AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Poly-attention: a general scheme for higher-order self-attention

Sayak Chakrabarti, Toniann Pitassi, Josh Alman

ICLR 2026 · Architectures and efficiency › Attention and transformers · approach: Linear attention approximations · 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
replace one-layer self-attention with one-layer tree-attentionsingle-head Transformer · function composition f1(f2(x))learnabilityImproved
use tree-attention instead of two-layer self-attentionsingle-head Transformer · function composition f1(f2(x))training epochs to learnImproved
use tree-attention instead of self-attentionsimple networks · COGSaccuracyImproved
use tree-attention instead of self-attentionsingle-layer attention · inference timerelative inference time: around 1.3x time as that of self-attentionHurt

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