SOTAVerified

Document AI

Papers

Showing 110 of 40 papers

TitleStatusHype
DocRes: A Generalist Model Toward Unifying Document Image Restoration TasksCode4
Unifying Vision, Text, and Layout for Universal Document ProcessingCode3
LayoutLM: Pre-training of Text and Layout for Document Image UnderstandingCode2
OfficeBench: Benchmarking Language Agents across Multiple Applications for Office AutomationCode1
On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and ReasoningCode1
DocTrack: A Visually-Rich Document Dataset Really Aligned with Human Eye Movement for Machine ReadingCode1
Document AI: A Comparative Study of Transformer-Based, Graph-Based Models, and Convolutional Neural Networks For Document Layout AnalysisCode1
Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents (Extended Version)Code1
Document Understanding Dataset and Evaluation (DUDE)Code1
Context-Aware Chart Element DetectionCode1
Show:102550
← PrevPage 1 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1LayoutLMv3Average F199.21Unverified