Theses

📖 Open Theses

The following projects are available for students. If you are interested or want more details, please contact me.

Automating the Compression of Large Language Models of Code

Research and implement search-based strategies to identify effective model compression pipelines that reduce model size while preserving performance. The work involves designing search procedures, evaluating compression candidates, and benchmarking tradeoffs between size, speed, and accuracy.

🧑‍💻 Theses in Progress

A.Y. 2025-2026

Application of advanced Machine Learning techniques for metabolic disease risk prediction in the LIFEMap project cohort

Implementation and Evaluation of a Low-Code Web Application for the Development of Fair Learning-Based Systems

✅ Co-Supervised Theses

A.Y. 2025-2026

Multi-Objective Search over the Decoding Policy of a Multi-Agent LLM Pipeline for Automated Program Repair

Understanding and Mitigating Gender Bias in Stable Diffusion 3: An Analysis of Embedding-Level InterventionUCL EDI Award Winner

A.Y. 2024-2025

The Moral Cost of Visual Bias: Intersectionality in AI Image Generation Across Religion, Ethnicity, and Gender

How Do Generative Models Draw a Software Engineer? Investigating and Mitigating Bias in Stable Diffusion Models

Improving Energy Consumption of Text2Image Generation Models

Towards Fair and Sustainable Machine Learning: A Multi-Objective Ensemble Optimization Approach