About
June 2026 arXiv paper accepted at the AIED NextGen Learning Interfaces Workshop. It argues that adaptive education should use Generative UI at authoring time, not only at learner runtime, so instructors can verify accessible, modality-specific representations before students encounter them.
Summary
Why This Paper Adds New Signal:
1. Design-time GenUI lens: Moves generation upstream into curriculum authoring instead of only adapting delivery at runtime
2. Accessibility argument: Frames audio-first, simplified, interactive, and low-bandwidth interfaces as representations to verify before use
3. Semantic-card model: Proposes modality-agnostic units that can become multiple interface forms
4. Cost and quality concern: Explains why per-learner runtime inference can be too expensive and hard to validate
5. Collection fit: Complements MAIC-UI with a sharper learning-sciences argument for verified educational GenUI
1. Design-time GenUI lens: Moves generation upstream into curriculum authoring instead of only adapting delivery at runtime
2. Accessibility argument: Frames audio-first, simplified, interactive, and low-bandwidth interfaces as representations to verify before use
3. Semantic-card model: Proposes modality-agnostic units that can become multiple interface forms
4. Cost and quality concern: Explains why per-learner runtime inference can be too expensive and hard to validate
5. Collection fit: Complements MAIC-UI with a sharper learning-sciences argument for verified educational GenUI
Tags
educationdesign-timeaccessibilitygenui