The article ‘Advancing GUI for Generative AI: Charting the Design Space of Human-AI Interactions through Task Creativity and Complexity’ by Zijian Ding, focuses on investigating human-AI interaction modalities across a range of tasks with differing levels of creativity and complexity. The study aims to contribute to the development of Graphical User Interfaces (GUIs) that effectively integrate with and enhance the capabilities of Generative AI systems. The research categorizes tasks into three levels: fixed-scope content curation tasks, atomic creative tasks, and complex tasks. The study explores a range of human-AI interaction methods to guide future GUI enhancements.
Publication date: 9 Jan 2024
Project Page: https://doi.org/10.1145/3581754.3584111
Paper: https://arxiv.org/pdf/2401.02494
