DocSeeker improves long-document understanding in MLLMs via a two-stage training process that combines supervised fine-tuning from distilled data with evidence-aware group relative policy optimization and memory-efficient resolution allocation.
mplug- docowl2: High-resolution compressing for ocr-free multi- page document understanding
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1roles
method 1polarities
baseline 1representative citing papers
citing papers explorer
-
DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding
DocSeeker improves long-document understanding in MLLMs via a two-stage training process that combines supervised fine-tuning from distilled data with evidence-aware group relative policy optimization and memory-efficient resolution allocation.