{"total":153,"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":"2402.17766","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","created":"2024-02-27","cited_by_count":137,"area":"mllm"},{"id":"2406.13743","title":"GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation","created":"2024-06-19","cited_by_count":135,"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":"2412.02193","title":"LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models","created":"2024-12-03","cited_by_count":96,"area":"lr"},{"id":"2403.12019","title":"LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation","created":"2024-03-18","cited_by_count":92,"area":null},{"id":"2404.02838","title":"I-Design: Personalized LLM Interior Designer","created":"2024-04-03","cited_by_count":87,"area":null},{"id":"2501.03936","title":"PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides","created":"2025-01-07","cited_by_count":86,"area":null},{"id":"2403.17920","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation","created":"2024-03-26","cited_by_count":77,"area":null},{"id":"2403.02234","title":"3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors","created":"2024-03-04","cited_by_count":74,"area":"diffusion"},{"id":"2405.19716","title":"Enhancing Large Vision Language Models with Self-Training on Image Comprehension","created":"2024-05-30","cited_by_count":70,"area":"mllm"},{"id":"2403.12409","title":"ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance","created":"2024-03-19","cited_by_count":59,"area":null},{"id":"2501.18590","title":"DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models","created":"2025-01-30","cited_by_count":57,"area":"diffusion"},{"id":"2403.14613","title":"DreamReward: Text-to-3D Generation with Human Preference","created":"2024-03-21","cited_by_count":56,"area":null},{"id":"2509.20414","title":"SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent","created":"2025-09-24","cited_by_count":56,"area":"agents"},{"id":"2407.21035","title":"Direct Unlearning Optimization for Robust and Safe Text-to-Image Models","created":"2024-07-17","cited_by_count":50,"area":"safety"},{"id":"2403.12032","title":"Generic 3D Diffusion Adapter Using Controlled Multi-View Editing","created":"2024-03-18","cited_by_count":47,"area":"diffusion"},{"id":"2502.13143","title":"SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation","created":"2025-02-18","cited_by_count":46,"area":"lr"},{"id":"2405.10255","title":"When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models","created":"2024-05-16","cited_by_count":43,"area":"mllm"},{"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":"2406.09417","title":"Rethinking Score Distillation as a Bridge Between Image Distributions","created":"2024-06-13","cited_by_count":38,"area":"diffusion"},{"id":"2411.16602","title":"Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models","created":"2024-11-25","cited_by_count":38,"area":"diffusion"},{"id":"2406.11802","title":"PhyBench: A Physical Commonsense Benchmark for Evaluating Text-to-Image Models","created":"2024-06-17","cited_by_count":36,"area":null},{"id":"2407.06191","title":"Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images","created":"2024-07-08","cited_by_count":35,"area":null},{"id":"2403.09625","title":"Make-Your-3D: Fast and Consistent Subject-Driven 3D Content Generation","created":"2024-03-14","cited_by_count":32,"area":null},{"id":"2402.01166","title":"A Comprehensive Survey on 3D Content Generation","created":"2024-02-02","cited_by_count":28,"area":null},{"id":"2403.16051","title":"Segment Anything Model for Road Network Graph Extraction","created":"2024-03-24","cited_by_count":28,"area":null},{"id":"2412.06592","title":"PrEditor3D: Fast and Precise 3D Shape Editing","created":"2024-12-09","cited_by_count":28,"area":null},{"id":"2405.08054","title":"Coin3D: Controllable and Interactive 3D Assets Generation with Proxy-Guided Conditioning","created":"2024-05-13","cited_by_count":26,"area":null},{"id":"2503.14756","title":"SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesis","created":"2025-03-18","cited_by_count":26,"area":null},{"id":"2405.18424","title":"3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting","created":"2024-05-28","cited_by_count":25,"area":null},{"id":"2503.04919","title":"FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement","created":"2025-03-06","cited_by_count":25,"area":"lr"},{"id":"2408.14765","title":"CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Street View Synthesis","created":"2024-08-27","cited_by_count":23,"area":"diffusion"},{"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":"2412.11258","title":"GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs","created":"2024-12-15","cited_by_count":23,"area":null},{"id":"2404.17672","title":"BlenderAlchemy: