AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Explaining Grokking and Information Bottleneck through Neural Collapse Emergence

Keitaro Sakamoto, Issei Sato

ICLR 2026 · Architectures and efficiency › RNNs and normalization · approach: Representation geometry and collapse · 4 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
train longer past training-loss convergence so within-class variance (RNC1) contracts4-layer MLP on MNIST with 8x init scale · MNIST grokkingtest accuracy (%): 15 -> 88Improved
increase weight decay lambda (ablation)MLP on MNIST · MNIST grokkingtiming of grokking and RNC1 decreaseImproved
increase weight decay lambda (ablation)MLP on MNIST · MNIST IB dynamicsredundant information (MI, nHSIC)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