I am a Master’s student in Computer Science at UC Irvine, working with Unnat Jain on robot learning and dexterous manipulation. I am applying to PhD programs in CS for Fall 2027.
In summer 2026, I worked with Reno Kriz and Dave Doermann at Johns Hopkins University on open-world video anomaly detection and understanding as part of SCALE. I hold a BS in Statistics with highest honors from UC Davis, where my research with Norman Matloff on fairness in machine learning earned a 2025 CRA Honorable Mention.
Conference on Robot Learning (CoRL), 2026
GLIDE generates and refines executable guardrails for data collection and policy deployment on robot manipulation tasks that are too difficult for humans to demonstrate.
In submission.
Undergraduate thesis, 2024
A post-processing method that uses the tower property to improve the fairness of black-box predictions without retraining the model.
Decision-making processes have increasingly come to rely on sophisticated machine learning tools, raising critical concerns about the fairness of their predictions with respect to sensitive groups. The widespread adoption of commercial "black-box" models necessitates careful consideration of their legal and ethical implications for consumers. When users interact with such black-box models, a key challenge arises: how can the influence of sensitive attributes, such as race or gender, be mitigated or removed from its predictions? We propose towerDebias (tDB), a novel post-processing method designed to reduce the influence of sensitive attributes in predictions made by black-box models. Our tDB approach leverages the Tower Property from probability theory to improve prediction fairness without requiring retraining of the original model. This method is highly versatile, as it requires no prior knowledge of the original algorithm's internal structure and is adaptable to a diverse range of applications. We present a formal fairness improvement theorem for tDB and showcase its effectiveness in both regression and classification tasks using multiple real-world datasets.
Technical report, 2024
R and Python tools for exploring discrimination and teaching statistical concepts through real-world fairness analysis.
The growing influence of data science in statistics education requires tools that make key concepts accessible through real-world applications. We introduce "Data Science Looks At Discrimination" (dsld), an R package that provides a comprehensive set of analytical and graphical methods for examining issues of discrimination involving attributes such as race, gender, and age. By positioning fairness analysis as a teaching tool, the package enables instructors to demonstrate confounder effects, model bias, and related topics through applied examples. An accompanying 80-page Quarto book guides students and legal professionals in understanding these principles and applying them to real data. We describe the implementation of the package functions and illustrate their use with examples. Python interfaces are also available.
Presented a two-stage Qwen vision-language pipeline that detects and explains anomalies in raw video without predefined anomaly categories.
PosterPresented mathematical foundations of algorithmic fairness and methods to reduce bias in model predictions across demographic groups.
PosterPresented the dsld R package for discrimination analysis in education, emphasizing how it teaches statistical concepts through real-world fairness and bias examples.
SlidesPresented TowerDebias, a post-processing method that improves the fairness of black-box predictions without retraining.
SlidesPresented the dsld package for discrimination analysis in education, showing how it supports teaching statistical concepts through real-world fairness examples.
Poster