Lindsey Linxi Wei

I am an undergraduate student at the University of Washington, pursuing a double major in Computer Science and Applied Mathematics. I am a researcher in the UW Database Group (UWDB), advised by Prof. Magdalena Balazinska. I have also collaborated with Prof. Dan Suciu. I spent Summer 2025 in the EPIC Data Lab at UC Berkeley as a visiting researcher, advised by Prof. Aditya Parameswaran. I am also fortunate to be mentored by Guorui Xiao and Shreya Shankar.

My research lies at the intersection of data management and machine learning. I am particularly interested in data semantics: how systems can understand the meaning of data and use that understanding to support intelligent and reliable data processing.

Recently, I have been exploring how large language models can be used as semantic reasoning modules inside data systems, and what new challenges this introduces for system design, optimization, and reliability.

News

• Jan 2026: I am honored to receive an honorable mention for the 2025-2026 CRA Outstanding Undergraduate Researcher Award!
• Dec 2025: We have released the preprint of MOAR (Multi-Objective Agentic Rewrites for Unstructured Data Processing).

Publications

*Equal contribution

RACOON: An LLM-based Framework for Retrieval-Augmented Column Type Annotation with a Knowledge Graph
Lindsey Linxi Wei, Guorui Xiao, Magdalena Balazinska
NeurIPS 2024 Third Table Representation Learning Workshop
[ paper ]

Demonstration of MaskSearch: Efficiently Querying Image Masks for Machine Learning Workflows
Lindsey Linxi Wei*, Chung Yik Edward Yeung*, Hongjian Yu*, Jingchuan Zhou*, Dong He, Magdalena Balazinska
VLDB 2024 Demonstration Track
[ paper ]