Related papers: Deconstructing Implicit Beliefs in Visual Data Jou…

In representation learning, a disentangled representation is highly desirable as it encodes generative factors of data in a separable and compact pattern. Researchers have advocated leveraging disentangled representations to complete…

Contrastive learning has revolutionized the field of computer vision, learning rich representations from unlabeled data, which generalize well to diverse vision tasks. Consequently, it has become increasingly important to explain these…

Data workers may have a a different mental model of their data that the one reified in code. Understanding the organization of their data is necessary for analyzing data, be it through scripting, visualization or abstract thought. More…

Concept-based explanation approach is a popular model interpertability tool because it expresses the reasons for a model's predictions in terms of concepts that are meaningful for the domain experts. In this work, we study the problem of…

Visualization supports exploratory data analysis (EDA), but EDA frequently presents spurious charts, which can mislead people into drawing unwarranted conclusions. We investigate interventions to prevent false discovery from visualized…

We present our in-progress work on co-designing a visualization tool for presenting unstructured text. We have conducted a focus group with a variety of professionals who regularly analyze large corpora of unstructured text. Our preliminary…

The proliferation of synthetic images generated by advanced AI models poses significant challenges in identifying and understanding manipulated visual content. Current fake image detection methods predominantly rely on binary classification…

Time series data are prevalent across various domains and often encompass large datasets containing multiple time-dependent features in each sample. Exploring time-varying data is critical for data science practitioners aiming to understand…

People commonly utilize visualizations not only to examine a given dataset, but also to draw generalizable conclusions about the underlying models or phenomena. Prior research has compared human visual inference to that of an optimal…

Vision-Language Models (VLMs) achieve strong results on multimodal tasks such as visual question answering, yet they can still fail even when the correct visual evidence is present. In this work, we systematically investigate whether these…

Visual Question Answering (VQA) deep-learning systems tend to capture superficial statistical correlations in the training data because of strong language priors and fail to generalize to test data with a significantly different…

Multimodal fake news detection is crucial for mitigating adversarial misinformation. Existing methods, relying on static fusion or LLMs, face computational redundancy and hallucination risks due to weak visual foundations. To address this,…

We analyze data leakage in visual datasets. Data leakage refers to images in evaluation benchmarks that have been seen during training, compromising fair model evaluation. Given that large-scale datasets are often sourced from the internet,…

Understanding how humans revise their beliefs in light of new information is crucial for developing AI systems which can effectively model, and thus align with, human reasoning. While theoretical belief revision frameworks rely on a set of…

Reasoning-augmented vision language models (VLMs) generate explicit chains of thought that promise greater capability and transparency but also introduce new failure modes: models may reach correct answers via visually unfaithful…

We introduce Prototype Generation, a stricter and more robust form of feature visualisation for model-agnostic, data-independent interpretability of image classification models. We demonstrate its ability to generate inputs that result in…

Vision-language models (VLMs) are increasingly deployed in socially sensitive applications, yet their behavior with respect to disability remains underexplored. We study disability aware descriptions for person centric images, where models…

Human knowledge is subject to uncertainties, imprecision, incompleteness and inconsistencies. Moreover, the meaning of many everyday terms is dependent on the context. That poses a huge challenge for the Semantic Web. This paper introduces…

Recent work shows that documents from encyclopedias serve as helpful auxiliary information for zero-shot learning. Existing methods align the entire semantics of a document with corresponding images to transfer knowledge. However, they…

Word vector embeddings have been shown to contain and amplify biases in data they are extracted from. Consequently, many techniques have been proposed to identify, mitigate, and attenuate these biases in word representations. In this paper,…