Wave-Domain Semantic Equalization Using a Practical Dynamic Metasurface Antenna with Strong Mutual Coupling
Abstract
Semantic mismatch between independently trained AI-native agents in heterogeneous networks can impair semantic communications. Hybrid analog-digital semantic equalization can align the incompatible latent representations without retraining the semantic transceivers. We study a practical realization of this approach based on a fabricated dynamic metasurface antenna (DMA), an emerging low-cost, low-power, ultracompact technology for hybrid analog-digital beamforming. We model the DMA-assisted channel using multiport-network theory (MNT), accounting for mutual coupling (MC), structural scattering, and binary lossy tuning states. We use the experimentally estimated MNT parameters of our fabricated 19-GHz DMA prototype with strong MC. We jointly optimize digital pre- and post-equalizers and the DMA at a reference receiver geometry for latent-space alignment, then freeze the digital stages and adapt only the DMA after receiver motion. In our CIFAR-10 image-classification task at the receiver, the jointly optimized system achieves 94.5% accuracy, while DMA-only adaptation restores a median accuracy of 90.3% after receiver motion. Our semantic-aware wave-domain adaptation substantially outperforms semantic-unaware benchmarks. We further observe that varying the DMA configuration across channel uses provides little additional benefit for either semantic-aware or semantic-unaware optimization.
Related
- Metasurface–TMDCs for Strong Coupling and Emerging Nanoscale Light Sources
- The vanishing distance: a practical range boundary for dynamic wavefront shaping
- Resilience Beyond the Light Cone: Error-Detected Primitives for Practical Dynamic Circuits
- Graphene-enabled dynamic H-J switching of dipole-dipole coupling
- Dynamic distortion from discretized coupling feedback in soft-spin Ising machines
BibTeX
@misc{sghaier2026wavedomain,
title = {{Wave-Domain Semantic Equalization Using a Practical Dynamic Metasurface Antenna with Strong Mutual Coupling}},
author = {Yassine Sghaier and Emilio Calvanese Strinati and Philipp del Hougne},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.33729},
eprint = {2609.33729},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.33729},
}
RIS
TY - UNPB
TI - Wave-Domain Semantic Equalization Using a Practical Dynamic Metasurface Antenna with Strong Mutual Coupling
AU - Yassine Sghaier
AU - Emilio Calvanese Strinati
AU - Philipp del Hougne
PY - 2026
DA - 2026/09/27
PB - arXiv
DO - 10.48550/arxiv.2609.33729
UR - https://arxiv.org/abs/2609.33729
AB - Semantic mismatch between independently trained AI-native agents in heterogeneous networks can impair semantic communications. Hybrid analog-digital semantic equalization can align the incompatible latent representations without retraining the semantic transceivers. We study a practical realization of this approach based on a fabricated dynamic metasurface antenna (DMA), an emerging low-cost, low-power, ultracompact technology for hybrid analog-digital beamforming. We model the DMA-assisted channel using multiport-network theory (MNT), accounting for mutual coupling (MC), structural scattering, and binary lossy tuning states. We use the experimentally estimated MNT parameters of our fabricated 19-GHz DMA prototype with strong MC. We jointly optimize digital pre- and post-equalizers and the DMA at a reference receiver geometry for latent-space alignment, then freeze the digital stages and adapt only the DMA after receiver motion. In our CIFAR-10 image-classification task at the receiver, the jointly optimized system achieves 94.5% accuracy, while DMA-only adaptation restores a median accuracy of 90.3% after receiver motion. Our semantic-aware wave-domain adaptation substantially outperforms semantic-unaware benchmarks. We further observe that varying the DMA configuration across channel uses provides little additional benefit for either semantic-aware or semantic-unaware optimization.
ER -