About Me
Hey there! I'm a passionate researcher and current physics graduate student at CUNY (City College). Over the past few years, I've been involved in a variety of projects in computational, solid state, and atomic physics.
Most recently, I worked as a research associate where I combined topology and graph neural networks to simulate biological phenomena. I'm developing a framework to run agent-based models on NVIDIA GPUs using CUDA. You can find some of my work and updates below!
My previous research endeavors include working as an undergraduate research assistant at Texas Christian University, where I studied surface properties of nanocrystalline oxides through spectroscopy, while also engineering UHV components to enable cathodoluminescence imaging. I have presented my research at various APS conferences around Texas and won multiple best presenter awards.
I'm actively searching for opportunities and collaborations to apply and grow my skills. Feel free to reach out!
Projects
Featured
Towards a Framework For Self-Supervised Graph-Based Machine Learning
Data represented in non-Euclidean space in the form of graphs provide invaluable insight into objects and their relationships. We start with an assay of unfused cells which forms our initial graph — nuclei as nodes, with edges formed by Delaunay triangulation.
Graph Convolutional Networks analyze topological properties of this graph, enabling prediction of spatial patterns such as syncytial-dominated or unfused-dominated regions. Self-supervised learning on small subgraphs and higher-order neighbor aggregation uncover consistent structural features.
Future work integrates persistent homology and advanced GCN architectures to enhance detection of spatial dynamics in biological systems.
View Source Code
Voronoi diagram
Delaunay triangulation
Graph Contrastive Learning