{"total":58,"rows":[{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366,"area":null},{"id":"2307.10088","title":"Android in the Wild: A Large-Scale Dataset for Android Device Control","created":"2023-07-19","cited_by_count":319,"area":null},{"id":"2309.11436","title":"You Only Look at Screens: Multimodal Chain-of-Action Agents","created":"2023-09-20","cited_by_count":185,"area":"agents"},{"id":"2308.15272","title":"AutoDroid: LLM-powered Task Automation in Android","created":"2023-08-29","cited_by_count":184,"area":null},{"id":"2409.02977","title":"Large Language Model-Based Agents for Software Engineering: A Survey","created":"2024-09-04","cited_by_count":178,"area":"agents"},{"id":"2404.05719","title":"Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs","created":"2024-04-08","cited_by_count":176,"area":"mllm"},{"id":"2311.07562","title":"GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation","created":"2023-11-13","cited_by_count":137,"area":"mllm"},{"id":"2108.03353","title":"Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning","created":"2021-08-07","cited_by_count":120,"area":null},{"id":"2407.17490","title":"AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents","created":"2024-07-03","cited_by_count":113,"area":"agents"},{"id":"2411.04890","title":"GUI Agents with Foundation Models: A Comprehensive Survey","created":"2024-11-07","cited_by_count":111,"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":"2311.11797","title":"Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents","created":"2023-11-20","cited_by_count":72,"area":"lr"},{"id":"2209.08655","title":"Enabling Conversational Interaction with Mobile UI using Large Language Models","created":"2022-09-18","cited_by_count":66,"area":null},{"id":"2209.14927","title":"Spotlight: Mobile UI Understanding using Vision-Language Models with a Focus","created":"2022-09-29","cited_by_count":62,"area":"mllm"},{"id":"2312.03003","title":"Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation","created":"2023-12-04","cited_by_count":58,"area":null},{"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":"2310.02424","title":"AXNav: Replaying Accessibility Tests from Natural Language","created":"2023-10-03","cited_by_count":31,"area":null},{"id":"2411.02006","title":"Foundations and Recent Trends in Multimodal Mobile Agents: A Survey","created":"2024-11-04","cited_by_count":31,"area":"agents"},{"id":"2201.04100","title":"Learning to Denoise Raw Mobile UI Layouts for Improving Datasets at Scale","created":"2022-01-11","cited_by_count":30,"area":null},{"id":"2406.07739","title":"UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback","created":"2024-06-11","cited_by_count":27,"area":"alignment"},{"id":"2112.05692","title":"VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modeling","created":"2021-12-10","cited_by_count":26,"area":null},{"id":"2312.06677","title":"Intelligent Virtual Assistants with LLM-based Process Automation","created":"2023-12-04","cited_by_count":26,"area":null},{"id":"2210.02663","title":"Towards Better Semantic Understanding of Mobile Interfaces","created":"2022-10-06","cited_by_count":24,"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":"2110.12536","title":"Neo: Generalizing Confusion Matrix Visualization to Hierarchical and Multi-Output Labels","created":"2021-10-24","cited_by_count":17,"area":null},{"id":"2310.04869","title":"ILuvUI: Instruction-tuned LangUage-Vision modeling of UIs from Machine Conversations","created":"2023-10-07","cited_by_count":17,"area":"mllm"},{"id":"2502.16796","title":"MobileSteward: Integrating Multiple App-Oriented Agents with Self-Evolution to Automate Cross-App Instructions","created":"2025-02-24","cited_by_count":16,"area":null},{"id":"2105.11941","title":"Understanding Mobile GUI: from Pixel-Words to Screen-Sentences","created":"2021-05-25","cited_by_count":13,"area":null},{"id":"2503.04730","title":"WinClick: GUI Grounding with Multimodal Large Language Models","created":"2025-01-27","cited_by_count":11,"area":null},{"id":"2410.09006","title":"From Interaction to Impact: Towards Safer AI Agents Through Understanding and Evaluating Mobile UI Operation Impacts","created":"2024-10-11","cited_by_count":10,"area":"agents"},{"id":"2204.02448","title":"Predicting and Explaining Mobile UI Tappability with