Computational genomics / biomedical machine learning / statistical inference

Bronson Jeong

PhD candidate in Computer Science at UCLA

Bronson Jeong is a computational genomics and biomedical machine learning researcher at UCLA. His work develops scalable, interpretable methods for genetic discovery, biobank-scale inference, medical imaging, and clinical data, with an emphasis on models that remain useful when individual-level data are unavailable or expensive to analyze.

Publications Google Scholar CV GitHub
9 research outputs listed
ICML Spotlight foundation-model embeddings for 3D medical volumes
Genome Research summary-statistics heritability estimation

Research program

Methods that turn large biomedical data into interpretable discovery.

Statistical genetics

Biobank-scale inference from summary statistics

Fast, stable estimators for genetic parameters that recover individual-level accuracy from widely shared summary statistics.

Medical AI

Foundation-model embeddings for 3D medical volumes

Train-free representations that make high-dimensional imaging phenotypes usable for prediction and genetic discovery without heavy task-specific training.

Clinical data

EHR and controlled-substance data

Interpretable models for longitudinal clinical records, disease-code representations, risk prediction, and opioid-prescription data.

Population genetics

Theory for ancestry-aware inference

Coalescent-informed limits and robustness questions for reference-based local ancestry inference.

Profile

A researcher trained across statistics, computer science, and physical science.

Bronson Jeong is a PhD candidate in Computer Science at UCLA, advised by Prof. Sriram Sankararaman. His research sits at the interface of machine learning, statistics, and biomedicine, with a focus on scalable and reproducible methods for understanding the genetic basis of complex traits and diseases.

Before graduate school, Bronson studied Mathematics of Computation and Physics at UCLA and worked on astronomical spectroscopy with Prof. Alice Shapley. That training continues to shape his approach to biomedical inference: careful modeling under noise, confounding, and limited observability.

Selected publications

Recent papers and preprints

View all publications