an overview of current and past research projects

Rice University

Advised by Dr. César A. Uribe and Dr. Lydia Beaudrot.

TL;DR: A systemic understanding of predator-prey relationships is central to maintaining biodiversity and the well-being of an ecosystem. As anthropogenic disturbance continues to rise in Sub-Saharan Africa, we are in need of a principled approach to study and anticipate changes among its food web networks as a result of human interference. We leverage optimal transport as the backbone of our newly proposed geometric data analysis toolkit over food web networks. Check out our preliminary results below!

[1] Hung, K., Zalles, A., et al. (2024). Towards Ecological Network Analysis with Gromov-Wasserstein Distances. ICLR 2024 Workshop on Tackling Climate Change with Machine Learning.

[2] Zalles, A., Hung, K., et al. (2023). Network Regression with Wasserstein Distances. NeurIPS 2023 Workshop on Optimal Transport and Machine Learning.

New York University

Advised by Dr. Esteban G. Tabak. Supported by the AM-SURE program, funded by NSF.

TL;DR: Often times, your data is affected by variables that should be excluded from your analysis (for ex. batch effect and protected attributes such as race, gender, socioeconomic class). We developed a theoretical framework for reducing the unwanted variability in our data distribution via optimal transport. Look out for our future works to extend this method for personalization, latent factor discovery, and semi-supervised variability reduction!

Berkeley AI Research

Advised by Dr. Alison Gopnik and Eunice Yiu. Supported by the SUPERB and BAIR NSF REU programs.

TL;DR: Have you ever contrasted the intelligence of children with adults, and maybe even artificial intelligence? Children are known to learn quickly and generalize accurately with little data to their disposal, contrary to deep neural networks and other modern machine learning frameworks. Our analysis is two-fold: (1) to understand the discrepancies in children and adults’ exploration v.s. exploitation modalities through fitting experimental data against reinforcement learning models, and (2) to understand the degree in which popular Q-learning-based RL algorithms can truly mimic what we observe within humans.

MD Anderson Cancer Center

Advised by Dr. Jagan Sastry and Dr. Venkatesh Hegde. Supported by the CPRIT CURE program.

TL;DR: HPV+ oropharyngeal cancer is rising in prevalence within the U.S. accounting for over 70% of all oropharyngeal cancers. Our group developed an anti-PD1 immunotherapy therapeudic procedure, but we observed that the treatment efficacy differed wildly between tumor implants in the neck v.s. the tongue. My work centered around identifying the differentially expressed genes across these two experiments using RNA-Sequencing Analysis, and eventually constructing a set of hypothesis on the activation/deactivation of biological pathways based on the set of differentially expressed genes.