Communicating the predictive uncertainty of deep neural networks transparently and reliably
is important in many safety-critical applications such as medicine. However, modern neural …

Uncertainty quantification, once a singular task, has evolved into a spectrum of tasks,
including abstained prediction, out-of-distribution detection, and aleatoric uncertainty …

Many real-world applications require machine-learning models to be able to deal with non-
stationary data distributions and thus learn autonomously over an extended period of time …

Large Language Models (LLMs) are increasingly employed in real-world applications,
driving the need to evaluate the trustworthiness of their generated text. To this end, reliable …

Reliable estimation of predictive uncertainty is crucial for machine learning applications,
particularly in high-stakes scenarios where hedging against risks is essential. Despite its …

Given the ability to model more realistic and dynamic problems, Federated Continual
Learning (FCL) has been increasingly investigated recently. A well-known problem …

Generative models, like large language models, are becoming increasingly relevant in our
daily lives, yet a theoretical framework to assess their generalization behavior and …

Shannon information and Shannon entropy are undoubtedly the most commonly used
quantitative measures of information, cropping up in the literature across a broad variety of …

With model trustworthiness being crucial for sensitive real-world applications, practitioners
are putting more and more focus on improving the uncertainty awareness of deep neural …