{"total":147,"rows":[{"id":"2109.00122","title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","created":"2021-09-01","cited_by_count":562,"area":null},{"id":"2501.00321","title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","created":"2024-12-31","cited_by_count":173,"area":"mllm"},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"area":null},{"id":"2110.00061","title":"PubTables-1M: Towards comprehensive table extraction from unstructured documents","created":"2021-09-30","cited_by_count":126,"area":null},{"id":"2206.01347","title":"MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data","created":"2022-06-03","cited_by_count":121,"area":null},{"id":"2509.22186","title":"MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing","created":"2025-09-26","cited_by_count":116,"area":"mllm"},{"id":"2105.02584","title":"TABBIE: Pretrained Representations of Tabular Data","created":"2021-05-06","cited_by_count":111,"area":null},{"id":"2203.01017","title":"TableFormer: Table Structure Understanding with Transformers","created":"2022-03-02","cited_by_count":94,"area":null},{"id":"2506.05218","title":"MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm","created":"2025-06-05","cited_by_count":87,"area":null},{"id":"2402.02315","title":"A Survey of Large Language Models in Finance (FinLLMs)","created":"2024-02-04","cited_by_count":79,"area":null},{"id":"2403.19128","title":"OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition","created":"2024-03-28","cited_by_count":74,"area":null},{"id":"2406.01326","title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","created":"2024-06-03","cited_by_count":71,"area":null},{"id":"2404.19205","title":"TableVQA-Bench: A Visual Question Answering Benchmark on Multiple Table Domains","created":"2024-04-30","cited_by_count":69,"area":null},{"id":"2305.05862","title":"Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks","created":"2023-05-10","cited_by_count":59,"area":null},{"id":"2302.05658","title":"DocILE Benchmark for Document Information Localization and Extraction","created":"2023-02-11","cited_by_count":58,"area":null},{"id":"2503.11576","title":"SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion","created":"2025-03-14","cited_by_count":53,"area":"mllm"},{"id":"2105.06224","title":"LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment","created":"2021-05-13","cited_by_count":46,"area":null},{"id":"2402.05131","title":"Financial Report Chunking for Effective Retrieval Augmented Generation","created":"2024-02-05","cited_by_count":46,"area":"rag"},{"id":"2410.21169","title":"Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction","created":"2024-10-28","cited_by_count":44,"area":"rag"},{"id":"2109.02199","title":"Parsing Table Structures in the Wild","created":"2021-09-06","cited_by_count":43,"area":null},{"id":"2201.09745","title":"Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks","created":"2022-01-24","cited_by_count":42,"area":null},{"id":"2303.06949","title":"Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling","created":"2023-03-13","cited_by_count":41,"area":null},{"id":"2502.12342","title":"REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark","created":"2025-02-17","cited_by_count":35,"area":"rag"},{"id":"2305.03393","title":"Optimized Table Tokenization for Table Structure Recognition","created":"2023-05-05","cited_by_count":34,"area":null},{"id":"2111.13359","title":"Neural Collaborative Graph Machines for Table Structure Recognition","created":"2021-11-26","cited_by_count":30,"area":null},{"id":"2203.09056","title":"Robust Table Detection and Structure Recognition from Heterogeneous Document Images","created":"2022-03-17","cited_by_count":30,"area":null},{"id":"2208.04921","title":"TSRFormer: Table Structure Recognition with Transformers","created":"2022-08-09","cited_by_count":27,"area":null},{"id":"2412.09613","title":"PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models","created":"2024-12-12","cited_by_count":25,"area":"mllm"},{"id":"2105.01736","title":"Retrieving Complex Tables with Multi-Granular Graph Representation Learning","created":"2021-05-04","cited_by_count":24,"area":null},{"id":"2502.16161","title":"OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models","created":"2025-02-22","cited_by_count":23,"area":"lr"},{"id":"2111.07533","title":"Automated scholarly paper review: Concepts, technologies, and challenges","created":"2021-11-15","cited_by_count":21,"area":null},{"id":"2210.05391","title":"PP-StructureV2: A Stronger Document Analysis System","created":"2022-10-11","cited_by_count":20,"area":null},{"id":"2502.09927","title":"Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence","created":"2025-02-14","cited_by_count":20,"area":null},{"id":"2208.14687","title":"TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformers","created":"2022-08-31","cited_by_count":19,"area":null},{"id":"2303.03730","title":"LORE: Logical Location Regression Network for Table Structure