Research#llm🔬 ResearchAnalyzed: Dec 25, 2025 03:55

Block-Recurrent Dynamics in Vision Transformers

Published:Dec 24, 2025 05:00
1 min read
ArXiv Vision

Analysis

This paper introduces the Block-Recurrent Hypothesis (BRH) to explain the computational structure of Vision Transformers (ViTs). The core idea is that the depth of ViTs can be represented by a small number of recurrently applied blocks, suggesting a more efficient and interpretable architecture. The authors demonstrate this by training \

Reference

trained ViTs admit a block-recurrent depth structure such that the computation of the original $L$ blocks can be accurately rewritten using only $k \ll L$ distinct blocks applied recurrently.