AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, so do risks from misalignment. To provide a comprehensive …

Computational models in neuroscience usually take the form of systems of differential
equations. The behaviour of such systems is the subject of dynamical systems theory …

This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …

Deep long-tailed learning, one of the most challenging problems in visual recognition, aims
to train well-performing deep models from a large number of images that follow a long-tailed …

The goal of domain generalization (DG) is to enhance the generalization capability of the
model learned from a source domain to other unseen domains. The recently developed …

Neural network classifiers can largely rely on simple spurious features, such as
backgrounds, to make predictions. However, even in these cases, we show that they still …

Traditional machine learning paradigms are based on the assumption that both training and
test data follow the same statistical pattern, which is mathematically referred to as …

Federated learning has emerged as a promising paradigm for privacy-preserving
collaboration among different parties. Recently, with the popularity of federated learning, an …

Abstract Federated Domain Generalization (FedDG) attempts to learn a global model in a
privacy-preserving manner that generalizes well to new clients possibly with domain shift …

Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …