The Big BANG! of Comics: Understanding comics at different granularities
Emanuele Vivoli will defend his PhD thesis on October 30, 2026. What is the thesis about? Comics present a uniquely challenging testbed for multimodal AI: their stylized visuals, dense text, unconventional layouts, and long-range narrative dependencies expose weaknesses in both specialized computer vision systems and large, general-purpose vision–language models (VLMs/MLLMs). Over the past three decades, … Read more