Hello World_
I am an incoming PhD student at Imperial under Felipe Tobar with the project title "Aligning Diffusion Models". The PhD is part of the Collaborative Computational Modelling at the Interface (CCMI) program in collaboration with UCL.
My interests lie in AI safety focusing on interpretability, explainability, and alignment as I believe this is still an under-researched field.
I have some thoughts though I very sporadically write them down. And will move previous and ongoing projects on here soon.