Stars Interwoven: A Cross-Cultural Study of Machine Imagination and Computational Aesthetics
Source of Publication
Proceedings of the 31st International Symposium on Electronic/Emerging Art (ISEA2026)
Conference Year
2026
Abstract
This study examines the production process of the artwork Stars Interwoven and explores whether generative artificial intelligence can translate cross-cultural textual references to the cosmos into coherent visual experience. Unlike prompt-driven creation workflows, this project develops a curated corpus of “star-related texts” drawn from twelve cultural contexts—poems, prayers, lullabies, folk songs, and mythic fragments in which the star is central. Through a process of AI-assisted selection and multimodal generation, we observe how the model interprets and transforms language carrying cultural memory into visual form, identifying patterns of misreading, recompositing, poetic inference, and latent bias. The work is not only concerned with the generated images themselves, but also treats the act of generation as a research site to examine how machines reorganize mythology, metaphor, and symbolic imagination. Through a small-scale cross-cultural artistic experiment, this project proposes a possible perspective for understanding machine imagination, cultural abstraction, and algorithmic tendencies in contemporary creative practice.
Document Type
Conference Proceeding
Publication Date
11-6-2026
Recommended Citation
Li, Yuelu; Xu, Ting; Liu, Siyuan; He, Minghao; and Yip, David Kei Man, "Stars Interwoven: A Cross-Cultural Study of Machine Imagination and Computational Aesthetics" (2026). ISEA 2026 Proceedings. 41.
https://zuscholars.zu.ac.ae/isea2026/41