AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Local Intrinsic Dimension of Representations Predicts Alignment and Generalization in AI Models and Human Brain

Junjie Yu, Wenxiao Ma, Chen Wei, Jianyu Zhang, Haotian Deng, Zihan Deng, Quanying Liu

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 0 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 lower local intrinsic dimension (K=100)vision models · ConvNeXt models, NSD + ImageNet-1KAI-AI alignmentImproved
lower local intrinsic dimensionvision models · NSD EBA regionAI-Brain alignmentImproved
lower local intrinsic dimensionvision models · ImageNet-1KgeneralizationImproved
measure dimension at global scale (large K) instead of local (ablation)intrinsic dimension · ConvNeXt modelscorrelation with alignment and generalizationHurt
randomly subsample 1,000 embeddings globally instead of local neighborhood (ablation)intrinsic dimension · ConvNeXt modelscorrelation with alignmentHurt
increase model sizeConvNeXt · NSD, ImageNet-1Klocal intrinsic dimensionImproved
increase pretraining dataset sizeConvNeXt · NSD, ImageNet-1Klocal intrinsic dimensionImproved
pool different architectures (ablation)intrinsic dimension correlations · ViT, ConvNeXt, ResNet, ResMLPcorrelation strengthMixed
architecture family as a factorAI-AI alignment · cross-architectureinter-model alignmentMixed

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