AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Quantitative Bounds for Length Generalization in Transformers

Zachary Izzo, Eshaan Nichani, Jason D. Lee

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
Increase training sequence lengthone-layer transformer · SimpleTaskplateau test lossImproved
Increase frequency omega of target function (larger weight norm L)one-layer transformer · SimpleTaskplateau test lossHurt
Increase training sequence lengthone-layer transformer · ModPTaskplateau test lossImproved
Increase period Deltaone-layer transformer · ModPTaskplateau test lossHurt
Increase training sequence lengthtwo-layer transformer · in-context k-gramplateau test lossImproved
Increase alphabet size S or ktwo-layer transformer · in-context k-gramplateau test lossHurt

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