{"total":21,"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":"2303.16434","title":"TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs","created":"2023-03-29","cited_by_count":184,"area":null},{"id":"2402.05930","title":"WebLINX: Real-World Website Navigation with Multi-Turn Dialogue","created":"2024-02-08","cited_by_count":180,"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":"2404.06369","title":"WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs","created":"2024-04-09","cited_by_count":44,"area":null},{"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":"2406.16386","title":"Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approach","created":"2024-06-24","cited_by_count":24,"area":null},{"id":"2508.16763","title":"WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation","created":"2025-08-22","cited_by_count":16,"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":"2303.06782","title":"AidUI: Toward Automated Recognition of Dark Patterns in User Interfaces","created":"2023-03-12","cited_by_count":9,"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":"2312.10170","title":"UINav: A Practical Approach to Train On-Device Automation Agents","created":"2023-12-15","cited_by_count":5,"area":null},{"id":"2412.16829","title":"Visual Prompting with Iterative Refinement for Design Critique Generation","created":"2024-12-22","cited_by_count":5,"area":null},{"id":"2509.21733","title":"UISim: An Interactive Image-Based UI Simulator for Dynamic Mobile Environments","created":"2025-09-26","cited_by_count":5,"area":null},{"id":"2204.03731","title":"GreaseVision: Rewriting the Rules of the Interface","created":"2022-04-07","cited_by_count":2,"area":null},{"id":"2504.02110","title":"ScreenAudit: Detecting Screen Reader Accessibility Errors in Mobile Apps Using Large Language Models","created":"2025-04-02","cited_by_count":2,"area":null},{"id":"2212.04065","title":"SpaceEditing: Integrating Human Knowledge into Deep Neural Networks via Interactive Latent Space Editing","created":"2022-12-08","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":"2511.19380","title":"UISearch: Graph-Based Embeddings for Multimodal Enterprise UI Screenshots Retrieval","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2607.22928","title":"Design Theater: Evaluating the Gap Between User-Facing Design Reasoning and Implementation in Generative UI Tools","created":"2026-07-24","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}