AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Max-Margin Token Selection in Attention Mechanism

Davoud Ataee Tarzanagh, Yingcong Li, Xuechen Zhang, Samet Oymak

NeurIPS 2023 · Architectures and efficiency › Attention and transformers · approach: Sparse and structured attention · 2 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
use normalized gradient descent (eta=0.1) instead of constant-step gradient descent (eta=1)Softmax attention model (synthetic) · Synthetic token selectiontime to reach softmax probability 1Improved
train longer so attention weight norm growsViT-base on CIFAR-10 · CIFAR-10 CLS attention mapattention sparsityImproved
correlation loss instead of logistic lossAttention model transient dynamics · Synthetic token scorestoken biasMixed

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