🎉 Caltech SURF 2025
I will be a mentor for Caltech Summer Undergraduate Research Fellowships (SURF) program in 2025.
🌞About Me
Bohan Chen is a postdoctoral researcher at Caltech under the supervision of Prof. Andrew Stuart. His research interests includes data assimilation, stochastic process models, graph-based machine learning, and active learning. His work during Ph.D. applied graph-based active learning methods to tackle different image processing problems, and developed innovative batch active learning strategies. He explored the integration of large language models with knowledge graphs. His current research is primarily focused on data assimilation.
Email: bhchen@caltech.edu
Phone: +1 424-402-7355
Interests
- Data Assimilation
- Graph-based Machine Learning
- Image Analysis and Processing
- Mathematical Modeling
- KG-enhanced LLMs
Education
Ph.D. in Mathematics
Department of Mathematics, University of California, Los Angeles
B.S. in Mathematics
School of Mathematical Sciences, Peking University
📚 My Research
My current research focuses on learning-based filtering processes in data assimilation problems.
Previously, I explored various topics in graph-based machine learning and active learning, applying these methods to semi-supervised learning tasks to reduce reliance on traditional data-hungry approaches. These tasks often involve training with scarce ground-truth information, such as manually labeled remote sensing data by LANL experts, SAR image classification, and hyperspectral unmixing.
If you’re interested in these topics, feel free to reach out to collaborate 😃
Recent News
My Personal Icon Design
I designed a unique personal icon inspired by mathematical symbols to represent my identity.
Featured Publications
Recent Publications
(2024).
Narrative Analysis of True Crime Podcasts With Knowledge Graph-Augmented Large Language Models.
Proceedings of the 33rd International Conference on Information and Knowledge Management, GTA3 Workshop-2024.
(2024).
Batch Active Learning for Multispectral and Hyperspectral Image Segmentation Using Similarity Graphs.
Communications on Applied Mathematics and Computation.
(2023).
AutoKG: Efficient Automated Knowledge Graph Generation for Language Models.
2023 IEEE International Conference on Big Data (BigData).
(2023).
Material Identification in Complex Environments: Neural Network Approaches to Hyperspectral Image Analysis.
2023 13th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS).
Recent & Upcoming Talks