SOURCE-LINKED INTELLIGENCE

Same path, different: a mechanistic comparison of looped and stacked transformer encoders on 12-lead ECG

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Recurrent Transformers reusing their weights rather than stacking $L$ distinct layers are becoming widely adopted due to their parameter efficiency [1,2,3]. However, the exact representational and dynamical differences between looped and stacked architectures remain uncharacterized. This paper presents a controlled study on the example of bViT model [1] applying one weight-tied block $L$ times. We train two models: bViT and standard ViT [4] on 12-lead electrocardiogram (ECG) classification tasks from the PTB-XL dataset under identical training protocols. Despite an $8.9\times$ parameter reduct

Read original source ↗ Open in workspace

recordType

paper

region

Global