works on

From the 2 of 9 linked papers with an AI index.

activity
20242026
collaborators

9 papers

math.NA2026

HORSES3D-GPU: A high-order discontinuous Galerkin solver for multi-GPU systems

Gerasimos Ntoukas, Gonzalo Rubio, Abbas Ballout +13

The paper describes the GPU-accelerated version of the open-source high-order discontinuous Galerkin CFD solver HORSES3D, showing its performance and scalability on multi‑GPU syste…

physics.flu-dyn2026

Can Explicit Subgrid Models Enhance Implicit LES Simulations? A Very High-Order Solver Perspective

Gonzalo Rubio, Gerasimos Ntoukas, Miguel Chávez-Módena +5

The paper studies how explicit Vreman subgrid‑scale models interact with the inherent numerical dissipation of very high‑order discontinuous Galerkin methods for turbulent flow sim…

cs.LG2026

Kolmogorov Arnold networks (KAN) for aerodynamic prediction: a comparison with MLPs and GNNs

Miguel Jaraiz, Fermin Gutierrez, Pablo Yeste +4

Kolmogorov Arnold networks (KAN) have recently been introduced as a (deep) neural network architecture whose trainable parameters adapt the activation functions, instead of the coe…

cs.LG2026

FluidFlow: a flow-matching generative model for fluid dynamics surrogates on unstructured meshes

David Ramos, Lucas Lacasa, Fermín Gutiérrez +2

Computational fluid dynamics (CFD) provides high-fidelity simulations of fluid flows but remains computationally expensive for many-query applications. In recent years deep learnin…

cs.LG2026

On the Role of Consistency Between Physics and Data in Physics-Informed Neural Networks

Nicolás Becerra-Zuniga, Lucas Lacasa, Eusebio Valero +1

Physics-informed neural networks (PINNs) have gained significant attention as a surrogate modeling strategy for partial differential equations (PDEs), particularly in regimes where…

cs.LG2025

Reliable Statistical Guarantees for Conformal Predictors with Small Datasets

Miguel Sánchez-Domínguez, Lucas Lacasa, Javier de Vicente +2

Surrogate models (including deep neural networks and other machine learning algorithms in supervised learning) are capable of approximating arbitrarily complex, high-dimensional in…