{"total":95,"rows":[{"id":"2312.03806","title":"XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies","created":"2023-12-06","cited_by_count":189,"area":null},{"id":"2403.01248","title":"SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code","created":"2024-03-02","cited_by_count":134,"area":"agents"},{"id":"2402.07207","title":"GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting","created":"2024-02-11","cited_by_count":109,"area":null},{"id":"2403.12034","title":"VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models","created":"2024-03-18","cited_by_count":56,"area":"diffusion"},{"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":"2407.20727","title":"SceneTeller: Language-to-3D Scene Generation","created":"2024-07-30","cited_by_count":43,"area":null},{"id":"2401.08577","title":"MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World","created":"2024-01-16","cited_by_count":39,"area":null},{"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":"2410.16770","title":"The Scene Language: Representing Scenes with Programs, Words, and Embeddings","created":"2024-10-22","cited_by_count":36,"area":null},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2510.25760","title":"Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks","created":"2025-10-29","cited_by_count":33,"area":"lr"},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2504.01786","title":"BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing","created":"2025-04-02","cited_by_count":31,"area":null},{"id":"2406.04983","title":"CityCraft: A Real Crafter for 3D City Generation","created":"2024-06-07","cited_by_count":26,"area":null},{"id":"2505.05474","title":"3D Scene Generation: A Survey","created":"2025-05-08","cited_by_count":24,"area":"diffusion"},{"id":"2404.15228","title":"Re-Thinking Inverse Graphics With Large Language Models","created":"2024-04-23","cited_by_count":23,"area":"lr"},{"id":"2412.17811","title":"ChatGarment: Garment Estimation, Generation and Editing via Large Language Models","created":"2024-12-23","cited_by_count":23,"area":"mllm"},{"id":"2404.17672","title":"BlenderAlchemy: Editing 3D Graphics with Vision-Language Models","created":"2024-04-26","cited_by_count":22,"area":"mllm"},{"id":"2407.17572","title":"CityX: Controllable Procedural Content Generation for Unbounded 3D Cities","created":"2024-07-24","cited_by_count":22,"area":null},{"id":"2401.06437","title":"3D-PreMise: Can Large Language Models Generate 3D Shapes with Sharp Features and Parametric Control?","created":"2024-01-12","cited_by_count":21,"area":null},{"id":"2408.04567","title":"Sketch2Scene: Automatic Generation of Interactive 3D Game Scenes from User's Casual Sketches","created":"2024-08-08","cited_by_count":21,"area":null},{"id":"2508.08228","title":"LL3M: Large Language 3D Modelers","created":"2025-08-11","cited_by_count":20,"area":null},{"id":"2407.06842","title":"Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts","created":"2024-07-09","cited_by_count":19,"area":"mllm"},{"id":"2410.07155","title":"Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis","created":"2024-10-09","cited_by_count":19,"area":"diffusion"},{"id":"2506.23329","title":"IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering","created":"2025-06-29","cited_by_count":19,"area":"mllm"},{"id":"2602.11757","title":"Code2Worlds: Empowering Coding LLMs for 4D World Generation","created":"2026-02-12","cited_by_count":19,"area":null},{"id":"2508.05899","title":"HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editing","created":"2025-08-07","cited_by_count":15,"area":null},{"id":"2606.01057","title":"3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code","created":"2026-05-31","cited_by_count":15,"area":"agents"},{"id":"2509.14981","title":"SPATIALGEN: Layout-guided 3D Indoor Scene Generation","created":"2025-09-18","cited_by_count":14,"area":null},{"id":"2410.00890","title":"Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation","created":"2024-10-01","cited_by_count":12,"area":"diffusion"},{"id":"2605.19587","title":"SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects","created":"2026-05-19","cited_by_count":11,"area":null},{"id":"2408.08054","title":"Text2BIM: Generating Building Models Using a Large Language Model-based Multi-Agent Framework","created":"2024-08-15","cited_by_count":9,"area":"agents"},{"id":"2501.18623","title":"VLMaterial: Procedural Material Generation with Large Vision-Language Models","created":"2025-01-27","cited_by_count":9,"area":"mllm"},{"id":"2505.20777","title":"TACO: Think-Answer