Editing 3D Graphics with Vision-Language Models","created":"2024-04-26","cited_by_count":22,"area":"mllm"},{"id":"2410.05664","title":"Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearning","created":"2024-10-08","cited_by_count":21,"area":"diffusion"},{"id":"2404.06510","title":"Can Large Vision-Language Models Correct Semantic Grounding Errors By Themselves?","created":"2024-04-09","cited_by_count":20,"area":"mllm"},{"id":"2405.18515","title":"Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication","created":"2024-05-28","cited_by_count":20,"area":"diffusion"},{"id":"2601.03444","title":"Grading Scale Impact on LLM-as-a-Judge: Human-LLM Alignment Is Highest on 0-5 Grading Scale","created":"2026-01-06","cited_by_count":20,"area":"alignment"},{"id":"2410.18974","title":"3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation","created":"2024-10-24","cited_by_count":19,"area":"diffusion"},{"id":"2503.13424","title":"Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generation","created":"2025-03-17","cited_by_count":19,"area":null},{"id":"2412.00174","title":"SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters","created":"2024-11-29","cited_by_count":18,"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":"2504.18509","title":"Eval3D: Interpretable and Fine-grained Evaluation for 3D Generation","created":"2025-04-25","cited_by_count":16,"area":null},{"id":"2404.15100","title":"Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation","created":"2024-04-23","cited_by_count":15,"area":"mllm"},{"id":"2405.09431","title":"A Survey On Text-to-3D Contents Generation In The Wild","created":"2024-05-15","cited_by_count":14,"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":"2403.13289","title":"Text-to-3D Shape Generation","created":"2024-03-20","cited_by_count":13,"area":null},{"id":"2410.16272","title":"MvDrag3D: Drag-based Creative 3D Editing via Multi-view Generation-Reconstruction Priors","created":"2024-10-21","cited_by_count":13,"area":null},{"id":"2603.26512","title":"CADSmith: Multi-Agent CAD Generation with Programmatic Geometric Validation","created":"2026-03-27","cited_by_count":13,"area":"agents"},{"id":"2412.09997","title":"GT23D-Bench: A Comprehensive General Text-to-3D Generation Benchmark","created":"2024-12-13","cited_by_count":12,"area":null},{"id":"2503.21745","title":"3DGen-Bench: Comprehensive Benchmark Suite for 3D Generative Models","created":"2025-03-27","cited_by_count":12,"area":null},{"id":"2411.16820","title":"DetailGen3D: Generative 3D Geometry Enhancement via Data-Dependent Flow","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2504.08125","title":"Gen3DEval: Using vLLMs for Automatic Evaluation of Generated 3D Objects","created":"2025-04-10","cited_by_count":11,"area":null},{"id":"2505.00704","title":"Controllable Weather Synthesis and Removal with Video Diffusion Models","created":"2025-05-01","cited_by_count":11,"area":"diffusion"},{"id":"2506.00512","title":"Pro3D-Editor : A Progressive-Views Perspective for Consistent and Precise 3D Editing","created":"2025-05-31","cited_by_count":11,"area":null},{"id":"2509.00269","title":"3D-LATTE: Latent Space 3D Editing from Textual Instructions","created":"2025-08-29","cited_by_count":11,"area":"diffusion"},{"id":"2405.20775","title":"Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models","created":"2024-05-26","cited_by_count":10,"area":"mllm"},{"id":"2506.09665","title":"VideoMat: Extracting PBR Materials from Video Diffusion Models","created":"2025-06-11","cited_by_count":10,"area":"diffusion"},{"id":"2604.02329","title":"Generative World Renderer","created":"2026-04-02","cited_by_count":10,"area":null},{"id":"2605.07807","title":"Text-to-CAD Evaluation with CADTests","created":"2026-05-08","cited_by_count":10,"area":null},{"id":"2410.09009","title":"Semantic Score Distillation Sampling for Compositional Text-to-3D Generation","created":"2024-10-11","cited_by_count":9,"area":"diffusion"},{"id":"2412.06614","title":"MVReward: Better Aligning and Evaluating Multi-View Diffusion Models with Human Preferences","created":"2024-12-09","cited_by_count":9,"area":"diffusion"},{"id":"2507.00006","title":"MVGBench: Comprehensive Benchmark for Multi-view Generation Models","created":"2025-06-11","cited_by_count":9,"area":"mllm"},{"id":"2410.22315","title":"Natural Language Inference Improves Compositionality in Vision-Language Models","created":"2024-10-29","cited_by_count":8,"area":"lr"},{"id":"2412.11170","title":"Benchmarking and Learning Multi-Dimensional Quality Evaluator for Text-to-3D Generation","created":"2024-12-15","cited_by_count":8,"area":null},{"id":"2505.01657","title":"RAGAR: Retrieval Augmented