Yongmin Kwon

F431, Faculty Building,

193, Munji-ro, Yuseong-gu,

Daejeon, Republic of Korea

I am a Ph.D. student at KAIST, advised by Prof. Namwoo Kang. My research asks how foundation models can be made useful for engineering design. Generative models now propose plausible forms in almost any modality, but an engineering design must also stay within its design domain, carry load, and remain manufacturable. Rather than retraining these models on more engineering data, I treat them as oracles to be queried under geometric and physical constraints, so that what they generate is engineering-valid, not just visually plausible.

I apply this idea across image, geometry, and language models, from guiding topology optimization with diffusion models to co-designing shape and mechanics with flow-matching samplers. Because none of this updates model weights, a new domain or objective only requires a new specification and set of constraints. See research for details.

I am also a co-founder of and AI researcher at Narnia Labs, where I work with global manufacturers on real-world design problems. That experience is why I focus on general formulations that transfer across industries, rather than solutions confined to a single domain or the lab. I completed a minor in Entrepreneurship at KAIST’s K-School and plan to stay actively involved in the startup ecosystem.

I received my M.S. from KAIST and my B.S. in Mechanical Engineering from Inha University, Korea.

latest updates

Oct 2026	Award Outstanding Student Research Award / 우수 학생연구상
Sep 2026	Publication Zero-Shot Rib Design: Merging Training-Free Generative Prior with Topology Optimization
Sep 2026	Award IPESK Next-Generation Engineering Researcher, 3rd Cohort / IPESK 차세대 공학연구자(3기)

selected publications

2026

Zero-Shot Rib Design: Merging Training-Free Generative Prior with Topology Optimization

Yongmin Kwon^*, and Namwoo Kang

Advanced Engineering Informatics (IF 11.5 · JCR Q1), 2026

Abs arXiv PDF Video

Natural load-bearing patterns such as leaf venation, trabecular bone, and spider webs achieve high stiffness per unit mass, yet classical topology optimizers rarely reach such geometries, and few let engineers express structural design intent through natural language. This work treats a frozen text-to-image diffusion model as a training-free source of design knowledge and distills it into the physics loop of density-based topology optimization via score distillation sampling, so that a text prompt becomes an explicit, machine-interpretable representation of engineer intent. The prompt-induced generative gradient and the finite element sensitivity are combined at every iteration, letting physics decide which prompt-induced features survive. In 245 primary SDS runs spanning four geometric domains and two physics regimes, 38 of 49 prompt–domain combinations achieved statistically significant compliance reductions (up to −31.5% mechanical and −23.0% thermoelastic), outperforming gradient-based baselines. Cross-domain morphological analysis identifies a recurring structural signature of improvement: in most domains the generative prior suppresses dead-end branches in the rib skeleton, with endpoint–compliance correlation r = +0.56 to +0.99. A Heaviside projection with β-continuation resolves a pronounced intermediate-density tendency in this diffusion–physics coupling (42.6% to < 3%), and an automated skeleton-based pipeline converts optimized density fields into candidate geometry ready for computer-aided design. By retargeting the generative prior across domains, loading conditions, and physics objectives through a change of text prompt, with each new problem’s physics setup specified separately, the framework uses a pretrained generative model as a reusable, training-free prior for engineering design.
Three-dimensional Geometric Augmentation Guided by Engineering Uncertainty

Yongmin Kwon^*, and Namwoo Kang

Engineering Applications of Artificial Intelligence (IF 8.92 · JCR Q1), 2026

Abs PDF

In the conceptual design stage, fast and accurate shape evaluation is crucial for efficient product development. This study proposes an integrated framework that combines geometry-based uncertainty quantification with free-form deformation augmentation. Uncertainty quantification is achieved using a deep ensemble model that incorporates a novel architecture comprising two regressors: an explicit lattice-based uncertainty regressor to quantify aleatoric uncertainty and a performance regressor to predict performance. The epistemic uncertainty extracted from this model is then leveraged to actively explore the regions effective for the practical training of a meta-model. Experimental results confirmed that the augmented datasets exhibit superior performance, demonstrating the framework’s robustness across diverse physical domains (structural mechanics and fluid dynamics) without requiring domain-specific modifications.

