MetaGen: A DSL, Database, and Benchmark for VLM-Assisted Metamaterial Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Makatura, Liane, Jones, Benjamin, Bian, Siyuan, Matusik, Wojciech
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911119607595008
author Makatura, Liane
Jones, Benjamin
Bian, Siyuan
Matusik, Wojciech
author_facet Makatura, Liane
Jones, Benjamin
Bian, Siyuan
Matusik, Wojciech
contents Metamaterials are micro-architected structures whose geometry imparts highly tunable-often counter-intuitive-bulk properties. Yet their design is difficult because of geometric complexity and a non-trivial mapping from architecture to behaviour. We address these challenges with three complementary contributions. (i) MetaDSL: a compact, semantically rich domain-specific language that captures diverse metamaterial designs in a form that is both human-readable and machine-parsable. (ii) MetaDB: a curated repository of more than 150,000 parameterized MetaDSL programs together with their derivatives-three-dimensional geometry, multi-view renderings, and simulated elastic properties. (iii) MetaBench: benchmark suites that test three core capabilities of vision-language metamaterial assistants-structure reconstruction, property-driven inverse design, and performance prediction. We establish baselines by fine-tuning state-of-the-art vision-language models and deploy an omni-model within an interactive, CAD-like interface. Case studies show that our framework provides a strong first step toward integrated design and understanding of structure-representation-property relationships.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17568
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MetaGen: A DSL, Database, and Benchmark for VLM-Assisted Metamaterial Generation
Makatura, Liane
Jones, Benjamin
Bian, Siyuan
Matusik, Wojciech
Computer Vision and Pattern Recognition
Artificial Intelligence
Computational Engineering, Finance, and Science
Machine Learning
Programming Languages
Metamaterials are micro-architected structures whose geometry imparts highly tunable-often counter-intuitive-bulk properties. Yet their design is difficult because of geometric complexity and a non-trivial mapping from architecture to behaviour. We address these challenges with three complementary contributions. (i) MetaDSL: a compact, semantically rich domain-specific language that captures diverse metamaterial designs in a form that is both human-readable and machine-parsable. (ii) MetaDB: a curated repository of more than 150,000 parameterized MetaDSL programs together with their derivatives-three-dimensional geometry, multi-view renderings, and simulated elastic properties. (iii) MetaBench: benchmark suites that test three core capabilities of vision-language metamaterial assistants-structure reconstruction, property-driven inverse design, and performance prediction. We establish baselines by fine-tuning state-of-the-art vision-language models and deploy an omni-model within an interactive, CAD-like interface. Case studies show that our framework provides a strong first step toward integrated design and understanding of structure-representation-property relationships.
title MetaGen: A DSL, Database, and Benchmark for VLM-Assisted Metamaterial Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computational Engineering, Finance, and Science
Machine Learning
Programming Languages
url https://arxiv.org/abs/2508.17568