{"total":48,"rows":[{"id":"2411.17465","title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent","created":"2024-11-26","cited_by_count":232,"area":null},{"id":"2411.14347","title":"DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding","created":"2024-11-21","cited_by_count":89,"area":null},{"id":"2503.15661","title":"UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction","created":"2025-03-19","cited_by_count":77,"area":null},{"id":"2504.14603","title":"UFO2: The Desktop AgentOS","created":"2025-04-20","cited_by_count":41,"area":null},{"id":"2508.03923","title":"CoAct-1: Computer-using Multi-Agent System with Coding Actions","created":"2025-08-05","cited_by_count":35,"area":null},{"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":"2412.09362","title":"Falcon-UI: Understanding GUI Before Following User Instructions","created":"2024-12-12","cited_by_count":22,"area":null},{"id":"2508.21456","title":"Morae: Proactively Pausing UI Agents for User Choices","created":"2025-08-29","cited_by_count":19,"area":null},{"id":"2501.13896","title":"GUI-Bee: Align GUI Action Grounding to Novel Environments via Autonomous Exploration","created":"2025-01-23","cited_by_count":18,"area":null},{"id":"2411.11098","title":"MolParser: End-to-end Visual Recognition of Molecule Structures in the Wild","created":"2024-11-17","cited_by_count":17,"area":null},{"id":"2605.13527","title":"MMSkills: Towards Multimodal Skills for General Visual Agents","created":"2026-05-13","cited_by_count":16,"area":null},{"id":"2603.13032","title":"Multimodal OCR: Parse Anything from Documents","created":"2026-03-13","cited_by_count":14,"area":null},{"id":"2412.17589","title":"PC Agent: While You Sleep, AI Works -- A Cognitive Journey into Digital World","created":"2024-12-23","cited_by_count":12,"area":null},{"id":"2503.14021","title":"MP-GUI: Modality Perception with MLLMs for GUI Understanding","created":"2025-03-18","cited_by_count":12,"area":null},{"id":"2512.05941","title":"Zoom in, Click out: Unlocking and Evaluating the Potential of Zooming for GUI Grounding","created":"2025-12-05","cited_by_count":8,"area":null},{"id":"2602.14276","title":"ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision","created":"2026-02-15","cited_by_count":6,"area":null},{"id":"2505.04670","title":"LLM Code Customization with Visual Results: A Benchmark on TikZ","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2509.21205","title":"TABLET: A Large-Scale Dataset for Robust Visual Table Understanding","created":"2025-09-25","cited_by_count":5,"area":null},{"id":"2503.11170","title":"DeskVision: Large Scale Desktop Region Captioning for Advanced GUI Agents","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2505.20424","title":"Robot Operation of Home Appliances by Reading User Manuals","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2509.13615","title":"See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles","created":"2025-09-17","cited_by_count":4,"area":null},{"id":"2602.06391","title":"POINTS-GUI-G: GUI-Grounding Journey","created":"2026-02-06","cited_by_count":4,"area":null},{"id":"2601.06031","title":"Beyond Clicking:A Step Towards Generalist GUI Grounding via Text Dragging","created":"2025-11-07","cited_by_count":3,"area":null},{"id":"2603.02951","title":"CGL: Advancing Continual GUI Learning via Reinforcement Fine-Tuning","created":"2026-03-03","cited_by_count":3,"area":null},{"id":"2603.17357","title":"WebPII: Benchmarking Visual PII Detection for Computer-Use Agents","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2605.06664","title":"BAMI: Training-Free Bias Mitigation in GUI Grounding","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2605.21082","title":"AutoRPA: Efficient GUI Automation through LLM-Driven Code Synthesis from Interactions","created":"2026-05-20","cited_by_count":3,"area":null},{"id":"2510.16051","title":"GUIrilla: A Scalable Framework for Automated Desktop UI Exploration","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2602.04101","title":"Interfaze: The Future of AI is built on Task-Specific Small Models","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2411.07441","title":"Automatically Detecting Online Deceptive Patterns","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2507.13505","title":"PHASE: Passive Human Activity Simulation Evaluation","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2601.19258","title":"GhostUI: Unveiling Hidden Interactions in Mobile UI","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2602.18548","title":"1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2604.24441","title":"AutoGUI-v2: A Comprehensive Multi-Modal GUI Functionality Understanding Benchmark","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2605.30628","title":"The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.12666","title":"CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2412.14054","title":"Digestion Algorithm in Hierarchical Symbolic Forests: A Fast Text Normalization Algorithm and Semantic Parsing Framework for Specific Scenarios and Lightweight Deployment","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2506.02183","title":"Natural, Artificial, and Human Intelligences","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2506.21369","title":"GenFlow: Interactive Modular System for Image Generation","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2508.16688","title":"Cybernaut: Towards Reliable Web Automation","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2602.03969","title":"Structural shifts in institutional participation and collaboration within the AI arXiv preprint research ecosystem","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2604.23855","title":"Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2605.14923","title":"SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.30697","title":"LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.28645","title":"Looks Right, Works Right: A Project-Level Benchmark for Multi-Screen Mobile App Generation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2608.03270","title":"GUI-Lens: Coarse-to-Fine Cropping for GUI Grounding with General-Purpose VLMs","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.26991","title":"ASIL: Replacing Screenshot-and-Click with Structured State and Semantic Actions","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.01344","title":"ExBind: A Controlled Diagnostic Benchmark for Visual-to-Executable Correspondence","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}