← Search

Nicola Saccomanno

4 accepted papers

2026

Composable Sparse Subnetworks via Maximum-Entropy Principle

ICLR 2026poster

Neural networks implicitly learn class-specific functional modules. In this work, we ask: Can such modules be isolated and recombined? We introduce a method for training sparse networks that accurately classify only a designated subset of classes while remaining deliberately uncertain on all others,…

Cited by 0SourceScholar
2026

Do LLMs Really Struggle at NL-FOL Translation? Revealing Their Strengths via a Novel Benchmarking Strategy

AAAI 2026technical

Due to its expressiveness and unambiguous nature, First-Order Logic (FOL) is a powerful formalism for representing concepts expressed in natural language (NL). This is useful, e.g., for specifying and verifying desired system properties. While translating FOL into human-readable English is relativel

Cited by 0SourcePDFScholar
2024

Learning What to Monitor: Using Machine Learning to Improve past STL Monitoring

IJCAI 2024poster

Monitoring is a runtime verification technique that can be used to check whether an execution of a system (trace) satisfies or not a given set of properties. Compared to other formal verification techniques, e.g., model checking, one needs to specify the properties to be monitored, but a complete mo…