Vision Modeling and Saliency Analysis","created":"2022-04-05","cited_by_count":9,"area":null},{"id":"2303.06782","title":"AidUI: Toward Automated Recognition of Dark Patterns in User Interfaces","created":"2023-03-12","cited_by_count":9,"area":null},{"id":"2502.08226","title":"TRISHUL: Towards Region Identification and Screen Hierarchy Understanding for Large VLM based GUI Agents","created":"2025-02-12","cited_by_count":9,"area":"mllm"},{"id":"2107.04452","title":"Multimodal Icon Annotation For Mobile Applications","created":"2021-07-09","cited_by_count":8,"area":null},{"id":"2410.00201","title":"DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation","created":"2024-09-30","cited_by_count":8,"area":null},{"id":"2206.10352","title":"Psychologically-Inspired, Unsupervised Inference of Perceptual Groups of GUI Widgets from GUI Images","created":"2022-06-15","cited_by_count":5,"area":null},{"id":"2312.10170","title":"UINav: A Practical Approach to Train On-Device Automation Agents","created":"2023-12-15","cited_by_count":5,"area":null},{"id":"2301.01224","title":"An Empirical Investigation into the Use of Image Captioning for Automated Software Documentation","created":"2023-01-03","cited_by_count":4,"area":null},{"id":"2303.04496","title":"MenuCraft: Interactive Menu System Design with Large Language Models","created":"2023-03-08","cited_by_count":4,"area":null},{"id":"2409.04081","title":"UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activity","created":"2024-09-06","cited_by_count":4,"area":null},{"id":"2503.19537","title":"Agent-Initiated Interaction in Phone UI Automation","created":"2025-03-25","cited_by_count":4,"area":"agents"},{"id":"2409.12089","title":"The Impact of Element Ordering on LM Agent Performance","created":"2024-09-18","cited_by_count":3,"area":"agents"},{"id":"2512.00846","title":"AFRAgent : An Adaptive Feature Renormalization Based High Resolution Aware GUI agent","created":"2025-11-30","cited_by_count":3,"area":"agents"},{"id":"2306.07298","title":"Referring to Screen Texts with Voice Assistants","created":"2023-06-10","cited_by_count":2,"area":null},{"id":"2309.09867","title":"EGFE: End-to-end Grouping of Fragmented Elements in UI Designs with Multimodal Learning","created":"2023-09-18","cited_by_count":2,"area":null},{"id":"2408.03827","title":"Automated Code Fix Suggestions for Accessibility Issues in Mobile Apps","created":"2024-08-07","cited_by_count":2,"area":null},{"id":"2504.09352","title":"Explorer: Robust Collection of Interactable GUI Elements","created":"2025-04-12","cited_by_count":2,"area":null},{"id":"2605.16402","title":"WinDeskGround: A Benchmark for Robust GUI Grounding in Complex Multi-Window Desktop Environments","created":"2026-05-13","cited_by_count":2,"area":"mllm"},{"id":"2206.13389","title":"UI Layers Merger: Merging UI layers via Visual Learning and Boundary Prior","created":"2022-06-18","cited_by_count":1,"area":null},{"id":"2409.09354","title":"PeriGuru: A Peripheral Robotic Mobile App Operation Assistant based on GUI Image Understanding and Prompting with LLM","created":"2024-09-14","cited_by_count":1,"area":null},{"id":"2411.07441","title":"Automatically Detecting Online Deceptive Patterns","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2505.19095","title":"ScreenExplorer: Training a Vision-Language Model for Diverse Exploration in Open GUI World","created":"2025-05-25","cited_by_count":1,"area":"mllm"},{"id":"2512.03568","title":"Synthetic Cognitive Walkthrough: Aligning Large Language Model Performance with Human Cognitive Walkthrough","created":"2025-12-03","cited_by_count":1,"area":"alignment"},{"id":"2403.13690","title":"MotorEase: Automated Detection of Motor Impairment Accessibility Issues in Mobile App UIs","created":"2024-03-20","cited_by_count":0,"area":null},{"id":"2502.03330","title":"ControlGUI: Guiding Generative GUI Exploration through Perceptual Visual Flow","created":"2025-02-05","cited_by_count":0,"area":null},{"id":"2609.05423","title":"Seeing Without Understanding: Large Language Model Evaluation of Mobile User Interface Quality, Failure Taxonomy, and Architectural Explanation","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2610.14228","title":"Latent World Action Model for GUI Agents","created":"2026-10-09","cited_by_count":0,"area":"wm"}],"next_cursor":null}