Ph.D. in Computer Science & A.I.

My research interests revolve around reinforcement learning and generative model reasoning. I am exploring ways to improve policy optimisation with policy gradients and expectation maximisation. I want to push the boundaries of world models and how they can support reasoning models (not limited to or even focused on LLM's, but also control, robotics, physics, gaming).

Attended
- Poster TAROS 2026, UKAIRS 2026
- Learning Theory Summer School (June 22-25, 2026)
Teaching Assistant
- COMP38311 Advanced Distributed Systems
- COMP63101 Formal Methods for Software Verification Security and Computer Science
- COMP16321 Introduction to Programming