The paper defines foundation models for computational science and presents DD-FEM, a local-to-global data-driven framework inspired by finite elements, as a candidate path to meet that definition.
Towards foundation models for scientific machine learning: Characterizing scaling and transfer behavior
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Defining Foundation Models for Computational Science: A Call for Clarity and Rigor
The paper defines foundation models for computational science and presents DD-FEM, a local-to-global data-driven framework inspired by finite elements, as a candidate path to meet that definition.