SOTAVerified

document understanding

Document understanding involves document classification, layout analysis, information extraction, and DocQA.

Papers

Showing 121130 of 309 papers

TitleStatusHype
M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework0
Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding0
M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding0
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection0
LoRA-Contextualizing Adaptation of Large Multimodal Models for Long Document Understanding0
MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding0
Data-driven Coreference-based Ontology BuildingCode0
"What is the value of templates?" Rethinking Document Information Extraction Datasets for LLMs0
Harnessing Webpage UIs for Text-Rich Visual Understanding0
ReLayout: Towards Real-World Document Understanding via Layout-enhanced Pre-training0
Show:102550
← PrevPage 13 of 31Next →

No leaderboard results yet.