Research

Note: All Figures are generated by GPT.

Personalized Sequential Decision-Making, Reinforcement Learning, and Latent Variable Models

This line develops statistical and machine learning methods for modeling individual-level learning and decision dynamics from behavioral and neurophysiological time processes. The focus is on latent cognitive states, reinforcement-learning experiments, and personalized sequential representations.

Publications:

Bian, Y., Guo, X., Wang, Y. (2025). Joint Modeling for Learning Decision-Making Dynamics in Behavioral Experiments. Annals of Applied Statistics [Paper][Arxiv] 

Guo, X., Zeng, D., Wang, Y. (2025). HMM for Discovering Decision-Making Dynamics Using Reinforcement Learning Experiments. Biostatistics. [Paper] [Arxiv] [Code] 

Guo, X., Yang, B., Loh, J. M., Wang, Q., Wang, Y., (2024). A Hierarchical Random Effects State-space Model for Modeling Brain Activities from Electroencephalogram Data. Biometrics. [Paper] [Arxiv] [Code]

Guo, X., Zeng, D., Wang, Y. (2024). A Semiparametric Inverse Reinforcement Learning Approach to Characterize Decision Making for Mental Disorders. Journal of the American Statistical Association. [Paper] [Code] 

Submitted:

Guo, X.* (2026+).  Anchored Variational Inference for Personalized Sequential Latent-State Models. [Arxiv] [Code]

Bian, Y., Wang, Y., Guo, X.* (2026+). Shared Hidden-factor Information Framework for Multiple Behavioral Tasks.

Working:

Personalized State-Partitioned GRUs for Learning Individual Differences in Reward Tasks.

A Joint State-space Model for fMRI and Trial-level Decision Processes.

High-dimensional Functional Data Analysis

This line focuses on statistical learning theory and methodology for complex high-dimensional functional data. The work addresses variable selection, prediction, and model form identification when signals are structured, infinite-dimensional, or difficult to represent using standard regression tools.

Publications:

Guo, X., Li, Y., Hsing, T. (2026+). Variable Selection and Minimax Prediction in High-dimensional Functional Linear Model. Statistica Sinica.  [Paper] [Arxiv] [Code] 

Submitted:

Guo, X.*, Li, Y., Du, P. (2026+).  Model Form Identification in High-Dimensional Functional Linear Regressions. [Arxiv] [Code]

Working:

Debiased Causal Learning for High-dimensional Functional Linear Models

Precision Medicine and Digital Phenotyping

This line develops statistical methods for learning individualized health patterns and treatment strategies from longitudinal, biomarker, and digital health data. The goal is to support interpretable, data-driven tools for precision medicine, including estimating sequential effects and tailoring interventions for chronic disorders.

Publications:

Yang, B., Guo, X., Loh, J. M., Wang, Q., Wang, Y., (2024). Learning Optimal Biomarker-Guided Treatment Policy for Chronic Disorders. Statistics in Medicine. [Paper] 

Submitted:

Guo, X.*, Cai, Z., Wang, Y., Zeng, D. (2026+). Cumulative Marginal Mean Model for Assessing Sequential Effects Using Digital Health Data. [Arxiv] 

Machine Learning Applications for Imaging and Spatial Omics Data

This line develops computational tools for extracting biological and scientific signals from complex image-based or high-throughput data. The work combines modern machine learning with domain-specific measurement challenges in spatial omics, plant phenotyping, and metabolomics.

Publications:

Guo, X., Qiu, Y., Nettleton, D., Schnable, P. S. (2023). High-Throughput Field Plant Phenotyping: A Self-Supervised Sequential CNN Method to Segment Overlapping Plants. Plant Phenomics. [Paper] [Code] 

Guo, X., Qiu, Y., Nettleton, D., Yeh, C. T., Zheng, Z., Hey, S., Schnable, P. S. (2021). KAT4IA: K-means assisted training for image analysis of field-grown plant phenotypes. Plant Phenomics. [Paper] [Code] 

Working:

Li, M., Wang, X., Xu, S., Yin, Y.,  Guo, X.*, Song, D.* (2026+). spEnhance: A Computational Framework for Trustworthy Super-Resolution Enhancement in Spatial Omics.

Uncertainty Quantification in Medical Image Segmentation: A Statistical Review.