Hello! I am currently a Biostatistics Ph.D. Candidate at New York University supervised by
Dr. Hai Shu.
My research focuses on creating statistical machine learning methods for high dimensional biomedical data (e.g. Alzheimer's disease). I enjoy integrating deep learning techniques into statistical frameworks (false discovery rate control, sparse canonical correlation analysis, survival modeling) to improve power, interpretability, and computational scalability.
Broadly, my projects span areas in:
- Representation learning (Self-supervised learning, CCA)
- Reliable error control (FDR control)
- Interpretability (Sparsity, feature importance)
- Medical Imaging (FDG-PET, MRI, Ultrasound)
Activities
- 11-2025: SSL project using child lingual ultrasound data is accepted to Conference on Motor Speech for oral presentation
- 09-2025: Selected as an FDA-OCE-ASA Oncology Educational Fellow
- 08-2025: Attended JSM 2025 in Nashville to present our work enjoyment paper
- 03-2025: Attended ENAR 2025 in New Orleans to present our causal discovery paper
- 08-2024: Attended JSM 2024 in Portland to present DeepFDR, funded partially by ASA Student Travel Award
- 05-2024: Attended AISTATS 2024 in Valencia to present DeepFDR
- 03-2024: Awarded Finalist for the ENAR DataFest, and attended ENAR 2024 in Baltimore to present our work
|
|
|
DeepFDR: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data
Taehyo Kim,
Hai Shu*,
Qiran Jia,
Mony de Leon
AISTATS, 2024 (JSM Student Paper Award, ASA Statistics in Imaging)
Paper
/
Code
We propose DeepFDR, the first work to integrate deep learning based unsupervised image segmentation model into multiple hypothesis testing.
|
|
|
A False Discovery Rate Control Method Using a Fully Connected Hidden Markov Random Field for Neuroimaging Data
Taehyo Kim,
Qiran Jia,
Mony de Leon,
Hai Shu
Major Revision at Medical Image Analysis, 2025
Paper
/
Code
We propose fcHMRF-LIS, a stable spatial multiple hypothesis testing framework that models voxel-wise spatial dependencies through a fully connected Hidden Markov Random Field.
|
|
|
Self-Supervised Learning on Lingual Ultrasound Video Encodes Clinically Meaningful Articulatory Structure of Rhotic Production in Residual Speech Sound Disorder
Anonymous
Under Review at a CS Conference
Paper
/
Code
We present the first self-supervised learning framework that focuses on within-phoneme articulatory structure of American English rhotic production (r sound) from lingual ultrasound video of children with residual speech sound disorder.
|
|
|
UKAN-EP: Enhancing U-KAN with Efficient Attention and Pyramid Aggregation for 3D Multi-Modal MRI Brain Tumor Segmentation
Yanbing Chen, Tianze Tang, Taehyo Kim, Hai Shu
BMC Medical Imaging, 2025
Paper
/
Code
We propose UKAN-EP, which integrates Kolmogorov-Arnold Network (KAN) layers into a U-Net backbone with Efficient Channel Attention (ECA) and Pyramid Feature Aggregation (PFA) modules to enhance inter-modality feature fusion and multi-scale feature representation.
|
|
|
Computational pathology: A survey review and the way forward
Mahdi S. Hosseini, Babak Ehteshami Bejnordi, Vincent Quoc-Huy Trinh,
Lyndon Chan, Danial Hasan, Xingwen Li, Stephen Yang, Taehyo Kim,
Haochen Zhang, Theodore Wu, Kajanan Chinniah, Sina Maghsoudlou,
Ryan Zhang, Jiadai Zhu, Samir Khaki , Andrei Buin, Fatemeh Chaji, Ala Salehi,
Bich Ngoc Nguyen, Dimitris Samaras, Konstantinos N. Plataniotis
Journal of Pathology Informatics, 2024
Paper
We provide a comprehensive review of over 800 papers and oversee the development of Computational Pathology from data-centric, model-centric, and application-centric perspectives to address the trends and challenges inherent in this multidisciplinary science.
|
|
|
A Global Understanding of Work Enjoyment and Human Wellbeing
Alden Yuanhong Lai, Taehyo Kim, Alex Dahlen, Tim Lomas
Under Review at Social Indicators Research, 2025
Code
This study uses a probability-based sample from the Gallup World Poll (2020-2023) to understand the experience of work among workers in 145 countries.
|
Teaching
- Spring 2026: Teaching Assistant, Statistical Methods in Genomics and Bioinformatics (GPH-GU 2378), New York University
- Fall 2025: Teaching Assistant, Survey Design, Analysis, and Reporting (GPH-GU 2387), New York University
- Fall 2024: Teaching Assistant, Applied Bayesian Analysis in Public Health (GPH-GU 2272/3372), New York University
- Spring 2024: Teaching Assistant, Applied Survival Analysis (GPH-GU 2368/3368), New York University
- Fall 2023: Teaching Assistant, Statistical Inference (GPH-GU 3225), New York University
- Summer 2024: Mentor, Pathways into Quantitative Aging Research Summer Program, New York University
- Summer 2022: Mentor, Pathways into Quantitative Aging Research Summer Program, New York University
|
|
