Acerca de
August 2026 HCI paper introducing information architecture as shared state for Generative UI. Maru captures how users partition, order, name, and prioritize information, turns those choices into persistent rules, and applies them across successive interface generations instead of rebuilding structure from each prompt.
Resumen
Why Maru Adds New Signal:
1. Persistent structural memory: Carries interface organization across generations rather than treating every prompt as a fresh layout request
2. Concrete design vocabulary: Maps partition, hierarchy, order, and vocabulary to specific UI-generation decisions
3. Interaction-derived preferences: Learns rules from both conversational instructions and direct interface actions
4. User-controlled alignment: Keeps the captured information architecture visible and editable instead of hiding it in model state
5. Study-backed finding: Reports that persistent IA maintained alignment over time while non-persistent generation degraded
1. Persistent structural memory: Carries interface organization across generations rather than treating every prompt as a fresh layout request
2. Concrete design vocabulary: Maps partition, hierarchy, order, and vocabulary to specific UI-generation decisions
3. Interaction-derived preferences: Learns rules from both conversational instructions and direct interface actions
4. User-controlled alignment: Keeps the captured information architecture visible and editable instead of hiding it in model state
5. Study-backed finding: Reports that persistent IA maintained alignment over time while non-persistent generation degraded
Etiquetas
generative-uiinformation-architecturepersonalizationpersistent-uihuman-in-the-loop