ABOUT ME

WELCOME!

I am a senior researcher/research scientist at Microsoft Research Cambridge, driving fundamental research on Artificial Intelligence. My longer-term research goal is to demystify the underlying computational principles of intelligence, and to leverage these insights to push the frontier of AI research.

LLM Dynamics and Optimization

In the near term, my research focuses on improving the cost-effectiveness of large language model (LLM) training through the lens of learning dynamics. Recently, we showcased how a basic understanding of LLM dynamics can lead to state-of-the-art optimization algorithms that dramatically reduce memory usage, effectively breaking the memory barrier in LLM training. Our first results along this line of work were presented at ICML 2025, NeurIPS 2025 with more to come.

Causal Reasoning and Foundation Models

Beyond LLMs, I maintain a broad interest in core areas of machine learning, including causal reasoning, decision-making, and probabilistic inference. More recently, I explored how to train large models that can reliably reason about cause and effect—a key capability for building generalizable AI systems. Check our research presented at ICML 2024 .

Applied Research

In addition to foundational research, I also co-lead several collaborations with product teams to deploy research output for real-world impact.

Music Composing

Apart from AI research, I am also a hobbyist composer during my free time. Check out some of my works!

Bio

Before joining Microsoft, I did my Ph.D (2018- early 2023) in Machine Learning Group, CBL at the University of Cambridge, supervised by Prof. José Miguel Hernández-Lobato, and advised by Prof. Richard Turner. My PhD research focused on the field of probabilistic and causal machine learning. Check out my PhD thesis Advances in Bayesian Machine Learning: From Uncertainty to Decision Making. During my PhD, I also worked as an intern researcher at Microsoft Reserach Cambridge (MSRC), under the supervision of Dr. Cheng Zhang. Before joining the University of Cambridge, I obtained an MRes degree in Computational Statistics and Machine Learning from the Depertment of Computer Science, University College London, supervised by Prof. David Barber. During my time at UCL, my research focused on Stein methods for Bayesian inference on doubly intractable models and Gaussian Processes. You can find my master’s thesis here.