8 papers
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…
AutoBench: Automating LLM Evaluation through Reciprocal Peer Assessment
Dario Loi, Elena Maria Muià, 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…
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…
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…
A Systematic Replicability and Comparative Study of BSARec and SASRec for Sequential Recommendation
Chiara D'Ercoli, Giulia Di Teodoro, Federico Siciliano
This study aims at comparing two sequential recommender systems: Self-Attention based Sequential Recommendation (SASRec), and Beyond Self-Attention based Sequential Recommendation…
Static Pruning in Dense Retrieval using Matrix Decomposition
Federico Siciliano, Francesca Pezzuti, Nicola Tonellotto +1
In the era of dense retrieval, document indexing and retrieval is largely based on encoding models that transform text documents into embeddings. The efficiency of retrieval is dir…