AI RESEARCH

Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers

arXiv CS.AI

ArXi:2605.25949v1 Announce Type: cross Neural PDE solvers have followed the scaling trajectory of vision and language, with recent foundation models reaching billions of parameters. We argue that scale is a poor substitute for architectural inductive bias in this domain: structured priors deliver outsized parameter efficiency, and the pattern of where they succeed and fail is itself informative about what they capture.