Master Theses

Tian Cheng Xia (2026). A Self-Supervised Attribution Method for Explaining Neural Networks.

Mohammed Oubia (2026). Agentic and Privacy-Preserving Retrieval-Augmented Generation: Architecture and Empirical Evaluation.

Riccardo Romeo (2026). Anomaly Detection in Railway Radio Signaling: Synthetic Data Generation and AI-Based Models.

Carlo Merola (2026). Bridging the Lexical-Semantic Gap in Music Discovery: The Reranker as a Foundational Enabler for Hybrid Agentic RAG Architectures.

Luca Tedeschini (2026). Investigating Mechanistic Interpretability in Large Language Models through Model Stitching Across Architectures.

Gabriele Nanni (2026). Prompt Sensitivity to Context in LLM Multi-Agent Decision-Making: a Prisoner’s Dilemma Case Study.

Davide Cremonini (2026). The Agent’s Dilemma: A Comparative Study of LLM-Based Architectures in Strategic Decision-Making.

Abylay Turekhassim (2025). Design and Implementation of a High-Accuracy Text-to-SQL Pipeline with LLMs.

Stamenov Lyudmil (2025). Leveraging Fine-Tuned LLMs for Policy Reasoning in Identity and Access Management.

Mattia Maranzana (2025). Optimizing Listwise Reranking with ModernBERT: A Data-Centric Approach with a Novel Graded Corpus.