Consistency for Optimized Long-Chain Reasoning and Efficient Data Learning via Reinforcement Learning in LVLMs","created":"2025-05-27","cited_by_count":9,"area":"lr"},{"id":"2510.04236","title":"Scaling Sequence-to-Sequence Generative Neural Rendering","created":"2025-10-05","cited_by_count":8,"area":null},{"id":"2607.01766","title":"SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation","created":"2026-07-02","cited_by_count":8,"area":"agents"},{"id":"2608.05248","title":"WorldClaw: Agentic 3D Open-World Generation at Scale","created":"2026-08-05","cited_by_count":8,"area":"agents"},{"id":"2411.18807","title":"Reconstructing Animals and the Wild","created":"2024-11-27","cited_by_count":7,"area":null},{"id":"2412.15200","title":"DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation","created":"2024-12-19","cited_by_count":7,"area":null},{"id":"2406.16903","title":"Towards a copilot in BIM authoring tool using a large language model-based agent for intelligent human-machine interaction","created":"2024-06-02","cited_by_count":6,"area":"agents"},{"id":"2503.12955","title":"HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding","created":"2025-03-17","cited_by_count":6,"area":null},{"id":"2510.10292","title":"From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries","created":"2025-10-11","cited_by_count":6,"area":null},{"id":"2511.20415","title":"MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts","created":"2025-11-25","cited_by_count":6,"area":"wm"},{"id":"2603.12238","title":"SceneAssistant: A Visual Feedback Agent for Open-Vocabulary 3D Scene Generation","created":"2026-03-12","cited_by_count":6,"area":"agents"},{"id":"2607.22393","title":"SceneActBench: Can Agents Act on the 3D Scenes They See?","created":"2026-07-24","cited_by_count":6,"area":"mllm"},{"id":"2506.14315","title":"ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2509.05263","title":"LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation","created":"2025-09-05","cited_by_count":5,"area":"wm"},{"id":"2602.05362","title":"Imagine a City: CityGenAgent for Procedural 3D City Generation","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2604.22984","title":"BrickNet: Graph-Backed Generative Brick Assembly","created":"2026-04-24","cited_by_count":5,"area":null},{"id":"2607.21522","title":"GS-Agent: Creating 4D Physical Worlds With Generative Simulation","created":"2026-07-23","cited_by_count":5,"area":"agents"},{"id":"2512.22351","title":"VULCAN: Tool-Augmented Multi Agents for Iterative 3D Object Arrangement","created":"2025-12-26","cited_by_count":4,"area":"mllm"},{"id":"2601.07143","title":"EZBlender: Efficient 3D Editing with Plan-and-ReAct Agent","created":"2026-01-12","cited_by_count":4,"area":"agents"},{"id":"2605.07342","title":"Mage: Multi-Axis Evaluation of LLM-Generated Executable Game Scenes Beyond Compile-Pass Rate","created":"2026-05-08","cited_by_count":4,"area":null},{"id":"2505.15765","title":"Constructing a 3D Scene from a Single Image","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2508.17568","title":"MetaGen: A DSL, Database, and Benchmark for VLM-Assisted Metamaterial Generation","created":"2025-08-25","cited_by_count":3,"area":null},{"id":"2510.04536","title":"3Dify: a Framework for Procedural 3D-CG Generation Assisted by LLMs Using MCP and RAG","created":"2025-10-06","cited_by_count":3,"area":null},{"id":"2512.08905","title":"Self-Evolving 3D Scene Generation from a Single Image","created":"2025-12-09","cited_by_count":3,"area":null},{"id":"2602.19542","title":"Vinedresser3D: Agentic Text-guided 3D Editing","created":"2026-02-23","cited_by_count":3,"area":"agents"},{"id":"2603.29089","title":"WorldFlow3D: Flowing Through 3D Distributions for Unbounded World Generation","created":"2026-03-31","cited_by_count":3,"area":null},{"id":"2505.03623","title":"Bounding Box-Guided Diffusion for Synthesizing Industrial Images and Segmentation Map","created":"2025-05-06","cited_by_count":2,"area":"diffusion"},{"id":"2603.14790","title":"Mind-of-Director: Multi-modal Agent-Driven Film Previsualization via Collaborative Decision-Making","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2605.17448","title":"Self-Improving CAD Generation Agents with Finite Element Analysis as Feedback","created":"2026-05-17","cited_by_count":2,"area":null},{"id":"2607.22738","title":"Nova3D: Code-Native Generation of Programmable 3D Assets","created":"2026-07-22","cited_by_count":2,"area":null},{"id":"2608.15265","title":"VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?","created":"2026-08-15","cited_by_count":2,"area":"agents"},{"id":"2403.15698","title":"SceneX: