3 papers
cs.CV2026
QG-MIL: A Gated Transformer Aggregator for Domain-Agnostic Multiple Instance Learning in Medical Imaging
Luca Zedda, Davide Antonio Mura, Cecilia Di Ruberto +4
Attention-based Multiple Instance Learning aggregators in medical imaging are prone to attention concentration, producing overconfident and unstable predictions. We introduce QG-MI…
cs.CL2025
From User Preferences to Optimization Constraints Using Large Language Models
Manuela Sanguinetti, Alessandra Perniciano, Luca Zedda +3
This work explores using Large Language Models (LLMs) to translate user preferences into energy optimization constraints for home appliances. We describe a task where natural langu…
eess.IV2025
A Comparative Analysis of Image Descriptors for Histopathological Classification of Gastric Cancer
Marco Usai, Andrea Loddo, Alessandra Perniciano +2
Gastric cancer ranks as the fifth most common and fourth most lethal cancer globally, with a dismal 5-year survival rate of approximately 20%. Despite extensive research on its pat…