Recognition","created":"2023-03-07","cited_by_count":19,"area":null},{"id":"2410.21311","title":"MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding","created":"2024-10-25","cited_by_count":19,"area":"mllm"},{"id":"2104.14272","title":"Current Status and Performance Analysis of Table Recognition in Document Images with Deep Neural Networks","created":"2021-04-29","cited_by_count":18,"area":null},{"id":"2307.07929","title":"DocTr: Document Transformer for Structured Information Extraction in Documents","created":"2023-07-16","cited_by_count":18,"area":null},{"id":"2111.07129","title":"Visual Understanding of Complex Table Structures from Document Images","created":"2021-11-13","cited_by_count":17,"area":null},{"id":"2411.19504","title":"TQA-Bench: Evaluating LLMs for Multi-Table Question Answering","created":"2024-11-29","cited_by_count":17,"area":null},{"id":"2509.19760","title":"Logics-Parsing Technical Report","created":"2025-09-24","cited_by_count":17,"area":"mllm"},{"id":"2510.15349","title":"Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing","created":"2025-10-17","cited_by_count":17,"area":"mllm"},{"id":"2511.03929","title":"NVIDIA Nemotron Nano V2 VL","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2211.08469","title":"Deep learning for table detection and structure recognition: A survey","created":"2022-11-15","cited_by_count":15,"area":null},{"id":"2303.00716","title":"Aligning benchmark datasets for table structure recognition","created":"2023-03-01","cited_by_count":15,"area":null},{"id":"2303.08648","title":"An End-to-End Multi-Task Learning Model for Image-based Table Recognition","created":"2023-03-15","cited_by_count":14,"area":null},{"id":"2309.14962","title":"GridFormer: Towards Accurate Table Structure Recognition via Grid Prediction","created":"2023-09-26","cited_by_count":13,"area":null},{"id":"2403.04822","title":"UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining","created":"2024-03-07","cited_by_count":13,"area":null},{"id":"2506.11375","title":"Benchmarking Multimodal LLMs on Recognition and Understanding over Chemical Tables","created":"2025-06-13","cited_by_count":13,"area":"mllm"},{"id":"2303.04384","title":"SEMv2: Table Separation Line Detection Based on Instance Segmentation","created":"2023-03-08","cited_by_count":12,"area":null},{"id":"2303.11615","title":"Robust Table Structure Recognition with Dynamic Queries Enhanced Detection Transformer","created":"2023-03-21","cited_by_count":12,"area":null},{"id":"2206.11229","title":"Business Document Information Extraction: Towards Practical Benchmarks","created":"2022-06-20","cited_by_count":11,"area":null},{"id":"2405.21013","title":"StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond","created":"2024-05-31","cited_by_count":11,"area":"mllm"},{"id":"2604.08538","title":"ParseBench: A Document Parsing Benchmark for AI Agents","created":"2026-04-09","cited_by_count":11,"area":"agents"},{"id":"2303.07641","title":"Rethinking Image-based Table Recognition Using Weakly Supervised Methods","created":"2023-03-14","cited_by_count":10,"area":null},{"id":"2307.04217","title":"LakeBench: Benchmarks for Data Discovery over Data Lakes","created":"2023-07-09","cited_by_count":10,"area":null},{"id":"2308.12896","title":"Beyond Document Page Classification: Design, Datasets, and Challenges","created":"2023-08-24","cited_by_count":10,"area":null},{"id":"2412.16158","title":"HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding","created":"2024-12-20","cited_by_count":10,"area":"mllm"},{"id":"2412.20662","title":"Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner","created":"2024-12-30","cited_by_count":9,"area":"lr"},{"id":"2501.11800","title":"TFLOP: Table Structure Recognition Framework with Layout Pointer Mechanism","created":"2025-01-21","cited_by_count":9,"area":null},{"id":"2505.22584","title":"DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG Rerankers","created":"2025-05-28","cited_by_count":9,"area":"rag"},{"id":"2212.07249","title":"APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning","created":"2022-12-14","cited_by_count":8,"area":null},{"id":"2401.01522","title":"LORE++: Logical Location Regression Network for Table Structure Recognition with Pre-training","created":"2024-01-03","cited_by_count":8,"area":null},{"id":"2508.21085","title":"Granite Embedding R2 Models","created":"2025-08-26","cited_by_count":8,"area":null},{"id":"2206.00785","title":"Delivering Document Conversion as a Cloud Service with High Throughput and Responsiveness","created":"2022-06-01","cited_by_count":7,"area":null},{"id":"2305.02769","title":"Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer","created":"2023-05-04","cited_by_count":7,"area":null},{"id":"2306.13526","title":"Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images","created":"2023-06-23","cited_by_count":7,"area":null},{"id":"2403.06249","title":"No Language is an Island: Unifying Chinese and English in Financial Large Language Models, Instruction