{"total":22,"rows":[{"id":"2504.13059","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins","created":"2025-04-17","cited_by_count":121,"area":null},{"id":"2209.08199","title":"ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots","created":"2022-09-16","cited_by_count":66,"area":null},{"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":"2210.02663","title":"Towards Better Semantic Understanding of Mobile Interfaces","created":"2022-10-06","cited_by_count":24,"area":null},{"id":"2407.08850","title":"UICrit: Enhancing Automated Design Evaluation with a UICritique Dataset","created":"2024-07-11","cited_by_count":21,"area":null},{"id":"2212.09877","title":"LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer","created":"2022-12-19","cited_by_count":15,"area":null},{"id":"2310.15455","title":"UI Layout Generation with LLMs Guided by UI Grammar","created":"2023-10-24","cited_by_count":15,"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":"2209.15099","title":"MUG: Interactive Multimodal Grounding on User Interfaces","created":"2022-09-29","cited_by_count":9,"area":null},{"id":"2404.13521","title":"Graph4GUI: Graph Neural Networks for Representing Graphical User Interfaces","created":"2024-04-21","cited_by_count":6,"area":null},{"id":"2407.15502","title":"WebRPG: Automatic Web Rendering Parameters Generation for Visual Presentation","created":"2024-07-22","cited_by_count":4,"area":null},{"id":"2504.16419","title":"PixelWeb: The First Web GUI Dataset with Pixel-Wise Labels","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2304.09012","title":"GUILGET: GUI Layout GEneration with Transformer","created":"2023-04-18","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":"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":"2310.04755","title":"Pairwise GUI Dataset Construction Between Android Phones and Tablets","created":"2023-10-07","cited_by_count":1,"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":"2212.03440","title":"UI Layers Group Detector: Grouping UI Layers via Text Fusion and Box Attention","created":"2022-12-07","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":"2511.19380","title":"UISearch: Graph-Based Embeddings for Multimodal Enterprise UI Screenshots Retrieval","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2603.04245","title":"LikeThis! Empowering App Users to Submit UI Improvement Suggestions Instead of Complaints","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2609.30466","title":"A Benchmarking Framework for Context-aware XR Interfaces","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}