Politecnico di Torino logo

Vincenzo Montana

Ph.D. candidate in Ingegneria Informatica E Dei Sistemi , 41st cycle (2025-2028)
Department of Control and Computer Engineering (DAUIN)

Adjunct lecturer/Adjunct instructor
Specialising Master’s Programmes and Lifelong Learning School (SCMAST)

Profile

PhD

Research topic

Preference models for multimodal annotations

Tutors

Keywords

Data science, Computer vision and AI

Biography

I am a PhD student enrolled in the PhD Program in Computer and Control Engineering at Politecnico di Torino, where I also earned my Master’s degree in Computer Engineering (Artificial Intelligence and Data Analytics).
My research is currently focused on the frontier of Multimodal Language Models, with a specific emphasis on Audio LMs.
During the first year the I will benchmark Multimodal LLMs on established tasks by prompting them with annotation of different types and modalities. I will not only study the effect of annotation types and modality but also the ways to transfer modalities and input formats effectively and efficiently.
During the second year, the research will focus on designing a modality preference model able to recommend the right modality and format of the input annotations according to the model, context, and task. Finally, in the third year the research will extend the modality preference model and test in different real-world use cases.

Research

Research groups