Seyed Parsa Neshaei, Abhinand Shibu, Fatma Betül Güres (2026) — NextGen Learning Interfaces Workshop, AIED 2026 📄 Full text (arXiv)
Argues the dominant paradigm of runtime GenUI adaptation in EdTech is insufficient. Proposes design-time card-based GenUI where educational content is encoded as modality-agnostic semantic units and GenAI produces multiple interface representations (interactive, audio, simplified text, low-bandwidth) at design time for instructor verification. Embeds Universal Design for Learning into authoring workflow and eliminates per-learner inference costs.
Key Contributions
- Proposes design-time (not runtime) generative UI for EdTech to embed UDL principles and eliminate per-learner inference costs.
Related Pages
- ai-k12-evidence-base — Empirical evidence on AI in K-12 education outcomes
- intelligent-tutoring — Automated tutoring systems and their evaluation
- student-experience — Student perspectives on AI in education
- learning-analytics — Data-driven approaches to understanding learning
- llm-feedback-programming-classroom — LLM feedback in classroom settings
Citation
APA: Seyed Parsa Neshaei, Abhinand Shibu, Fatma Betül Güres (2026). The Missing Layer: Why EdTech Needs Design-Time Generative UI, Not Just Runtime Personalization. arXiv:2606.15902. NextGen Learning Interfaces Workshop, AIED 2026.