Muhammad Faaiz Taufiq

  github   linkedin   scholar

I am currently a 3rd year PhD student in statistical machine learning at Oxford, under the supervision of Rob Cornish, Arnaud Doucet and Yee Whye Teh, and funded by Google DeepMind.

My research interests include uncertainty quantification, decision-making, causal inference, fairness and explainability. I am also interested in applying ideas from these disciplines for alignment within Large Language Models (LLMs).

I recently completed a research internship in the Responsible AI team at ByteDance, London. Here, I was exploring the reliability and trustworthiness of LLMs.

I am also part of the organising committee for ELLIS RobustML workshops. This year we are organising two robustness-related workshops with the aim of bringing together theoretical robustness research with real-world applications.


Feel free to reach out to me at muhammad.taufiq (at)