Our work “Two-Sided State-Space Models for Sequential Recommendation with Non-Random Multimodal Review Feedback” has been accepted to the Findings of EMNLP 2026.
Ph.D. Student · Computational Biology and Bioinformatics · Duke University
I study how models remain reliable under uncertainty.
I am a Ph.D. student in Computational Biology and Bioinformatics at Duke University, advised by Prof. Anru Zhang. I work in clinical informatics and health data science, building models from electronic health records, clinical notes, and medical images.
Research
Health records capture the process of care, not the disease itself.
What gets recorded, and when, reflects how patients move through the health system as much as how they are doing. I develop machine learning methods for longitudinal and multimodal clinical data, including EHR time series, clinical notes, and medical images, drawing on representation learning, causal inference, and statistics.
-
Longitudinal patient representations
Learning representations of patients from irregular, multimodal EHR histories to support downstream clinical prediction.
-
Informative missingness
Treating which measurements, notes, and modalities get recorded as signal rather than noise.
-
Reliable clinical prediction
Calibration, robustness under distribution shift, and causal reasoning so that predictions can inform clinical decisions.
Recent News
I am excited to announce that I have completed my Bachelor of Science in Applied Mathematics and Statistics, graduating with Highest Honors, at Emory University. I am deeply grateful to my mentor, Prof. Ruoxuan Xiong, for her guidance and support throughout my studies.
Our work “Learning Dynamic Representations and Policies from Multimodal Clinical Time-Series with Informative Missingness” has been accepted to the Findings of ACL 2026.
Our work “DART: Mitigating Harm Drift in Difference-Aware LLMs via Distill-Audit-Repair Training” has been accepted to ACL 2026 Findings.
Our work “MambaDATG: Domain-Adaptive Tri-Plane-Gated Pre-training for 3D Abdominal Segmentation” has been accepted as an oral presentation at ICASSP 2026.
My new personal website is now live! It is accessible worldwide, including regions where Google services are restricted.
Beyond Research
All experiences-
AI literacy
Founded the Emory Artificial Intelligence and Data Association and its “AI for ALL” initiative, growing it to 200+ members across majors.
-
Community
Led a 100+ person team as President of the Emory Chinese Student Association, with programs reaching 2,000+ students and families.
-
Teaching
Teaching assistant for an undergraduate machine learning course at Emory and for Olympiad algebra at AwesomeMath.