4 papers
KathDB-FAO: Optimizing Multimodal Queries through Operator Grouping and Code Reuse
Guorui Xiao, Douglas Brown, Artur Borycki +1
Advances in multimodal large language models (multimodal LLMs) allow data systems to answer analytical queries over text and images alongside relational tables, but at a significan…
KathDB: Explainable Multimodal Database Management System with Human-AI Collaboration
Guorui Xiao, Enhao Zhang, Nicole Sullivan +2
Traditional DBMSs execute user- or application-provided SQL queries over relational data with strong semantic guarantees and advanced query optimization, but writing complex SQL is…
RACOON: An LLM-based Framework for Retrieval-Augmented Column Type Annotation with a Knowledge Graph
Lindsey Linxi Wei, Guorui Xiao, Magdalena Balazinska
As an important component of data exploration and integration, Column Type Annotation (CTA) aims to label columns of a table with one or more semantic types. With the recent develo…
Demonstration of MaskSearch: Efficiently Querying Image Masks for Machine Learning Workflows
Lindsey Linxi Wei, Chung Yik Edward Yeung, Hongjian Yu +3
We demonstrate MaskSearch, a system designed to accelerate queries over databases of image masks generated by machine learning models. MaskSearch formalizes and accelerates a new c…