AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Language as a Wave Phenomenon: Semantic Phase Locking and Interference in Neural Networks

Alper YILDIRIM, İbrahim Yücedağ

ICML 2026 · Architectures and efficiency › Attention and transformers · approach: Transformer expressivity and circuits · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
retain only the phase of the spectral filter (H/|H|) instead of the full learned filter (ablation)PRISM encoder (frozen) · WikiText-103 filter interventiondegradation factor: 1.41× (constrained), 1.51× (unconstrained)No clear effect
retain only magnitude |H| of the spectral filter (ablation)PRISM encoder (frozen) · WikiText-103 filter interventiondegradation factor: 153× (constrained), 173× (unconstrained)Hurt
reverse the filter phase (H*) (ablation)PRISM encoder (frozen) · WikiText-103 filter interventiondegradation factor: 245× (constrained), 139× (unconstrained)Hurt
shuffle the filter phase (ablation)PRISM encoder (frozen) · WikiText-103 filter interventiondegradation factor: 160× (constrained), 161× (unconstrained)Hurt
remove the spectral filter (H = 1) (ablation)PRISM encoder (frozen) · WikiText-103 filter interventiondegradation factor: 328× (constrained), 78× (unconstrained)Hurt
scramble phase versus magnitude at a single layer (ablation)unconstrained PRISM · WikiText-103 layer-wise interventiondegradation factor: 72-205× (phase) vs 1.1× (magnitude)Hurt
use complex PRISM spectral stream instead of real spectral encoder in WPT (ablation)WPT · WikiText-103 masked LMperplexity: 5.55 -> 4.94Improved
use CReLU + LayerNorm instead of ModReLU + PPLN in standalone PRISM (ablation)PRISM · WikiText-103 masked LMperplexity: 6.06 -> 5.80Improved
use CReLU + LayerNorm instead of ModReLU + PPLN in the WPT relational stream (ablation)WPT · WikiText-103 masked LMperplexity: 4.94 -> 5.46Hurt
use complex PRISM instead of real-valued spectral encoder (standalone)spectral encoder · WikiText-103 masked LMperplexity: 6.15 -> 6.06Improved
replace FNet Hybrid with PRISM Hybridhybrid spectral encoder · WikiText-103 masked LMperplexity: 9.87 -> 6.06Improved
use WPT dual-stream instead of Transformerencoder · WikiText-103 masked LMperplexity: 5.28 -> 4.94Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy