5 papers
Where Animacy Lives in Large Language Models: Tracing the Circuits of the Animacy Concept
Samuele Punzo, Giovanni CinÃ, Sandro Pezzelle
Distinguishing animate from inanimate concepts in written language requires more than shallow text processing, as it involves recognizing complex selectional constraints and contex…
Do Video Foundation Models Understand Intuitive Physics? A Layerwise Probing Analysis
Samuele Punzo, Niccolò Caselli, Ippokratis Pantelidis +3
We study whether pretrained video foundation models encode intuitive-physics information in their frozen representations, and how this information varies across model families, lay…
Is my model perplexed for the right reason? Contrasting LLMs' Benchmark Behavior with Token-Level Perplexity
Zoë Prins, Samuele Punzo, Frank Wildenburg +2
Standard evaluations of Large language models (LLMs) focus on task performance, offering limited insight into whether correct behavior reflects appropriate underlying mechanisms an…
Machine Learning for analysis of Multiple Sclerosis cross-tissue bulk and single-cell transcriptomics data
Francesco Massafra, Samuele Punzo, Silvia Giulia Galfré +8
Multiple Sclerosis (MS) is a chronic autoimmune disease of the central nervous system whose molecular mechanisms remain incompletely understood. In this study, we developed an end-…
A Machine Learning Pipeline for Multiple Sclerosis Biomarker Discovery: Comparing explainable AI and Traditional Statistical Approaches
Samuele Punzo, Silvia Giulia Galfrè, Francesco Massafra +3
We present a machine learning pipeline for biomarker discovery in Multiple Sclerosis (MS), integrating eight publicly available microarray datasets from Peripheral Blood Mononuclea…