Chao Chen
Associate Professor
Stony Brook, NY 11794-8322
Contact
- Office: Computer Science Building, 2313C
- Tel: +1-631-632-2593
- Email: chao.chen.1 (@) stonybrook.edu
Research Interests
I develop robust and trustworthy learning methods for modern biomedical data and beyond. My research draws from the following different domains.
Robust and Trustworthy Machine Learning: backdoor attacks, adversarial attacks, label noise, uncertainty.
Biomedical informatics: digital pathology, multi-omics data analytics, spatial and topological analysis of tissue micorenvionment.
Topological data analysis: learning with topological features, topology-informed image segmentation and analysis.
For more information, please see the Research Webpage.
Past Experience
Awards
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.
|