Education

Master Theses

• Diagnosing Failure Patterns in Large Language Models. [Thesis]
• Exploring the capabilities of generative image captioning models for producing structured output. [Thesis]
• Developing a user-centered explainability tool to support the NLP Data Scientist in creating LLM-based solutions. [Thesis]
• Data Model for Computer Vision Explainability, Fairness, and Robustness. [Thesis]
• Clearing the Air: An Exploration of Pulmonologists’ Needs and Intents in XAI Solutions for Respiratory Medicine. [Thesis]
• A System for Model Diagnosis centered around Human Computation. [Thesis]
• CHIME: Causal Human-In-the-Loop Model Explanations. [Thesis]
• Characterizing the knowns and unknowns of text simplification models. [Thesis]

Bachelor Theses

• Explaining Deep Learning Models for Fact-Checking. [Thesis 1, Thesis 2, Thesis 3, Thesis 4, Thesis 5]

Course Projects

• Capstone Applied AI Project: Characterising Toxicity in Language Models. [Repo]

Teaching

• TU Delft: DSAIT4210 (2025), CS4145 (2022 - 2024), IFEEMCS520100 (2022 - 2023), IN4326 (2022 - 2023), CS4360 (2023 - 2026).
• Quantia Consulting (2020 - 2022): ad-hoc sessions on Generative Adversarial Networks, NoSQL technologies (MongoDB, neo4j, Cassandra), Information Retrieval and ELK stack.
• Politecnico di Milano: Software Methodologies and Architectures for Security - Enterprise ICT Architectures (2020 - 2021), Computer Science Fundamentals (2021).