Sajjad Hussain

Zero-Shot Frequency Generalization for Radio Map Prediction via Cross-Attention Physics-Residual Learning

A two-stream network learning a residual over an analytic prior is proposed, fusing environment and physics streams by cross-attention, and reduces RMSE by 35.3% zero-shot at unseen carriers and scenes, and by 37.6% at extrapolated 60 GHz, outperforming interpolated 10 GHz.