About me

My background #

I was born and raised in Nanjing, a city in China that blends ancient charm with modern vibrancy. My journey took me to Singapore and Cambridge (UK), where I had the privilege of living and studying before embarking on my PhD in Baltimore (US).

During my time at Cambridge, I spent four years studying the Mathematical Tripos, which exposed me to a diverse range of mathematical areas. This experience fueled my passion for two distinct directions: the rigorous study of abstract structures (with abstract algebra, geometry, topology, and category theory as my favorites) and the practical modeling of real-world data (involving statistics and machine learning). The convergence of these interests prompted me to explore interdisciplinary realms, as I began to believe that the deepest human wisdom is embedded in the underlying connections and shared insights across different topics.

In my fourth year at Cambridge, I was introduced to the field of Geometric Deep Learning through Prof. Michael Bronstein’s illuminating talk. This area, precisely at the intersection of my interests, captivated me with its expansive mathematical theories and exciting applications propelling advancements in artificial intelligence. Intrigued by the possibilities it presented, I decided to pursue a PhD to delve deeper into this area. I was very fortunate to have joined Soledad’s group at JHU, and I am now relishing every moment of my time here!

Resesarch interests #

Here, I outline some of the topics I am currently exploring and feel passionately about. If you share an interest in these areas, we should chat!

• Imposing symmetries in Neural Networks (equivariance in neural networks).
• Expressivity and universality of Graph Neural Networks and Equivariant Neural Networks.
• Algorithmic alignment with GNN.
• Applying Category Theory to build novel Neural Networks (Categorical Deep Learning)