> Hello. You've found a latent space.

> This space is spanned by Dulhan.

I like to do machine learning research. Enough, apparently, that I'm currently doing a PhD in machine learning at the University of Oxford. Specifically, I'm part of the Oxford Robotics Institute and I'm funded by Amazon AWS in a doctoral programme called AIMS.

Here, I work on reading brains using deep learning in the Neural Processing Lab. I focus on deep learning and representation learning for decoding inner speech (i.e. processing the latent thoughts in brain signals into text we can read). In the not so distant future, we hope this technology could assist those with paralysis to communicate via low-cost non-invasive brain-computer interfaces (BCIs).

Before doing brain stuff I did a master's at the University of Cambridge where I was funded by the company formerly known as Twitter to do machine learning research. There, I worked on multi-agent RL in the robotics lab and reasoning with graph neural networks with Petar.

I've also done a bit of work on large language models at Speechmatics and developing assembly-level machine learning kernels for new hardware at Arm.

Feel free to reach out to me about anything that interests you. I find it difficult to pinpoint exactly what my research interests are; I'm broadly interested in anything cool. Under duress, I would say that I mostly care about representation learning in interesting applications---yes, that can be pretty much anything. You may like to look at my publications.