My research interests include statistical genetics, high-dimensional data analysis, robust statistics, and deep neural networks, with a strong focus on practical applications in genomics and cancer research. I have developed robust statistical methods to address the challenges of complex high-dimensional data, including data contamination, heteroscedasticity, and structured sparsity. My work extends to advanced methodologies for outlier detection and variable selection, which I actively apply in cancer clinical trials to identify predictive biomarkers and enhance prognostic models. Moving forward, I aim to integrate AI techniques into areas of high-dimensional data and robust statistics, focusing on improving real-world data analysis across various domains, particularly within the health sciences.