A preliminary version of “Divide et Calibra: Multiclass Local Calibration via Vector Quantization” accepted at the AISTATS 2026 calibration workshop
A preliminary version of “Divide et Calibra: Multiclass Local Calibration via Vector Quantization” was accepted at Towards Trustworthy Predictions: Theory and Applications of Calibration for Modern AI, an AISTATS 2026 workshop.
I am a PhD candidate in Artificial Intelligence at the University of Pisa, and I work with the Structured Machine Learning Group at the University of Trento.
My research focuses on uncertainty quantification and reliable machine learning, with particular interests in probabilistic calibration, conformal prediction, and human-AI decision making. More broadly, I am interested in developing the next generation of uncertainty-aware, trustworthy and human-centric AI frameworks.
I am always happy to chat about research, possible collaborations or interesting ideas, so feel free to reach out.