2 papers
cs.AI2026
DOSA: A Tree-Guided, Self-Regressive Framework for Long Document Structure Analysis
Bohou Li, Benjamin Sowell, Mehul Shah +2
In visually-rich documents, information is encoded not only in individual page objects such as tables, headers, and text blocks, but also in the structural relations among them, ma…
cs.DB2024
The Design of an LLM-powered Unstructured Analytics System
Eric Anderson, Jonathan Fritz, Austin Lee +11
LLMs demonstrate an uncanny ability to process unstructured data, and as such, have the potential to go beyond search and run complex, semantic analyses at scale. We describe the d…