Rita Cucchiara's talk at ELLIS Sofia: Rethinking Multimodal Foundation Models
Rita Cucchiara and Sara Sarto represented AImageLab and the Modena ELLIS Unit at the ELLIS Workshop on Computer Vision and Machine Learning, held in Sofia, Bulgaria, on April 27, 2024. Rita Cucchiara's talk, "Rethinking Multimodal Foundation Models: From Retrieval to Reflection and Reasoning," presented the lab's research roadmap on building more efficient, trustworthy multimodal AI systems through retrieval-augmented generation, self-reflective architectures, and reasoning-enhanced models.