Schedule

11:00 Invited talk by Sandro Pezzelle, Not (yet) the whole story: The need for human-like evaluation of visual LLMs in multimodal communicative tasks. 

12:00  Lorenzo Baraldi Building and Benchmarking Retrieval-Augmented Multimodal LLMs 

12:30-13:30 Lunch Break

13:30 Davide Testa,  Beyond the Veil: Benchmarking Multimodal AI with MAIA 

14:00 Alessandro Bondielli Gender Representation in Professions: Comparing AI-Generated Workers and Real-World Distributions in Multimodal LLM

14:30 Paolo Rota, Inferring Everything: Scene Understanding in the Age of Large Vision and Language Models

15:00 Fabrizio Falchi, Evaluation activities of Vision and Language Models at AIMH Lab 

15:30-16:00 Coffee Break

16:00-17:30  Invited Pitches by Stefania Bracci, Oswald Lanz, and Sandro Pezzelle with follow-up discussion