AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Softmax Transformers are Turing-Complete

Hongjian Jiang, Michael Hahn, Georg Zetzsche, Anthony Widjaja Lin

ICLR 2026 · Architectures and efficiency › Attention and transformers · approach: Transformer expressivity and learnability · 8 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
remove relative positional encodings for binary inputs (ablation)SMAT binary · five arithmetic languages, test1/test2 (longer lengths)exact-match accuracy: 100 -> 0.40 (Prime test1), 100 -> 0.00 (test2)Hurt
remove relative positional encodings for binary inputs (ablation)SMAT binary · in-distribution test0exact-match accuracy: 100 -> 95.00 (Prime), 100 -> 64.40 (Multiplication)Hurt
unary representation with no positional encoding (NoPE)SMAT · five arithmetic languageslength-generalization accuracy: 99.70-100 on test2Improved
add relative positional encodings for binary representation (ablation)SMAT binary · five arithmetic languagesexact-match accuracy: 0.00 -> 100 (Multiplication test2)Improved

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