AI Paper Atlas

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

Revisiting the Platonic Representation Hypothesis: An Aristotelian View

Fabian Gröger, Shuo Wen, Maria Brbic

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
add null calibration to linear CKALinear CKA · Image-text convergence (WIT, 204 pairs)Pearson correlation with LM ranking: 0.86 -> 0.45Hurt
add null calibration to Procrustes distanceProcrustes distance · Image-text convergence (WIT, 204 pairs)Pearson correlation with LM ranking: 0.89 -> 0.39Hurt
add null calibration to mutual kNN and CKNNALocal neighborhood metrics · Image-text convergence (WIT, 204 pairs)Pearson correlation with LM ranking: mutual kNN stays near 0.85, CKNNA near 0.87No clear effect
increase layer count from 2 to 128 without aggregation-aware calibration (ablation)Max-aggregated CKA under null · Synthetic depth experimentmax CKA scoreHurt
add aggregation-aware calibration instead of entry-wise calibration (ablation)Max-aggregated CKA under null · Synthetic depth experimentmax CKA scoreImproved
add permutation null calibrationSimilarity metrics under H0 · Synthetic width experimentType-I error rate: rejection rates at or below alpha=0.05Improved

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