Adv. Human–Computer Interaction

Information

Course Overview

This course explores the intersection of generative AI and Human-Computer Interaction, equipping researcher to design, critique, and ethically deploy text-to-image (T2I) and multimodal generative AI technologies. By 2025, generative AI has evolved from single-modality models to multimodal frameworks integrating text, images, audio, and video, reshaping how users interact with intelligent systems. Students bridge technical foundations with HCI principles — focusing on usability, human-AI collaboration, and societal impact.

Course Objectives

• Be able to:

  • Explain how diffusion models and text-image alignment (CLIP) work at a conceptual level

  • Compare the strengths/weaknesses of major T2I tools for design tasks

  • Apply prompt engineering techniques to generate usable outputs for design scenarios.

  • Design AI-augmented workflows and evaluate their efficacy.

  • Diagnose biases in T2I outputs and propose mitigation strategies.

  • Develop a functional prototype that integrates T2I into a user-facing application.

Reference Material

• Interaction Design: Beyond Human-Computer Interaction (6th ed.), by Yvonne Rogers, Helen Sharp & Jennifer Preece — Wiley, 2023

• The Design of Everyday Things, by Don Norman — Basic Books, 2013

• Artificial Intelligence in HCI — AI-HCI 2025 Conference Proceedings, Degen & Ntoa (eds.), Springer LNAI, 2025

• HCI International 2025 – Late Breaking Papers, Harris et al. (eds.), Springer LNCS, 2025

Lecture Note

• Advanced Human-Computer Interaction: Human-Centered Generative AI, Text-to-Image Systems, and Multimodal Interaction, by Mahmmoud Mahdi (Ch 1)

Important Course Notes

Class Sessions

• Saturday {3:00-4:00} PM

Office Hours

• Tuesday {13:30-15:30} [Office Room] @4321

Grading Criteria

• Paper - 30%

• Report - 20%

• Project - 40%

• Participation - 10%