Oana-Maria Camburu

Assistant Professor in ML, Department of Computing, Imperial College London

I work on Alignment and AI Safety. Research directions include measuring and improving the faithfulness of Chain-of-Thought (CoT) such that CoTs can be used reliably in scalable oversight of powerful models, and the usefulness of CoTs for end users (e.g., in medical applications).  Previously, I was a Principal Research Fellow at University College London, holding an Early Career Leverhulme Fellowship. I obtained my PhD from the University of Oxford, with the thesis "Explaining Deep Neural Networks". I was also an intern at Google, and a visiting student at MIT. I obtained my MEng from the Ecole Polytechnique, Paris.