Research

Paper

TESTING March 02, 2026

Latent attention on masked patches for flow reconstruction

Authors

Ben Eze, Luca Magri, Andrea Nóvoa

Abstract

Vision transformers have demonstrated outstanding performance on image generation applications, but their adoption in scientific disciplines, like fluid dynamics, has been limited. We introduce the Latent Attention on Masked Patches (LAMP) model, an interpretable regression-based modified vision transformer designed for masked flow reconstruction. LAMP follows a three-fold strategy: (i) partition of each flow snapshot into patches, (ii) dimensionality reduction of each patch via patch-wise proper orthogonal decomposition, and (iii) reconstruction of the full field from a masked input using a single-layer transformer trained via closed-form linear regression. We test the method on two canonical 2D unsteady wakes: a wake past a bluff body, and a chaotic wake past a flat plate. We show that the LAMP accurately reconstructs the full flow field from a 90\%-masked and noisy input, across signal-to-noise ratios between 10 and 30\,dB. Incorporating nonlinear measurement states can reduce the prediction error by up to an order of magnitude. The learned attention matrix yields physically interpretable multi-fidelity optimal sensor-placement maps. The modularity of the framework enables nonlinear compression and deep attention blocks, thereby providing an efficient baseline for nonlinear and high-dimensional masked flow reconstruction.

Metadata

arXiv ID: 2603.02028
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-03-02
Fetched: 2026-03-03 04:34

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.02028v1</id>\n    <title>Latent attention on masked patches for flow reconstruction</title>\n    <updated>2026-03-02T16:12:40Z</updated>\n    <link href='https://arxiv.org/abs/2603.02028v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.02028v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Vision transformers have demonstrated outstanding performance on image generation applications, but their adoption in scientific disciplines, like fluid dynamics, has been limited. We introduce the Latent Attention on Masked Patches (LAMP) model, an interpretable regression-based modified vision transformer designed for masked flow reconstruction. LAMP follows a three-fold strategy: (i) partition of each flow snapshot into patches, (ii) dimensionality reduction of each patch via patch-wise proper orthogonal decomposition, and (iii) reconstruction of the full field from a masked input using a single-layer transformer trained via closed-form linear regression. We test the method on two canonical 2D unsteady wakes: a wake past a bluff body, and a chaotic wake past a flat plate. We show that the LAMP accurately reconstructs the full flow field from a 90\\%-masked and noisy input, across signal-to-noise ratios between 10 and 30\\,dB. Incorporating nonlinear measurement states can reduce the prediction error by up to an order of magnitude. The learned attention matrix yields physically interpretable multi-fidelity optimal sensor-placement maps. The modularity of the framework enables nonlinear compression and deep attention blocks, thereby providing an efficient baseline for nonlinear and high-dimensional masked flow reconstruction.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-03-02T16:12:40Z</published>\n    <arxiv:comment>8 pages, 5 figures, submitted to ICCS (International Conference on Computational Science) 2026</arxiv:comment>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Ben Eze</name>\n    </author>\n    <author>\n      <name>Luca Magri</name>\n    </author>\n    <author>\n      <name>Andrea Nóvoa</name>\n    </author>\n  </entry>"
}