{"total":100,"rows":[{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543,"area":"wm"},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353,"area":null},{"id":"2407.12772","title":"LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models","created":"2024-07-17","cited_by_count":353,"area":"mllm"},{"id":"2403.12895","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","created":"2024-03-19","cited_by_count":220,"area":null},{"id":"2407.01523","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","created":"2024-07-01","cited_by_count":183,"area":null},{"id":"2301.04883","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","created":"2023-01-12","cited_by_count":179,"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":"2309.07915","title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","created":"2023-09-14","cited_by_count":172,"area":"mllm"},{"id":"2305.11854","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","created":"2023-05-19","cited_by_count":160,"area":null},{"id":"2402.17553","title":"OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web","created":"2024-02-27","cited_by_count":157,"area":"agents"},{"id":"2310.05126","title":"UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model","created":"2023-10-08","cited_by_count":143,"area":"mllm"},{"id":"2212.02623","title":"Unifying Vision, Text, and Layout for Universal Document Processing","created":"2022-12-05","cited_by_count":140,"area":null},{"id":"2506.03569","title":"MiMo-VL Technical Report","created":"2025-06-04","cited_by_count":115,"area":"lr"},{"id":"2409.03420","title":"mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding","created":"2024-09-05","cited_by_count":114,"area":null},{"id":"2402.07945","title":"ScreenAgent: A Vision Language Model-driven Computer Control Agent","created":"2024-02-09","cited_by_count":102,"area":"mllm"},{"id":"2409.12959","title":"MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines","created":"2024-09-19","cited_by_count":101,"area":null},{"id":"2404.05955","title":"VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?","created":"2024-04-09","cited_by_count":100,"area":"mllm"},{"id":"2402.04615","title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding","created":"2024-02-07","cited_by_count":98,"area":"mllm"},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"id":"2502.10391","title":"MM-RLHF: The Next Step Forward in Multimodal LLM Alignment","created":"2025-02-14","cited_by_count":83,"area":"mllm"},{"id":"2207.11871","title":"Towards Complex Document Understanding By Discrete Reasoning","created":"2022-07-25","cited_by_count":82,"area":null},{"id":"2406.20098","title":"Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs","created":"2024-06-28","cited_by_count":74,"area":"mllm"},{"id":"2411.15296","title":"MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs","created":"2024-11-22","cited_by_count":72,"area":"mllm"},{"id":"2507.19478","title":"MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents","created":"2025-07-25","cited_by_count":67,"area":"agents"},{"id":"2209.08199","title":"ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots","created":"2022-09-16","cited_by_count":66,"area":null},{"id":"2307.02469","title":"What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?","created":"2023-07-05","cited_by_count":64,"area":null},{"id":"2111.08609","title":"Document AI: Benchmarks, Models and Applications","created":"2021-11-16","cited_by_count":62,"area":null},{"id":"2504.13865","title":"A Survey on (M)LLM-Based GUI Agents","created":"2025-03-27","cited_by_count":62,"area":"agents"},{"id":"2410.18967","title":"Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms","created":"2024-10-24","cited_by_count":51,"area":null},{"id":"2509.03498","title":"OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation","created":"2025-09-03","cited_by_count":50,"area":"moe"},{"id":"2504.04423","title":"UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding","created":"2025-04-06","cited_by_count":49,"area":null},{"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":"2110.08518","title":"MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding","created":"2021-10-16","cited_by_count":45,"area":null},{"id":"2411.02959","title":"HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems","created":"2024-11-05","cited_by_count":37,"area":"rag"},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2202.00217","title":"WebFormer: The Web-page Transformer for Structure Information Extraction","created":"2022-02-01","cited_by_count":34,"area":null},{"id":"2411.02006","title":"Foundations and Recent Trends in Multimodal Mobile Agents: A Survey","created":"2024-11-04","cited_by_count":31,"area":"agents"},{"id":"2410.13824","title":"Harnessing Webpage UIs for Text-Rich Visual Understanding","created":"2024-10-17","cited_by_count":28,"area":"mllm"},{"id":"2505.17399","title":"FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow","created":"2025-05-23","cited_by_count":28,"area":null},{"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":"2411.10640","title":"BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices","created":"2024-11-16","cited_by_count":25,"area":"mllm"},{"id":"2201.10608","title":"DOM-LM: Learning Generalizable Representations for HTML Documents","created":"2022-01-25","cited_by_count":24,"area":null},{"id":"2508.21767","title":"UItron: Foundational GUI Agent with Advanced Perception and Planning","created":"2025-08-29","cited_by_count":22,"area":"agents"},{"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":"2311.16087","title":"DUnE: Dataset for Unified Editing","created":"2023-11-27","cited_by_count":19,"area":null},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2503.03196","title":"SpiritSight Agent: Advanced GUI Agent with One Look","created":"2025-03-05","cited_by_count":18,"area":"agents"},{"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":"2508.16763","title":"WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation","created":"2025-08-22","cited_by_count":16,"area":null},{"id":"2403.03346","title":"Enhancing Vision-Language Pre-training with Rich Supervisions","created":"2024-03-05","cited_by_count":13,"area":"mllm"},{"id":"2210.02849","title":"XDoc: Unified Pre-training for Cross-Format Document Understanding","created":"2022-10-06","cited_by_count":12,"area":null},{"id":"2403.16516","title":"Visually Guided Generative Text-Layout Pre-training for Document