AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Test-time regression: a unifying framework for designing sequence models with associative memory

Ke Alexander Wang, Jiaxin Shi, Emily B. Fox

JMLR 2026 · Architectures and efficiency › Attention and transformers · approach: State space and recurrent sequence models · 65 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 unweighted recursive least squares instead of linear attention in MQAR with P=128 keys and d_model=64single test-time regression layer · MQAR (P=128, d_model=64)MQAR recallImproved
increase softmax regressor order from p=0 to p=1 (local linear regression) (ablation)nonparametric softmax regression layer · switching autoregressive online regressionone-step test lossImproved
add exponential weighting/forgetting to regression instead of unweighted RLS (ablation)RLS layer · switching autoregressive online regressionone-step test lossImproved
use linear attention instead of RLS when keys are correlatedparametric regression layer · switching autoregressive online regressionone-step test lossHurt
increase MQAR sequence length with large enough memory (ablation)linear attention with orthonormal keys · MQAR (P=64, d_model=64)MQAR recallNo clear effect

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