The open-world deployment of Machine Learning (ML) algorithms in safety-critical
applications such as autonomous vehicles needs to address a variety of ML vulnerabilities …

Recently, Miller et al. showed that a model's in-distribution (ID) accuracy has a strong linear
correlation with its out-of-distribution (OOD) accuracy, on several OOD benchmarks, a …

The task of out-of-distribution (OOD) detection is crucial for deploying machine learning
models in real-world settings. In this paper, we observe that the singular value distributions …

We introduce the problem of domain adaptation under Open Set Label Shift (OSLS), where
the label distribution can change arbitrarily and a new class may arrive during deployment …

Large-scale vision-language models (VLMs) like CLIP successfully find correspondences
between images and text. Through the standard deterministic mapping process, an image or …

Evaluating the performance of machine learning models on diverse and underrepresented
subgroups is essential for ensuring fairness and reliability in real-world applications …

Self-training and contrastive learning have emerged as leading techniques for incorporating
unlabeled data, both under distribution shift (unsupervised domain adaptation) and when it …

Evaluating the performance of graph neural networks (GNNs) is an essential task for
practical GNN model deployment and serving, as deployed GNNs face significant …

Machine learning models, while progressively advanced, rely heavily on the IID assumption,
which is often unfulfilled in practice due to inevitable distribution shifts. This renders them …

Despite the emergence of principled methods for domain adaptation under label shift, their
sensitivity to shifts in class conditional distributions is precariously under explored …