Chao Chen
Contact
- Office: Computer Science Building, 2313C
- Tel: +1-631-632-2593
- Email: chao.chen.1 (@) stonybrook.edu
Research Interests
I explore geometric and topological properties of data. These global and robust information can provide insight for modern data and image analytics. My research draws from the following different domains.
Biomedical imaging informatics: topology-informed image segmentation, generation and analysis.
Machine learning: robustness of deep neural networks, label noise, graph neural networks.
Topological data analysis: persistent homology, computation and learning with topological features.
Past Experience
Assistant Professor of Computer Science, City University of New York (CUNY), United States
Postdoc at Rutgers University, United States (advised by Prof. Dimitris Metaxas)
Postdoc at Institute of Science and Technology, Austria (advised by Prof. Herbert Edelsbrunner)
Ph.D. at Rensselaer Polytechnic Institute, United States (advised by Prof. Daniel Freedman)
B.S. at Peking University, China
Awards
2022, NSF CAREER Award Topology-Driven Learning for Biomedical Imaging Informatics
More details can be found at the department news!
2023, Stony Brook Trustees Faculty Awards (Story)
Recent Services
Associate Editor, Pattern Recognition
Action Editor, TMLR
Area Chair, ICML 2023-2025
Area Chair, CVPR 2025
Area Chair, NeurIPS 2021-2025
News and Annoucement
-
New!!
Two papers accepted by CVPR 2025!
Congratulations to Meilong and Ani for getting their papers accepted by the top CV conference CVPR.
Meilong's paper proposes the first topology-aware diffusion model for cell layout generation. Ani's paper proposes a novel gene prediction method based on spatial transcriptomics data, using a multi-faceted graph GNN that is well motivated by the biology.
-
New!!
Three papers accepted by ICLR 2025!
Congratulations to Saumya, Weimin, and Chris for getting their papers accepted by the top ML conference ICLR.
Saumya's paper proposes the first topology-aware diffusion network, generating images with explicit topological constraints (thus correct object counts and correct holes). Weimin's paper tackles backdoor attack problem for vision-language models, especially for out-of-distribution data. Chris' paper studies the geometry of long-tail data representation, and proposes a new solution via feature generation.
-
New!!
One paper accepted to JMLR!
Congratulations to Zuoyu for his paper being accepted by the top ML journal JMLR.
Zuoyu's paper discusses in details the theoretical foundation and applicaiton benefit of incoporating topological features (i.e., persistent homology) into graph neural networks.
-
New!!
One paper accepted to MeDIA!
Congratulations to Fan and Zhilin for their paper being accepted by the top medical imaging journal MeDIA.
Their paper Proposes TopoTxR, a topology-guided deep neural network for breat tissue analysis from DEC-MRIs.