{"total":151,"rows":[{"id":"2312.08914","title":"CogAgent: A Visual Language Model for GUI Agents","created":"2023-12-14","cited_by_count":704,"area":"mllm"},{"id":"2504.17761","title":"Step1X-Edit: A Practical Framework for General Image Editing","created":"2025-04-24","cited_by_count":429,"area":null},{"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":"2311.10089","title":"Emu Edit: Precise Image Editing via Recognition and Generation Tasks","created":"2023-11-16","cited_by_count":324,"area":null},{"id":"2403.16999","title":"Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning","created":"2024-03-25","cited_by_count":280,"area":"lr"},{"id":"2410.10594","title":"VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents","created":"2024-10-14","cited_by_count":245,"area":"rag"},{"id":"2507.05595","title":"PaddleOCR 3.0 Technical Report","created":"2025-07-08","cited_by_count":143,"area":null},{"id":"2305.18259","title":"GlyphControl: Glyph Conditional Control for Visual Text Generation","created":"2023-05-29","cited_by_count":131,"area":"diffusion"},{"id":"2206.03001","title":"PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System","created":"2022-06-07","cited_by_count":106,"area":null},{"id":"2310.02251","title":"Talk2BEV: Language-enhanced Bird's-eye View Maps for Autonomous Driving","created":"2023-10-03","cited_by_count":89,"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":"2505.22019","title":"VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning","created":"2025-05-28","cited_by_count":68,"area":"rag"},{"id":"2402.04236","title":"CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning","created":"2024-02-06","cited_by_count":67,"area":"lr"},{"id":"2507.15846","title":"GUI-G$^2$: Gaussian Reward Modeling for GUI Grounding","created":"2025-07-21","cited_by_count":63,"area":"alignment"},{"id":"2504.13865","title":"A Survey on (M)LLM-Based GUI Agents","created":"2025-03-27","cited_by_count":62,"area":"agents"},{"id":"2302.05658","title":"DocILE Benchmark for Document Information Localization and Extraction","created":"2023-02-11","cited_by_count":58,"area":null},{"id":"2410.00086","title":"ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer","created":"2024-09-30","cited_by_count":56,"area":"diffusion"},{"id":"2311.09797","title":"FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains","created":"2023-11-16","cited_by_count":40,"area":"lr"},{"id":"2503.01645","title":"DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models","created":"2025-03-03","cited_by_count":40,"area":"diffusion"},{"id":"2109.03144","title":"PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System","created":"2021-09-07","cited_by_count":39,"area":null},{"id":"2402.03310","title":"V-IRL: Grounding Virtual Intelligence in Real Life","created":"2024-02-05","cited_by_count":35,"area":null},{"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":"2504.19838","title":"LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects","created":"2025-04-28","cited_by_count":32,"area":"agents"},{"id":"2507.00008","title":"DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning","created":"2025-06-12","cited_by_count":31,"area":"lr"},{"id":"2308.09991","title":"AltDiffusion: A Multilingual Text-to-Image Diffusion Model","created":"2023-08-19","cited_by_count":30,"area":"diffusion"},{"id":"2402.19014","title":"Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models","created":"2024-02-29","cited_by_count":30,"area":"mllm"},{"id":"2505.24417","title":"EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering","created":"2025-05-30","cited_by_count":26,"area":"diffusion"},{"id":"2308.12234","title":"MolGrapher: Graph-based Visual Recognition of Chemical Structures","created":"2023-08-23","cited_by_count":24,"area":null},{"id":"2503.06470","title":"Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow Systems","created":"2025-03-09","cited_by_count":23,"area":null},{"id":"2601.14251","title":"LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR","created":"2026-01-20","cited_by_count":23,"area":"mllm"},{"id":"2602.20903","title":"TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering","created":"2026-02-24","cited_by_count":15,"area":null},{"id":"2508.07493","title":"VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding","created":"2025-08-10","cited_by_count":14,"area":"rag"},{"id":"2606.13108","title":"PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks","created":"2026-06-11","cited_by_count":14,"area":"mllm"},{"id":"2303.05325","title":"BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis Dataset","created":"2023-03-09","cited_by_count":13,"area":null},{"id":"2308.12774","title":"LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition","created":"2023-08-24","cited_by_count":13,"area":null},{"id":"2507.20025","title":"Region-based Cluster Discrimination for Visual Representation