Intelligence","created":"2024-03-25","cited_by_count":12,"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":"2503.14021","title":"MP-GUI: Modality Perception with MLLMs for GUI Understanding","created":"2025-03-18","cited_by_count":12,"area":null},{"id":"2503.21817","title":"Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping","created":"2025-03-26","cited_by_count":12,"area":"mllm"},{"id":"2506.08972","title":"Atomic-to-Compositional Generalization for Mobile Agents with A New Benchmark and Scheduling System","created":"2025-06-10","cited_by_count":12,"area":"agents"},{"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":"2304.09660","title":"MPMQA: Multimodal Question Answering on Product Manuals","created":"2023-04-19","cited_by_count":10,"area":null},{"id":"2505.15372","title":"X-WebAgentBench: A Multilingual Interactive Web Benchmark for Evaluating Global Agentic System","created":"2025-05-21","cited_by_count":10,"area":"lr"},{"id":"2607.24904","title":"Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model","created":"2026-07-27","cited_by_count":10,"area":"lr"},{"id":"2402.09841","title":"LAPDoc: Layout-Aware Prompting for Documents","created":"2024-02-15","cited_by_count":9,"area":null},{"id":"2403.19454","title":"JDocQA: Japanese Document Question Answering Dataset for Generative Language Models","created":"2024-03-28","cited_by_count":9,"area":null},{"id":"2212.11541","title":"Generative Colorization of Structured Mobile Web Pages","created":"2022-12-22","cited_by_count":8,"area":null},{"id":"2412.05243","title":"CompCap: Improving Multimodal Large Language Models with Composite Captions","created":"2024-12-06","cited_by_count":8,"area":"mllm"},{"id":"2503.24180","title":"Navi-plus: Managing Ambiguous GUI Navigation Tasks with Follow-up Questions","created":"2025-03-31","cited_by_count":8,"area":null},{"id":"2406.11403","title":"Multimodal Structured Generation: CVPR's 2nd MMFM Challenge Technical Report","created":"2024-06-17","cited_by_count":7,"area":null},{"id":"2203.07828","title":"Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs","created":"2022-03-15","cited_by_count":5,"area":null},{"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":"2509.24361","title":"UI-UG: A Unified MLLM for UI Understanding and Generation","created":"2025-09-29","cited_by_count":5,"area":"mllm"},{"id":"2510.13366","title":"Document Intelligence in the Era of Large Language Models: A Survey","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2205.06435","title":"TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pages","created":"2022-05-13","cited_by_count":4,"area":null},{"id":"2402.18262","title":"Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2407.15502","title":"WebRPG: Automatic Web Rendering Parameters Generation for Visual Presentation","created":"2024-07-22","cited_by_count":4,"area":null},{"id":"2407.02842","title":"MindBench: A Comprehensive Benchmark for Mind Map Structure Recognition and Analysis","created":"2024-07-03","cited_by_count":3,"area":"mllm"},{"id":"2408.12188","title":"Reasoning Factual Knowledge in Structured Data with Large Language Models","created":"2024-08-22","cited_by_count":3,"area":"lr"},{"id":"2505.05446","title":"Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2511.00389","title":"Rethinking Facial Expression Recognition in the Era of Multimodal Large Language Models: Benchmark, Datasets, and Beyond","created":"2025-11-01","cited_by_count":3,"area":"lr"},{"id":"2604.08115","title":"Revise: A Framework for Revising OCRed text in Practical Information Systems with Data Contamination Strategy","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2305.10448","title":"Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding","created":"2023-05-16","cited_by_count":2,"area":null},{"id":"2409.11282","title":"Leveraging Distillation Techniques for Document Understanding: A Case Study with FLAN-T5","created":"2024-09-17","cited_by_count":2,"area":null},{"id":"2410.00773","title":"BabelBench: An Omni Benchmark for Code-Driven Analysis of Multimodal and Multistructured Data","created":"2024-10-01","cited_by_count":2,"area":null},{"id":"2512.17221","title":"DAVE: A VLM Vision Encoder for Document Understanding and Web Agents","created":"2025-12-19","cited_by_count":2,"area":"mllm"},{"id":"2208.02252","title":"GROWN+UP: A Graph Representation Of a Webpage Network Utilizing Pre-training","created":"2022-08-03","cited_by_count":1,"area":null},{"id":"2509.25107","title":"Knowledge Extraction on Semi-Structured Content: Does It Remain Relevant for Question Answering in the Era of LLMs?","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2602.01838","title":"AXE: Low-Cost Cross-Domain Web Structured Information Extraction","created":"2026-02-02","cited_by_count":1,"area":null},{"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":"2606.24602","title":"ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2608.08392","title":"CAP: A Scalable Benchmark for Evaluating Cross-Site Browser Agents with Complex Actions and Perception","created":"2026-08-09","cited_by_count":1,"area":"agents"},{"id":"2305.14218","title":"DUBLIN -- Document Understanding By Language-Image Network","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2409.05275","title":"RexUniNLU: Recursive Method with Explicit Schema Instructor for Universal NLU","created":"2024-09-09","cited_by_count":0,"area":null},{"id":"2411.08278","title":"Knowledge Bases in Support of Large Language Models for Processing Web News","created":"2024-11-13","cited_by_count":0,"area":null},{"id":"2506.12015","title":"EMLoC: Emulator-based Memory-efficient Fine-tuning with LoRA Correction","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2607.05927","title":"CMDR: Contextual Multimodal Document Retrieval","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2608.05139","title":"Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2609.01344","title":"ExBind: A Controlled Diagnostic Benchmark for Visual-to-Executable Correspondence","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.37515","title":"Hierarchical Compression of Vision-Language Model Benchmarks","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2610.12516","title":"TraceICL: Thread-Resolved Demonstration Curation with Consistency Calibration for Robust Multimodal In-Context Learning","created":"2026-10-07","cited_by_count":0,"area":"mllm"},{"id":"2610.17057","title":"VL-DocIR: A Benchmark for Vision-Based Long Document Information Retrieval","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}