Edward Gunn

Hi! I’m Ed. I currently a PhD Student in the Cooperative AI Lab at King’s Collect London under the supervision of Yali Du. Previously I was a researcher in AI for radar at The Alan Turing Institute. My interests include reasoning, multi-agent systems, LLMs, open-endedness, and philosophy of mind. I am a keen proponent of the argumentative theory of reasoning and think it could prove instrumental to unlocking reasoning in AI.

Besides research, I run and climb a little too much. I am an avid reader and can be partial to a beer. Recently I have started trying to pick up photography, learn the piano, and practice vipassana meditation.

latest posts

May 03, 2025	Can LLMs really be intelligent?
Apr 13, 2025	Tuning chain of thought on questions with verifiable answers

selected publications

Radar Pulse Deinterleaving with Transformer Based Deep Metric Learning

Edward Gunn, Adam Hosford, Daniel Mannion, and 3 more authors

2025

Abs arXiv

When receiving radar pulses it is common for a recorded pulse train to contain pulses from many different emitters. The radar pulse deinterleaving problem is the task of separating out these pulses by the emitter from which they originated. Notably, the number of emitters in any particular recorded pulse train is considered unknown. In this paper, we define the problem and present metrics that can be used to measure model performance. We propose a metric learning approach to this problem using a transformer trained with the triplet loss on synthetic data. This model achieves strong results in comparison with other deep learning models with an adjusted mutual information score of 0.882.