Papers with Code 아카이브
Document AI
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 1
- 보존된 평가 기록
- 1
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Zero-Shot Complex Question-Answering on Long Scientific Documents
Shakti-VLMs: Scalable Vision-Language Models for Enterprise AI
OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models
KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding
Qwen2.5-VL Technical Report
Assessing Generative AI value in a public sector context: evidence from a field experiment
DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
AIN: The Arabic INclusive Large Multimodal Model
Ocean-OCR: Towards General OCR Application via a Vision-Language Model
HERITAGE: An End-to-End Web Platform for Processing Korean Historical Documents in Hanja
BoundingDocs: a Unified Dataset for Document Question Answering with Spatial Annotations
Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends
LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating
Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Models
Zero-Shot Prompting and Few-Shot Fine-Tuning: Revisiting Document Image Classification Using Large Language Models
DoPTA: Improving Document Layout Analysis using Patch-Text Alignment
Memory-Augmented Agent Training for Business Document Understanding
Learned Compression for Compressed Learning
DocVLM: Make Your VLM an Efficient Reader
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks
MATATA: Weakly Supervised End-to-End MAthematical Tool-Augmented Reasoning for Tabular Applications
Enhancing Document AI Data Generation Through Graph-Based Synthetic Layouts
DOGE: Towards Versatile Visual Document Grounding and Referring
StructFormer: Document Structure-based Masked Attention and its Impact on Language Model Pre-Training
Information Extraction from Heterogeneous Documents without Ground Truth Labels using Synthetic Label Generation and Knowledge Distillation
Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction
Is Cognition consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document Understanding
M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework
Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding
M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
LoRA-Contextualizing Adaptation of Large Multimodal Models for Long Document Understanding
MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding
CAMEL-Bench: A Comprehensive Arabic LMM Benchmark
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.