Learning","created":"2025-07-26","cited_by_count":13,"area":null},{"id":"2102.09127","title":"Efficient Online ML API Selection for Multi-Label Classification Tasks","created":"2021-02-18","cited_by_count":11,"area":null},{"id":"2301.10165","title":"Lexi: Self-Supervised Learning of the UI Language","created":"2023-01-23","cited_by_count":10,"area":null},{"id":"2410.05267","title":"Grounding Partially-Defined Events in Multimodal Data","created":"2024-10-07","cited_by_count":10,"area":null},{"id":"2502.10999","title":"ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations","created":"2025-02-16","cited_by_count":10,"area":"diffusion"},{"id":"2508.13238","title":"DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Model","created":"2025-08-18","cited_by_count":10,"area":"lr"},{"id":"2204.12743","title":"Self-Supervised Text Erasing with Controllable Image Synthesis","created":"2022-04-27","cited_by_count":9,"area":null},{"id":"2309.00378","title":"Long-Term Ad Memorability: Understanding & Generating Memorable Ads","created":"2023-09-01","cited_by_count":9,"area":null},{"id":"2404.04624","title":"Bridging the Gap Between End-to-End and Two-Step Text Spotting","created":"2024-04-06","cited_by_count":9,"area":null},{"id":"2507.15085","title":"OCRGenBench: A Comprehensive Benchmark for Evaluating OCR Generative Capabilities","created":"2025-07-20","cited_by_count":9,"area":null},{"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":"2402.08017","title":"Lumos : Empowering Multimodal LLMs with Scene Text Recognition","created":"2024-02-12","cited_by_count":8,"area":"mllm"},{"id":"2406.11432","title":"AnyTrans: Translate AnyText in the Image with Large Scale Models","created":"2024-06-17","cited_by_count":8,"area":"diffusion"},{"id":"2506.04641","title":"Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation Decoders","created":"2025-06-05","cited_by_count":7,"area":"diffusion"},{"id":"2609.11929","title":"SenseNova-U1.5: Towards Native Unified Visual Intelligence","created":"2026-09-10","cited_by_count":7,"area":"distill"},{"id":"2207.06744","title":"TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents","created":"2022-07-14","cited_by_count":6,"area":null},{"id":"2209.08443","title":"HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions","created":"2022-09-18","cited_by_count":6,"area":null},{"id":"2307.04643","title":"MultiQG-TI: Towards Question Generation from Multi-modal Sources","created":"2023-07-07","cited_by_count":6,"area":null},{"id":"2603.15616","title":"GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering","created":"2026-03-16","cited_by_count":6,"area":"alignment"},{"id":"2102.10884","title":"Revisiting Classification Perspective on Scene Text Recognition","created":"2021-02-22","cited_by_count":5,"area":null},{"id":"2108.06949","title":"Data Augmentation for Scene Text Recognition","created":"2021-08-16","cited_by_count":5,"area":null},{"id":"2210.07903","title":"Text Detection Forgot About Document OCR","created":"2022-10-14","cited_by_count":5,"area":null},{"id":"2301.02363","title":"Text2Poster: Laying out Stylized Texts on Retrieved Images","created":"2023-01-06","cited_by_count":5,"area":null},{"id":"2503.12532","title":"STEVE: A Step Verification Pipeline for Computer-use Agent Training","created":"2025-03-16","cited_by_count":5,"area":"agents"},{"id":"2503.16096","title":"MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2105.07795","title":"STRIDE : Scene Text Recognition In-Device","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2410.21414","title":"CT2C-QA: Multimodal Question Answering over Chinese Text, Table and Chart","created":"2024-10-28","cited_by_count":4,"area":null},{"id":"2501.19353","title":"Do Large Multimodal Models Solve Caption Generation for Scientific Figures? Lessons Learned from SciCap Challenge 2023","created":"2025-01-31","cited_by_count":4,"area":"mllm"},{"id":"2502.18148","title":"NusaAksara: A Multimodal and Multilingual Benchmark for Preserving Indonesian Indigenous Scripts","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2505.13483","title":"EmoMeta: A Multimodal Dataset for Fine-grained Emotion Classification in Chinese Metaphors","created":"2025-05-12","cited_by_count":4,"area":null},{"id":"2505.17473","title":"InfoDet: A Dataset for Infographic Element Detection","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2506.23009","title":"MusiXQA: Advancing Visual Music Understanding in Multimodal Large Language Models","created":"2025-06-28","cited_by_count":4,"area":"lr"},{"id":"2109.12212","title":"An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog","created":"2021-09-24","cited_by_count":3,"area":null},{"id":"2307.04245","title":"A Novel Pipeline for Improving Optical Character Recognition through Post-processing Using Natural Language Processing","created":"2023-07-09","cited_by_count":3,"area":null},{"id":"2410.04439","title":"Empowering Backbone Models for Visual Text Generation with Input Granularity Control and