activity
20242026
collaborators

10 papers

cs.LG2026

Efficient Recommendations via Graph Coarsening and Label Propagation

Alessandro Sbandi, Federico Siciliano, Fabrizio Silvestri

Graph-based recommendations are widely adopted in real-world industrial applications. However, graphs in these systems often reach a massive scale, posing notable scalability and e…

cs.LG2026

Directional Sheaf Hypergraph Networks: Unifying Learning on Directed and Undirected Hypergraphs

Emanuele Mule, Stefano Fiorini, Antonio Purificato +3

Hypergraphs provide a natural way to represent higher-order interactions among multiple entities. While undirected hypergraphs have been extensively studied, the case of directed h…

cs.CV2026

Concept-Enhanced Multimodal RAG: Towards Interpretable and Accurate Radiology Report Generation

Marco Salmè, Federico Siciliano, Fabrizio Silvestri +3

Radiology Report Generation (RRG) through Vision-Language Models (VLMs) promises to reduce documentation burden, improve reporting consistency, and accelerate clinical workflows. H…

cs.CL2025

AutoBench: Automating LLM Evaluation through Reciprocal Peer Assessment

Dario Loi, Elena Maria MuiÃ, Federico Siciliano +4

We present AutoBench, a fully automated and self-sustaining framework for evaluating Large Language Models (LLMs) through reciprocal peer assessment. This paper provides a rigorous…

cs.LG2025

Titans Revisited: A Lightweight Reimplementation and Critical Analysis of a Test-Time Memory Model

Gavriel Di Nepi, Federico Siciliano, Fabrizio Silvestri

By the end of 2024, Google researchers introduced Titans: Learning at Test Time, a neural memory model achieving strong empirical results across multiple tasks. However, the lack o…

cs.IR2025

A Theoretical Analysis of Recommendation Loss Functions under Negative Sampling

Giulia Di Teodoro, Federico Siciliano, Nicola Tonellotto +1

Loss functions like Categorical Cross Entropy (CCE), Binary Cross Entropy (BCE), and Bayesian Personalized Ranking (BPR) are commonly used in training Recommender Systems (RSs) to…