Educational framework demonstrates enhanced creative modeling and iterative design in art curricula, highlighting utility for computational engineering workflows.
Key Points
Investigate how integrating AI technology through a human–AI collaborative framework enhances students' innovative modeling and design capabilities in art curricula.
Designed a four-stage human–AI collaborative model encompassing independent conceptualization, AI-assisted generation, critical evaluation, and iterative optimization.
Embedded contextualized design practice and a diversified evaluation system powered by AI feedback mechanisms to foster adaptive learning and student-centered interaction.
Integrated multimodal AI tools to connect visual information processing and digital modeling to computational engineering design applications.
The framework effectively balanced computational assistance with student originality and aesthetic judgment by avoiding passive automatic generation.
The approach qualitatively improved design efficiency, creative reasoning, and critical iterative refinement across the creative cycle.
The collaborative workflow provided translatable methodologies for computational design optimization and decision support in engineering domains like electromagnetic propagation.