Papers with Code 아카이브
document understanding
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
Document understanding involves document classification, layout analysis, information extraction, and DocQA.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Machine Unlearning for Document Classification
A LayoutLMv3-Based Model for Enhanced Relation Extraction in Visually-Rich Documents
Towards Efficient Resume Understanding: A Multi-Granularity Multi-Modal Pre-Training Approach
HRVDA: High-Resolution Visual Document Assistant
LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding
BuDDIE: A Business Document Dataset for Multi-task Information Extraction
OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition
Can AI Models Appreciate Document Aesthetics? An Exploration of Legibility and Layout Quality in Relation to Prediction Confidence
Visually Guided Generative Text-Layout Pre-training for Document Intelligence
LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding
mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding
TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document
Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models
3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding
Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding
Read and Think: An Efficient Step-wise Multimodal Language Model for Document Understanding and Reasoning
RJUA-MedDQA: A Multimodal Benchmark for Medical Document Question Answering and Clinical Reasoning
LAPDoc: Layout-Aware Prompting for Documents
Financial Report Chunking for Effective Retrieval Augmented Generation
LongFin: A Multimodal Document Understanding Model for Long Financial Domain Documents
On the Affinity, Rationality, and Diversity of Hierarchical Topic Modeling
InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions
INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning
Long Context Compression with Activation Beacon
DocGraphLM: Documental Graph Language Model for Information Extraction
DocLLM: A layout-aware generative language model for multimodal document understanding
Privacy-Aware Document Visual Question Answering
WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data
SLJP: Semantic Extraction based Legal Judgment Prediction
Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs
DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding
Efficient End-to-End Visual Document Understanding with Rationale Distillation
DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency
A Multi-Modal Multilingual Benchmark for Document Image Classification
DocTrack: A Visually-Rich Document Dataset Really Aligned with Human Eye Movement for Machine Reading
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.