Related papers: Learning to Intervene on Concept Bottlenecks

Concept bottleneck models are interpretable predictive models that are often used in domains where model trust is a key priority, such as healthcare. They identify a small number of human-interpretable concepts in the data, which they then…

Concept Bottleneck Models (CBMs) aim to deliver interpretable and interventionable predictions by bridging features and labels with human-understandable concepts. While recent CBMs show promising potential, they suffer from information…

Large audio language models (LALMs) process both speech and environmental acoustic cues, yet struggle to retain non-speech information across multi-turn interactions. The performance gap between semantic (speech) and acoustic (non-speech)…

Black-box deep neural networks excel in text classification, yet their application in high-stakes domains is hindered by their lack of interpretability. To address this, we propose Text Bottleneck Models (TBM), an intrinsically…

A plain well-trained deep learning model often does not have the ability to learn new knowledge without forgetting the previously learned knowledge, which is known as catastrophic forgetting. Here we propose a novel method, SupportNet, to…

Concept Bottleneck Models (CBMs) try to make the decision-making process transparent by exploring an intermediate concept space between the input image and the output prediction. Existing CBMs just learn coarse-grained relations between the…

Transfer learning enhances the training of novel sensory and decision models by employing rich feature representations from large, pre-trained teacher models. Cognitive neuroscience shows that the human brain creates low-dimensional,…

Custom Diffusion Models (CDMs) have gained significant attention due to their remarkable ability to personalize generative processes. However, existing CDMs suffer from catastrophic forgetting when continuously learning new concepts. Most…

Explainable AI seeks to bring light to the decision-making processes of black-box models. Traditional saliency-based methods, while highlighting influential data segments, often lack semantic understanding. Recent advancements, such as…

Deep learning-based medical image classification techniques are rapidly advancing in medical image analysis, making it crucial to develop accurate and trustworthy models that can be efficiently deployed across diverse clinical scenarios.…

Conventional deep learning models have limited capacity in learning multiple tasks sequentially. The issue of forgetting the previously learned tasks in continual learning is known as catastrophic forgetting or interference. When the input…

Models based on human-understandable concepts have received extensive attention to improve model interpretability for trustworthy artificial intelligence in the field of medical image analysis. These methods can provide convincing…

Large language models (LLMs) have advanced the field of artificial intelligence (AI) and are a powerful enabler for interactive systems. However, they still face challenges in long-term interactions that require adaptation towards the user…

We introduce Concept Bottleneck Reward Models (CB-RM), a reward modeling framework that enables interpretable preference learning through selective concept annotation. Unlike standard RLHF methods that rely on opaque reward functions, CB-RM…

Large, publicly available clinical datasets have emerged as a novel resource for understanding disease heterogeneity and to explore personalization of therapy. These datasets are derived from data not originally collected for research…

Multimodal large language models (MLLMs) promise enhanced reasoning by integrating diverse inputs such as text, vision, and audio. Yet cross-modal reasoning remains underexplored, with conflicting reports on whether added modalities help or…

Concept-based learning enhances prediction accuracy and interpretability by leveraging high-level, human-understandable concepts. However, existing CBL frameworks do not address survival analysis tasks, which involve predicting event times…

Concept Bottleneck Models (CBMs) aim to enhance interpretability by structuring predictions around human-understandable concepts. However, unintended information leakage, where predictive signals bypass the concept bottleneck, compromises…

Bayesian Neural Networks (BNNs) provide superior estimates of uncertainty by generating an ensemble of predictive distributions. However, inference via ensembling is resource-intensive, requiring additional entropy sources to generate…

Recent unified models integrate multimodal understanding and generation within a single framework. However, an "understanding-generation gap" persists, where models can capture user intent but often fail to translate this semantic knowledge…