A Human-Guided Generative Model Based on Diffusion Processes for Topology Optimization

Clicks: 13
ID: 316505
2026
Free PDF
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Steady

Ranked #11 of 31 articles by views in journal of computational design and engineering

Most read Least read

Bar heights use a square-root scale.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
Abstract Recent advances in denoising diffusion models have enabled the rapid generation of optimized structures for topology optimization. However, these machine-learning (ML) models often rely on surrogate predictors to enforce physical constraints, which may fail to capture subtle yet critical design flaws such as floating components or boundary discontinuities that are obvious to human experts. In this work, we propose a novel human-guided diffusion framework that steers the generative process using a lightweight reward model trained on minimal human feedback. Inspired by preference alignment techniques in generative modeling, our method learns to suppress unrealistic outputs by modulating the reverse diffusion trajectory using gradients of human-aligned rewards. Specifically, we collect binary human evaluations of generated topologies and train classifiers to detect floating material and boundary violations. These reward models are then integrated into the sampling loop of a pre-trained diffusion generator, guiding it to produce designs that are not only structurally performant but also physically plausible and manufacturable. Our approach is modular, does not require retraining the diffusion model, and can be readily integrated with existing ML-based topology optimization. The results show substantial reductions in failure modes and improved design realism across diverse test conditions. This work bridges the gap between AI-driven design generation and human experts’ judgments, offering a scalable solution to reliable generative design.
Reference Key
openalex_W7164006997 Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Eui Hyun Kim, Yeoneung Kim, Keun Park
Journal journal of computational design and engineering
Year 2026
DOI
10.1093/jcde/qwag055
URL
https://doi.org/10.1093/jcde/qwag055
Keywords Keywords not found

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.