AI Paper Atlas

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

There Was Never a Bottleneck in Concept Bottleneck Models

Antonio Almudévar, José Miguel Hernández-Lobato, Alfonso Ortega

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Concept bottleneck models · 6 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 Information Bottleneck regularization (MCBM) to a CBM (ablation)CBM · MPI3DURR for task-related nuisances (%): 28.1 -> 0.0 (high γ)Improved
add Information Bottleneck regularization (MCBM) to a CBM (ablation)CBM · Shapes3DURR for task-related nuisances (%): 18.1 -> 0.0 (high γ)Improved
add Information Bottleneck regularization (MCBM) to a CBM (ablation)CBM · CIFAR-10URR for task-related nuisances (%): 18.5 -> 17.6No clear effect
add Information Bottleneck to remove task-unrelated nuisances (ablation)CBM · MPI3DURR for task-unrelated nuisances (%): 7.4 -> 0.0Improved
increase gamma in MCBM (ablation)MCBM · MPI3Dtask accuracy: 92.7 -> 24.9Hurt
increase gamma in MCBM (ablation)MCBM · CUBtask accuracy: 78.3 -> 73.5Hurt
increase gamma in MCBM (ablation)MCBM · CUBconcept accuracy: 96.3 -> 95.8Hurt
use MCBM instead of CBM on CIFAR-10 at low gammaCBM · CIFAR-10task accuracy: 73.8 -> 72.4No clear effect
use CEM or ECBM instead of CBMCBM · MPI3DURR for task-related nuisances (%): 28.1 -> 43.2 (CEM)Hurt
apply MCBM interventions at low/medium gamma instead of ARCBM/SCBMMCBM · CIFAR-10 / CUB interventionsprediction errorImproved
apply MCBM intervention on AwA2MCBM · AwA2 interventionsprediction errorNo 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