SOTAVerified

document understanding

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 309 papers

TitleStatusHype
Docopilot: Improving Multimodal Models for Document-Level UnderstandingCode1
DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document UnderstandingCode1
LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and LocatingCode1
Zero-Shot Prompting and Few-Shot Fine-Tuning: Revisiting Document Image Classification Using Large Language Models—0
Typhoon 2: A Family of Open Text and Multimodal Thai Large Language ModelsCode1
Memory-Augmented Agent Training for Business Document Understanding—0
Learned Compression for Compressed LearningCode0
DocVLM: Make Your VLM an Efficient Reader—0
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time ScalingCode0
BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks—0
MATATA: Weakly Supervised End-to-End MAthematical Tool-Augmented Reasoning for Tabular Applications—0
DOGE: Towards Versatile Visual Document Grounding and Referring—0
StructFormer: Document Structure-based Masked Attention and its Impact on Language Model Pre-Training—0
Information Extraction from Heterogeneous Documents without Ground Truth Labels using Synthetic Label Generation and Knowledge Distillation—0
Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown ExtractionCode2
Is Cognition consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document Understanding—0
M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework—0
Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding—0
M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding—0
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection—0
LoRA-Contextualizing Adaptation of Large Multimodal Models for Long Document Understanding—0
MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding—0
CAMEL-Bench: A Comprehensive Arabic LMM BenchmarkCode1
Data-driven Coreference-based Ontology BuildingCode0
"What is the value of templates?" Rethinking Document Information Extraction Datasets for LLMs—0
Harnessing Webpage UIs for Text-Rich Visual Understanding—0
DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive PerceptionCode9
ChuLo: Chunk-Level Key Information Representation for Long Document ProcessingCode0
ReLayout: Towards Real-World Document Understanding via Layout-enhanced Pre-training—0
LLMMapReduce: Simplified Long-Sequence Processing using Large Language ModelsCode4
PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse SamplingCode2
DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models—0
DAViD: Domain Adaptive Visually-Rich Document Understanding with Synthetic Insights—0
Modeling Layout Reading Order as Ordering Relations for Visually-rich Document UnderstandingCode1
Leveraging Long-Context Large Language Models for Multi-Document Understanding and Summarization in Enterprise Applications—0
Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary ResolutionCode3
DocMamba: Efficient Document Pre-training with State Space Model—0
Leveraging Distillation Techniques for Document Understanding: A Case Study with FLAN-T5—0
One missing piece in Vision and Language: A Survey on Comics UnderstandingCode2
Information Extraction from Visually Rich Documents Using Directed Weighted Graph Neural NetworkCode0
mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document UnderstandingCode0
ViRED: Prediction of Visual Relations in Engineering Drawings—0
The MERIT Dataset: Modelling and Efficiently Rendering Interpretable Transcripts—0
DocLayLLM: An Efficient and Effective Multi-modal Extension of Large Language Models for Text-rich Document UnderstandingCode1
SynthDoc: Bilingual Documents Synthesis for Visual Document Understanding—0
Building and better understanding vision-language models: insights and future directions—0
Arctic-TILT. Business Document Understanding at Sub-Billion Scale—0
Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image PyramidCode5
Deep Learning based Visually Rich Document Content Understanding: A Survey—0
Deep Learning based Key Information Extraction from Business Documents: Systematic Literature Review—0
Show:102550
← PrevPage 2 of 7Next →

No leaderboard results yet.