{"total":114,"rows":[{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203,"area":null},{"id":"2407.03320","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","created":"2024-07-03","cited_by_count":195,"area":"mllm"},{"id":"2403.03163","title":"Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering","created":"2024-03-05","cited_by_count":152,"area":"mllm"},{"id":"2403.09029","title":"Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset","created":"2024-03-14","cited_by_count":129,"area":"mllm"},{"id":"2312.11556","title":"StarVector: Generating Scalable Vector Graphics Code from Images and Text","created":"2023-12-17","cited_by_count":102,"area":null},{"id":"2401.00812","title":"If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents","created":"2024-01-01","cited_by_count":79,"area":"agents"},{"id":"2406.20098","title":"Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs","created":"2024-06-28","cited_by_count":74,"area":"mllm"},{"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":"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":"2404.14368","title":"Graphic Design with Large Multimodal Model","created":"2024-04-22","cited_by_count":40,"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":"2410.16232","title":"Sketch2Code: Evaluating Vision-Language Models for Interactive Web Design Prototyping","created":"2024-10-21","cited_by_count":29,"area":"mllm"},{"id":"2505.17399","title":"FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow","created":"2025-05-23","cited_by_count":28,"area":null},{"id":"2507.22827","title":"ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents","created":"2025-07-30","cited_by_count":26,"area":"agents"},{"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":"2601.02430","title":"WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics","created":"2026-01-05","cited_by_count":18,"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":"2310.04869","title":"ILuvUI: Instruction-tuned LangUage-Vision modeling of UIs from Machine Conversations","created":"2023-10-07","cited_by_count":17,"area":"mllm"},{"id":"2409.18980","title":"IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Web","created":"2024-09-14","cited_by_count":16,"area":"mllm"},{"id":"2508.09945","title":"VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models","created":"2025-08-13","cited_by_count":16,"area":"mllm"},{"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":"2511.02778","title":"VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation","created":"2025-11-04","cited_by_count":16,"area":null},{"id":"2506.07818","title":"WebUIBench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in WebUI-to-Code","created":"2025-06-09","cited_by_count":15,"area":"mllm"},{"id":"2509.22644","title":"WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning","created":"2025-09-26","cited_by_count":15,"area":"lr"},{"id":"2511.08195","title":"UI2Code^N: UI-to-Code Generation as Interactive Visual Optimization","created":"2025-11-11","cited_by_count":15,"area":null},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2603.13032","title":"Multimodal OCR: Parse Anything from Documents","created":"2026-03-13","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":"2509.24709","title":"IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?","created":"2025-09-29","cited_by_count":12,"area":null},{"id":"2511.06251","title":"WebVIA: A Web-based Vision-Language Agentic Framework for Interactive and Verifiable UI-to-Code Generation","created":"2025-11-09","cited_by_count":10,"area":"agents"},{"id":"2511.15567","title":"Computer-Use Agents as Judges for Generative User Interface","created":"2025-11-19","cited_by_count":9,"area":"agents"},{"id":"2512.19918","title":"Widget2Code: From Visual Widgets to UI Code via Multimodal LLMs","created":"2025-12-22","cited_by_count":9,"area":"mllm"},{"id":"2602.05998","title":"VisRefiner: Learning from Visual Differences for Screenshot-to-Code Generation","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2605.15677","title":"VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and Editing","created":"2026-05-15","cited_by_count":9,"area":"mllm"},{"id":"2606.01869","title":"WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis","created":"2026-06-01","cited_by_count":9,"area":null},{"id":"2212.11541","title":"Generative Colorization of Structured Mobile Web Pages","created":"2022-12-22","cited_by_count":8,"area":null},{"id":"2603.09652","title":"MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants","created":"2026-03-10","cited_by_count":8,"area":null},{"id":"2604.09577","title":"Generative UI: LLMs are Effective UI Generators","created":"2026-02-24","cited_by_count":8,"area":null},{"id":"2103.12801","title":"Variable Name Recovery in Decompiled Binary Code using Constrained Masked Language Modeling","created":"2021-03-23","cited_by_count":7,"area":null},{"id":"2503.12293","title":"Unified Modeling Language Code Generation from Diagram Images Using Multimodal Large Language Models","created":"2025-03-15","cited_by_count":7,"area":null},{"id":"2509.25297","title":"Automatically Generating Web Applications from Requirements Via Multi-Agent Test-Driven Development","created":"2025-09-29","cited_by_count":7,"area":"agents"},{"id":"2508.19227","title":"Generative Interfaces for Language Models","created":"2025-08-26","cited_by_count":6,"area":null},{"id":"2604.18224","title":"WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models","created":"2026-04-20","cited_by_count":6,"area":"agents"},{"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":"2509.12159","title":"EfficientUICoder: A Bidirectional Token Compression Framework for Efficient MLLM-Based UI Code Generation","created":"2025-09-15","cited_by_count":5,"area":"inference"},{"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":"2509.24361","title":"UI-UG: A Unified MLLM for UI Understanding and Generation","created":"2025-09-29","cited_by_count":5,"area":"mllm"},{"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":"2608.10408","title":"VisEditBench: Can Vision-Language Models Edit Visualization