{"total":102,"rows":[{"id":"2312.08914","title":"CogAgent: A Visual Language Model for GUI Agents","created":"2023-12-14","cited_by_count":704,"area":"mllm"},{"id":"2401.01614","title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","created":"2024-01-03","cited_by_count":563,"area":"mllm"},{"id":"2401.13919","title":"WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models","created":"2024-01-25","cited_by_count":438,"area":"mllm"},{"id":"2410.23218","title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","created":"2024-10-30","cited_by_count":378,"area":"mllm"},{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357,"area":"mllm"},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326,"area":"mllm"},{"id":"2404.05719","title":"Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs","created":"2024-04-08","cited_by_count":176,"area":"mllm"},{"id":"2403.04473","title":"TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document","created":"2024-03-07","cited_by_count":174,"area":"mllm"},{"id":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173,"area":"mllm"},{"id":"2307.02499","title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","created":"2023-07-04","cited_by_count":168,"area":"mllm"},{"id":"2311.16483","title":"ChartLlama: A Multimodal LLM for Chart Understanding and Generation","created":"2023-11-27","cited_by_count":163,"area":"mllm"},{"id":"2305.14761","title":"UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning","created":"2023-05-24","cited_by_count":160,"area":"mllm"},{"id":"2311.10774","title":"MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning","created":"2023-11-15","cited_by_count":150,"area":"mllm"},{"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":"2408.15998","title":"Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders","created":"2024-08-28","cited_by_count":139,"area":"mllm"},{"id":"2403.09029","title":"Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset","created":"2024-03-14","cited_by_count":129,"area":"mllm"},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126,"area":"mllm"},{"id":"2406.11317","title":"GUICourse: From General Vision Language Models to Versatile GUI Agents","created":"2024-06-17","cited_by_count":114,"area":"mllm"},{"id":"2311.11810","title":"DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding","created":"2023-11-20","cited_by_count":106,"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":"2404.05225","title":"LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding","created":"2024-04-08","cited_by_count":95,"area":"mllm"},{"id":"2306.07915","title":"Image Captioners Are Scalable Vision Learners Too","created":"2023-06-13","cited_by_count":89,"area":"mllm"},{"id":"2312.06109","title":"Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models","created":"2023-12-11","cited_by_count":84,"area":"mllm"},{"id":"2404.13046","title":"MoVA: Adapting Mixture of Vision Experts to Multimodal Context","created":"2024-04-19","cited_by_count":83,"area":"mllm"},{"id":"2401.02384","title":"ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning","created":"2024-01-04","cited_by_count":79,"area":"mllm"},{"id":"2404.12803","title":"TextSquare: Scaling up Text-Centric Visual Instruction Tuning","created":"2024-04-19","cited_by_count":62,"area":"mllm"},{"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":"2409.14818","title":"MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding","created":"2024-09-23","cited_by_count":48,"area":"mllm"},{"id":"2407.12709","title":"MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models","created":"2024-07-17","cited_by_count":46,"area":"mllm"},{"id":"2401.12503","title":"Small Language Model Meets with Reinforced Vision Vocabulary","created":"2024-01-23","cited_by_count":43,"area":"mllm"},{"id":"2404.06918","title":"HRVDA: High-Resolution Visual Document Assistant","created":"2024-04-10","cited_by_count":37,"area":"mllm"},{"id":"2406.11633","title":"DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models","created":"2024-06-17","cited_by_count":36,"area":"mllm"},{"id":"2406.19101","title":"DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming","created":"2024-06-27","cited_by_count":35,"area":"mllm"},{"id":"2509.01215","title":"POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion","created":"2025-09-01","cited_by_count":34,"area":"mllm"},{"id":"2410.09733","title":"MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models","created":"2024-10-13","cited_by_count":31,"area":"mllm"},{"id":"2410.13824","title":"Harnessing Webpage UIs for Text-Rich Visual Understanding","created":"2024-10-17","cited_by_count":28,"area":"mllm"},{"id":"2404.09204","title":"TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models","created":"2024-04-14","cited_by_count":27,"area":"mllm"},{"id":"2407.20174","title":"Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction