How do large language models (LLMs) develop and evolve over the course of training?
How do these patterns change as models scale? To answer these questions, we introduce …

We argue that representations in AI models, particularly deep networks, are converging.
First, we survey many examples of convergence in the literature: over time and across …

Purpose To recognize and address various sources of bias essential for algorithmic fairness
and trustworthiness and to contribute to a just and equitable deployment of AI in medical …

Design biases in NLP systems, such as performance differences for different populations,
often stem from their creator's positionality, ie, views and lived experiences shaped by …

Recent advances in the capacity of large language models to generate human-like text have
resulted in their increased adoption in user-facing settings. In parallel, these improvements …

Bias amplification is a phenomenon in which models exacerbate biases or stereotypes
present in the training data. In this paper, we study bias amplification in the text-to-image …

In the dynamic field of medical artificial intelligence (AI), cardiology stands out as a key area
for its technological advancements and clinical application. This review explores the …

Computer vision datasets frequently contain spurious correlations between task-relevant
labels and (easy to learn) latent task-irrelevant attributes (eg context). Models trained on …

Datasets scraped from the internet have been critical to large-scale machine learning. Yet,
its success puts the utility of future internet-derived datasets at potential risk, as model …

Humans evolved to learn from one another. Today, however, learning opportunities often
emerge from interactions with AI systems. We argue that learning from AI systems resemble …