Glyph-Aware Training","created":"2024-10-06","cited_by_count":3,"area":"diffusion"},{"id":"2505.01435","title":"AdaParse: An Adaptive Parallel PDF Parsing and Resource Scaling Engine","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2604.23970","title":"LLM-Guided Agentic Floor Plan Parsing for Accessible Indoor Navigation of Blind and Low-Vision People","created":"2026-04-27","cited_by_count":3,"area":"agents"},{"id":"2605.16740","title":"TRACE: Evidence Grounding-Guided Multi-Video Event Understanding and Claim Generation","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2606.01050","title":"TextFake: Benchmarking AI-Generated Image Detection on Text-Rich Images","created":"2026-05-31","cited_by_count":3,"area":null},{"id":"2607.00535","title":"Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition","created":"2026-07-01","cited_by_count":3,"area":"lr"},{"id":"2207.06694","title":"Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting","created":"2022-07-14","cited_by_count":2,"area":null},{"id":"2405.08427","title":"Impact of Stickers on Multimodal Sentiment and Intent in Social Media: A New Task, Dataset and Baseline","created":"2024-05-14","cited_by_count":2,"area":null},{"id":"2407.06950","title":"Spanish TrOCR: Leveraging Transfer Learning for Language Adaptation","created":"2024-07-09","cited_by_count":2,"area":null},{"id":"2409.04117","title":"Confidence-Aware Document OCR Error Detection","created":"2024-09-06","cited_by_count":2,"area":null},{"id":"2504.16723","title":"Detecting and Understanding Hateful Contents in Memes Through Captioning and Visual Question-Answering","created":"2025-04-23","cited_by_count":2,"area":null},{"id":"2507.05805","title":"DREAM: Document Reconstruction via End-to-end Autoregressive Model","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2510.03570","title":"Evaluating OCR performance on food packaging labels in South Africa","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2601.16113","title":"synthocr-gen: A synthetic ocr dataset generator for low-resource languages- breaking the data barrier","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2603.11044","title":"LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Reference","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2607.21617","title":"Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Models","created":"2026-05-29","cited_by_count":2,"area":"mllm"},{"id":"2608.19637","title":"TextRefine: Improving Textual Fidelity, Spatial Placement, and Glyph Rendering for Text Editing in Product Posters","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2403.07553","title":"The future of document indexing: GPT and Donut revolutionize table of content processing","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2409.05125","title":"PdfTable: A Unified Toolkit for Deep Learning-Based Table Extraction","created":"2024-09-08","cited_by_count":1,"area":null},{"id":"2409.10016","title":"AceParse: A Comprehensive Dataset with Diverse Structured Texts for Academic Literature Parsing","created":"2024-09-16","cited_by_count":1,"area":null},{"id":"2410.21801","title":"PerSRV: Personalized Sticker Retrieval with Vision-Language Model","created":"2024-10-29","cited_by_count":1,"area":"mllm"},{"id":"2503.17735","title":"RDTF: Resource-efficient Dual-mask Training Framework for Multi-frame Animated Sticker Generation","created":"2025-03-22","cited_by_count":1,"area":null},{"id":"2504.18948","title":"Use of Metric Learning for the Recognition of Handwritten Digits, and its Application to Increase the Outreach of Voice-based Communication Platforms","created":"2025-04-26","cited_by_count":1,"area":null},{"id":"2505.02418","title":"SymbioticRAG: Enhancing Document Intelligence Through Human-LLM Symbiotic Collaboration","created":"2025-05-05","cited_by_count":1,"area":"rag"},{"id":"2505.05895","title":"Leveraging Vision-Language Models for Visual Grounding and Analysis of Automotive UI","created":"2025-05-09","cited_by_count":1,"area":"mllm"},{"id":"2505.06918","title":"Uni-AIMS: AI-Powered Microscopy Image Analysis","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2507.21924","title":"MMAT-1M: A Large Reasoning Dataset for Multimodal Agent Tuning","created":"2025-07-29","cited_by_count":1,"area":"lr"},{"id":"2510.02543","title":"Exploring OCR-augmented Generation for Bilingual VQA","created":"2025-10-02","cited_by_count":1,"area":"mllm"},{"id":"2510.03160","title":"SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k Corpus","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2605.05831","title":"Unifying Scientific Communication: Fine-Grained Correspondence Across Scientific Media","created":"2026-05-07","cited_by_count":1,"area":"mllm"},{"id":"2605.15523","title":"Self-Prompting Diffusion Transformer for Open-Vocabulary Scene Text Editing via In-Context Learning","created":"2026-05-15","cited_by_count":1,"area":"diffusion"}],"next_cursor":"100"}