Concept Bottleneck Models
PulseAugur coverage of Concept Bottleneck Models — every cluster mentioning Concept Bottleneck Models across labs, papers, and developer communities, ranked by signal.
- 2026-10-09 research_milestone Researchers introduced CREAM, a new framework for Concept Bottleneck Models that enhances reasoning capabilities. source
3 day(s) with sentiment data
-
New framework enhances video recognition interpretability with dynamic concepts
Researchers have developed a new framework to enhance the interpretability of video recognition models by incorporating dynamic conceptual representations. This approach extends concept bottleneck models, typically used…
-
Dermatology AI models show bias against darker skin tones
A new study published on arXiv highlights significant skin-tone bias in dermatology concept datasets, specifically the widely used SkinCon dataset. The research found that erythema, a key indicator of skin inflammation,…
-
AI models' concept accuracy audited, revealing potential benchmark flaws
A new research paper published on arXiv investigates the accuracy of Concept Bottleneck Models (CBMs) and Concept Embedding Models (CEMs) on the CUB-200-2011 dataset. The study reveals that while CBMs promise human-insp…
-
Concept Bottleneck Models Enhance Explainable Visual Anomaly Detection
Researchers have introduced a novel framework for explainable visual anomaly detection (VAD) by extending Concept Bottleneck Models (CBMs). This approach aims to provide more semantically meaningful interpretations of a…
-
New CREAM framework enhances Concept Bottleneck Models with reasoning capabilities
Researchers have introduced CREAM (Concept Reasoning Models), a new framework for Concept Bottleneck Models (CBMs). CREAM allows for the explicit encoding of prior knowledge about concept-concept and concept-task relati…
-
AnyBottle method creates compact, task-specific AI concept models
Researchers have developed AnyBottle, a novel method for creating compact, task-specific concept bottleneck models (CBMs). Unlike previous annotation-free variants that used large, static concept vocabularies, AnyBottle…
-
Concept bottleneck models enhance explainability in speech emotion recognition
Researchers have adapted concept bottleneck models, previously used for image classification, to speech emotion recognition (SER). This adaptation aims to improve the explainability of SER systems, particularly those ut…
-
Concept Bottleneck Models: Interpretability vs. Robustness Trade-off Explored
A new research paper explores the robustness of Concept Bottleneck Models (CBMs), which are designed for interpretability. The study argues that previous findings on CBM robustness have been contradictory due to a confl…
-
New CHOQOLATE layer organizes concept bottleneck models for better interpretability
Researchers have developed CHOQOLATE, a novel interpretable layer for Concept Bottleneck Models (CBMs) that utilizes 2-additive Choquet integrals to organize latent spaces. This method addresses the issue of entangled c…
-
New method integrates expert knowledge for improved image classification
Researchers have developed a novel approach to integrate domain expert knowledge into image classification models, moving beyond existing Concept Bottleneck Models (CBMs) and Concept-based Embedding Models (CEMs). This …
-
New Causal Model Enhances Chest X-Ray Interpretation and Interpretability
Researchers have developed XpertCausal, a novel causal concept bottleneck model designed to enhance the interpretability of chest X-ray interpretation. This model explicitly models the generative process from disease to…
-
New benchmark uses MLLM council to evaluate AI model explanations
Researchers have developed CBX-Bench, a new benchmark designed to quantitatively evaluate the quality of explanations generated by Concept Bottleneck Models (CBMs). This benchmark utilizes a council of multimodal large …
-
New CBM method reduces annotation burden for interpretable cancer imaging
Researchers have developed a new method for interpretable cancer imaging diagnosis using concept bottleneck models (CBMs). This approach integrates limited concept annotations with class-conditional distribution matchin…
-
New research rethinks concept bottleneck models for better interpretability
Two new research papers explore the interpretability of Concept Bottleneck Models (CBMs), which aim to make deep learning models more transparent by factoring predictions through human-understandable concepts. The first…
-
New ReCBM framework enhances interpretable AI models with uncertainty reasoning
Researchers have developed ReCBM, a new framework for Concept Bottleneck Models (CBMs) that enhances interpretability and reasoning capabilities. This approach incorporates semantically defined concept relations and use…
-
New research questions interpretability of AI models in healthcare
Researchers have developed a new method to evaluate the interpretability of concept bottleneck models, particularly in clinical applications like echocardiography. They found that simply predicting an outcome accurately…
-
New method explores diverse, equally accurate AI models
Researchers have developed a new method to efficiently explore the "Rashomon set" of Concept Bottleneck Models (CBMs). This set comprises multiple models that achieve similar predictive performance but operate on differ…
-
New Graph-based Model Enhances Visual Explanation Interpretability
Researchers have developed a Graph-based Concept Bottleneck Model (G-CBM) that enhances interpretability in visual explanations. This new framework performs unsupervised concept discovery using Non-negative Matrix Facto…
-
New Caption Bottleneck Models Enhance AI Interpretability with Natural Language
Researchers have introduced Caption Bottleneck Models (CaBM), a novel framework designed to enhance interpretability in machine learning by using natural language captions instead of predefined concept sets. Unlike trad…
-
New COCOLogic-V2 dataset advances AI visual inductive reasoning
Researchers have introduced COCOLogic-V2, a new dataset designed to advance visual inductive reasoning capabilities in AI models. This dataset focuses on object-centric real-world images and covers a significant portion…