A multitude of explainability methods has been described to try to help users better
understand how modern AI systems make decisions. However, most performance metrics …

Aligning model representations to humans has been found to improve robustness and
generalization. However, such methods often focus on standard observational data …

How can we build AI systems that can learn any set of individual human values both quickly
and safely, avoiding causing harm or violating societal standards for acceptable behavior …

A major challenge in studying robustness in deep learning is defining the set of
“meaningless” perturbations to which a given Neural Network (NN) should be invariant. Most …

Understanding the enigmatic black-box representations within Deep Neural Networks
(DNNs) is an essential problem in the community of deep learning. An initial step towards …

As generative artificial intelligence (AI) becomes more common in day-to-day life, AI-
generated content (AIGC) needs to be accurate, relevant, and comprehensive. These …

Measuring the human alignment of trained models is gaining traction because it is not clear
to which extent artificial image representations are proper models of the visual brain …

Data has powered incredible advances in machine learning (ML). Yet, the kinds of data
used for training are often hard labels aggregated over humans' annotations, which fail to …