{"total":45,"rows":[{"id":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476,"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":"2403.02469","title":"Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review","created":"2024-03-04","cited_by_count":125,"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":"2510.14528","title":"PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model","created":"2025-10-16","cited_by_count":89,"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":"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":"2312.10160","title":"Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning","created":"2023-12-15","cited_by_count":49,"area":"mllm"},{"id":"2307.06930","title":"mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs","created":"2023-07-13","cited_by_count":41,"area":"mllm"},{"id":"2505.11935","title":"ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing","created":"2025-05-17","cited_by_count":32,"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":"2502.01977","title":"AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMs","created":"2025-02-04","cited_by_count":19,"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":"2508.04650","title":"EncQA: Benchmarking Vision-Language Models on Visual Encodings for Charts","created":"2025-08-06","cited_by_count":12,"area":"mllm"},{"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":"2412.05983","title":"Chimera: Improving Generalist Model with Domain-Specific Experts","created":"2024-12-08","cited_by_count":11,"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":"2604.25884","title":"QCalEval: Benchmarking Vision-Language Models for Quantum Calibration Plot Understanding","created":"2026-04-28","cited_by_count":11,"area":"mllm"},{"id":"2502.20503","title":"Protecting multimodal large language models against misleading visualizations","created":"2025-02-27","cited_by_count":8,"area":"mllm"},{"id":"2503.12326","title":"Leveraging Vision Capabilities of Multimodal LLMs for Automated Data Extraction from Plots","created":"2025-03-16","cited_by_count":7,"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":"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":"2507.03262","title":"Investigating Redundancy in Multimodal Large Language Models with Multiple Vision Encoders","created":"2025-07-04","cited_by_count":5,"area":"mllm"},{"id":"2509.18425","title":"Losing the Plot: How VLM responses degrade on imperfect charts","created":"2025-09-22","cited_by_count":5,"area":"mllm"},{"id":"2602.16455","title":"Visual Self-Refine: A Pixel-Guided Paradigm for Accurate Chart Parsing","created":"2026-02-18","cited_by_count":5,"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":"2504.09764","title":"Socratic Chart: Cooperating Multiple Agents for Robust SVG Chart Understanding","created":"2025-04-14","cited_by_count":3,"area":"mllm"},{"id":"2505.17374","title":"Chart-to-Experience: Benchmarking Multimodal LLMs for Predicting Experiential Impact of Charts","created":"2025-05-23","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":"2603.24326","title":"Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing","created":"2026-03-25","cited_by_count":3,"area":"mllm"},{"id":"2510.07098","title":"TALENT: Table VQA via Augmented Language-Enhanced Natural-text Transcription","created":"2025-10-08","cited_by_count":2,"area":"mllm"},{"id":"2606.29808","title":"Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework","created":"2026-06-29","cited_by_count":2,"area":"mllm"},{"id":"2603.28583","title":"Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering","created":"2026-03-30","cited_by_count":1,"area":"mllm"},{"id":"2606.00065","title":"Beyond Text and Tables: Vision-Language Model Integration in ComProScanner for Extracting Materials Data from Scientific Figures with High Accuracy","created":"2026-05-19","cited_by_count":1,"area":"mllm"},{"id":"2606.31732","title":"UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization","created":"2026-06-30","cited_by_count":1,"area":"mllm"},{"id":"2411.11479","title":"Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts","created":"2024-11-18","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":"2605.27195","title":"EpiCurveBench: Evaluating VLMs on Epidemic Curve Digitization","created":"2026-05-26","cited_by_count":0,"area":"mllm"},{"id":"2606.29966","title":"RiverONE: Generating Knowledge-Intensive VLM by Simulated Quantum Machines","created":"2026-06-29","cited_by_count":0,"area":"mllm"},{"id":"2609.33694","title":"Seeing and Solving Are Not Enough for Vision-Language Models","created":"2026-09-27","cited_by_count":0,"area":"mllm"},{"id":"2610.17928","title":"Learning How to Remember: Memory Modality Selection for GUI Agents","created":"2026-10-13","cited_by_count":0,"area":"mllm"}],"next_cursor":null}