{"total":64,"rows":[{"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":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"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":"2411.02394","title":"AutoVFX: Physically Realistic Video Editing from Natural Language Instructions","created":"2024-11-04","cited_by_count":27,"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":"2503.16848","title":"HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2508.08228","title":"LL3M: Large Language 3D Modelers","created":"2025-08-11","cited_by_count":20,"area":null},{"id":"2511.16825","title":"WorldGen: From Text to Traversable and Interactive 3D Worlds","created":"2025-11-20","cited_by_count":19,"area":null},{"id":"2602.11757","title":"Code2Worlds: Empowering Coding LLMs for 4D World Generation","created":"2026-02-12","cited_by_count":19,"area":null},{"id":"2410.12836","title":"EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing","created":"2024-10-03","cited_by_count":15,"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":"2509.14981","title":"SPATIALGEN: Layout-guided 3D Indoor Scene Generation","created":"2025-09-18","cited_by_count":14,"area":null},{"id":"2508.14893","title":"Virtual Community: An Open World for Humans, Robots, and Society","created":"2025-08-20","cited_by_count":13,"area":null},{"id":"2503.11060","title":"BannerAgency: Advertising Banner Design with Multimodal LLM Agents","created":"2025-03-14","cited_by_count":11,"area":null},{"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":"2506.22291","title":"RoomCraft: Controllable and Complete 3D Indoor Scene Generation","created":"2025-06-27","cited_by_count":9,"area":null},{"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":"2506.17450","title":"BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing","created":"2025-06-20","cited_by_count":7,"area":null},{"id":"2405.20319","title":"ParSEL: Parameterized Shape Editing with Language","created":"2024-05-30","cited_by_count":6,"area":null},{"id":"2507.14841","title":"Towards Geometric and Textural Consistency 3D Scene Generation via Single Image-guided Model Generation and Layout Optimization","created":"2025-07-20","cited_by_count":6,"area":null},{"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":"2504.15049","title":"ScanEdit: Hierarchically-Guided Functional 3D Scan Editing","created":"2025-04-21","cited_by_count":4,"area":null},{"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":"2607.08970","title":"MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs","created":"2026-07-09","cited_by_count":4,"area":null},{"id":"2502.07128","title":"Cardiverse: Harnessing LLMs for Novel Card Game Prototyping","created":"2025-02-10","cited_by_count":3,"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":"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":"2512.17445","title":"LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents","created":"2025-12-19","cited_by_count":3,"area":null},{"id":"2512.24986","title":"PhysTalk: Language-driven Real-time Physics in 3D Gaussian Scenes","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2604.03315","title":"StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics","created":"2026-04-01","cited_by_count":3,"area":null},{"id":"2605.12449","title":"LychSim: A Controllable and Interactive Simulation Framework for Vision Research","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2511.05533","title":"MCP4IFC: IFC-Based Building Design Using Large Language Models","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2602.04053","title":"Seeing Through Clutter: Structured 3D Scene Reconstruction via Iterative Object Removal","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2603.22972","title":"WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion","created":"2026-03-24","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":"2409.10090","title":"InteractPro: A Unified Framework for Motion-Aware Image Composition","created":"2024-09-16","cited_by_count":1,"area":null},{"id":"2601.05016","title":"From Idea to Co-Creation: A Planner-Actor-Critic Framework for Agent Augmented 3D Modeling","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2601.12234","title":"Proc3D: Procedural 3D Generation and Parametric Editing of 3D Shapes with Large Language Models","created":"2026-01-18","cited_by_count":1,"area":null},{"id":"2601.19433","title":"RoamScene3D: Immersive Text-to-3D Scene Generation via Adaptive Object-aware Roaming","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2604.16552","title":"Co-generation of Layout and Shape from Text via Autoregressive 3D Diffusion","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.26509","title":"3D Generation for Embodied AI and Robotic Simulation: A Survey","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2605.25326","title":"Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.30326","title":"RoboWits: Unexpected Challenges for Robotic Creative Problem Solving","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.10478","title":"3D-CoS: A New 3D Reconstruction Paradigm Based on VLM Code Synthesis","created":"2026-06-09","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":"2608.09691","title":"Diffuse the object, keep its label: curating detector training data from a few unlabeled photographs via VLM-built 3D vegetation scenes","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2411.18644","title":"Scene Co-pilot: Procedural Text to Video Generation with Human in the Loop","created":"2024-11-26","cited_by_count":0,"area":null},{"id":"2505.24086","title":"ComposeAnything: Composite Object Priors for Text-to-Image Generation","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2506.04606","title":"SmartAvatar: Text- and Image-Guided Human Avatar Generation with VLM AI Agents","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2512.22016","title":"SketchPlay: Intuitive Creation of Physically Realistic VR Content with Gesture-Driven Sketching","created":"2025-12-26","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":"2607.05393","title":"Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.07547","title":"Learning an Interior Layout Policy in a Domain Specific Language Action Space","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.10838","title":"PolyLayout: Hierarchical VLM-Guided Layout Generation Beyond Rectangular Rooms","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.15392","title":"ESG: Generating Physically Consistent Dynamic 3D Scenes from Text Descriptions","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.36380","title":"LEGO-Anything: Coding Agents for 3D Scene Reconstruction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.10622","title":"WorldBench: Evaluating LLMs on Three.js Voxel World Generation","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.12374","title":"AgentGarten: Code Worlds for Evolving Agents","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.13145","title":"VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.19520","title":"Spectral World Renderer: Unified 3D Hyperspectral Unmixing","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}