About Me

I am a researcher in Natural Language Processing and Vision-Language Models. I recently graduated (March 2025) with an M.Sc. in Cognitive Science and Computational Modeling of Language and Cognition from CIMeC, University of Trento, after conducting my master’s thesis under Professor Albert Gatt at Utrecht University .

My thesis evaluated the visual scene comprehension abilities of state-of-the-art VLMs in a reference expression generation task, curating a semantically minimal COCO-based dataset and applying attention analysis to interpret model behavior.

Prior work includes:

• Investigating human-inspired progressive alignment and comparative learning frameworks for compositional concept acquisition in VLMs, presented at the CORE Workshop 2024 at Universitat Pompeu Fabra (UPF)
• Exploring ChatGPT’s information-seeking strategies in the 20-Questions game, which earned the Best Evaluation Paper award at INLG-2023.

I also served as a tutor for the Computational Linguistics course at the University of Trento, mentoring students on Python and Hugging Face projects.

My academic foundation includes a B.Sc. in Cognitive and Psychobiological Sciences from the University of Padua and a year in Neuroscience and Psychological Rehabilitation (including an Erasmus+ program in Warsaw), where I gained experience with fMRI, EEG, and machine learning.