Neural compression is the application of neural networks and other machine learning
methods to data compression. Recent advances in statistical machine learning have opened …

We design a predictive layer for structured-output prediction (SOP) that can be plugged into
any neural network guaranteeing its predictions are consistent with a set of predefined …

Despite the success of autoregressive large language models in text generation, it remains
a major challenge to generate text that satisfies complex constraints: sampling from the …

Numerous neuro-symbolic approaches have recently been proposed typically with the goal
of adding symbolic knowledge to the output layer of a neural network. Ideally, such losses …

Sum–product networks (SPNs) in deep probabilistic models have made great progress in
computer vision, robotics, neuro-symbolic artificial intelligence, natural language …

Probabilistic models based on continuous latent spaces, such as variational autoencoders,
can be understood as uncountable mixture models where components depend continuously …

In structured output prediction, the goal is to jointly predict several output variables that
together encode a structured object–a path in a graph, an entity-relation triple, or an …

Abstract Probabilistic Circuits (PCs) are a general and unified computational framework for
tractable probabilistic models that support efficient computation of various inference tasks …

A sum-product network (SPN) is a probabilistic model, based on a rooted acyclic directed
graph, in which terminal nodes represent probability distributions and non-terminal nodes …

Probabilistic circuits (PCs) are a tractable representation of probability distributions allowing
for exact and efficient computation of likelihoods and marginals. There has been significant …