Normalizing flows provide a general mechanism for defining expressive probability
distributions, only requiring the specification of a (usually simple) base distribution and a …

Normalizing Flows are generative models which produce tractable distributions where both
sampling and density evaluation can be efficient and exact. The goal of this survey article is …

Abstract Out-of-distribution (OOD) detection has received much attention lately due to its
practical importance in enhancing the safe deployment of neural networks. One of the …

Detecting out-of-distribution (OOD) data has become a critical component in ensuring the
safe deployment of machine learning models in the real world. Existing OOD detection …

A class of generative models that unifies flow-based and diffusion-based methods is
introduced. These models extend the framework proposed in Albergo & Vanden-Eijnden …

Determining whether inputs are out-of-distribution (OOD) is an essential building block for
safely deploying machine learning models in the open world. However, previous methods …

A generative model based on a continuous-time normalizing flow between any pair of base
and target probability densities is proposed. The velocity field of this flow is inferred from the …

Detecting out-of-distribution (OOD) inputs is a central challenge for safely deploying
machine learning models in the real world. Existing solutions are mainly driven by small …

Estimating out-of-distribution (OOD) uncertainty is a major challenge for safely deploying
machine learning models in the open-world environment. Improved methods for OOD …

Normalizing flows are a class of deep generative models that are especially interesting for
modeling probability distributions in physics, where the exact likelihood of flows allows …