Robotic applications often involve working in environments that are uncertain, dynamic, and
partially observable. Recently, diffusion models have been proposed for learning trajectory …

Abstract Language models (LMs) may lead their users to make suboptimal downstream
decisions when they confidently hallucinate. This issue can be mitigated by having the LM …

Calibrated probabilistic classifiers are models whose predicted probabilities can directly be
interpreted as uncertainty estimates. It has been shown recently that deep neural networks …

Whenever a binary classifier is used to provide decision support, it typically provides both a
label prediction and a confidence value. Then, the decision maker is supposed to use the …

Introduced as a notion of algorithmic fairness, multicalibration has proved to be a powerful
and versatile concept with implications far beyond its original intent. This stringent notion …

Selective classification allows models to abstain from making predictions (eg, say" I don't
know") when in doubt in order to obtain better effective accuracy. While typical selective …

Multimodal machine learning has achieved remarkable progress in a wide range of
scenarios. However, the reliability of multimodal learning remains largely unexplored. In this …

In the current landscape of deep learning research, there is a predominant emphasis on
achieving high predictive accuracy in supervised tasks involving large image and language …

In the current landscape of deep learning research, there is a predominant emphasis on
achieving high predictive accuracy in supervised tasks involving large image and language …

We study the problem of making predictions so that downstream agents who best respond to
them will be guaranteed diminishing swap regret, no matter what their utility functions are. It …