AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Focus and Dilution: The Multi-stage Learning Process of Attention

Zheng-An Chen, Pengxiao Lin, Zhi-Qin John Xu, Tao Luo

ICML 2026 · Architectures and efficiency › Attention and transformers · approach: Theory of self-attention dynamics · 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
add residual connections to the one-layer attention model (ablation)one-layer Transformer on Markov data · synthetic Markov datafocus-dilution pattern and embedding norm evolutionNo clear effect
use multiple attention layers instead of one (ablation)Transformer on Markov data · synthetic Markov datafocus-dilution and embedding retractionMixed
use multi-head attention instead of single head (ablation)Transformer on Markov data · synthetic Markov dataembedding retractionNo clear effect
train on real text (WikiText) instead of synthetic Markov datasimplified one-layer Transformer · WikiTextattention focus then dilution on high-frequency tokensNo clear effect
train on TinyStories instead of synthetic Markov datasimplified one-layer Transformer · TinyStoriesattention focus then dilution on high-frequency tokensNo clear effect

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