{"total":67,"rows":[{"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":"2508.15769","title":"SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass","created":"2025-08-21","cited_by_count":54,"area":null},{"id":"2602.10116","title":"SAGE: Scalable Agentic 3D Scene Generation for Embodied AI","created":"2026-02-10","cited_by_count":50,"area":"agents"},{"id":"2601.11109","title":"Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning","created":"2026-01-16","cited_by_count":49,"area":"lr"},{"id":"2510.18135","title":"World-in-World: World Models in a Closed-Loop World","created":"2025-10-20","cited_by_count":47,"area":"wm"},{"id":"2508.02095","title":"VLM4D: Towards Spatiotemporal Awareness in Vision Language Models","created":"2025-08-04","cited_by_count":46,"area":"lr"},{"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":"2511.16825","title":"WorldGen: From Text to Traversable and Interactive 3D Worlds","created":"2025-11-20","cited_by_count":19,"area":null},{"id":"2509.22281","title":"MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning","created":"2025-09-26","cited_by_count":16,"area":"lr"},{"id":"2606.01057","title":"3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code","created":"2026-05-31","cited_by_count":15,"area":"agents"},{"id":"2510.05560","title":"HoloScene: Simulation-Ready Interactive 3D Worlds from a Single Video","created":"2025-10-07","cited_by_count":14,"area":null},{"id":"2511.18734","title":"Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion","created":"2025-11-24","cited_by_count":9,"area":null},{"id":"2606.01869","title":"WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis","created":"2026-06-01","cited_by_count":9,"area":null},{"id":"2608.05248","title":"WorldClaw: Agentic 3D Open-World Generation at Scale","created":"2026-08-05","cited_by_count":8,"area":"agents"},{"id":"2506.20601","title":"Video Perception Models for 3D Scene Synthesis","created":"2025-06-25","cited_by_count":7,"area":null},{"id":"2601.13304","title":"CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning","created":"2026-01-19","cited_by_count":7,"area":"lr"},{"id":"2602.14968","title":"PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangement","created":"2026-02-16","cited_by_count":7,"area":"agents"},{"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":"2510.02178","title":"DisCo-Layout: Disentangling and Coordinating Semantic and Physical Refinement in a Multi-Agent Framework for 3D Indoor Layout Synthesis","created":"2025-10-02","cited_by_count":6,"area":"agents"},{"id":"2512.13683","title":"I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners","created":"2025-12-15","cited_by_count":6,"area":null},{"id":"2602.09432","title":"SceneReVis: A Self-Reflective Vision-Grounded Framework for 3D Indoor Scene Synthesis via Multi-Turn RL","created":"2026-02-10","cited_by_count":6,"area":null},{"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":"2606.31388","title":"One Video, One World: Turning Monocular Video into Physical 4D Scenes","created":"2026-06-30","cited_by_count":6,"area":null},{"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":"2511.18200","title":"InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity","created":"2025-11-22","cited_by_count":5,"area":"lr"},{"id":"2603.19598","title":"FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow","created":"2026-03-20","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":"2506.14763","title":"RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills","created":"2025-06-17","cited_by_count":4,"area":"agents"},{"id":"2512.01204","title":"TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulation","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2604.10578","title":"Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models","created":"2026-04-12","cited_by_count":3,"area":"diffusion"},{"id":"2510.17157","title":"GACO-CAD: Geometry-Augmented and Conciseness-Optimized CAD Model Generation from Single Image","created":"2025-10-20","cited_by_count":2,"area":null},{"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":"2604.13035","title":"SceneCritic: A Symbolic Evaluator for 3D Indoor Scene Synthesis","created":"2026-04-14","cited_by_count":2,"area":"mllm"},{"id":"2604.19907","title":"SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generation","created":"2026-04-21","cited_by_count":2,"area":"agents"},{"id":"2605.20837","title":"ArchSIBench: Benchmarking the Architectural Spatial Intelligence of Vision-Language Models","created":"2026-05-20","cited_by_count":2,"area":"mllm"},{"id":"2606.08402","title":"SceneConductor: 3D Scene Generation from a Single Image with Multi-Agent Orchestration","created":"2026-06-07","cited_by_count":2,"area":null},{"id":"2606.29395","title":"NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation","created":"2026-06-28","cited_by_count":2,"area":"agents"},{"id":"2510.27148","title":"HiGS: Hierarchical Generative Scene Framework for Multi-Step Associative Semantic Spatial Composition","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2511.03001","title":"Apples on the Table? Evaluating Text-Guided 3D Scene Synthesis via Fine-Grained Constraint Verification","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2511.14884","title":"GeoSceneGraph: Geometric Scene Graph Diffusion Model for Text-guided 3D Indoor Scene Synthesis","created":"2025-11-18","cited_by_count":1,"area":"diffusion"},{"id":"2601.14602","title":"3D Space as a Scratchpad for Editable Text-to-Image Generation","created":"2026-01-21","cited_by_count":1,"area":"lr"},{"id":"2603.28548","title":"Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow","created":"2026-03-30","cited_by_count":1,"area":"diffusion"},{"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":"2606.01649","title":"PhyScene3D: Physically Consistent Interactive 3D Tabletop Scene Generation","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2608.03064","title":"Global Graph-Validated Optimization for VLM-based 3D Indoor Scene Generation","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.24169","title":"ViSculpt: Visual-Centric Agentic Geometry Editing","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2609.05927","title":"GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning","created":"2026-09-05","cited_by_count":1,"area":"agents"},{"id":"2609.06758","title":"Agentic Visual Generation: From Generative Models to Agentic Control","created":"2026-09-06","cited_by_count":1,"area":"agents"},{"id":"2609.23103","title":"DiagGen: Agentic Generation of Deformable Assets with Sim-based Diagnostics for Robotic Simulation","created":"2026-09-19","cited_by_count":1,"area":"agents"},{"id":"2505.22633","title":"Spatial Knowledge Graph-Guided Multimodal Synthesis","created":"2025-05-28","cited_by_count":0,"area":"mllm"},{"id":"2506.04562","title":"Handle-based Mesh Deformation Guided By Vision Language Model","created":"2025-06-05","cited_by_count":0,"area":"mllm"},{"id":"2506.08174","title":"LLM-BT-Terms: Back-Translation as a Framework for Terminology Standardization and Dynamic Semantic Embedding","created":"2025-06-09","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":"2604.01972","title":"SDesc3D: Towards Layout-Aware 3D Indoor Scene Generation from Short Descriptions","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.06758","title":"R$^3$L: Reasoning 3D Layouts from Relative Spatial Relations","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2607.03614","title":"IDEAL-Bench: Indoor Dataset and Evaluation suite for Analyzing 3D Layout reasoning","created":"2026-07-03","cited_by_count":0,"area":"lr"},{"id":"2607.03990","title":"InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360{\\deg} Image","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2608.01973","title":"Roomer: Reflective Object-Grounded Model Editing and Repair for 3D Indoor Layout Synthesis","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.05879","title":"To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.06279","title":"IM-ENGINE: Image Editing for Embodied Data Generation","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.13494","title":"Generative AI and Extended Reality in Collaborative Architectural Design Education: An Exploratory Studio Study","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.23796","title":"Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstruction","created":"2026-09-20","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":"2610.07460","title":"ElasticFit: Fit-Aware 3D Object Insertion via VLM Reasoning and Generative Adaptation","created":"2026-10-05","cited_by_count":0,"area":"lr"}],"next_cursor":null}