3 papers
cs.LG2025
Scaling Continuous Latent Variable Models as Probabilistic Integral Circuits
Gennaro Gala, Cassio de Campos, Antonio Vergari +1
Probabilistic integral circuits (PICs) have been recently introduced as probabilistic models enjoying the key ingredient behind expressive generative models: continuous latent vari…
cs.LG2025
What is the Relationship between Tensor Factorizations and Circuits (and How Can We Exploit it)?
Lorenzo Loconte, Antonio Mari, Gennaro Gala +5
This paper establishes a rigorous connection between circuit representations and tensor factorizations, two seemingly distinct yet fundamentally related areas. By connecting these…
cs.LG2025
E(n)-equivariant Graph Neural Cellular Automata
Gennaro Gala, Daniele Grattarola, Erik Quaeghebeur
Cellular automata (CAs) are notable computational models exhibiting rich dynamics emerging from the local interaction of cells arranged in a regular lattice. Graph CAs (GCAs) gener…