Personalized Image Generation Guided by Recommendation","created":"2025-05-03","cited_by_count":8,"area":"rag"},{"id":"2505.10634","title":"Cross-Image Contrastive Decoding: Precise, Lossless Suppression of Language Priors in Large Vision-Language Models","created":"2025-05-15","cited_by_count":8,"area":"mllm"},{"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":"2411.17945","title":"MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation","created":"2024-11-26","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":"2505.12635","title":"MVPainter: Accurate and Detailed 3D Texture Generation via Multi-View Diffusion with Geometric Control","created":"2025-05-19","cited_by_count":7,"area":null},{"id":"2506.09814","title":"DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward Supervision","created":"2025-06-11","cited_by_count":7,"area":"alignment"},{"id":"2506.20601","title":"Video Perception Models for 3D Scene Synthesis","created":"2025-06-25","cited_by_count":7,"area":null},{"id":"2502.14316","title":"Textured 3D Regenerative Morphing with 3D Diffusion Prior","created":"2025-02-20","cited_by_count":6,"area":"diffusion"},{"id":"2509.15772","title":"Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generation","created":"2025-09-19","cited_by_count":6,"area":"mllm"},{"id":"2510.11631","title":"EvoCAD: Evolutionary CAD Code Generation with Vision Language Models","created":"2025-10-13","cited_by_count":6,"area":null},{"id":"2602.07045","title":"VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing","created":"2026-02-04","cited_by_count":6,"area":"lr"},{"id":"2406.00093","title":"Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data","created":"2024-05-31","cited_by_count":5,"area":"diffusion"},{"id":"2503.19914","title":"Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Models","created":"2025-03-25","cited_by_count":5,"area":"diffusion"},{"id":"2504.12788","title":"ARAP-GS: Drag-driven As-Rigid-As-Possible 3D Gaussian Splatting Editing with Diffusion Prior","created":"2025-04-17","cited_by_count":5,"area":"diffusion"},{"id":"2606.03994","title":"SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image","created":"2026-06-02","cited_by_count":5,"area":null},{"id":"2406.18581","title":"Dream-in-Style: Text-to-3D Generation Using Stylized Score Distillation","created":"2024-06-05","cited_by_count":4,"area":null},{"id":"2506.18407","title":"IntuiTF: MLLM-Guided Transfer Function Optimization for Direct Volume Rendering","created":"2025-06-23","cited_by_count":4,"area":null},{"id":"2601.07963","title":"3DGS-Drag: Dragging Gaussians for Intuitive Point-Based 3D Editing","created":"2026-01-12","cited_by_count":4,"area":null},{"id":"2608.26238","title":"Procedura: Agentic 3D Modeling with Procedural Control","created":"2026-08-26","cited_by_count":4,"area":"agents"},{"id":"2404.11824","title":"TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation","created":"2024-04-18","cited_by_count":3,"area":null},{"id":"2410.23730","title":"An Empirical Analysis of GPT-4V's Performance on Fashion Aesthetic Evaluation","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2502.04762","title":"Autoregressive Generation of Static and Growing Trees","created":"2025-02-07","cited_by_count":3,"area":null},{"id":"2508.05609","title":"Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity","created":"2025-08-07","cited_by_count":3,"area":null},{"id":"2509.23841","title":"Towards Fine-Grained Text-to-3D Quality Assessment: A Benchmark and A Two-Stage Rank-Learning Metric","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2510.16017","title":"InfraGPT Smart Infrastructure: An End-to-End VLM-Based Framework for Detecting and Managing Urban Defects","created":"2025-10-15","cited_by_count":3,"area":"mllm"},{"id":"2602.01623","title":"Omni-Judge: Can Omni-LLMs Serve as Human-Aligned Judges for Text-Conditioned Audio-Video Generation?","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2602.22284","title":"BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning","created":"2026-02-25","cited_by_count":3,"area":"lr"},{"id":"2606.21596","title":"$\\phi$-Scene: Physically Grounded Image-to-3D Scene Reconstruction","created":"2026-06-19","cited_by_count":3,"area":null},{"id":"2411.18135","title":"ModeDreamer: Mode Guiding Score Distillation for Text-to-3D Generation using Reference Image Prompts","created":"2024-11-27","cited_by_count":2,"area":null},{"id":"2503.10660","title":"Text-to-3D Generation using Jensen-Shannon Score Distillation","created":"2025-03-08","cited_by_count":2,"area":"diffusion"},{"id":"2509.08777","title":"Calibrating MLLM-as-a-judge via Multimodal Bayesian Prompt Ensembles","created":"2025-09-10","cited_by_count":2,"area":"mllm"}],"next_cursor":"100"}