AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Attention as Implicit Structural Inference

Ryan Singh, Christopher Buckley

NeurIPS 2023 · Architectures and efficiency › Attention and transformers · approach: Attention head and block redesign · 1 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 two-hop Multihop Attention instead of single-layer self-attentionsingle-layer attention · Multihop toy problemtask performanceImproved
use Multihop Attention instead of two-layer self-attentionMultihop Attention · Multihop toy problemtask performanceNo clear effect
Multihop Attention balances attention across two positionsMultihop Attention · Multihop toy problemattention weightsImproved
replace uniform prior with geometric prior and Beta hyper-prior (Expanding Attention)self-attention · Expanding toy problemtraining curvesNo clear effect
use Expanding Attention when recency bias (1/p) or feature dimension d is largeself-attention · Expanding toy problemrelative number of operationsImproved

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