Generative AI for material design: A mechanics perspective from burgers to matter

2026-04-03

AI Summary

This work addresses the limited applicability of generative AI in computational mechanics due to its lack of interpretability. Bridging diffusion-based generative models with principles from mechanics, the study proposes a physically interpretable generative design framework. It begins by constructing an analytically tractable benchmark using low-dimensional hamburger recipes, then extends to high-dimensional material design spaces through discrete and continuous diffusion models, Bayesian inversion, and neural network–based inverse dynamics modeling. Trained on 2,260 recipes, the framework generates over one million candidate designs and successfully produces five novel hamburger formulations. In sensory evaluations involving one hundred participants, three of these outperformed the classic Big Mac in overall rating, demonstrating the framework’s practical efficacy and physical grounding.

Abstract

Generative artificial intelligence offers a new paradigm to design matter in high-dimensional spaces. However, its underlying mechanisms remain difficult to interpret and limit adoption in computational mechanics. This gap is striking because its core tools-diffusion, stochastic differential equations, and inverse problems-are fundamental to the mechanics of materials. Here we show that diffusion-based generative AI and computational mechanics are rooted in the same principles. We illustrate this connection using a three-ingredient burger as a minimal benchmark for material design in a low-dimensional space, where both forward and reverse diffusion admit analytical solutions: Markov chains with Bayesian inversion in the discrete case and the Ornstein-Uhlenbeck process with score-based reversal in the continuous case. We extend this framework to a high-dimensional design space with 146 ingredients and 8.9x10^43 possible configurations, where analytical solutions become intractable. We therefore learn the discrete and continuous reverse processes using neural network models that infer inverse dynamics from data. We train the models on only 2,260 recipes and generate one million samples that capture the statistical structure of the data, including ingredient prevalence and quantitative composition. We further generate five new burgers and validate them in a restaurant-based sensory study with 100 participants, where three of the AI-designed burgers outperform the classical Big Mac in overall liking, flavor, and texture. These results establish diffusion-based generative modeling as a physically grounded approach to design in high-dimensional spaces. They position generative AI as a natural extension of computational mechanics, with applications from burgers to matter, and establish a path toward data-driven, physics-informed generative design.

Problem

• generative AI
• material design
• computational mechanics
• diffusion models
• high-dimensional design

Innovation

• diffusion-based generative AI
• computational mechanics
• inverse problems
• physics-informed design
• high-dimensional material design