IdeaBlocks modularizes divergent intents into Exploration Blocks with multi-level reuse options, enabling 2.13 times more images explored and 12.5% greater visual diversity than baseline in a comparative user study.
InProceedings of the 30th International Conference on Intelligent User Interfaces (IUI ’25)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.HC 4verdicts
UNVERDICTED 4representative citing papers
Adaptive Prompt Elicitation (APE) uses an information-theoretic framework to generate visual queries that elicit and compile user intent into better prompts for text-to-image models, showing improved alignment in benchmarks and a user study.
A human-centered design workshop with journalism practitioners yields an evaluation cookbook and design requirements for contextualized, value-aligned generative AI benchmarks.
A Privacy Guardian Agent automates routine consent choices with user profiles and contextual awareness, escalating unclear or high-risk cases to users while keeping autonomous decisions reviewable for transparency.
citing papers explorer
-
IdeaBlocks: Expressing and Reusing Divergent Intents for Graphic Design Exploration using Generative AI
IdeaBlocks modularizes divergent intents into Exploration Blocks with multi-level reuse options, enabling 2.13 times more images explored and 12.5% greater visual diversity than baseline in a comparative user study.
-
Adaptive Prompt Elicitation for Text-to-Image Generation
Adaptive Prompt Elicitation (APE) uses an information-theoretic framework to generate visual queries that elicit and compile user intent into better prompts for text-to-image models, showing improved alignment in benchmarks and a user study.
-
Towards Real-World Validity in Generative AI Benchmarks: Understanding and Designing Domain-Centered Evaluations for Journalism Practitioners
A human-centered design workshop with journalism practitioners yields an evaluation cookbook and design requirements for contextualized, value-aligned generative AI benchmarks.
-
The Privacy Guardian Agent: Towards Trustworthy AI Privacy Agents
A Privacy Guardian Agent automates routine consent choices with user profiles and contextual awareness, escalating unclear or high-risk cases to users while keeping autonomous decisions reviewable for transparency.