{"list":"other","total":53,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2312.08914","title":"CogAgent: A Visual Language Model for GUI Agents","created":"2023-12-14","cited_by_count":704},{"id":"2401.10935","title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","created":"2024-01-17","cited_by_count":567},{"id":"2410.05243","title":"Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents","created":"2024-10-07","cited_by_count":382},{"id":"2307.10088","title":"Android in the Wild: A Large-Scale Dataset for Android Device Control","created":"2023-07-19","cited_by_count":319},{"id":"2412.04454","title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","created":"2024-12-05","cited_by_count":278},{"id":"2406.11896","title":"DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning","created":"2024-06-14","cited_by_count":214},{"id":"2408.00203","title":"OmniParser for Pure Vision Based GUI Agent","created":"2024-08-01","cited_by_count":198},{"id":"2406.08451","title":"GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices","created":"2024-06-12","cited_by_count":194},{"id":"2309.11436","title":"You Only Look at Screens: Multimodal Chain-of-Action Agents","created":"2023-09-20","cited_by_count":185},{"id":"2308.15272","title":"AutoDroid: LLM-powered Task Automation in Android","created":"2023-08-29","cited_by_count":184},{"id":"2005.03776","title":"Mapping Natural Language Instructions to Mobile UI Action Sequences","created":"2020-05-07","cited_by_count":181},{"id":"2404.05719","title":"Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs","created":"2024-04-08","cited_by_count":176},{"id":"2501.11733","title":"Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks","created":"2025-01-20","cited_by_count":131},{"id":"2108.03353","title":"Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning","created":"2021-08-07","cited_by_count":120},{"id":"2407.17490","title":"AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents","created":"2024-07-03","cited_by_count":113},{"id":"2402.04615","title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding","created":"2024-02-07","cited_by_count":98},{"id":"2010.04295","title":"Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements","created":"2020-10-08","cited_by_count":95},{"id":"2107.13731","title":"UIBert: Learning Generic Multimodal Representations for UI Understanding","created":"2021-07-29","cited_by_count":95},{"id":"1711.04305","title":"Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a survey","created":"2017-11-12","cited_by_count":91},{"id":"2105.13231","title":"AndroidEnv: A Reinforcement Learning Platform for Android","created":"2021-05-27","cited_by_count":90},{"id":"2205.11029","title":"META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI","created":"2022-05-23","cited_by_count":81},{"id":"2402.11941","title":"CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation","created":"2024-02-19","cited_by_count":70},{"id":"2209.08199","title":"ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots","created":"2022-09-16","cited_by_count":66},{"id":"2209.08655","title":"Enabling Conversational Interaction with Mobile UI using Large Language Models","created":"2022-09-18","cited_by_count":66},{"id":"2209.14927","title":"Spotlight: Mobile UI Understanding using Vision-Language Models with a Focus","created":"2022-09-29","cited_by_count":62},{"id":"2404.16660","title":"Benchmarking Mobile Device Control Agents across Diverse Configurations","created":"2024-04-25","cited_by_count":55},{"id":"2410.18967","title":"Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms","created":"2024-10-24","cited_by_count":51},{"id":"2409.14818","title":"MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding","created":"2024-09-23","cited_by_count":48},{"id":"2304.07061","title":"DroidBot-GPT: GPT-powered UI Automation for Android","created":"2023-04-14","cited_by_count":47},{"id":"2012.12350","title":"ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces","created":"2020-12-22","cited_by_count":43},{"id":"2102.05216","title":"VINS: Visual Search for Mobile User Interface Design","created":"2021-02-10","cited_by_count":37},{"id":"2305.08144","title":"Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction","created":"2023-05-14","cited_by_count":36},{"id":"2404.16054","title":"LlamaTouch: A Faithful and Scalable Testbed for Mobile UI Task Automation","created":"2024-04-12","cited_by_count":36},{"id":"2311.15732","title":"GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?","created":"2023-11-27","cited_by_count":35},{"id":"2411.02006","title":"Foundations and Recent Trends in Multimodal Mobile Agents: A Survey","created":"2024-11-04","cited_by_count":31},{"id":"2104.08560","title":"Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments","created":"2021-04-17","cited_by_count":28},{"id":"2312.11190","title":"VisionTasker: Mobile Task Automation Using Vision Based UI Understanding and LLM Task Planning","created":"2023-12-18","cited_by_count":28},{"id":"2112.05692","title":"VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modeling","created":"2021-12-10","cited_by_count":26},{"id":"1808.09132","title":"Mapping Natural Language Commands to Web Elements","created":"2018-08-28","cited_by_count":23},{"id":"1902.11247","title":"Modeling Mobile Interface Tappability Using Crowdsourcing and Deep Learning","created":"2019-02-28","cited_by_count":18},{"id":"2106.00133","title":"AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learning","created":"2021-05-31","cited_by_count":17},{"id":"2306.01242","title":"Responsible Task Automation: Empowering Large Language Models as Responsible Task Automators","created":"2023-06-02","cited_by_count":14},{"id":"2501.17799","title":"Leveraging Multimodal LLM for Inspirational User Interface Search","created":"2025-01-29","cited_by_count":13},{"id":"2204.02448","title":"Predicting and Explaining Mobile UI Tappability with Vision Modeling and Saliency Analysis","created":"2022-04-05","cited_by_count":9},{"id":"2209.15099","title":"MUG: Interactive Multimodal Grounding on User Interfaces","created":"2022-09-29","cited_by_count":9},{"id":"2308.08726","title":"Never-ending Learning of User Interfaces","created":"2023-08-17","cited_by_count":9},{"id":"2305.09699","title":"Mobile User Interface Element Detection Via Adaptively Prompt Tuning","created":"2023-05-16","cited_by_count":8},{"id":"2404.08755","title":"Training a Vision Language Model as Smartphone Assistant","created":"2024-04-12","cited_by_count":8},{"id":"2112.12886","title":"Rediscovering Affordance: A Reinforcement Learning Perspective","created":"2021-12-24","cited_by_count":4},{"id":"2309.10328","title":"Computational Approaches for App-to-App Retrieval and Design Consistency Check","created":"2023-09-19","cited_by_count":3}],"next_cursor":null}