Biological and artificial information processing systems form representations that they can
use to categorize, reason, plan, navigate, and make decisions. How can we measure the …

Should we care whether AI systems have representations of the world that are similar to
those of humans? We provide an information-theoretic analysis that suggests that there …

Placing a human in the loop may help abate the risks of deploying AI systems in safety-
critical settings (eg, a clinician working with a medical AI system). However, mitigating risks …

Recently, learning with soft labels has been shown to achieve better performance than
learning with hard labels in terms of model generalization, calibration, and robustness …

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

The suite of datasets commonly used to train and evaluate the mathematical capabilities of
AI-based mathematical copilots (primarily large language models) exhibit several …

Human feedback plays a critical role in learning and refining reward models for text-to-
image generation, but the optimal form the feedback should take for learning an accurate …

Humans rely on strong inductive biases to learn from few examples and abstract useful
information from sensory data. Instilling such biases in machine learning models has been …

Humans learn about the world, and how to act in the world, in many ways: from individually
conducting experiments to observing and reproducing others' behavior. Different learning …

Conversational tones--the manners and attitudes in which speakers communicate--are
essential to effective communication. Amidst the increasing popularization of Large …