About me
I am an Assistant Professor in the Department of Computer Science at California State University, Fresno. I develop principled foundations for trustworthy AI by connecting learning systems with topology, geometry, algorithms, and multi-agent interaction.
Before joining Fresno State, I was a postdoctoral researcher at Rutgers University, working with Prof. Jie Gao. I earned my Ph.D. in Computer Science from Purdue University, advised by Prof. Tamal K. Dey, where my doctoral research focused on topological data analysis and the theory and algorithms of multiparameter persistent homology.
My work moves between mathematical foundations and empirical systems. A recurring theme is structure preservation: building representations and algorithms that respect the intrinsic geometry, topology, and interaction structure of data while improving interpretability, robustness, and reliability.
News
- August 2026Joined California State University, Fresno as an Assistant Professor of Computer Science.
- June 2026Two papers appeared at SoCG 2026: D-GRIL: End-to-End Topological Learning with 2-parameter Persistence and Locality Sensitive Hashing in Hyperbolic Space.
- December 2025Johnson-Lindenstrauss Lemma Beyond Euclidean Geometry appeared at NeurIPS 2025.
- May 2025TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration was accepted to ICML 2025.
Current Research Directions
Trustworthy & Multi-Agent AI
Safety, robustness, and intervention in networked learning systems, including how agents influence one another and how reliable collective behavior can be designed.
Topological & Geometric Learning
Topological representations for graph learning, interpretable AI, and scientific data, together with foundations in multiparameter persistent homology.
Non-Euclidean Representations
Dimensionality reduction, embedding, and retrieval beyond Euclidean geometry, including MDS, Johnson–Lindenstrauss transforms, and hyperbolic methods.
AI for Science
Structure-aware learning for biological, molecular, physical, graph-structured, and 3D/video data.
Research Approach
I view mathematical structure not as an auxiliary tool, but as an organizing principle for learning systems. By characterizing invariance, stability, expressivity, and interaction at a mathematical level, my work seeks explanations and guarantees beyond black-box performance metrics.
Invited Talks
- November 2025“TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration,” Conference on Topological Data Analysis: Recent Developments and Applications, University of Missouri.
- October 2024“Understanding through Shape of Data: Topological Data Analysis for Interpretable AI,” Management Science and Information Systems Department Colloquium, Rutgers University.
- November 2023“Multiparameter Persistence and Its Applications,” Theory Seminar, Department of Computer Science, Rutgers University.
- July 2020“Generalized Persistence Algorithm for Decomposing Multiparameter Persistence Modules,” Applied Algebraic Topology Network Seminar.
Links
Last updated September 2026.