Summary
Emanuele Vivoli is a PhD student and researcher with 11 years of engineering experience, specializing in Vision & Language for Comics and Manga through dataset creation, benchmarks, models and new tasks across CVC (UAB) and MICC (UNIFI). He has a strong publication record including NeurIPS and ECCV and authored a recent survey on the field, reflecting both deep technical expertise and a drive to synthesize the state of the art. His background spans applied research and production: from prototyping self-navigating demining robots with multi-spectrum deep learning to multilingual scene-text VQA and table extraction using GNNs. Equally comfortable with full-stack engineering and academic rigor, he combines practical deployment experience (Firebase/Angular) with advanced ML experimentation and reproducible code practices. Based in Florence, he brings a rare niche focus on visual narrative media that connects computer vision, language understanding, and real-world systems.
11 years of coding experience
2 years of employment as a software developer
Doctor of Philosophy - PhD, Artificial Intelligence, Doctor of Philosophy - PhD, Artificial Intelligence at Universitat Autònoma de Barcelona
Doctor of Philosophy - PhD, Doctor of Philosophy - PhD at Università degli Studi di Firenze
High School Diploma, Computer and Information Sciences, General, High School Diploma, Computer and Information Sciences, General at Leonardo Da Vinci High School