GLUE: Coordinating Pre-Trained Generative Models for System-Level Design

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Aebersold, Tim, Massoudi, Soheyl, Fuge, Mark D.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915921112596480
author Aebersold, Tim
Massoudi, Soheyl
Fuge, Mark D.
author_facet Aebersold, Tim
Massoudi, Soheyl
Fuge, Mark D.
contents Engineering complex systems (aircraft, buildings, vehicles) requires coordinating geometric and performance couplings across subsystems. As generative models proliferate for specialized domains, a key research gap is how to coordinate frozen, pre-trained submodels to generate full-system designs that are feasible, diverse, and high-performing. We introduce GLUE, which orchestrates pre-trained, frozen generators while enforcing system-level feasibility, optimality, and diversity. Compatible models must be end-to-end differentiable with a smooth, well-behaved latent-to-output mapping. We propose and benchmark (i) data-driven GLUE models trained on pre-generated system-level designs and (ii) a data-free GLUE model trained on a differentiable geometry layer. On a UAV design problem with five coupling constraints, we find that data-driven approaches yield diverse, high-performing designs but require large datasets to satisfy constraints reliably. The data-free approach is competitive with Bayesian optimization and gradient-based optimization in performance and feasibility while training a full generative model in only ~10 min on an RTX 4090 GPU, requiring more than two orders of magnitude fewer geometry evaluations and FLOPs than the data-driven method. We identify equality constraint satisfaction as a key difficulty and remaining limitation, and ablate approaches that improve this for the data-free approach. As a first step toward scaling generative design to complex, real-world engineering systems, this work explores how unmodified, domain-informed submodels can be integrated into a modular generative workflow.
format Preprint
id arxiv_https___arxiv_org_abs_2512_19469
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GLUE: Coordinating Pre-Trained Generative Models for System-Level Design
Aebersold, Tim
Massoudi, Soheyl
Fuge, Mark D.
Computational Engineering, Finance, and Science
Machine Learning
Engineering complex systems (aircraft, buildings, vehicles) requires coordinating geometric and performance couplings across subsystems. As generative models proliferate for specialized domains, a key research gap is how to coordinate frozen, pre-trained submodels to generate full-system designs that are feasible, diverse, and high-performing. We introduce GLUE, which orchestrates pre-trained, frozen generators while enforcing system-level feasibility, optimality, and diversity. Compatible models must be end-to-end differentiable with a smooth, well-behaved latent-to-output mapping. We propose and benchmark (i) data-driven GLUE models trained on pre-generated system-level designs and (ii) a data-free GLUE model trained on a differentiable geometry layer. On a UAV design problem with five coupling constraints, we find that data-driven approaches yield diverse, high-performing designs but require large datasets to satisfy constraints reliably. The data-free approach is competitive with Bayesian optimization and gradient-based optimization in performance and feasibility while training a full generative model in only ~10 min on an RTX 4090 GPU, requiring more than two orders of magnitude fewer geometry evaluations and FLOPs than the data-driven method. We identify equality constraint satisfaction as a key difficulty and remaining limitation, and ablate approaches that improve this for the data-free approach. As a first step toward scaling generative design to complex, real-world engineering systems, this work explores how unmodified, domain-informed submodels can be integrated into a modular generative workflow.
title GLUE: Coordinating Pre-Trained Generative Models for System-Level Design
topic Computational Engineering, Finance, and Science
Machine Learning
url https://arxiv.org/abs/2512.19469