AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

An evolutionary perspective on modes of learning in Transformers

Alexander Ku, Thomas L. Griffiths, Stephanie C.Y. Chan

ICLR 2026 · Architectures and efficiency › Attention and transformers · approach: Training dynamics of in-context learning · 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
increase environmental stability (alpha toward 1) in sinusoid regression (ablation)Transformer · Sinusoid regressionS_ICLHurt
increase mapping persistence (alpha toward 1) in Omniglot (ablation)Transformer · Omniglot classificationS_ICLHurt
increase cue reliability (lower noise variance) in volatile sinusoid environments (ablation)Transformer · Sinusoid regressionS_ICLImproved
increase label correctness probability rho when alpha < 0.95 (ablation)Transformer · Omniglot classificationS_ICLImproved
perfectly reliable cues (rho = 1) in a perfectly stable environment (ablation)Transformer · Omniglot classificationS_ICLNo clear effect
reduce Omniglot vocabulary size from 1623 to 100 (ablation)Transformer · Omniglot classification (alpha=0.999, rho=0.95)early-training S_ICL: 1623 -> 100 classes; S_ICL < 0.2Hurt
compare prequential codelength of ICL vs IWL on OmniglotTransformer · Omniglot classificationprequential codelengthImproved
compare prequential codelength of IWL vs ICL on sinusoidTransformer · Sinusoid regressionprequential codelengthImproved

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