Metraipolis › archive › dc_54f3d7e64cfa
Zero-Shot Frequency Generalization for Radio Map Prediction via Cross-Attention Physics-Residual Learning — arXiv:2608.16194
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16194
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:14:00.538Z
- SHA-256 of the archived text
75f30a43ed1dc8910eaf6462bb3b70a99fe69a35fdc984cb1eedfe9beccb032d- Stable URL of this page
https://metraipolis.com/documento/dc_54f3d7e64cfa
How to cite
Zero-Shot Frequency Generalization for Radio Map Prediction via Cross-Attention Physics-Residual Learning — arXiv:2608.16194 — arXiv (en), https://arxiv.org/abs/2608.16194 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_54f3d7e64cfa (Metraipolis archive dc_54f3d7e64cfa, sha256 75f30a43ed1dc8910eaf6462bb3b70a99fe69a35fdc984cb1eedfe9beccb032d)
BibTeX
@misc{dc54f3d7e64cfa,
title = {Zero-Shot Frequency Generalization for Radio Map Prediction via Cross-Attention Physics-Residual Learning — arXiv:2608.16194},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16194},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_54f3d7e64cfa; sha256 75f30a43ed1dc8910eaf6462bb3b70a99fe69a35fdc984cb1eedfe9beccb032d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16194. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Deep learning models for radio map prediction are trained and tested at the same carriers and cannot serve unseen frequencies. We propose a two-stream network learning a residual over an analytic prior, fusing environment and physics streams by cross-attention. Evaluated at the query frequency, this free-space and knife-edge prior absorbs dominant frequency scaling of pathloss, leaving a residual that varies little across bands. Across 150 ray-traced scenes and four training carriers (1.8--28 GHz), the method reduces RMSE by 35.3% zero-shot at unseen carriers and scenes, and by 37.6% at extrapolated 60 GHz, outperforming interpolated 10 GHz. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-18 in eess.SP). Categorie arXiv: Signal Processing (eess.SP). Pagina del lavoro: https://arxiv.org/abs/2608.16194 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T01:25:14.323Z dalla pagina https://arxiv.org/catchup/eess.SP/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).