Theses

Open Theses

The following theses are open for students interested in working on them. If you are interested, please contact me.

• Implementing a Low-Code Web Application for the Development of Fair Learning-Based Systems

  This thesis aims to extend and improve the MANILA web application by including additional features such as:

  • Ability to specify custom fairness metrics
  • Allow exporting and importing a fairness configuration file defined using a domain-specific language (DSL)
  • Improve the user interface
  • Add a tutorial to guide users in using the application

• Automating the Compression of Large Language Models of Code

  This thesis aims to develop search-based approaches to identify the best compression techniques for large language models of code. The goal is to reduce the size of these models while maintaining their performance.

Theses in Progress

I’m currently co-supervising the following theses:

Bachelor Theses

• How Do Generative Models Draw a Software Engineer? Investigating and Mitigating Bias in Stable Diffusion Models @ University College London
• Improving Energy Consumption of Text2Image Generation Models @ University College London
• A Comparative Study on Energy Efficiency and Fairness in Machine Learning Models with Ensemble Strategies @ University College London

Master Theses

• Investigating the Gender, Ethnicity, and Religious Intersectional Bias in Image Generation Models @ University of L’Aquila