TabPFN for Zero-shot Parametric Engineering Design Generation

TL;DR

This paper introduces a zero-shot, data-efficient generative framework for engineering design based on TabPFN, capable of producing diverse, high-performance designs without task-specific training, thus enhancing practical engineering workflows.

Contribution

The paper presents a novel zero-shot parametric design generation method using TabPFN, eliminating the need for training on specific datasets and enabling flexible, efficient design synthesis.

Findings

Achieves less than 2% performance error in ship hull design

Demonstrates robustness across different design datasets and parameters

Reduces computational and data requirements compared to diffusion models

Abstract

Deep generative models for engineering design often require substantial computational cost, large training datasets, and extensive retraining when design requirements or datasets change, limiting their applicability in real-world engineering design workflow. In this work, we propose a zero-shot generation framework for parametric engineering design based on TabPFN, enabling conditional design generation using only a limited number of reference samples and without any task-specific model training or fine-tuning. The proposed method generates design parameters sequentially conditioned on target performance indicators, providing a flexible alternative to conventional generative models. The effectiveness of the proposed approach is evaluated on three engineering design datasets, i.e., ship hull design, BlendedNet aircraft, and UIUC airfoil. Experimental results demonstrate that the proposed method achieves competitive diversity across highly structured parametric design spaces, remains robust to variations in sampling, resolution and parameter dimensionality of geometry generation, and achieves a low performance error (e.g., less than 2% in generated ship hull designs' performance). Compared with diffusion-based generative models, the proposed framework significantly reduces computational overhead and data requirements while preserving reliable generation performance. These results highlight the potential of zero-shot, data-efficient generation as a practical and efficient tool for engineering design, enabling rapid deployment, flexible adaptation to new design settings, and ease of integration into real-world engineering workflows.