Author

Mikel M. Iparraguirre

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Jan 2026

MeshGraphNet-Transformer: Scalable Mesh-based Learned Simulation for Solid Mechanics

MeshGraphNet-Transformer (MGN-T) is presented, a novel architecture that combines the global modeling capabilities of Transformers with the geometric inductive bias of MeshGraphNets, while preserving a mesh-based graph representation, and outperforms state-of-the-art approaches on classical benchmarks.

Mikel M. Iparraguirre, Icíar Alfaro, David González et al. · arXiv.org · 9 citations

Jul 2026

Data-free neural PDE solvers based on Graph Neural Networks and weak forms

This work presents a physics-informed, data-free neural solver for partial differential equations, built on a graph neural network architecture that utilises message passing, and uses gradients of finite-element shape functions rather than automatic differentiation operators to compute the residuals of the equation fro...

Mikel M. Iparraguirre, Icíar Alfaro, David González et al. · arXiv.org · 0 citations