Defining Foundation Models for Computational Science: A Call for Clarity and Rigor
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909628964536320 |
|---|---|
| author | Choi, Youngsoo Cheung, Siu Wun Kim, Youngkyu Tsai, Ping-Hsuan Diaz, Alejandro N. Zanardi, Ivan Chung, Seung Whan Copeland, Dylan Matthew Kendrick, Coleman Anderson, William Iliescu, Traian Heinkenschloss, Matthias |
| author_facet | Choi, Youngsoo Cheung, Siu Wun Kim, Youngkyu Tsai, Ping-Hsuan Diaz, Alejandro N. Zanardi, Ivan Chung, Seung Whan Copeland, Dylan Matthew Kendrick, Coleman Anderson, William Iliescu, Traian Heinkenschloss, Matthias |
| contents | The widespread success of foundation models in natural language processing and computer vision has inspired researchers to extend the concept to scientific machine learning and computational science. However, this position paper argues that as the term "foundation model" is an evolving concept, its application in computational science is increasingly used without a universally accepted definition, potentially creating confusion and diluting its precise scientific meaning. In this paper, we address this gap by proposing a formal definition of foundation models in computational science, grounded in the core values of generality, reusability, and scalability. We articulate a set of essential and desirable characteristics that such models must exhibit, drawing parallels with traditional foundational methods, like the finite element and finite volume methods. Furthermore, we introduce the Data-Driven Finite Element Method (DD-FEM), a framework that fuses the modular structure of classical FEM with the representational power of data-driven learning. We demonstrate how DD-FEM addresses many of the key challenges in realizing foundation models for computational science, including scalability, adaptability, and physics consistency. By bridging traditional numerical methods with modern AI paradigms, this work provides a rigorous foundation for evaluating and developing novel approaches toward future foundation models in computational science. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_22904 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Defining Foundation Models for Computational Science: A Call for Clarity and Rigor Choi, Youngsoo Cheung, Siu Wun Kim, Youngkyu Tsai, Ping-Hsuan Diaz, Alejandro N. Zanardi, Ivan Chung, Seung Whan Copeland, Dylan Matthew Kendrick, Coleman Anderson, William Iliescu, Traian Heinkenschloss, Matthias Machine Learning Artificial Intelligence Numerical Analysis The widespread success of foundation models in natural language processing and computer vision has inspired researchers to extend the concept to scientific machine learning and computational science. However, this position paper argues that as the term "foundation model" is an evolving concept, its application in computational science is increasingly used without a universally accepted definition, potentially creating confusion and diluting its precise scientific meaning. In this paper, we address this gap by proposing a formal definition of foundation models in computational science, grounded in the core values of generality, reusability, and scalability. We articulate a set of essential and desirable characteristics that such models must exhibit, drawing parallels with traditional foundational methods, like the finite element and finite volume methods. Furthermore, we introduce the Data-Driven Finite Element Method (DD-FEM), a framework that fuses the modular structure of classical FEM with the representational power of data-driven learning. We demonstrate how DD-FEM addresses many of the key challenges in realizing foundation models for computational science, including scalability, adaptability, and physics consistency. By bridging traditional numerical methods with modern AI paradigms, this work provides a rigorous foundation for evaluating and developing novel approaches toward future foundation models in computational science. |
| title | Defining Foundation Models for Computational Science: A Call for Clarity and Rigor |
| topic | Machine Learning Artificial Intelligence Numerical Analysis |
| url | https://arxiv.org/abs/2505.22904 |