In healthcare, the development and deployment of insufficiently fair systems of artificial
intelligence (AI) can undermine the delivery of equitable care. Assessments of AI models …

The development of medical applications of machine learning has required manual
annotation of data, often by medical experts. Yet, the availability of large-scale unannotated …

The mixture proportions of pretraining data domains (eg, Wikipedia, books, web text) greatly
affect language model (LM) performance. In this paper, we propose Domain Reweighting …

Recognizing out-of-distribution (OOD) samples is critical for machine learning systems
deployed in the open world. The vast majority of OOD detection methods are driven by a …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

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 …

An estimated 3 billion people lack access to dermatological care globally. Artificial
intelligence (AI) may aid in triaging skin diseases and identifying malignancies. However …

Widely used alignment techniques, such as reinforcement learning from human feedback
(RLHF), rely on the ability of humans to supervise model behavior-for example, to evaluate …

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 …