2025/12/01 by Alper Yıldırım, İbrahim Yücedağ, Yıldırım, Alper +1 · 2 voices
Engineering · Computer Science · #Ferroelectric and Negative Capacitance Devices #Neural Networks and Reservoir Computing #Advanced Memory and Neural Computing
paper · pdf · doi:10.48550/arxiv.2512.01208
In standard Transformer architectures, semantic importance is often conflated with activation magnitude, obscuring the geometric structure of latent representations. To disentangle these factors, we introduce PRISM, a complex-valued architecture designed to isolate the computational role of phase. By enforcing a strict unit-norm constraint (|z| = 1) and replacing attention with gated harmonic convolutions, the model is encouraged to utilize subtractive interference in the frequency domain to suppress noise, rather than relying on magnitude-based gating. We utilize this constrained regime to study a hybrid architecture -- fusing phase-based routing with standard attention -- which achieves improved parameter efficiency and representation quality compared to baselines in our evaluated settings. Mechanistically, interventional ablations indicate that the model carries substantial task-relevant information in phase: preserving phase largely maintains performance, whereas disrupting phase causes severe degradation. Together, these results suggest that phase-based spectral interference is a usable computational mechanism for neural sequence modeling at the evaluated scale.