In-context modeling as a retrain-free paradigm for foundation models in computational science

TL;DR

In-Context Modeling (ICM) is a novel, retrain-free approach that enables foundation models to infer physical relationships directly from observational data, generalizing across systems without retraining.

Contribution

The paper introduces ICM, a physics-informed, retrain-free paradigm that generalizes physical modeling across systems using in-context inference and scaling behavior similar to foundation models.

Findings

ICM generalizes across unseen materials, geometries, and conditions.

Performance improves with more diverse data and higher computational resources.

ICM integrates with finite-element simulations and is validated with experimental data.

Abstract

Building models that generalize across physical systems without retraining remains a central challenge in computational science. Here we introduce In-Context Modeling (ICM), a retrain-free paradigm that infers physical relationships directly from observational fields. Rather than encoding system-specific behavior in fixed parameters, ICM assimilates measurements as physical context and performs inference through a single forward pass. Trained in a physics-informed, label-free manner using governing equations, a single model generalizes across unseen materials, geometries, and loading conditions. Demonstrated on hyperelasticity, ICM integrates with finite-element simulations and is validated using experimental full-field measurements. Moreover, performance improves with increasing data diversity and computational budget, exhibiting favorable scaling behavior analogous to foundation models. By recasting physical modeling as in-context inference, this work establishes a transferable paradigm for retrain-free scientific learning and a foundation for scalable modeling across computational science.