Research

Heading Hierarchy Reconstruction for Complex and Long Documents with Level-Wise Multimodal Memory

Single source1 source14 Oct 2026

arXiv:2610.18238v1 Announce Type: cross Abstract: Vision-language models (VLMs) have been widely adopted for document parsing and optical character recognition (OCR), as they can accurately extract page-level elements.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2610.18238

← Back to all developments · Signals are a development reported by more than one source. See the methodology.