Federico D'Asaro

Ph.D. candidate in Ingegneria Informatica E Dei Sistemi , 39^th cycle (2023-2026)
Department of Control and Computer Engineering (DAUIN)

Docente esterno e/o collaboratore didattico
Department of Control and Computer Engineering (DAUIN)

federico.dasaro@polito.it

Profile

PhD

Research topic

Visual and language models

Tutors

Research interests

Data science, Computer vision and AI

Biography

Federico D'Asaro is an AI Applied Researcher at LINKS Foundation, with a focus on multimodal deep learning applications. He completed his Master’s degree in Data Science and Engineering in 2021 and began his PhD studies in 2023 within the Computer Graphics & Vision Group (CGVG). His research explores the transfer capabilities of Vision-Language Models to downstream tasks, with a particular focus on the Modality Gap—an issue affecting the quality of multimodal feature space. By bridging both Natural Language Processing and Computer Vision, his research aims to understand how reducing the Modality Gap can enhance performance in downstream tasks.

Teaching

Teachings

Master of Science

Applied data science project. A.A. 2025/26, DATA SCIENCE AND ENGINEERING. Collaboratore del corso
Applied data science project. A.A. 2024/25, DATA SCIENCE AND ENGINEERING. Collaboratore del corso

Research

Research groups

CGVG - Computer Graphics and Vision Group (DAUIN)

Publications

Latest publications View all publications in Porto@Iris

Catalano, Luca; D'Asaro, Federico; Pantaleo, Michele; Jamshed, Minal; Acharjee, Prima; ... (In stampa)
Classifying Gas Pipe Damage Descriptions in Low-Diversity Corpora. In: CLiC-it 2025 – Eleventh Italian Conference on Computational Linguistics, Cagliari (ITA), September 24-26, 2025
Contributo in Atti di Convegno (Proceeding)
Márquez Villacis, Juan José; D'Asaro, Federico; Rizzo, Giuseppe; Bottino, Andrea (In stampa)
Exploring the Adaptability of Large Speech Models to Non-Verbal Vocalization Task. In: CLiC-it 2025 – Eleventh Italian Conference on Computational Linguistics, Cagliari (ITA), September 24-26, 2025
Contributo in Atti di Convegno (Proceeding)
D'Asaro, Federico; Rizzo, Giuseppe; Bottino, Andrea (In stampa)
Investigating Mask-Text Contrastive Alignment in Semantic Segmentation. In: 28th European Conference on Artificial Intelligence (ECAI 2025), Bologna (ITA), October 25 to 30, 2025
Contributo in Atti di Convegno (Proceeding)
D'Asaro, Federico; Márquez Villacís, Juan José; Rizzo, Giuseppe; Bottino, Andrea (2024)
Using Large Speech Models for Feature Extraction in Cross-Lingual Speech Emotion Recognition. In: CLiC-it 2024 – Tenth Italian Conference on Computational Linguistics, Pisa (ITA), December 4-6, 2024. ISSN 1613-0073
Contributo in Atti di Convegno (Proceeding)
D’Asaro, Federico; Marquez Villacis, Juan Jose; Rizzo, Giuseppe; Bottino, Andrea (2024)
Transfer Learning of Large Speech Models for Italian Speech Emotion Recognition. In: 18th IEEE International Conference Application of Information and Communication Technologies 2024, Turin (ITA), 25-27 September 2024. ISBN: 979-8-3503-8753-7
Contributo in Atti di Convegno (Proceeding)