Procedural Controllable Large-scale Scene Generation","created":"2024-03-23","cited_by_count":1,"area":"wm"},{"id":"2601.22455","title":"ScribbleSense: Generative Scribble-Based Texture Editing with Intent Prediction","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2607.13318","title":"Reflecting Process Expertise in Procedural Material Generation","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2608.29137","title":"Chat-Edit-3D++: Interactive 3D and 4D Scene Editing via Large Language Models","created":"2026-08-29","cited_by_count":1,"area":"mllm"},{"id":"2609.06535","title":"3DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Models","created":"2026-09-06","cited_by_count":1,"area":"mllm"},{"id":"2609.24487","title":"AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos","created":"2026-09-21","cited_by_count":1,"area":null},{"id":"2610.04262","title":"CADForge: Agentic Single-View CAD Reconstruction with Explicit Geometry Reasoning","created":"2026-10-03","cited_by_count":1,"area":"agents"},{"id":"2406.16273","title":"YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals","created":"2024-06-24","cited_by_count":0,"area":"diffusion"},{"id":"2410.23803","title":"Generative AI for Accessible and Inclusive Extended Reality","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2504.01619","title":"3DBonsai: Structure-Aware Bonsai Modeling Using Conditioned 3D Gaussian Splatting","created":"2025-04-02","cited_by_count":0,"area":null},{"id":"2506.04562","title":"Handle-based Mesh Deformation Guided By Vision Language Model","created":"2025-06-05","cited_by_count":0,"area":"mllm"},{"id":"2509.15249","title":"Causal Reasoning Elicits Controllable 3D Scene Generation","created":"2025-09-18","cited_by_count":0,"area":"lr"},{"id":"2510.08590","title":"Evolutionary Computation as Natural Generative AI","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2511.11777","title":"Large Language Models and 3D Vision for Intelligent Robotic Perception and Autonomy","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2512.11925","title":"FloraForge: LLM-Assisted Procedural Generation of Editable and Analysis-Ready 3D Plant Geometric Models For Agricultural Applications","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2601.11801","title":"RobotDesignGPT: Automated Robot Design Synthesis using Vision Language Models","created":"2026-01-16","cited_by_count":0,"area":"mllm"},{"id":"2602.11706","title":"LLM-Driven 3D Scene Generation of Agricultural Simulation Environments","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2604.01777","title":"GardenDesigner: Encoding Aesthetic Principles into Jiangnan Garden Construction via a Chain of Agents","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.26943","title":"ProcFunc: Function-Oriented Abstractions for Procedural 3D Generation in Python","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2604.27578","title":"World2Minecraft: Occupancy-Driven Simulated Scenes Construction","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.00632","title":"BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis","created":"2026-05-01","cited_by_count":0,"area":"rag"},{"id":"2608.10838","title":"PolyLayout: Hierarchical VLM-Guided Layout Generation Beyond Rectangular Rooms","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.16484","title":"Remote-Sensing City Layout Extraction with MLLM","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.33208","title":"WorldAgent: Verification-Guided Agentic Physical World Construction","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.34221","title":"WorldWeave: Growing Persistent Geometric Worlds for Video Generation","created":"2026-09-28","cited_by_count":0,"area":"wm"},{"id":"2609.40353","title":"AssemblyWorld: Rethinking 3D Assembly with General-Purpose Agents","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01863","title":"LiteReality-Agent: An Agentic System for Interactable 3D Indoor Scene Reconstruction","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.13098","title":"VETR: Execution-Grounded Self-Improving Agent for Symbolic Graphics Reasoning","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.17288","title":"PhysCodeGym: Benchmarking Coding Agents for Physically Verifiable 4D Reconstruction","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.17651","title":"Code2Worlds-2: Physically Plausible Agent Harness for Embodied World Simulation","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}