mlsanityData to 14 Oct 2026

Learn the Dynamics, Enforce the Physics: Generative Latent Operators for High-Dimensional Beam Evolution

arXiv 2610.14537 ↗First posted 10 Oct 2026physics.acc-ph cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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 107 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-L2 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 73 references that are in the map. First posted on arXiv 10 Oct 2026.

Builds on

35 of 73 references.

References · 35

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022Scalable Diffusion Models with Transformerscited by 6,054
  3. 2022Flow Matching for Generative Modelingcited by 5,702
  4. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  6. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  8. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
  9. 2018On the Spectral Bias of Neural Networkscited by 1,341
  10. 2020Learning to Simulate Complex Physics with Graph Networkscited by 880
  11. 2022Message Passing Neural PDE Solverscited by 386
  12. 2021Choose a Transformer: Fourier or Galerkincited by 343
23 more
  1. 2023GNOT: A General Neural Operator Transformer for Operator Learningcited by 336
  2. 2024Transolver: A Fast Transformer Solver for PDEs on General Geometriescited by 326
  3. 2022Transformer for Partial Differential Equations' Operator Learningcited by 283
  4. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Modelscited by 217
  5. 2024DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Trainingcited by 151
  6. 2023Scalable Transformer for PDE Surrogate Modelingcited by 128
  7. 2023Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscalingcited by 110
  8. 2024DiffusionPDE: Generative PDE-Solving Under Partial Observationcited by 108
  9. 2024Latent Neural Operator for Solving Forward and Inverse PDE Problemscited by 80
  10. 2023Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulationcited by 71
  11. 2024On conditional diffusion models for PDE simulationscited by 60
  12. 2024Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEscited by 59
  13. 2024CViT: Continuous Vision Transformer for Operator Learningcited by 51
  14. 2023From Zero to Turbulence: Generative Modeling for 3D Flow Simulationcited by 49
  15. 2022Learning to Accelerate Partial Differential Equations via Latent Global Evolutioncited by 39
  16. 2024AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fieldscited by 39
  17. 2021Probabilistic Forecasting with Generative Networks via Scoring Rule Minimizationcited by 37
  18. 2025Mitigating Spectral Bias in Neural Operators via High-Frequency Scaling for Physical Systemscited by 31
  19. 2024Continuous Ensemble Weather Forecasting with Diffusion modelscited by 30
  20. 2024A conditional latent autoregressive recurrent model for generation and forecasting of beam dynamics in particle acceleratorscited by 8
  21. 2025VideoPDE: Unified Generative PDE Solving via Video Inpainting Diffusion Modelscited by 8
  22. 2026PhaseFlow4D: Physically Constrained 4D Beam Reconstruction via Feedback-Guided Latent Diffusioncited by 3
  23. 2026Physics-Preserving Latent Compression for Zero-Shot Resolution Transfer in 3D Turbulencecited by 3

Built on by

Not cited yet.