3 papers
cs.LG2026
Discrete World Models via Regularization
Davide Bizzaro, Luciano Serafini
World models aim to capture the states and dynamics of an environment in a compact latent space. Moreover, using Boolean state representations is particularly useful for search heu…
cs.LG2025
Logic of Hypotheses: from Zero to Full Knowledge in Neurosymbolic Integration
Davide Bizzaro, Alessandro Daniele
Neurosymbolic integration (NeSy) blends neural-network learning with symbolic reasoning. The field can be split between methods injecting hand-crafted rules into neural models, and…
cs.LO2024
Towards Counting Markov Equivalence Classes with Logical Constraints
Davide Bizzaro, Luciano Serafini, Sagar Malhotra
We initiate the study of counting Markov Equivalence Classes (MEC) under logical constraints. MECs are equivalence classes of Directed Acyclic Graphs (DAGs) that encode the same co…