HeMAI 2026: Multimodal Interaction with Generative AI Health Applications
This workshop explores the potential of multimodal interaction for generative AI health applications. Healthcare is an inherently multimodal setting, combining language, speech, vision, gesture, physiological signals, and interactive visualizations, and one in which transparency, reliability, and trust are prerequisites for deployment. The workshop brings together researchers and practitioners from multimodal interaction, natural language processing, generative artificial intelligence, affective computing, human-computer interaction, and clinical practice to examine how generative and multimodal systems can support interactive, collaborative decision-making in clinical and patient-facing scenarios. Through paper presentations, invited talks, and posters, the workshop aims to identify shared methodological challenges, promote responsible design, and foster cross-disciplinary collaboration.
