et al. (2025). Analysis of a Generative AI-Based Graphical Learning Assistance Tool in IPR Courses. IEEE ICALT.
• Furqon & Chang (2025). Evaluating Cognitive Performance Through Prompt-Based Methods Using LLM in Education. IEEE ICALT.
• D'Mello & Graesser (2012). AutoTutor and Affective AutoTutor. ACM TIIS.
• Kasneci et al. (2023). ChatGPT for Good? On Opportunities and Challenges of Large Language Models for Education. LID.

Materials