Adaptive 3D-RoPE: Physics-Aligned Rotary Positional Encoding for Wireless Foundation Models
Researchers have developed Adaptive 3D-RoPE, a novel positional encoding method designed to improve the performance of wireless foundation models. This new approach aligns with the physical properties of wireless channels by incorporating a learnable, axis-decoupled 3D frequency bank and a channel-conditioned controller. Experiments show significant improvements in scale extrapolation and zero-shot generalization, with reductions in normalized mean square error of up to 10.7 dB in antenna scale extrapolation. AI
IMPACT Introduces a new method for improving generalization in wireless foundation models, potentially impacting future applications in signal processing and communication.