{"total":34,"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":"2305.11854","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","created":"2023-05-19","cited_by_count":160,"area":null},{"id":"2107.13731","title":"UIBert: Learning Generic Multimodal Representations for UI Understanding","created":"2021-07-29","cited_by_count":95,"area":null},{"id":"2205.11029","title":"META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI","created":"2022-05-23","cited_by_count":81,"area":null},{"id":"2312.13108","title":"ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation","created":"2023-12-20","cited_by_count":45,"area":null},{"id":"2406.10227","title":"VideoGUI: A Benchmark for GUI Automation from Instructional Videos","created":"2024-06-14","cited_by_count":35,"area":null},{"id":"2303.18248","title":"Towards Flexible Multi-modal Document Models","created":"2023-03-31","cited_by_count":31,"area":null},{"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":"2211.07615","title":"UGIF: UI Grounded Instruction Following","created":"2022-11-14","cited_by_count":25,"area":null},{"id":"2210.02663","title":"Towards Better Semantic Understanding of Mobile Interfaces","created":"2022-10-06","cited_by_count":24,"area":null},{"id":"2312.15820","title":"WebVLN: Vision-and-Language Navigation on Websites","created":"2023-12-25","cited_by_count":19,"area":null},{"id":"2310.04716","title":"Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API","created":"2023-10-07","cited_by_count":18,"area":null},{"id":"2205.06907","title":"Multimodal Conversational AI: A Survey of Datasets and Approaches","created":"2022-05-13","cited_by_count":16,"area":null},{"id":"2410.13757","title":"MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation","created":"2024-10-17","cited_by_count":14,"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":"2310.07023","title":"Automatic Macro Mining from Interaction Traces at Scale","created":"2023-10-10","cited_by_count":12,"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":"2301.10165","title":"Lexi: Self-Supervised Learning of the UI Language","created":"2023-01-23","cited_by_count":10,"area":null},{"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":"2209.15099","title":"MUG: Interactive Multimodal Grounding on User Interfaces","created":"2022-09-29","cited_by_count":9,"area":null},{"id":"2503.03743","title":"CHOP: Mobile Operating Assistant with Constrained High-frequency Optimized Subtask Planning","created":"2025-03-05","cited_by_count":6,"area":null},{"id":"2203.07828","title":"Do BERTs Learn to Use Browser User Interface? Exploring Multi-Step Tasks with Unified Vision-and-Language BERTs","created":"2022-03-15","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":"2406.07822","title":"Tell Me What's Next: Textual Foresight for Generic UI Representations","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2206.02977","title":"DETR++: Taming Your Multi-Scale Detection Transformer","created":"2022-06-07","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":"2204.03731","title":"GreaseVision: Rewriting the Rules of the Interface","created":"2022-04-07","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":"2411.03709","title":"AutoGameUI: Constructing High-Fidelity GameUI via Multimodal Correspondence Matching","created":"2024-11-06","cited_by_count":1,"area":null},{"id":"2506.12623","title":"MS4UI: A Dataset for Multi-modal Summarization of User Interface Instructional Videos","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2510.10180","title":"TCMA: Text-Conditioned Multi-granularity Alignment for Drone Cross-Modal Text-Video Retrieval","created":"2025-10-11","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":"2403.10170","title":"Computer User Interface Understanding. A New Dataset and a Learning Framework","created":"2024-03-15","cited_by_count":0,"area":null}],"next_cursor":null}