Tuning","created":"2024-07-29","cited_by_count":27,"area":"mllm"},{"id":"2411.01106","title":"SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding","created":"2024-11-02","cited_by_count":25,"area":"mllm"},{"id":"2407.14439","title":"Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding","created":"2024-07-19","cited_by_count":22,"area":"mllm"},{"id":"2502.01977","title":"AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMs","created":"2025-02-04","cited_by_count":19,"area":"mllm"},{"id":"2506.07818","title":"WebUIBench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in WebUI-to-Code","created":"2025-06-09","cited_by_count":15,"area":"mllm"},{"id":"2403.03346","title":"Enhancing Vision-Language Pre-training with Rich Supervisions","created":"2024-03-05","cited_by_count":13,"area":"mllm"},{"id":"2407.14506","title":"On Pre-training of Multimodal Language Models Customized for Chart Understanding","created":"2024-07-19","cited_by_count":13,"area":"mllm"},{"id":"2602.01785","title":"Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understanding","created":"2026-02-02","cited_by_count":13,"area":"mllm"},{"id":"2401.03105","title":"Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models","created":"2024-01-06","cited_by_count":12,"area":"mllm"},{"id":"2411.05254","title":"Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding","created":"2024-11-08","cited_by_count":12,"area":"mllm"},{"id":"2503.23131","title":"RefChartQA: Grounding Visual Answer on Chart Images through Instruction Tuning","created":"2025-03-29","cited_by_count":11,"area":"mllm"},{"id":"2411.03313","title":"Classification Done Right for Vision-Language Pre-Training","created":"2024-11-05","cited_by_count":10,"area":"mllm"},{"id":"2502.01341","title":"AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding","created":"2025-02-03","cited_by_count":9,"area":"mllm"},{"id":"2603.24373","title":"PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks","created":"2026-03-25","cited_by_count":9,"area":"mllm"},{"id":"2412.13871","title":"LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer","created":"2024-12-18","cited_by_count":8,"area":"mllm"},{"id":"2311.17647","title":"Text as Images: Can Multimodal Large Language Models Follow Printed Instructions in Pixels?","created":"2023-11-29","cited_by_count":7,"area":"mllm"},{"id":"2402.15307","title":"Representing Online Handwriting for Recognition in Large Vision-Language Models","created":"2024-02-23","cited_by_count":7,"area":"mllm"},{"id":"2410.16472","title":"DocEdit-v2: Document Structure Editing Via Multimodal LLM Grounding","created":"2024-10-21","cited_by_count":7,"area":"mllm"},{"id":"2407.08707","title":"Extracting Training Data from Document-Based VQA Models","created":"2024-07-11","cited_by_count":6,"area":"mllm"},{"id":"2411.13076","title":"Hints of Prompt: Enhancing Visual Representation for Multimodal LLMs in Autonomous Driving","created":"2024-11-20","cited_by_count":6,"area":"mllm"},{"id":"2503.04095","title":"Chart-HQA: A Benchmark for Hypothetical Question Answering in Charts","created":"2025-03-06","cited_by_count":6,"area":"mllm"},{"id":"2511.21750","title":"SO-Bench: A Structural Output Evaluation of Multimodal LLMs","created":"2025-11-23","cited_by_count":6,"area":"mllm"},{"id":"2501.04675","title":"Enhancing Financial VQA in Vision Language Models using Intermediate Structured Representations","created":"2025-01-08","cited_by_count":5,"area":"mllm"},{"id":"2505.17202","title":"CHART-6: Human-Centered Evaluation of Data Visualization Understanding in Vision-Language Models","created":"2025-05-22","cited_by_count":5,"area":"mllm"},{"id":"2506.19072","title":"HAWAII: Hierarchical Visual Knowledge Transfer for Efficient Vision-Language Models","created":"2025-06-23","cited_by_count":5,"area":"mllm"},{"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":"2411.07722","title":"Is Cognition Consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document Understanding","created":"2024-11-12","cited_by_count":4,"area":"mllm"},{"id":"2412.20715","title":"ChartAdapter: Large Vision-Language Model for Chart Summarization","created":"2024-12-30","cited_by_count":4,"area":"mllm"},{"id":"2504.04653","title":"LEO-MINI: An Efficient Multimodal Large Language Model using Conditional Token Reduction and Mixture of Multi-Modal Experts","created":"2025-04-07","cited_by_count":4,"area":"mllm"},{"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":"2410.16163","title":"Griffon-G: Bridging Vision-Language and Vision-Centric Tasks via Large Multimodal Models","created":"2024-10-21","cited_by_count":3,"area":"mllm"},{"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":"2504.09764","title":"Socratic Chart: Cooperating Multiple Agents for Robust SVG Chart Understanding","created":"2025-04-14","cited_by_count":3,"area":"mllm"},{"id":"2505.04214","title":"CM1 -- A