Showcased state-of-the-art optimization algorithms that dramatically reduce memory usage in LLM training at ICML 2025; explored training large models capable of reliable causal reasoning, with research presented at ICML 2024.
Research Experience
Interned at Microsoft Research Cambridge under Dr. Cheng Zhang; current research focuses on improving the cost-effectiveness of large language model (LLM) training through the lens of learning dynamics; also exploring how to train large models that can reliably reason about cause and effect; co-leads several collaborations with product teams to deploy research output for real-world impact.
Education
Ph.D. (2018-early 2023) from the Machine Learning Group, CBL at the University of Cambridge, supervised by Prof. José Miguel Hernández-Lobato and advised by Prof. Richard Turner. The focus was on probabilistic and causal machine learning. Prior to Cambridge, he obtained an MRes degree in Computational Statistics and Machine Learning from the Department of Computer Science, University College London, supervised by Prof. David Barber, with a focus on Stein methods for Bayesian inference on doubly intractable models and Gaussian Processes.
Background
A senior researcher/research scientist at Microsoft Research Cambridge, driving fundamental research on Artificial Intelligence. His long-term goal is to demystify the underlying computational principles of intelligence and leverage these insights to push the frontier of AI research.