AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

What Linear Probes Miss: Multi-View Probing for Weight-Space Learning

Eunwoo Heo, Kyeongkook Seo, Jaejun Yoo

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Layer-wise analysis of language models · 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 all four probing branches vs XU only (ablation)MVProbe · Model Jungle (ResNet)accuracy: 90.42 -> 92.24Improved
add all four probing branches vs XU only (ablation)MVProbe · Model Jungle (DINO)accuracy: 74.17 -> 78.29Improved
add second-order branches to first-order (ablation)MVProbe · Model Jungle (ResNet)accuracy: 91.24 -> 92.24Improved
add first-order branches to second-order (ablation)MVProbe · Model Jungle (SupViT)accuracy: 92.04 -> 92.33Improved
add second-order over first-order only (ablation)MVProbe · Model Jungle (DINO)accuracy: 76.01 -> 75.82Hurt
add per-sample standardization of branch features (ablation)MVProbe · Model Jungle (all layers, average)accuracy: 65.9 -> 68.8Improved
add per-sample standardization of branch features (ablation)MVProbe · Model Jungle (MAE, all layers)accuracy: 62.1 -> 62.9Improved
add per-sample standardization of branch features (ablation)MVProbe · Model Jungle (ResNet, middle layers stage 2)accuracy: 73.6 -> 78.6Improved
add third-order branches (6 branches) (ablation)MVProbe · Model Jungle (DINO)accuracy: 78.29 -> 77.02Hurt
add third-order branches (6 branches) (ablation)MVProbe · Model Jungle (ResNet)accuracy: 92.24 -> 93.15Improved
add fourth-order branches (8 branches) (ablation)MVProbe · Model Jungle (MAE)accuracy: 81.62 -> 81.16Mixed
quadruple ProbeX probes (x4)ProbeX · Model Jungle (MAE)accuracy: 77.11 -> 77.26No 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