Dataset for Evaluating Few-Shot Information Extraction with Large Vision Language Models","created":"2025-05-07","cited_by_count":3,"area":"mllm"},{"id":"2505.19360","title":"ChartLens: Fine-grained Visual Attribution in Charts","created":"2025-05-25","cited_by_count":3,"area":"mllm"},{"id":"2507.14298","title":"In-Depth and In-Breadth: Pre-training Multimodal Language Models Customized for Comprehensive Chart Understanding","created":"2025-07-18","cited_by_count":3,"area":"mllm"},{"id":"2507.20842","title":"METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models","created":"2025-07-28","cited_by_count":3,"area":"mllm"},{"id":"2508.18984","title":"Enhancing Document VQA Models via Retrieval-Augmented Generation","created":"2025-08-26","cited_by_count":2,"area":"mllm"},{"id":"2509.10129","title":"Towards Reliable and Interpretable Document Question Answering via VLMs","created":"2025-09-12","cited_by_count":2,"area":"mllm"},{"id":"2510.22045","title":"VLM-SlideEval: Evaluating VLMs on Structured Comprehension and Perturbation Sensitivity in PPT","created":"2025-10-24","cited_by_count":2,"area":"mllm"},{"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":"2310.04914","title":"Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks","created":"2023-10-07","cited_by_count":1,"area":"mllm"},{"id":"2510.18703","title":"Exploring a Unified Vision-Centric Contrastive Alternatives on Multi-Modal Web Documents","created":"2025-10-21","cited_by_count":1,"area":"mllm"},{"id":"2605.06058","title":"Towards Self-Explainable Document Visual Question Answering with Chain-of-Explanation Predictions","created":"2026-05-07","cited_by_count":1,"area":"mllm"},{"id":"2606.03410","title":"Enginuity: A Dataset and Benchmark for Vision-Language Understanding of Engineering Diagrams","created":"2026-06-02","cited_by_count":1,"area":"mllm"},{"id":"2608.21762","title":"Learning to Look Again: Loss-Gap Supervision for Free-form Crop Routing in Vision-Language Models","created":"2026-08-22","cited_by_count":1,"area":"mllm"},{"id":"2504.02971","title":"QID: Efficient Query-Informed ViTs in Data-Scarce Regimes for OCR-free Visual Document Understanding","created":"2025-04-03","cited_by_count":0,"area":"mllm"},{"id":"2509.12492","title":"Evaluating Robustness of Vision-Language Models Under Noisy Conditions","created":"2025-09-15","cited_by_count":0,"area":"mllm"},{"id":"2509.26235","title":"Interpret, prune and distill Donut : towards lightweight VLMs for VQA on document","created":"2025-09-30","cited_by_count":0,"area":"mllm"},{"id":"2602.03850","title":"WebAccessVL: Violation-Aware VLM for Web Accessibility","created":"2025-12-19","cited_by_count":0,"area":"mllm"},{"id":"2602.13232","title":"PlotChain: Deterministic Checkpointed Evaluation of Multimodal LLMs on Engineering Plot Reading","created":"2026-01-29","cited_by_count":0,"area":"mllm"},{"id":"2603.08930","title":"Using Vision Language Foundation Models to Generate Plant Simulation Configurations via In-Context Learning","created":"2026-03-09","cited_by_count":0,"area":"mllm"},{"id":"2604.01226","title":"DOne: Decoupling Structure and Rendering for High-Fidelity Design-to-Code Generation","created":"2026-03-12","cited_by_count":0,"area":"mllm"},{"id":"2604.16504","title":"From Handwriting to Structured Data: Benchmarking AI Digitisation of Handwritten Forms","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2604.27389","title":"COHERENCE: Benchmarking Fine-Grained Image-Text Alignment in Interleaved Multimodal Contexts","created":"2026-04-30","cited_by_count":0,"area":"mllm"},{"id":"2605.17447","title":"FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing","created":"2026-05-17","cited_by_count":0,"area":"mllm"},{"id":"2605.30265","title":"LoMo: Local Modality Substitution for Deeper Vision-Language Fusion","created":"2026-05-28","cited_by_count":0,"area":"mllm"},{"id":"2606.25343","title":"Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity","created":"2026-06-24","cited_by_count":0,"area":"mllm"},{"id":"2607.22600","title":"Chart Deception in Vision-Language Models: From Vulnerability to Mitigation","created":"2026-06-12","cited_by_count":0,"area":"mllm"},{"id":"2608.03691","title":"Pattern over Pixels: Measuring Pattern Completion Bias in Multimodal Code Generation","created":"2026-08-04","cited_by_count":0,"area":"mllm"},{"id":"2608.29268","title":"Learning to Ground Before Reading: Unified PCB Engineering Drawing Parsing with Compact Vision-Language Models","created":"2026-08-29","cited_by_count":0,"area":"mllm"},{"id":"2609.15706","title":"Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document Extraction","created":"2026-09-14","cited_by_count":0,"area":"mllm"},{"id":"2609.25770","title":"Reading Right, Answering Wrong: How Visual Configuration Changes Affect Evidence Use in VLMs","created":"2026-09-22","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}