{"total":82,"rows":[{"id":"2407.01449","title":"ColPali: Efficient Document Retrieval with Vision Language Models","created":"2024-06-27","cited_by_count":195,"area":"mllm"},{"id":"2407.01523","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","created":"2024-07-01","cited_by_count":183,"area":null},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"area":null},{"id":"2409.11402","title":"NVLM: Open Frontier-Class Multimodal LLMs","created":"2024-09-17","cited_by_count":125,"area":"mllm"},{"id":"2501.15368","title":"Baichuan-Omni-1.5 Technical Report","created":"2025-01-26","cited_by_count":111,"area":null},{"id":"2212.05935","title":"Hierarchical multimodal transformers for Multi-Page DocVQA","created":"2022-12-07","cited_by_count":105,"area":null},{"id":"2305.07498","title":"Visual Information Extraction in the Wild: Practical Dataset and End-to-end Solution","created":"2023-05-12","cited_by_count":54,"area":null},{"id":"2510.17269","title":"FineVision: Open Data Is All You Need","created":"2025-10-20","cited_by_count":53,"area":"mllm"},{"id":"2505.20147","title":"FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities","created":"2025-05-26","cited_by_count":46,"area":"mllm"},{"id":"2210.08817","title":"PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance","created":"2022-10-17","cited_by_count":45,"area":null},{"id":"2501.08828","title":"MMDocIR: Benchmarking Multimodal Retrieval for Long Documents","created":"2025-01-15","cited_by_count":43,"area":null},{"id":"2406.15187","title":"UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis","created":"2024-06-21","cited_by_count":40,"area":"rag"},{"id":"2412.08802","title":"jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images","created":"2024-12-11","cited_by_count":37,"area":null},{"id":"2505.16470","title":"Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering","created":"2025-05-22","cited_by_count":36,"area":"rag"},{"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":"2412.08746","title":"DocVLM: Make Your VLM an Efficient Reader","created":"2024-12-11","cited_by_count":28,"area":"mllm"},{"id":"2605.27365","title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","created":"2026-05-26","cited_by_count":28,"area":"mllm"},{"id":"2401.13313","title":"InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions","created":"2024-01-24","cited_by_count":27,"area":null},{"id":"2506.04997","title":"Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings","created":"2025-06-05","cited_by_count":26,"area":"inference"},{"id":"2601.08620","title":"ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios","created":"2026-01-13","cited_by_count":26,"area":"rag"},{"id":"2408.01287","title":"Deep Learning based Visually Rich Document Content Understanding: A Survey","created":"2024-08-02","cited_by_count":21,"area":null},{"id":"2510.03663","title":"UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG","created":"2025-10-04","cited_by_count":21,"area":"rag"},{"id":"2401.13223","title":"TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data","created":"2024-01-24","cited_by_count":19,"area":"lr"},{"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":"2410.01744","title":"Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks","created":"2024-10-02","cited_by_count":18,"area":"mllm"},{"id":"2511.22850","title":"Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding","created":"2025-11-28","cited_by_count":18,"area":"agents"},{"id":"2209.07692","title":"Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder","created":"2022-09-16","cited_by_count":17,"area":null},{"id":"2407.08706","title":"HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models","created":"2024-07-11","cited_by_count":16,"area":"mllm"},{"id":"2403.14442","title":"RoDLA: Benchmarking the Robustness of Document Layout Analysis Models","created":"2024-03-21","cited_by_count":13,"area":null},{"id":"2409.13711","title":"WebQuest: A Benchmark for Multimodal QA on Web Page Sequences","created":"2024-09-06","cited_by_count":12,"area":"mllm"},{"id":"2510.05038","title":"Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization","created":"2025-10-06","cited_by_count":12,"area":null},{"id":"2305.03458","title":"Multi-View Graph Representation Learning for Answering Hybrid Numerical Reasoning Question","created":"2023-05-05","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":"2602.19549","title":"Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework","created":"2026-02-23","cited_by_count":10,"area":null},{"id":"2502.16586","title":"Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review","created":"2025-02-23","cited_by_count":9,"area":"mllm"},{"id":"2510.15253","title":"Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding","created":"2025-10-17","cited_by_count":9,"area":"rag"},{"id":"2308.01979","title":"RealCQA: Scientific Chart Question Answering as a Test-bed for First-Order Logic","created":"2023-08-03","cited_by_count":8,"area":null},{"id":"2502.11431","title":"Any Information Is Just Worth One Single Screenshot: Unifying Search With Visualized Information Retrieval","created":"2025-02-17","cited_by_count":8,"area":null},{"id":"2503.05185","title":"Towards Temporal-Aware Multi-Modal Retrieval Augmented Generation in Finance","created":"2025-03-07","cited_by_count":8,"area":"rag"},{"id":"2511.20648","title":"LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight","created":"2025-11-25","cited_by_count":8,"area":null},{"id":"2602.19961","title":"Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2212.13465","title":"A Survey on Table-and-Text HybridQA: Concepts, Methods, Challenges and Future Directions","created":"2022-12-27","cited_by_count":7,"area":null},{"id":"2401.10744","title":"FinLLMs: