Salvato in:
Dettagli Bibliografici
Autori principali: Cao, Nan, Qi, Xiaoyu, Chen, Chuer, Yan, Xiaoke
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.18455
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916806576308224
author Cao, Nan
Qi, Xiaoyu
Chen, Chuer
Yan, Xiaoke
author_facet Cao, Nan
Qi, Xiaoyu
Chen, Chuer
Yan, Xiaoke
contents We introduce CODS (Computational Optimization in Design Space), a theoretical model that frames computational design as a constrained optimization problem over a structured, multi-dimensional design space. Unlike existing methods that rely on handcrafted heuristics or domain-specific rules, CODS provides a generalizable and interpretable framework that supports diverse design tasks. Given a user requirement and a well-defined design space, CODS automatically derives soft and hard constraints using large language models through a structured prompt engineering pipeline. These constraints guide the optimization process to generate design solutions that are coherent, expressive, and aligned with user intent. We validate our approach across two domains-visualization design and knitwear generation-demonstrating superior performance in design quality, intent alignment, and user preference compared to existing LLM-based methods. CODS offers a unified foundation for scalable, controllable, and AI-powered design automation.
format Preprint
id arxiv_https___arxiv_org_abs_2506_18455
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CODS : A Theoretical Model for Computational Design Based on Design Space
Cao, Nan
Qi, Xiaoyu
Chen, Chuer
Yan, Xiaoke
Human-Computer Interaction
We introduce CODS (Computational Optimization in Design Space), a theoretical model that frames computational design as a constrained optimization problem over a structured, multi-dimensional design space. Unlike existing methods that rely on handcrafted heuristics or domain-specific rules, CODS provides a generalizable and interpretable framework that supports diverse design tasks. Given a user requirement and a well-defined design space, CODS automatically derives soft and hard constraints using large language models through a structured prompt engineering pipeline. These constraints guide the optimization process to generate design solutions that are coherent, expressive, and aligned with user intent. We validate our approach across two domains-visualization design and knitwear generation-demonstrating superior performance in design quality, intent alignment, and user preference compared to existing LLM-based methods. CODS offers a unified foundation for scalable, controllable, and AI-powered design automation.
title CODS : A Theoretical Model for Computational Design Based on Design Space
topic Human-Computer Interaction
url https://arxiv.org/abs/2506.18455