{"total":58,"rows":[{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733,"area":null},{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366,"area":null},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255,"area":null},{"id":"2308.15272","title":"AutoDroid: LLM-powered Task Automation in Android","created":"2023-08-29","cited_by_count":184,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2304.04947","title":"Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference","created":"2023-04-11","cited_by_count":69,"area":null},{"id":"2306.00245","title":"From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces","created":"2023-05-31","cited_by_count":68,"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":"2503.13436","title":"Unified Autoregressive Visual Generation and Understanding with Continuous Tokens","created":"2025-03-17","cited_by_count":51,"area":null},{"id":"2208.09323","title":"Beyond Text Generation: Supporting Writers with Continuous Automatic Text Summaries","created":"2022-08-19","cited_by_count":47,"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":"2503.18943","title":"SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding","created":"2025-03-24","cited_by_count":30,"area":null},{"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":"2209.05534","title":"PreSTU: Pre-Training for Scene-Text Understanding","created":"2022-09-12","cited_by_count":27,"area":null},{"id":"2401.13313","title":"InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions","created":"2024-01-24","cited_by_count":27,"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":"2502.17159","title":"RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness","created":"2025-02-24","cited_by_count":26,"area":null},{"id":"2412.09362","title":"Falcon-UI: Understanding GUI Before Following User Instructions","created":"2024-12-12","cited_by_count":22,"area":null},{"id":"2407.03418","title":"HEMM: Holistic Evaluation of Multimodal Foundation Models","created":"2024-07-03","cited_by_count":21,"area":null},{"id":"2502.09927","title":"Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence","created":"2025-02-14","cited_by_count":20,"area":null},{"id":"2502.16796","title":"MobileSteward: Integrating Multiple App-Oriented Agents with Self-Evolution to Automate Cross-App Instructions","created":"2025-02-24","cited_by_count":16,"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":"2404.12500","title":"UIClip: A Data-driven Model for Assessing User Interface Design","created":"2024-04-18","cited_by_count":14,"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":"2310.07023","title":"Automatic Macro Mining from Interaction Traces at Scale","created":"2023-10-10","cited_by_count":12,"area":null},{"id":"2503.14021","title":"MP-GUI: Modality Perception with MLLMs for GUI Understanding","created":"2025-03-18","cited_by_count":12,"area":null},{"id":"2502.19335","title":"Gatekeeper: Improving Model Cascades Through Confidence Tuning","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2110.07775","title":"Creating User Interface Mock-ups from High-Level Text Descriptions with Deep-Learning Models","created":"2021-10-14","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":"2503.24180","title":"Navi-plus: Managing Ambiguous GUI Navigation Tasks with Follow-up Questions","created":"2025-03-31","cited_by_count":8,"area":null},{"id":"2603.06242","title":"DC-Merge: Improving Model Merging with Directional Consistency","created":"2026-03-06","cited_by_count":8,"area":null},{"id":"2511.20513","title":"DesignPref: Capturing Personal Preferences in Visual Design Generation","created":"2025-11-25","cited_by_count":7,"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":"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":"2308.05828","title":"DiLogics: Creating Web Automation Programs With Diverse Logics","created":"2023-08-10","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":"2303.04496","title":"MenuCraft: Interactive Menu System Design with Large Language Models","created":"2023-03-08","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":"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":"2509.16779","title":"Improving User Interface Generation Models from Designer Feedback","created":"2025-09-20","cited_by_count":3,"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":"2310.04755","title":"Pairwise GUI Dataset Construction Between Android Phones and Tablets","created":"2023-10-07","cited_by_count":1,"area":null},{"id":"2503.20978","title":"ScreenLLM: Stateful Screen Schema for Efficient Action Understanding and Prediction","created":"2025-03-26","cited_by_count":1,"area":null},{"id":"2509.12423","title":"Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition","created":"2025-09-15","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":"2303.12709","title":"Evaluation of Sketch-Based and Semantic-Based Modalities for Mockup Generation","created":"2023-03-22","cited_by_count":0,"area":null},{"id":"2305.14218","title":"DUBLIN -- Document Understanding By Language-Image Network","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2309.14774","title":"BLIP-Adapter: Parameter-Efficient Transfer Learning for Mobile Screenshot Captioning","created":"2023-09-26","cited_by_count":0,"area":null},{"id":"2512.14130","title":"UIXPOSE: Mobile Malware Detection via Intention-Behaviour Discrepancy Analysis","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2602.20531","title":"A Lightweight Vision-Language Fusion Framework for Predicting App Ratings from User Interfaces and Metadata","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2604.09876","title":"Efficient Personalization of Generative User Interfaces","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.09803","title":"Insight: Enhancing Mobile Accessibility for Blind and Visually Impaired Users with LLMs","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2607.28645","title":"Looks Right, Works Right: A Project-Level Benchmark for Multi-Screen Mobile App Generation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2609.12897","title":"Tracing and Coordinating Cross-Layer Influence for Multimodal Model Merging","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.15229","title":"Pre-PEFT Probing: Weight Statistics and Perturbation Robustness for Layer Selection in VLM Vision Encoders","created":"2026-09-14","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},{"id":"2610.20335","title":"Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}