{"total":78,"rows":[{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565,"area":"mllm"},{"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":"2311.06607","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":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267,"area":null},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209,"area":"mllm"},{"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":"2105.05486","title":"TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text","created":"2021-05-12","cited_by_count":171,"area":null},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151,"area":null},{"id":"2308.09936","title":"BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions","created":"2023-08-19","cited_by_count":125,"area":"mllm"},{"id":"2409.11402","title":"NVLM: Open Frontier-Class Multimodal LLMs","created":"2024-09-17","cited_by_count":125,"area":"mllm"},{"id":"2212.05935","title":"Hierarchical multimodal transformers for Multi-Page DocVQA","created":"2022-12-07","cited_by_count":105,"area":null},{"id":"2111.10056","title":"Medical Visual Question Answering: A Survey","created":"2021-11-19","cited_by_count":93,"area":null},{"id":"2401.10208","title":"MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer","created":"2024-01-18","cited_by_count":80,"area":null},{"id":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2406.08418","title":"OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text","created":"2024-06-12","cited_by_count":59,"area":null},{"id":"2203.15442","title":"Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding","created":"2022-03-29","cited_by_count":53,"area":"lr"},{"id":"2510.17269","title":"FineVision: Open Data Is All You Need","created":"2025-10-20","cited_by_count":53,"area":"mllm"},{"id":"2502.07411","title":"EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering","created":"2025-02-11","cited_by_count":44,"area":null},{"id":"2410.05261","title":"TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer Tokens","created":"2024-10-07","cited_by_count":32,"area":"mllm"},{"id":"2505.18129","title":"One RL to See Them All: Visual Triple Unified Reinforcement Learning","created":"2025-05-23","cited_by_count":30,"area":"lr"},{"id":"2304.06447","title":"PDFVQA: A New Dataset for Real-World VQA on PDF Documents","created":"2023-04-13","cited_by_count":28,"area":null},{"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":"2209.05534","title":"PreSTU: Pre-Training for Scene-Text Understanding","created":"2022-09-12","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":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2103.05187","title":"Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning","created":"2021-03-09","cited_by_count":20,"area":null},{"id":"2211.05588","title":"Watching the News: Towards VideoQA Models that can Read","created":"2022-11-10","cited_by_count":20,"area":"lr"},{"id":"2503.14140","title":"Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding","created":"2025-03-18","cited_by_count":20,"area":"mllm"},{"id":"2503.02358","title":"Are Large Vision Language Models Good Game Players?","created":"2025-03-04","cited_by_count":19,"area":"mllm"},{"id":"2401.06395","title":"ModaVerse: Efficiently Transforming Modalities with LLMs","created":"2024-01-12","cited_by_count":18,"area":null},{"id":"2307.11558","title":"Advancing Visual Grounding with Scene Knowledge: Benchmark and Method","created":"2023-07-21","cited_by_count":17,"area":null},{"id":"2511.03929","title":"NVIDIA Nemotron Nano V2 VL","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2108.08965","title":"Localize, Group, and Select: Boosting Text-VQA by Scene Text Modeling","created":"2021-08-20","cited_by_count":14,"area":null},{"id":"2110.00711","title":"Asking questions on handwritten document collections","created":"2021-10-02","cited_by_count":14,"area":null},{"id":"2212.10278","title":"Fully and Weakly Supervised Referring Expression Segmentation with End-to-End Learning","created":"2022-12-17","cited_by_count":14,"area":null},{"id":"2405.06706","title":"Exploring the Capabilities of Large Multimodal Models on Dense Text","created":"2024-05-09","cited_by_count":14,"area":"mllm"},{"id":"2407.03200","title":"SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding","created":"2024-07-03","cited_by_count":14,"area":null},{"id":"2104.06806","title":"Continual learning in cross-modal retrieval","created":"2021-04-14","cited_by_count":10,"area":null},{"id":"2304.09660","title":"MPMQA: Multimodal Question Answering on Product Manuals","created":"2023-04-19","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":"2602.01334","title":"What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom","created":"2026-02-01","cited_by_count":9,"area":"mllm"},{"id":"2412.00151","title":"DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness","created":"2024-11-29","cited_by_count":8,"area":"lr"},{"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":"2511.20648","title":"LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight","created":"2025-11-25","cited_by_count":8,"area":null},{"id":"2308.16383","title":"Separate