Professional Summary
Hi, I'm Marco Mistretta!
Iām a PhD student in Artificial Intelligence at MICC, University of Florence, working under the guidance of Prof. Andrew D. Bagdanov and Prof. Marco Bertini.With a background in Computer Engineering and AI, my research focuses on pushing the boundaries of Multimodal Vision-Language Models (like CLIP) and their real-world applications.
My expertise spans from Natural Language Processing, Contrastive Self-Supervised Learning, Incremental Learning, Few-Shot Adaptation, Prompt Learning, to Test-Time Adaptation. This expertise is demonstrated through my first author publications in top-tier venues, including one ECCV (main conference), one NeurIPS (workshop), and one ICLR (main conference). These works reflect my dedication to solving challenging problems and advancing the field of AI.
Seeking a 2025 internship to contribute to innovative teams and apply expertise to real-world challenges!
News
-
Jan, 2025
A paper on multimodal VLMs representation is accepted at ICLR 2025.
-
Sep, 2024
Presented a paper on prompt learning at ECCV 2024.
-
Aug, 2024
KDPL source code is finally available!
-
Dec, 2023
Presented a paper on continual learning at NeurIPS 2023 (workshop).
Recent Pubblications
-
Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion
Marco Mistretta, Alberto Baldrati, Lorenzo Agnolucci, Marco Bertini, Andrew D. Bagdanov
-
KDPL: Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation
Marco Mistretta, Alberto Baldrati, Marco Bertini, Andrew D. Bagdanov
-
RE-tune: Incremental Fine Tuning of Biomedical Vision-Language Models for Multi-label Chest X-ray Classification
Marco Mistretta, Andrew D. Bagdanov
Education
-
PhD student in Artificial Intelligence
Nov, 2023 ā PresentUniversity of Florence, Florence, Italy
Topic: Multimodal Vision-Language Models, Incremental Learning, Prompt Learning.
-
M.S. in Artificial Intelligence
Sep, 2021 ā Jul 2023University of Florence, Florence, Italy
Thesis: "RE-Tune - Incremental Fine-Tuning of Biomedical Vision-Language Models"
-
B.S. in Computer Science and Engineering
Sep, 2018 ā Sep, 2021University of Florence, Florence, Italy
Thesis: "Scarlatti-Gen - AI-Driven Sonata Generation Using Weighted Graphs and CNNs"
Teaching and Mentoring
-
Teaching Assistant, University of Florence
Delivering interactive lessons on C/C++ and Python to over 200 bachelor students.
Jan 2024, Jan 2025 -
Thesis Co-Supervisor, University of Florence
Apr 2024, Sep 2024"Mitigating Catastrophic Zero-shot Forgetting in CLIP via Distillation of Low-Rank Adapters from Learned Prompts", Proposed a novel method to efficiently few-shots fine-tune CLIP models that mitigates catastrophic forgetting and preserves zero-shot capabilities, based on distilling learned prompts in LoRa adapters.
-
Student Ambassador, University of Florence
Jan 2020, Dec 2020Mentoring students on exams projects, internships, and career development.