Research#llm🔬 Research分析: 2025年12月25日 03:55

Block-Recurrent Dynamics in Vision Transformers

发布:2025年12月24日 05:00
1分で読める
ArXiv Vision

分析

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 \

要点

    引用

    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.