Related papers: Contextualizing Large-Scale Domain Knowledge for C…

Concept-based explanations translate the internal representations of deep learning models into a language that humans are familiar with: concepts. One popular method for finding concepts is Concept Activation Vectors (CAVs), which are…

This thesis tackles the problem of learning efficient representations of complex, structured data with a natural application to web page and element classification. We hypothesise that the context around the element inside the web page is…

Open-domain question answering (QA) is known to involve several underlying knowledge and reasoning challenges, but are models actually learning such knowledge when trained on benchmark tasks? To investigate this, we introduce several new…

Large language model (LLM) agents have been applied to sequential decision-making tasks such as web navigation, but without any environment-specific experiences, they often fail in these complex tasks. Moreover, current LLM agents are not…

The Collaborative Analysis Versioning Environment System (CAVES) project concentrates on the interactions between users performing data and/or computing intensive analyses on large data sets, as encountered in many contemporary scientific…

Vision-language-action (VLA) models provide a powerful approach to training control policies for physical systems, such as robots, by combining end-to-end learning with transfer of semantic knowledge from web-scale vision-language model…

Large Language Models (LLMs) are transforming Conversational Visual Analytics (CVA) by enabling data analysis through natural language. However, evaluating LLMs for CVA remains a challenge: requiring programming expertise, overlooking…

In recent years, summarizers that incorporate domain knowledge into the process of text summarization have outperformed generic methods, especially for summarization of biomedical texts. However, construction and maintenance of domain…

Most of the existing question answering models can be largely compiled into two categories: i) open domain question answering models that answer generic questions and use large-scale knowledge base along with the targeted web-corpus…

The paper introduces a framework for the evaluation of the encoding of factual scientific knowledge, designed to streamline the manual evaluation process typically conducted by domain experts. Inferring over and extracting information from…

Ecological momentary assessment (EMA) is used to evaluate subjects' behaviors and moods in their natural environments, yet collecting real-time and self-report data with EMA is challenging due to user burden. Integrating voice into EMA data…

Vertical-domain large language models (LLMs) play a crucial role in specialized scenarios such as finance, healthcare, and law; however, their training often relies on large-scale annotated data and substantial computational resources,…

Domain generalization aims at developing suitable learning algorithms in source training domains such that the model learned can generalize well on a different unseen testing domain. We present a novel two-stage approach called…

In domains with high knowledge distribution a natural objective is to create principle foundations for collaborative interactive learning environments. We present a first mathematical characterization of a collaborative learning group, a…

Process discovery aims to derive process models from event logs, providing insights into operational behavior and forming a foundation for conformance checking and process improvement. However, models derived solely from event data may not…

Unsupervised domain adaptation (UDA) is important for applications where large scale annotation of representative data is challenging. For semantic segmentation in particular, it helps deploy on real "target domain" data models that are…

The dynamic nature of knowledge in an ever-changing world presents challenges for language models trained on static data; the model in the real world often requires not only acquiring new knowledge but also overwriting outdated information…

While generative models such as Latent Dirichlet Allocation (LDA) have proven fruitful in topic modeling, they often require detailed assumptions and careful specification of hyperparameters. Such model complexity issues only compound when…

ContextVis introduces a workflow by integrating generative models to create contextual learning materials. It aims to boost knowledge acquisition through the creation of resources with contextual cues. A case study on vocabulary learning…

Interpretability has become an essential topic for artificial intelligence in some high-risk domains such as healthcare, bank and security. For commonly-used tabular data, traditional methods trained end-to-end machine learning models with…