SOTAVerified

document understanding

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

Papers

Showing 301309 of 309 papers

TitleStatusHype
HERITAGE: An End-to-End Web Platform for Processing Korean Historical Documents in HanjaCode0
SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain GapCode0
Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document UnderstandingCode0
GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document UnderstandingCode0
Token-level Correlation-guided Compression for Efficient Multimodal Document UnderstandingCode0
Financial Report Chunking for Effective Retrieval Augmented GenerationCode0
SFDLA: Source-Free Document Layout AnalysisCode0
KRED: Knowledge-Aware Document Representation for News RecommendationsCode0
XDoc: Unified Pre-training for Cross-Format Document UnderstandingCode0
Show:102550
← PrevPage 13 of 13Next →

No leaderboard results yet.