2025

Three-dimensional Deep Shape Optimization with a Limited Dataset

Yongmin Kwon^*, and Namwoo Kang

Engineering Applications of Artificial Intelligence (IF 8.92 · JCR Q1), 2025

Abs arXiv PDF

Generative models have attracted considerable attention for their ability to produce novel shapes. However, their application in mechanical design remains constrained due to the limited size and variability of available datasets. This study proposes a deep learning-based optimization framework specifically tailored for shape optimization with limited datasets, leveraging positional encoding and a Lipschitz regularization term to robustly learn geometric characteristics and maintain a meaningful latent space. Through extensive experiments, the proposed approach demonstrates robustness, generalizability and effectiveness in addressing typical limitations of conventional optimization frameworks. The validity of the methodology is confirmed through multi-objective shape optimization experiments conducted on diverse three-dimensional datasets, including wheels and cars, highlighting the model’s versatility in producing practical and high-quality design outcomes even under data-constrained conditions.

2024

DeepJEB: 3D Deep Learning-based Synthetic Jet Engine Bracket Dataset

Seongjun Hong^*, Yongmin Kwon^*, Dongju Shin, and 2 more authors

Journal of Mechanical Design (IF 3.96 · JCR Q1), 2024

Abs arXiv PDF

Recent advances in artificial intelligence (AI) have impacted various fields, including mechanical engineering. However, the development of diverse, high-quality datasets for structural analysis remains a challenge. Traditional datasets, like the jet engine bracket dataset, are limited by small sample sizes, hindering the creation of robust surrogate models. This study introduces the DeepJEB dataset, generated through deep generative models and automated simulation pipelines, to address these limitations. DeepJEB offers comprehensive 3D geometries and corresponding structural analysis data. Key experiments validated its effectiveness, showing significant improvements in surrogate model performance. Models trained on DeepJEB achieved up to a 23% increase in the coefficient of determination and over a 70% reduction in mean absolute percentage error (MAPE) compared to those trained on traditional datasets. These results underscore the superior generalization capabilities of DeepJEB. By supporting advanced modeling techniques, such as graph neural networks (GNNs) and convolutional neural networks (CNNs), DeepJEB enables more accurate predictions in structural performance. The DeepJEB dataset is publicly accessible at: this URL.
Deep Generative Design for Mass Production

Jihoon Kim^*, Yongmin Kwon^*, and Namwoo Kang

2024

Abs arXiv PDF

Generative Design (GD) has evolved as a transformative design approach, employing advanced algorithms and AI to create diverse and innovative solutions beyond traditional constraints. Despite its success, GD faces significant challenges regarding the manufacturability of complex designs, often necessitating extensive manual modifications due to limitations in standard manufacturing processes and the reliance on additive manufacturing, which is not ideal for mass production. Our research introduces an innovative framework addressing these manufacturability concerns by integrating constraints pertinent to die casting and injection molding into GD, through the utilization of 2D depth images. This method simplifies intricate 3D geometries into manufacturable profiles, removing unfeasible features such as non-manufacturable overhangs and allowing for the direct consideration of essential manufacturing aspects like thickness and rib design. Consequently, designs previously unsuitable for mass production are transformed into viable solutions. We further enhance this approach by adopting an advanced 2D generative model, which offer a more efficient alternative to traditional 3D shape generation methods. Our results substantiate the efficacy of this framework, demonstrating the production of innovative, and, importantly, manufacturable designs. This shift towards integrating practical manufacturing considerations into GD represents a pivotal advancement, transitioning from purely inspirational concepts to actionable, production-ready solutions. Our findings underscore usefulness and potential of GD for broader industry adoption, marking a significant step forward in aligning GD with the demands of manufacturing challenges.