Sina Shafiezadeh

Research Interests
I am working on multimodal AI and vision-language models, focusing on understanding the modality gap between image and text embeddings in the context of numerosity perception. Specifically, I'm exploring how these models process and understand numerosity, analyzing the differences and interactions between different input modalities.

Education
Ph.D., Brain, Mind, and Computer Science, University of Padova (2025)
Laurea (M.Sc.), Cognitive Science, Institute for Cognitive Science Studies, Iran (2018)

Representative publications

• Shafiezadeh, S., Duma, G. M., Mento, G., ... & Testolin, A. (2023). Methodological issues in evaluating machine learning models for EEG seizure prediction: Good cross-validation accuracy does not guarantee generalization to new patients. Applied Sciences, 13(7), 4262.

• Shafiezadeh, S., Duma, G. M., Mento, G., ... & Testolin, A. (2024). Calibrating deep learning classifiers for patient-independent electroencephalogram seizure forecasting. Sensors, 24(9), 2863.

• Shafiezadeh, S., Duma, G. M., Pozza, M., & Testolin, A. (2024). A systematic review of cross-patient approaches for EEG epileptic seizure prediction. Journal of Neural Engineering, 21(6), 061004.