{"total":31,"rows":[{"id":"2411.03292","title":"Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping","created":"2024-11-05","cited_by_count":51,"area":null},{"id":"2506.06251","title":"DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation","created":"2025-06-06","cited_by_count":45,"area":null},{"id":"2102.05216","title":"VINS: Visual Search for Mobile User Interface Design","created":"2021-02-10","cited_by_count":37,"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":"2101.09978","title":"GUIGAN: Learning to Generate GUI Designs Using Generative Adversarial Networks","created":"2021-01-25","cited_by_count":17,"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":"2301.10165","title":"Lexi: Self-Supervised Learning of the UI Language","created":"2023-01-23","cited_by_count":10,"area":null},{"id":"2106.10507","title":"GLIB: Towards Automated Test Oracle for Graphically-Rich Applications","created":"2021-06-19","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":"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":"2106.07615","title":"Magic Layouts: Structural Prior for Component Detection in User Interface Designs","created":"2021-06-14","cited_by_count":5,"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":"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":"2405.00145","title":"GUing: A Mobile GUI Search Engine using a Vision-Language Model","created":"2024-04-30","cited_by_count":4,"area":null},{"id":"2104.08301","title":"Text2App: A Framework for Creating Android Apps from Text Descriptions","created":"2021-04-16","cited_by_count":3,"area":null},{"id":"2510.04097","title":"WebRenderBench: Enhancing Web Interface Generation through Layout-Style Consistency and Reinforcement Learning","created":"2025-10-05","cited_by_count":3,"area":null},{"id":"2103.05704","title":"Automatic code generation from sketches of mobile applications in end-user development using Deep Learning","created":"2021-03-09","cited_by_count":2,"area":null},{"id":"2208.06658","title":"ULDGNN: A Fragmented UI Layer Detector Based on Graph Neural Networks","created":"2022-08-13","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":"2408.03507","title":"GUI Element Detection Using SOTA YOLO Deep Learning Models","created":"2024-08-07","cited_by_count":2,"area":null},{"id":"2507.04469","title":"The role of large language models in UI/UX design: A systematic literature review","created":"2025-07-06","cited_by_count":2,"area":null},{"id":"2601.10536","title":"CoGen: Creation of Reusable UI Components in Figma via Textual Commands","created":"2026-01-15","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":"2211.14607","title":"Sketch2FullStack: Generating Skeleton Code of Full Stack Website and Application from Sketch using Deep Learning and Computer Vision","created":"2022-11-26","cited_by_count":1,"area":null},{"id":"2303.13055","title":"Reimagining Application User Interface (UI) Design using Deep Learning Methods: Challenges and Opportunities","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2407.08610","title":"Semantic GUI Scene Learning and Video Alignment for Detecting Duplicate Video-based Bug Reports","created":"2024-07-11","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":"2409.10811","title":"Grounded GUI Understanding for Vision-Based Spatial Intelligent Agent: Exemplified by Extended Reality Apps","created":"2024-09-17","cited_by_count":0,"area":null},{"id":"2601.01944","title":"The Invisible Hand of AI Libraries Shaping Open Source Projects and Communities","created":"2026-01-05","cited_by_count":0,"area":null}],"next_cursor":null}