and Locate: Rethink the Text in Text-based Visual Question Answering","created":"2023-08-31","cited_by_count":7,"area":null},{"id":"2407.03243","title":"Visual Grounding with Attention-Driven Constraint Balancing","created":"2024-07-03","cited_by_count":7,"area":null},{"id":"2407.03251","title":"ACTRESS: Active Retraining for Semi-supervised Visual Grounding","created":"2024-07-03","cited_by_count":7,"area":null},{"id":"2412.20613","title":"Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study","created":"2024-12-29","cited_by_count":7,"area":"mllm"},{"id":"2112.02834","title":"A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statistics","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2310.09147","title":"Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2208.08104","title":"Understanding Attention for Vision-and-Language Tasks","created":"2022-08-17","cited_by_count":4,"area":null},{"id":"2212.01638","title":"VLG: General Video Recognition with Web Textual Knowledge","created":"2022-12-03","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":"2505.05446","title":"Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2509.11662","title":"MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUs","created":"2025-09-15","cited_by_count":3,"area":"mllm"},{"id":"2602.04296","title":"ProxyWar: Dynamic Assessment of LLM Code Generation in Game Arenas","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2203.12929","title":"Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2312.12723","title":"Multi-Clue Reasoning with Memory Augmentation for Knowledge-based Visual Question Answering","created":"2023-12-20","cited_by_count":2,"area":null},{"id":"2402.00453","title":"Instruction Makes a Difference","created":"2024-02-01","cited_by_count":2,"area":null},{"id":"2508.08066","title":"ExpVG: Investigating the Design Space of Visual Grounding in Multimodal Large Language Model","created":"2025-08-11","cited_by_count":2,"area":"mllm"},{"id":"2508.08275","title":"MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis","created":"2025-07-31","cited_by_count":2,"area":"lr"},{"id":"2508.17334","title":"Mind the (Language) Gap: Towards Probing Numerical and Cross-Lingual Limits of LVLMs","created":"2025-08-24","cited_by_count":2,"area":"mllm"},{"id":"2204.09774","title":"Attention in Reasoning: Dataset, Analysis, and Modeling","created":"2022-04-20","cited_by_count":1,"area":"lr"},{"id":"2406.15050","title":"Tri-VQA: Triangular Reasoning Medical Visual Question Answering for Multi-Attribute Analysis","created":"2024-06-21","cited_by_count":1,"area":null},{"id":"2410.22648","title":"SimpsonsVQA: Enhancing Inquiry-Based Learning with a Tailored Dataset","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2504.12316","title":"Data Metabolism: An Efficient Data Design Schema For Vision Language Model","created":"2025-04-10","cited_by_count":1,"area":"mllm"},{"id":"2509.17418","title":"Vision Language Models Are Not (Yet) Spelling Correctors","created":"2025-09-22","cited_by_count":1,"area":"mllm"},{"id":"2511.17881","title":"MGA-VQA: Secure and Interpretable Graph-Augmented Visual Question Answering with Memory-Guided Protection Against Unauthorized Knowledge Use","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2601.01526","title":"BARE: Towards Bias-Aware and Reasoning-Enhanced One-Tower Visual Grounding","created":"2026-01-04","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":"2605.00905","title":"DIAGRAMS: A Review Framework for Reasoning-Level Attribution in Diagram QA","created":"2026-04-29","cited_by_count":1,"area":null},{"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":"2208.05798","title":"Aesthetic Visual Question Answering of Photographs","created":"2022-08-10","cited_by_count":0,"area":null},{"id":"2504.12315","title":"Capybara-OMNI: An Efficient Paradigm for Building Omni-Modal Language Models","created":"2025-04-10","cited_by_count":0,"area":"mllm"},{"id":"2505.10055","title":"PsOCR: Benchmarking Large Multimodal Models for Optical Character Recognition in Low-resource Pashto Language","created":"2025-05-15","cited_by_count":0,"area":"mllm"},{"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":"2608.27154","title":"ReViCo: Unveiling the Limitations of VLMs in Visual Text Understanding via Error Correction","created":"2026-08-27","cited_by_count":0,"area":"mllm"},{"id":"2608.28784","title":"ClearText-Video: A Large-Scale Text-Centric Video Dataset Bridging Video Restoration and Scene-Text Enhancement","created":"2026-08-28","cited_by_count":0,"area":"mllm"}],"next_cursor":null}