analiza aiqbench
This paper extends learned radio propagation prediction so one model can handle different antenna array sizes, receiver orientations, and beam settings, not just new locations and scenes. The reported gains are relative to baselines on simulated data, with only a secondary check on measured channels and a beam-management task, so real-world robustness is still an open question. For ML readers, the main interest is the tokenization of individual antenna elements and pairwise geometry as a way to make a model handle variable-size inputs.
RFWeave: Learning Wireless Propagation Across Scenes and Transceiver Configurations
arXiv:2610.16656v1 Announce Type: cross Abstract: Wireless propagation modeling is foundational to the evaluation and design of modern communication systems. To achieve accurate wireless propagation prediction, recent learning-based approaches leverage scene geometry and materials, demonstrating promising generalization across transceiver locations and unseen scenes. However, these approaches remain largely confined to a fixed configuration of array size, receiver orientation, and transmit beam. In this work, we introduce RFWeave, a learned wireless propagation model designed to generalize across scenes, transceiver locations, and transceiver configurations. To accommodate varying array structures, RFWeave incorporates variable-length transceiver tokens that represent antenna elements individually. Furthermore, to capture the geometry between transmit and receive antenna elements, RFWeave aggregates their pairwise spatial relations into propagation tokens. A configuration-conditioned decoder predicts the spatial spectrum and received power. RFWeave is trained on a large-scale simulated dataset spanning 10,000 indoor scenes and more than 5 million channel records under diverse transceiver configurations. Extensive evaluations show that RFWeave achieves state-of-the-art performance across all evaluated generalization settings, improving spatial spectrum structural similarity (SSIM) by up to 15.7% and reducing received power mean absolute error (MAE) by up to 35.4% over the strongest baselines on unseen scenes. Additional experiments on measured DICHASUS data and in beam management further demonstrate RFWeave's broader applicability to real-world channels and downstream wireless tasks.
Abstract:Wireless propagation modeling is foundational to the evaluation and design of modern communication systems. To achieve accurate wireless propagation prediction, recent learning-based approaches leverage scene geometry and materials, demonstrating promising generalization across transceiver locations and unseen scenes. However, these approaches remain largely confined to a fixed configuration of array size, receiver orientation, and transmit beam. In this work, we introduce RFWeave, a learned wireless propagation model designed to generalize across scenes, transceiver locations, and transceiver configurations. To accommodate varying array structures, RFWeave incorporates variable-length transceiver tokens that represent antenna elements individually. Furthermore, to capture the geometry between transmit and receive antenna elements, RFWeave aggregates their pairwise spatial relations into propagation tokens. A configuration-conditioned decoder predicts the spatial spectrum and received power. RFWeave is trained on a large-scale simulated dataset spanning 10,000 indoor scenes and more than 5 million channel records under diverse transceiver configurations. Extensive evaluations show that RFWeave achieves state-of-the-art performance across all evaluated generalization settings, improving spatial spectrum structural similarity (SSIM) by up to 15.7% and reducing received power mean absolute error (MAE) by up to 35.4% over the strongest baselines on unseen scenes. Additional experiments on measured DICHASUS data and in beam management further demonstrate RFWeave's broader applicability to real-world channels and downstream wireless tasks.
Signal Processing (eess.SP); Machine Learning (cs.LG)
arXiv:2610.16656 [eess.SP]
(or arXiv:2610.16656v1 [eess.SP] for this version)
https://doi.org/10.48550/arXiv.2610.16656 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 305 cuvinte
Subiecte conexe
TRACE: Learning to Self-Calibrate Wireless Digital Twins from ISAC Measurements
arXiv · 29 sept. 2026
Point2Radio: A Foundation Model for Cross-Scene Radio Fields from Material-Aware Point Clouds
arXiv · 3 aug. 2026
AIMS: An Agentic AI Framework for Sim-to-Real Multi-Modal ISAC
arXiv · 1 oct. 2026
Physics-Unrolled Neural Operator for Wireless Field Modeling
arXiv · 21 aug. 2026