{
  "abstract": "Particle-in-cell (PIC) simulation is indispensable for modeling beam dynamics in particle accelerators, but its computational cost limits many-query workflows, such as configuration exploration, virtual diagnostics, and controller design. We introduce GLOBE, a physics-constrained Generative Latent Operator for Beam Evolution, modeling the nonlinear, control-dependent, multiscale evolution of 3D beam--field dynamics covering $10^7$ spatial cells. GLOBE compresses beam--field states into a compact latent space and factors their evolution into two components. A control-conditioned neural operator learns the dominant dynamics, while an amplitude-normalized generative model captures the residual distribution, recovering fine-scale structures and conditional variations. GLOBE enforces field constraints by regime-specific, parameter-free operators: a Poisson solve reconstructs the electric field in the electrostatic regime, and a spectral projection imposes Gauss's law and a divergence-free magnetic field in the electromagnetic regime. On two high-resolution 3D particle-accelerator benchmarks, bunched-beam transport and plasma-wakefield acceleration, GLOBE lowers relative-$L_2$ error by 9\\% and 13\\%, low-frequency spectral error by 69\\% and 51\\%, and mid-frequency spectral error by 54\\% and 20\\% relative to the strongest baseline (DPOT), satisfies field constraints, and reduces hours of PIC simulation to a minute per rollout.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.14537",
  "author_total": 3,
  "authors": [
    {
      "name": "Haohan Zou"
    },
    {
      "name": "Alexander Scheinker"
    },
    {
      "name": "Yuanyuan Shi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dzcf0b4k2e40f.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.14537",
  "fulltext_url": null,
  "id": "dzcf0b4k2e40f",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.14537",
  "language": null,
  "licence": "CC-BY-NC-SA-4.0",
  "licence_label": "CC BY-NC-SA 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "physics.acc-ph"
    ],
    [
      "openalex",
      "3109|Model Reduction and Neural Networks"
    ]
  ],
  "openalex": "W7221797681",
  "pdf_url": "https://arxiv.org/pdf/2610.14537",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-10",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/dzcf0b4k2e40f.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:06Z",
      "native_id": "2610.14537",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.14537"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.acc-ph",
      "subfield": "applied-instrumentation"
    }
  ],
  "title": "Learn the Dynamics, Enforce the Physics: Generative Latent Operators for High-Dimensional Beam Evolution",
  "title_text": "Learn the Dynamics, Enforce the Physics: Generative Latent Operators for High-Dimensional Beam Evolution",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:06Z",
  "url": "https://research.draconitic.com/paper/dzcf0b4k2e40f",
  "venue": "arXiv",
  "versions": []
}