{"ID":2832368,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.05361","arxiv_id":"2512.05361","title":"FieldSeer I: Physics-Guided World Models for Long-Horizon Electromagnetic Dynamics under Partial Observability","abstract":"We introduce FieldSeer I, a geometry-aware world model that forecasts electromagnetic field dynamics from partial observations in 2-D TE waveguides. The model assimilates a short prefix of observed fields, conditions on a scalar source action and structure/material map, and generates closed-loop rollouts in the physical domain. Training in a symmetric-log domain ensures numerical stability. Evaluated on a reproducible FDTD benchmark (200 unique simulations, structure-wise split), FieldSeer I achieves higher suffix fidelity than GRU and deterministic baselines across three practical settings: (i) software-in-the-loop filtering (64x64, P=80-\u003eQ=80), (ii) offline single-file rollouts (80x140, P=240-\u003eQ=40), and (iii) offline multi-structure rollouts (80x140, P=180-\u003eQ=100). Crucially, it enables edit-after-prefix geometry modifications without re-assimilation. Results demonstrate that geometry-conditioned world models provide a practical path toward interactive digital twins for photonic design.","short_abstract":"We introduce FieldSeer I, a geometry-aware world model that forecasts electromagnetic field dynamics from partial observations in 2-D TE waveguides. The model assimilates a short prefix of observed fields, conditions on a scalar source action and structure/material map, and generates closed-loop rollouts in the physica...","url_abs":"https://arxiv.org/abs/2512.05361","url_pdf":"https://arxiv.org/pdf/2512.05361v1","authors":"[\"Ziheng Guo\",\"Fang Wu\",\"Maoxiong Zhao\",\"Chaoqun Fang\",\"Yang Bu\"]","published":"2025-12-05T02:00:20Z","proceeding":"physics.optics","tasks":"[\"physics.optics\",\"cs.LG\",\"physics.comp-ph\"]","methods":"[]","has_code":false}