Feature selection helps reduce data acquisition costs in ML, but the standard approach is to
train models with static feature subsets. Here, we consider the dynamic feature selection …

Abstract Information Pursuit (IP) is a classical active testing algorithm for predicting an output
by sequentially and greedily querying the input in order of information gain. However, IP is …

We propose an interactive multi-agent classifier that provides provable interpretability
guarantees even for complex agents such as neural networks. These guarantees consist of …

There is a growing interest in the machine learning community in developing predictive
algorithms that are" interpretable by design". Towards this end, recent work proposes to …

Variational Information Pursuit (V-IP) is an interpretable-by-design framework that makes
predictions by sequentially selecting a short chain of user-defined, interpretable queries …

Hallucinations and unfaithful synthesis due to inaccurate prompts with insufficient semantic
details are widely observed in multimodal generative models. A prevalent strategy to align …

Vision-Language models (VLMs) have proved effective at aligning image and text
representations, producing superior zero-shot results when transferred to many downstream …

Information Pursuit (IP) is an explainable prediction algorithm that greedily selects a
sequence of interpretable queries about the data in order of information gain, updating its …

In this article, we address the problem of using non-interpretable Machine Learning (ML)
algorithms in safety critical applications, especially automated driving functions. We focus on …

Due to the high stakes in medical decision-making, there is a compelling demand for
interpretable deep learning methods in medical image analysis. Concept Bottleneck Models …