{
  "abstract": "Full-wave electromagnetic (EM) simulation enables accurate patch-antenna analysis but is computationally expensive for large-scale forward prediction and inverse design. We present a mesh-native, physics-augmented graph-learning framework that treats radiation-pattern prediction as signal reconstruction on an irregular surface mesh. For the forward problem, a GPS graph transformer is trained with Physics-Augmented Intermediate Supervision (PAIS), an auxiliary node-level objective that predicts complex surface currents, the physical intermediate linking geometry to radiation. PAIS improves multiple GNN backbones at no inference-time cost, while shuffled-current and non-physical controls show the gain comes from physical correspondence. Direction-conditioned decoding and a differentiable radiation-integral consistency loss further exploit this structure. On an 80,000-sample CST benchmark, GPS+PAIS reaches MSE 0.17 / PSNR 19.67, generalizes to a PCA split, and transfers zero-shot to canonical patches. For inverse design, surrogate-filtered diffusion beats nearest-neighbor retrieval by 32% relative MSE.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.05004",
  "author_total": 4,
  "authors": [
    {
      "name": "Avi Epstein"
    },
    {
      "name": "Snir Nehemia"
    },
    {
      "name": "Haim Suchowski"
    },
    {
      "name": "Lior Wolf"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ftfcj53ah9kz9.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.05004",
  "fulltext_url": null,
  "id": "ftfcj53ah9kz9",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.05004",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "physics.comp-ph"
    ],
    [
      "openalex",
      "2202|Antenna Design and Analysis"
    ]
  ],
  "openalex": "W7220699415",
  "pdf_url": "https://arxiv.org/pdf/2610.05004",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-04",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/ftfcj53ah9kz9.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:01Z",
      "native_id": "2610.05004",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.05004"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.comp-ph",
      "subfield": "computational"
    }
  ],
  "title": "Physics-Augmented Graph Transformers for Patch-Antenna Forward and Inverse Design",
  "title_text": "Physics-Augmented Graph Transformers for Patch-Antenna Forward and Inverse Design",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:01Z",
  "url": "https://research.draconitic.com/paper/ftfcj53ah9kz9",
  "venue": "arXiv",
  "versions": []
}