Preprint
Jul 2026
DOSA: A Tree-Guided, Self-Regressive Framework for Long Document Structure Analysis
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, making document structure analysis fundamental to information retrieval and document understanding. However, accurately inferring such relatio...
Bohou Li, Ben Sowell, Mehul A. Shah et al.
· 0 citations