The Università degli Studi di Napoli Parthenope is an Italian institution focused on economics, engineering, and maritime sciences. It fosters innovation in sustainable mobility and environmental technologies. In collaboration with Parthenope University, NECLA researchers focused on leveraging multimodal data—encompassing both vision and language—for learning from unlabeled sources. Our joint efforts contributed to improved data efficiency and robustness in AI systems, particularly for complex tasks such as image captioning and cross-modal retrieval.