Code from Multimodal Feedback?","created":"2026-08-11","cited_by_count":4,"area":"mllm"},{"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":"2202.04847","title":"A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspective","created":"2022-02-10","cited_by_count":3,"area":null},{"id":"2305.13504","title":"Neural Machine Translation for Code Generation","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2412.13386","title":"An Exploratory Study of ML Sketches and Visual Code Assistants","created":"2024-12-17","cited_by_count":3,"area":null},{"id":"2509.16779","title":"Improving User Interface Generation Models from Designer Feedback","created":"2025-09-20","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":"2510.15306","title":"WebGen-V Bench: Structured Representation for Enhancing Visual Design in LLM-based Web Generation and Evaluation","created":"2025-10-17","cited_by_count":3,"area":null},{"id":"2606.00750","title":"I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications","created":"2026-05-30","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":"2204.03731","title":"GreaseVision: Rewriting the Rules of the Interface","created":"2022-04-07","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":"2504.18729","title":"Multimodal graph representation learning for website generation based on visual sketch","created":"2025-04-25","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":"2511.09483","title":"CrochetBench: Can Vision-Language Models Move from Describing to Doing in Crochet Domain?","created":"2025-11-12","cited_by_count":2,"area":"mllm"},{"id":"2602.06090","title":"SVRepair: Structured Visual Reasoning for Automated Program Repair","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2602.10880","title":"Chart Specification: Structural Representations for Incentivizing VLM Reasoning in Chart-to-Code Generation","created":"2026-02-11","cited_by_count":2,"area":"lr"},{"id":"2608.24138","title":"Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation","created":"2026-08-25","cited_by_count":2,"area":"mllm"},{"id":"2101.09194","title":"It Takes Two to Tango: Combining Visual and Textual Information for Detecting Duplicate Video-Based Bug Reports","created":"2021-01-22","cited_by_count":1,"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":"2305.14637","title":"Learning UI-to-Code Reverse Generator Using Visual Critic Without Rendering","created":"2023-05-24","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":"2511.01817","title":"SciTextures: Collecting and Connecting Visual Patterns, Models, and Code Across Science and Art","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2601.19171","title":"Bridging Gulfs in UI Generation through Semantic Guidance","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2602.18548","title":"1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2603.14724","title":"GameUIAgent: An LLM-Powered Framework for Automated Game UI Design with Structured Intermediate Representation","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2606.00154","title":"Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.10334","title":"Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual Artifacts","created":"2026-06-09","cited_by_count":1,"area":"distill"},{"id":"2606.16262","title":"UXBench: Measuring the Actionability of LLM-Generated UX Critiques","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2606.20711","title":"Video2Code: Generating Interactive Webpages from UI Videos via Action-Aware Revisit","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2608.00548","title":"DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editable","created":"2026-08-01","cited_by_count":1,"area":"agents"},{"id":"2608.03689","title":"LiveEvalBench: Toward Open-World Evaluation for Web Generation","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.12611","title":"From Visual Widgets to UI Code: Efficient Tool-Grounded Generation","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2609.29718","title":"PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2208.13361","title":"NL2GDPR: Automatically Develop GDPR Compliant Android Application Features from Natural Language","created":"2022-08-29","cited_by_count":0,"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":"2509.05394","title":"Reverse Browser: Vector-Image-to-Code Generator","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2601.05344","title":"Coding the Visual World: From Image to Simulation Using Vision Language Models","created":"2026-01-08","cited_by_count":0,"area":"mllm"},{"id":"2602.03850","title":"WebAccessVL: Violation-Aware VLM for Web Accessibility","created":"2025-12-19","cited_by_count":0,"area":"mllm"},{"id":"2604.01226","title":"DOne: Decoupling Structure and Rendering for High-Fidelity Design-to-Code Generation","created":"2026-03-12","cited_by_count":0,"area":"mllm"},{"id":"2604.18591","title":"SPRITE: From Static Mockups to Engine-Ready Game UI","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2605.11680","title":"ShapeCodeBench: A Renewable Benchmark for Perception-to-Program Reconstruction of Synthetic Shape Scenes","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.01022","title":"ProductWebGen: Benchmarking Multimodal Product Webpage Generation","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.02434","title":"Bridging the Sim-to-Real Gap in Semiconductor Visual Program Synthesis via Input Binarization","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.17727","title":"LongWebBench: Evaluating Structural and Functional Webpage Generation in Long-Horizon Settings","created":"2026-06-16","cited_by_count":0,"area":"mllm"},{"id":"2606.28593","title":"Animation2Code: Evaluating Temporal Visual Reasoning in Video-to-Code Generation","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2607.01849","title":"Decomposer: Learning to Decompile Symbolic Music to Programs","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.06306","title":"UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation","created":"2026-07-07","cited_by_count":0,"area":null}],"next_cursor":"100"}