AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Deep sequence models tend to memorize geometrically; it is unclear why

Shahriar Noroozizadeh, Vaishnavh Nagarajan, Elan Rosenfeld, Sanjiv Kumar

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Associative memory networks

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
memorize the graph in weights instead of giving it in contextnext-token trained Transformer on path-star · path-star taskfirst-token accuracyImproved
train only on first-token loss, removing supervision of later path tokens (ablation)Transformer · in-weights path-star, unseen pathsfirst-token accuracyNo clear effect
add reverse edges to edge-memorization data (ablation)Transformer · large in-weights path-star graphsfirst-token accuracyImproved

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