About Me
I am a PhD student in the Camera Culture group at the MIT Media Laboratory, advised by Ramesh Raskar. My research focuses on data-centric machine learning, specifically data markets, incentives, and data attribution. I am supported by the National Science Foundation's Graduate Research Fellowship.
I study how data influences the reliability and transparency of machine learning systems through frameworks for data attribution and incentive alignment.
Outside the lab, I enjoy activites:
Research Focus
My current research focus
- Data Markets:Design of economic and algorithmic frameworks for data exchange.
- Data Attribution: Measuring influence and provenance in model.
- Responsible AI:Improving alignment, accountability, and fairness in ML systems.
Experience
2025 (Upcoming)
Research Intern Microsoft Research, Redmond
Working on data attribution in large language models to identify the influence of training data on model outputs.
2024
Visiting Researcher University of Chicago
Explored data markets and data escrow mechanisms with Raul Castro Fernandez in the Department of Computer Science at the University of Chicago.
2022–present
Research Assistant MIT Media Lab
Working on data-centric machine learning in the Camera Culture group at the Massachusetts Institute of Technology.
2020–2022
Machine Learning Researcher Harvard Medical School
Developed fairness and uncertainty quantification methods for medical imaging at the Martinos Center.
2019–2022
Machine Learning Scientist Massachusetts General Hospital
Built deep learning models for medical applications including stroke detection and aortic aneurysm quantification.
2018
Research Intern Oak Ridge National Laboratory
Applied machine learning to molecular dynamics simulations on supercomputing infrastructure.
2018
Research Intern NASA
Analyzed hurricane damage using satellite imagery for environmental policy planning.
Selected papers
Data Acquisition via Experimental Design for Decentralized Data Markets
NeurIPS 2024
Developed a framework for optimizing budget-aware data acquisition in decentralized markets with a experimental design informed loss.
Federated Conformal Predictors for Distributed Uncertainty Quantification
ICML 2023
Introduced novel methods for uncertainty quantification in federated learning scenarios, extending conformal prediction theory to distributed data contexts.
Improving Trustworthiness in Automatic Disease Severity Rating with Ordinal Conformal Prediction
MICCAI 2022
Developed ordinal conformal prediction methods for disease severity assessment in medical imaging, providing rigorous uncertainty quantification for clinical decision support.
Fair Conformal Predictors for Applications in Medical Imaging
AAAI 2022
Proposed novel algorithms for ensuring fairness in uncertainty quantification across diverse patient populations, addressing algorithmic bias in medical AI systems.
Radiology: Artificial Intelligence
Designed and validated an automated system for detecting aortic aneurysms in CT scans, demonstrating clinical utility through rigorous evaluation with expert radiologists.