{"list":"other","total":58,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668},{"id":"2603.16666","title":"Fast-WAM: Do World Action Models Need Test-time Future Imagination?","created":"2026-03-17","cited_by_count":349},{"id":"2511.22699","title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","created":"2025-11-27","cited_by_count":277},{"id":"2305.10855","title":"TextDiffuser: Diffusion Models as Text Painters","created":"2023-05-18","cited_by_count":229},{"id":"2401.11708","title":"Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs","created":"2024-01-22","cited_by_count":224},{"id":"2505.00703","title":"T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT","created":"2025-05-01","cited_by_count":166},{"id":"2403.03163","title":"Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering","created":"2024-03-05","cited_by_count":152},{"id":"2407.05600","title":"GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing","created":"2024-07-08","cited_by_count":133},{"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},{"id":"2406.09961","title":"ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation","created":"2024-06-14","cited_by_count":129},{"id":"2503.10639","title":"GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing","created":"2025-03-13","cited_by_count":104},{"id":"2312.11556","title":"StarVector: Generating Scalable Vector Graphics Code from Images and Text","created":"2023-12-17","cited_by_count":102},{"id":"2508.09987","title":"Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation","created":"2025-08-13","cited_by_count":100},{"id":"2501.06598","title":"ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation","created":"2025-01-11","cited_by_count":92},{"id":"2501.03936","title":"PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides","created":"2025-01-07","cited_by_count":86},{"id":"2507.16746","title":"Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning","created":"2025-07-22","cited_by_count":84},{"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},{"id":"2504.06263","title":"OmniSVG: A Unified Scalable Vector Graphics Generation Model","created":"2025-04-08","cited_by_count":74},{"id":"2501.00912","title":"AutoPresent: Designing Structured Visuals from Scratch","created":"2025-01-01","cited_by_count":68},{"id":"2503.14905","title":"Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation","created":"2025-03-19","cited_by_count":68},{"id":"2503.15264","title":"LEGION: Learning to Ground and Explain for Synthetic Image Detection","created":"2025-03-19","cited_by_count":65},{"id":"2504.02782","title":"GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation","created":"2025-04-03","cited_by_count":58},{"id":"2505.14671","title":"UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens","created":"2025-05-20","cited_by_count":56},{"id":"2508.05606","title":"Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Vision","created":"2025-08-07","cited_by_count":56},{"id":"2410.09732","title":"LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models","created":"2024-10-13","cited_by_count":51},{"id":"2411.03292","title":"Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping","created":"2024-11-05","cited_by_count":51},{"id":"2605.12090","title":"World Action Models: The Next Frontier in Embodied AI","created":"2026-05-12","cited_by_count":50},{"id":"2506.06251","title":"DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation","created":"2025-06-06","cited_by_count":45},{"id":"2311.16974","title":"COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Design","created":"2023-11-28","cited_by_count":43},{"id":"2404.14368","title":"Graphic Design with Large Multimodal Model","created":"2024-04-22","cited_by_count":40},{"id":"2506.10741","title":"PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework","created":"2025-06-12","cited_by_count":40},{"id":"2310.08541","title":"Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation","created":"2023-10-12","cited_by_count":38},{"id":"2406.08232","title":"OpenCOLE: Towards Reproducible Automatic Graphic Design Generation","created":"2024-06-12","cited_by_count":37},{"id":"2510.14958","title":"MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning","created":"2025-10-16","cited_by_count":35},{"id":"2605.12500","title":"SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture","created":"2026-05-12","cited_by_count":32},{"id":"2602.01756","title":"Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation","created":"2026-02-02","cited_by_count":23},{"id":"2505.09904","title":"UICopilot: Automating UI Synthesis via Hierarchical Code Generation from Webpage Designs","created":"2025-05-15","cited_by_count":22},{"id":"2603.28088","title":"GEMS: Agent-Native Multimodal Generation with Memory and Skills","created":"2026-03-30","cited_by_count":21},{"id":"2509.25502","title":"Seeing Before Reasoning: A Unified Framework for Generalizable and Explainable Fake Image Detection","created":"2025-09-29","cited_by_count":20},{"id":"2506.10376","title":"MLLM-Based UI2Code Automation Guided by UI Layout Information","created":"2025-06-12","cited_by_count":17},{"id":"2511.08195","title":"UI2Code^N: UI-to-Code Generation as Interactive Visual Optimization","created":"2025-11-11","cited_by_count":15},{"id":"2510.11341","title":"InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models","created":"2025-10-13","cited_by_count":14},{"id":"2509.09666","title":"Unified Multimodal Models as Auto-Encoders","created":"2025-09-11","cited_by_count":13},{"id":"2511.08423","title":"OmniAID: Decoupling Semantics and Artifacts for Universal AI-Generated Image Detection in the Wild","created":"2025-11-11","cited_by_count":13},{"id":"2512.05112","title":"DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation","created":"2025-12-04","cited_by_count":13},{"id":"2606.26907","title":"Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation","created":"2026-06-25","cited_by_count":13},{"id":"2512.00473","title":"RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards","created":"2025-11-29","cited_by_count":12},{"id":"2602.11144","title":"GENIUS: Generative Fluid Intelligence Evaluation Suite","created":"2026-02-11","cited_by_count":12},{"id":"2605.30248","title":"GenClaw: Code-Driven Agentic Image Generation","created":"2026-05-28","cited_by_count":11},{"id":"2508.03560","title":"LaTCoder: Converting Webpage Design to Code with Layout-as-Thought","created":"2025-08-05","cited_by_count":9},{"id":"2608.13560","title":"AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design","created":"2026-08-13","cited_by_count":9},{"id":"2607.27380","title":"VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System","created":"2026-07-29","cited_by_count":8},{"id":"2605.08043","title":"SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation","created":"2026-05-08","cited_by_count":7},{"id":"2510.23272","title":"Code Aesthetics with Agentic Reward Feedback","created":"2025-10-27","cited_by_count":6},{"id":"2603.01083","title":"Can Vision Language Models Assess Graphic Design Aesthetics? A Benchmark, Evaluation, and Dataset Perspective","created":"2026-03-01","cited_by_count":6}],"next_cursor":null}