A Framework for Financial Reasoning Dataset Generation with Large Language Models","created":"2024-01-19","cited_by_count":6,"area":"lr"},{"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":"2305.01938","title":"Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs","created":"2023-05-03","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":"2211.03462","title":"NAPG: Non-Autoregressive Program Generation for Hybrid Tabular-Textual Question Answering","created":"2022-11-07","cited_by_count":4,"area":null},{"id":"2501.02235","title":"Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends","created":"2025-01-04","cited_by_count":4,"area":null},{"id":"2507.20145","title":"Multi-Agent Interactive Question Generation Framework for Long Document Understanding","created":"2025-07-27","cited_by_count":4,"area":"agents"},{"id":"2510.16505","title":"PRISMM-Bench: A Benchmark of Peer-Review Grounded Multimodal Inconsistencies","created":"2025-10-18","cited_by_count":4,"area":"mllm"},{"id":"2408.04632","title":"Arctic-TILT. Business Document Understanding at Sub-Billion Scale","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2503.04065","title":"PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks","created":"2025-03-06","cited_by_count":3,"area":null},{"id":"2503.21839","title":"M-DocSum: Do LVLMs Genuinely Comprehend Interleaved Image-Text in Document Summarization?","created":"2025-03-27","cited_by_count":3,"area":"mllm"},{"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":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2503.02603","title":"OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Query Processing","created":"2025-03-04","cited_by_count":2,"area":"rag"},{"id":"2508.15690","title":"GRAFT: GRaPH and Table Reasoning for Textual Alignment -- A Benchmark for Structured Instruction Following and Visual Reasoning","created":"2025-08-21","cited_by_count":2,"area":"lr"},{"id":"2605.11864","title":"Very Efficient Listwise Multimodal Reranking for Long Documents","created":"2026-05-12","cited_by_count":2,"area":"rag"},{"id":"2607.11192","title":"GDP.pdf: Benchmarking Grounded Multimodal Reasoning over Professional PDF Documents","created":"2026-07-13","cited_by_count":2,"area":null},{"id":"2607.18155","title":"Testing Retrieval-Augmented Generation Systems with Chunk Coverage","created":"2026-07-20","cited_by_count":2,"area":"rag"},{"id":"2411.18915","title":"MATATA: Weakly Supervised End-to-End MAthematical Tool-Augmented Reasoning for Tabular Applications","created":"2024-11-28","cited_by_count":1,"area":"lr"},{"id":"2504.20047","title":"HCT-QA: A Benchmark for Question Answering on Human-Centric Tables","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2507.06999","title":"Learning Deliberately, Acting Intuitively: Unlocking Test-Time Reasoning in Multimodal LLMs","created":"2025-07-09","cited_by_count":1,"area":"lr"},{"id":"2511.06582","title":"TabRAG: Improving Tabular Document Question Answering for Retrieval Augmented Generation via Structured Representations","created":"2025-11-10","cited_by_count":1,"area":"rag"},{"id":"2602.12203","title":"ExStrucTiny: A Benchmark for Schema-Variable Structured Information Extraction from Document Images","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2603.13349","title":"MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrieval","created":"2026-03-07","cited_by_count":1,"area":"mllm"},{"id":"2604.00161","title":"Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models","created":"2026-03-31","cited_by_count":1,"area":"mllm"},{"id":"2604.05087","title":"Document Optimization for Black-Box Retrieval via Reinforcement Learning","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2604.25855","title":"SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring","created":"2026-04-28","cited_by_count":1,"area":"mllm"},{"id":"2509.02864","title":"A-SEA3L-QA: A Fully Automated Self-Evolving, Adversarial Workflow for Arabic Long-Context Question-Answer Generation","created":"2025-09-02","cited_by_count":0,"area":"synth"},{"id":"2511.16470","title":"Arctic-Extract Technical Report","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2511.19919","title":"HybriDLA: Hybrid Generation for Document Layout Analysis","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2603.29211","title":"Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.14581","title":"A Picture is Worth a Thousand Words? An Empirical Study of Aggregation Strategies for Visual Financial Document Retrieval","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.30027","title":"DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.16092","title":"VinQA: Visual Elements Interleaved Long-form Answer Generation for Real-World Multimodal Document QA","created":"2026-06-15","cited_by_count":0,"area":"mllm"},{"id":"2607.05927","title":"CMDR: Contextual Multimodal Document Retrieval","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.29638","title":"HierDoc: Hierarchical Page-to-Region Evidence Routing for Long-Document Visual Question Answering","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.27790","title":"Credo: Reusable Declarative Primitives for Agentic Workflows","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.07262","title":"Query-Aware Token Budgeting for Efficient Late-Interaction Visual Document Retrieval","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.21018","title":"MAGIC: Marginal-Guided Compression with Optimal Transport for Efficient Visual Document Retrieval","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.24092","title":"DocMIDE: Learning Multi-Hop Implicit Derivation in Visually Rich Documents","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}