ConceptVIS: Generating and Exploring Design Concepts for Early-stage Ideation using Large Language Model

Abstract

This paper presents ConceptVIS, a system for generating and exploring design concepts in early-stage ideation using a large language model. The work investigates how LLMs can support idea generation and concept exploration at the beginning of the design process, where ambiguity and breadth are especially important. It contributes a human-AI ideation workflow that helps users expand and inspect possible design directions more effectively.

Publication
In ASME International Design Engineering Technical Conferences & Computers and Information in Engineering Conference (IDETC/CIE) 2024; collected in ASME Journal of Computing and Information Science in Engineering (JCISE)