{"total":53,"rows":[{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474,"area":null},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"area":null},{"id":"2312.14867","title":"VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation","created":"2023-12-22","cited_by_count":201,"area":null},{"id":"2402.07939","title":"UFO: A UI-Focused Agent for Windows OS Interaction","created":"2024-02-08","cited_by_count":148,"area":null},{"id":"2406.16855","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","created":"2024-06-24","cited_by_count":131,"area":null},{"id":"2402.16843","title":"Multi-LoRA Composition for Image Generation","created":"2024-02-26","cited_by_count":80,"area":null},{"id":"2505.16707","title":"KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models","created":"2025-05-22","cited_by_count":71,"area":null},{"id":"2408.14339","title":"ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty","created":"2024-08-26","cited_by_count":61,"area":null},{"id":"2505.06507","title":"Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilities","created":"2025-05-10","cited_by_count":43,"area":null},{"id":"2406.14643","title":"Holistic Evaluation for Interleaved Text-and-Image Generation","created":"2024-06-20","cited_by_count":28,"area":null},{"id":"2409.17106","title":"Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Prompts","created":"2024-09-25","cited_by_count":23,"area":null},{"id":"2505.08137","title":"Large Language Models for Computer-Aided Design: A Survey","created":"2025-05-13","cited_by_count":18,"area":null},{"id":"2404.01667","title":"METAL: Towards Multilingual Meta-Evaluation","created":"2024-04-02","cited_by_count":15,"area":null},{"id":"2409.19242","title":"SciDoc2Diagrammer-MAF: Towards Generation of Scientific Diagrams from Documents guided by Multi-Aspect Feedback Refinement","created":"2024-09-28","cited_by_count":15,"area":null},{"id":"2412.04300","title":"T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts","created":"2024-12-05","cited_by_count":14,"area":null},{"id":"2402.12525","title":"LangXAI: Integrating Large Vision Models for Generating Textual Explanations to Enhance Explainability in Visual Perception Tasks","created":"2024-02-19","cited_by_count":13,"area":null},{"id":"2506.01955","title":"Dual-Process Image Generation","created":"2025-06-02","cited_by_count":12,"area":null},{"id":"2312.10321","title":"LLM-SQL-Solver: Can LLMs Determine SQL Equivalence?","created":"2023-12-16","cited_by_count":10,"area":null},{"id":"2401.02147","title":"Exploring Boundary of GPT-4V on Marine Analysis: A Preliminary Case Study","created":"2024-01-04","cited_by_count":9,"area":null},{"id":"2407.11771","title":"XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach","created":"2024-07-16","cited_by_count":8,"area":null},{"id":"2510.24134","title":"VC4VG: Optimizing Video Captions for Text-to-Video Generation","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2405.17104","title":"LLM-Optic: Unveiling the Capabilities of Large Language Models for Universal Visual Grounding","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2412.11767","title":"IDEA-Bench: How Far are Generative Models from Professional Designing?","created":"2024-12-16","cited_by_count":7,"area":null},{"id":"2410.11374","title":"Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing","created":"2024-10-15","cited_by_count":6,"area":null},{"id":"2512.10619","title":"DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM","created":"2025-12-11","cited_by_count":6,"area":null},{"id":"2404.09690","title":"Harnessing GPT-4V(ision) for Insurance: A Preliminary Exploration","created":"2024-04-15","cited_by_count":5,"area":null},{"id":"2410.10291","title":"Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective","created":"2024-10-14","cited_by_count":4,"area":null},{"id":"2411.10309","title":"Modification Takes Courage: Seamless Image Stitching via Reference-Driven Inpainting","created":"2024-11-15","cited_by_count":4,"area":null},{"id":"2507.18625","title":"3D Software Synthesis Driven by Constraint-Expressive Intermediate Representation","created":"2025-07-24","cited_by_count":4,"area":null},{"id":"2511.18825","title":"Q-Save: Towards Scoring and Attribution for Generated Video Evaluation","created":"2025-11-24","cited_by_count":4,"area":null},{"id":"2512.05119","title":"RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering","created":"2025-10-11","cited_by_count":4,"area":null},{"id":"2503.04983","title":"Leveraging Large Language Models For Scalable Vector Graphics Processing: A Review","created":"2025-03-06","cited_by_count":3,"area":null},{"id":"2505.05026","title":"Do MLLMs Capture How Interfaces Guide User Behavior? A Benchmark for Multimodal UI/UX Design Understanding","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2503.14754","title":"Bayesian Modeling of Zero-Shot Classifications for Urban Flood Detection","created":"2025-03-18","cited_by_count":2,"area":null},{"id":"2508.06937","title":"CannyEdit: Selective Canny Control and Dual-Prompt Guidance for Training-Free Image Editing","created":"2025-08-09","cited_by_count":2,"area":null},{"id":"2601.06309","title":"VideoWeave: A Data-Centric Approach for Efficient Video Understanding","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2605.24702","title":"Do Image-Text Metrics Respect Semantic Invariances?","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2410.08172","title":"On the Evaluation of Generative Robotic Simulations","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2410.18823","title":"Towards Visual Text Design Transfer Across Languages","created":"2024-10-24","cited_by_count":1,"area":null},{"id":"2503.18680","title":"ArchSeek: Retrieving Architectural Case Studies Using Vision-Language Models","created":"2025-03-24","cited_by_count":1,"area":null},{"id":"2505.18730","title":"Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image Generation","created":"2025-05-24","cited_by_count":1,"area":null},{"id":"2603.03657","title":"InEdit-Bench: Benchmarking Intermediate Logical Pathways for Intelligent Image Editing Models","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2604.14591","title":"Prompt-Guided Image Editing with Masked Logit Nudging in Visual Autoregressive Models","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2607.25300","title":"MEDit-Bench: A Dataset for Evaluating Message-Driven Narrative Video Editing","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2403.15528","title":"Evaluating GPT-4 with Vision on Detection of Radiological Findings on Chest Radiographs","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2411.11494","title":"Alien Recombination: Exploring Concept Blends Beyond Human Cognitive Availability in Visual Art","created":"2024-11-18","cited_by_count":0,"area":null},{"id":"2506.02494","title":"MINOS: A Multimodal Evaluation Model for Bidirectional Generation Between Image and Text","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2602.13345","title":"BLUEPRINT Rebuilding a Legacy: Multimodal Retrieval for Complex Engineering Drawings and Documents","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2604.01973","title":"NearID: Identity Representation Learning via Near-identity Distractors","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2606.25445","title":"C3-Bench: A Context-Aware Change Captioning Benchmark","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.25578","title":"H-Adapter: Pose-Robust Hairstyle Transfer via Attention-Derived, Source-Aligned Hair Masks","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2609.20819","title":"Can 4D Foundation Models Remember?","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.16441","title":"VisExMEM: Visual Evidence-Based Explainable Multimodal Evaluation Metric","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}