About Me

I am currently completing my MSc in Applied Computational Science and Engineering at Imperial College London, graduating with Distinction. My academic background spans operator learning, Koopman theory, and physics-inspired machine learning, with applications to partial differential equations, nonlinear wave phenomena, and reduced-order modeling for fluid and atmospheric systems.

I have published as first author in Physical Review E and IJCAI 2023, and recently co-authored Information Shapes Koopman Representation (under review at ICLR 2026). These experiences have gradually guided me toward interpretable and trustworthy machine learning, where I aspire to balance theoretical rigor with practical scalability.

Research Vision

My goal is to advance trustworthy and interpretable machine learning. I aim to develop models that not only achieve predictive accuracy but also reveal underlying structures, provide interpretability, and support reasoning and intervention in complex systems.

Seeking PhD Opportunities

I am actively seeking PhD opportunities in scientific / trustworthy ML, with the aim of developing interpretable and reliable algorithms for modeling complex systems. I aspire to push the boundaries of ML by contributing methods that are both mathematically grounded and impactful for addressing key challenges.

For detailed information, please see my CV and Publications.