AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Prototype-Grounded Concept Models for Verifiable Concept Alignment

Stefano Colamonaco, David Debot, Pietro Barbiero, Giuseppe Marra

ICML 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Concept bottleneck 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
remove wrong prototypes after training on noisy concept labels (ablation)PGCM · ColorMNIST+ (noisy labels)concept accuracy: 92.9 -> 96.9Improved
edit concepts of wrong prototypes after training on noisy concept labels (ablation)PGCM · ColorMNIST+ (noisy labels)concept accuracy: 92.8 -> 97.8Improved
remove wrong prototypes after training on noisy concept labels (ablation)PGCM · CLEVR-Hans3 (noisy labels)concept accuracy: 81.6 -> 95.1Improved
edit concepts of wrong prototypes after training on noisy concept labels (ablation)PGCM · CLEVR-Hans3 (noisy labels)concept accuracy: 81.6 -> 97.5Improved
increase the number of learned prototypes (ablation)PGCM · CLEVR-Hans3concept and task accuracyImproved
ground concepts in prototypes instead of a standard CBMPGCM vs CBM · CelebAconcept accuracy: 81.3 -> 78.5Hurt
ground concepts in prototypes instead of a standard CBMPGCM vs CBM · CelebAtask accuracy: 84.0 -> 83.0Hurt
ground concepts in prototypes instead of a standard CBMPGCM vs CBM · ColorMNIST+ and CUBtask accuracy: 99.6 -> 99.7 (ColorMNIST+); 63.6 -> 63.4 (CUB)No clear effect
use prototype-aware concept interventions that update multiple concepts at oncePGCM · ColorMNIST+ and CUBconcept accuracy after interventionsImproved
use prototype-aware concept interventions instead of standard onesPGCM · CelebAconcept accuracy after interventionsHurt

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