Data, and Benchmarks","created":"2024-03-10","cited_by_count":7,"area":null},{"id":"2405.11862","title":"SEMv3: A Fast and Robust Approach to Table Separation Line Detection","created":"2024-05-20","cited_by_count":7,"area":null},{"id":"2506.21393","title":"TableMoE: Neuro-Symbolic Routing for Structured Expert Reasoning in Multimodal Table Understanding","created":"2025-06-26","cited_by_count":7,"area":"lr"},{"id":"2603.23885","title":"Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training","created":"2026-03-25","cited_by_count":7,"area":"mllm"},{"id":"2203.03819","title":"Table Structure Recognition with Conditional Attention","created":"2022-03-08","cited_by_count":6,"area":null},{"id":"2303.09174","title":"Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberation","created":"2023-03-16","cited_by_count":6,"area":null},{"id":"2305.00630","title":"TRACE: Table Reconstruction Aligned to Corner and Edges","created":"2023-05-01","cited_by_count":6,"area":null},{"id":"2410.13959","title":"FinQAPT: Empowering Financial Decisions with End-to-End LLM-driven Question Answering Pipeline","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2503.11932","title":"SPRINT: Script-agnostic Structure Recognition in Tables","created":"2025-03-15","cited_by_count":6,"area":null},{"id":"2509.07966","title":"Visual-TableQA: Open-Domain Benchmark for Reasoning over Table Images","created":"2025-09-09","cited_by_count":6,"area":"lr"},{"id":"2111.06016","title":"Synthetic Document Generator for Annotation-free Layout Recognition","created":"2021-11-11","cited_by_count":5,"area":null},{"id":"2404.10305","title":"TC-OCR: TableCraft OCR for Efficient Detection & Recognition of Table Structure & Content","created":"2024-04-16","cited_by_count":5,"area":null},{"id":"2404.13268","title":"Multi-Cell Decoder and Mutual Learning for Table Structure and Character Recognition","created":"2024-04-20","cited_by_count":5,"area":null},{"id":"2405.00187","title":"Towards End-to-End Semi-Supervised Table Detection with Semantic Aligned Matching Transformer","created":"2024-04-30","cited_by_count":5,"area":null},{"id":"2506.07015","title":"TABLET: Table Structure Recognition using Encoder-only Transformers","created":"2025-06-08","cited_by_count":5,"area":null},{"id":"2602.15958","title":"DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting","created":"2026-02-17","cited_by_count":5,"area":null},{"id":"2603.09677","title":"Logics-Parsing-Omni Technical Report","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2603.28130","title":"MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios","created":"2026-03-30","cited_by_count":5,"area":null},{"id":"2102.08445","title":"TableLab: An Interactive Table Extraction System with Adaptive Deep Learning","created":"2021-02-16","cited_by_count":4,"area":null},{"id":"2304.10439","title":"A Study on Reproducibility and Replicability of Table Structure Recognition Methods","created":"2023-04-20","cited_by_count":4,"area":null},{"id":"2311.05565","title":"High-Performance Transformers for Table Structure Recognition Need Early Convolutions","created":"2023-11-09","cited_by_count":4,"area":null},{"id":"2504.04085","title":"DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning","created":"2025-04-05","cited_by_count":4,"area":null},{"id":"2601.12318","title":"Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligence","created":"2026-01-18","cited_by_count":4,"area":null},{"id":"2605.07492","title":"How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings","created":"2026-05-08","cited_by_count":4,"area":null},{"id":"2607.07836","title":"Infinity-Parser2 Technical Report","created":"2026-07-08","cited_by_count":4,"area":"lr"},{"id":"2402.07502","title":"ClusterTabNet: Supervised clustering method for table detection and table structure recognition","created":"2024-02-12","cited_by_count":3,"area":null},{"id":"2404.00401","title":"How Robust are the Tabular QA Models for Scientific Tables? A Study using Customized Dataset","created":"2024-03-30","cited_by_count":3,"area":null},{"id":"2502.14918","title":"RAPTOR: Refined Approach for Product Table Object Recognition","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2506.03197","title":"Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing","created":"2025-06-01","cited_by_count":3,"area":"lr"},{"id":"2506.12071","title":"T$^2$-RAGBench: Text-and-Table Benchmark for Evaluating Retrieval-Augmented Generation","created":"2025-06-04","cited_by_count":3,"area":"rag"},{"id":"2607.13347","title":"LLM-as-a-Judge Scores Are Unreliable Optimization Signals in Closed-Loop Table Recognition","created":"2026-07-15","cited_by_count":3,"area":null},{"id":"2201.01654","title":"TableParser: Automatic Table Parsing with Weak Supervision from Spreadsheets","created":"2022-01-05","cited_by_count":2,"area":null},{"id":"2307.13617","title":"GPT-3 Models are Few-Shot Financial Reasoners","created":"2023-07-25","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}