About me
I am currently a postdoctoral researcher, advised by Dr. Jie Gao, in the computer science department at Rutgers University. My research focuses on the intersection of computational topology, geometry, machine learning, and artificial intelligence.
I earned my Ph.D. in Computer Science from Purdue University, advised by Dr. Tamal Dey. My doctoral research centered on topological data analysis and graph representations learning. My work explores innovative approaches to data representation and analysis, seeking to uncover hidden patterns and structures in complex datasets.
My recent projects include developing topological frameworks for interpretable AI, advancing AI for Science through generative AI techniques, % analyzing human brain networks through graph diffusion generative models, and contributing to the DL3DV benchmark for 3D/video generation.
My research bridges the gap between theoretical foundations and practical applications. I develop novel mathematical frameworks and algorithms that leverage topology and geometry to create robust, interpretable, and reliable AI solutions. My goal is to address real-world challenges and drive impact across both scientific and industrial domains.
My CV. My google scholar. I work on the following projects at the moment.
- Explainable Graph Neural Networks
- Differentiable Topological Representations;
- Non-Euclidean Representations;
- Cooperative learning in Social Settings;