{"total":96,"rows":[{"id":"2505.02836","title":"Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation","created":"2025-05-05","cited_by_count":67,"area":"agents"},{"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":"2503.18470","title":"MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse","created":"2025-03-24","cited_by_count":51,"area":"lr"},{"id":"2602.10116","title":"SAGE: Scalable Agentic 3D Scene Generation for Embodied AI","created":"2026-02-10","cited_by_count":50,"area":"agents"},{"id":"2602.09153","title":"SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes","created":"2026-02-09","cited_by_count":46,"area":"agents"},{"id":"2506.05341","title":"Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning","created":"2025-06-05","cited_by_count":28,"area":"lr"},{"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":"2503.11892","title":"DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning","created":"2025-03-14","cited_by_count":24,"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":"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":"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":"2506.07570","title":"OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization","created":"2025-06-09","cited_by_count":14,"area":"synth"},{"id":"2509.14981","title":"SPATIALGEN: Layout-guided 3D Indoor Scene Generation","created":"2025-09-18","cited_by_count":14,"area":null},{"id":"2507.07644","title":"FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations","created":"2025-07-10","cited_by_count":13,"area":"lr"},{"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":"2506.04220","title":"Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs","created":"2025-06-04","cited_by_count":10,"area":"lr"},{"id":"2505.05288","title":"PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes","created":"2025-05-08","cited_by_count":9,"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":"2507.04451","title":"CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step","created":"2025-07-06","cited_by_count":8,"area":null},{"id":"2505.08854","title":"Generative AI for Autonomous Driving: Frontiers and Opportunities","created":"2025-05-13","cited_by_count":7,"area":"driving"},{"id":"2506.20601","title":"Video Perception Models for 3D Scene Synthesis","created":"2025-06-25","cited_by_count":7,"area":null},{"id":"2510.18316","title":"MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation","created":"2025-10-21","cited_by_count":7,"area":"offlinerl"},{"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":"2506.02459","title":"ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editing","created":"2025-06-03","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":"2508.18597","title":"SemLayoutDiff: Semantic Layout Generation with Diffusion Model for Indoor Scene Synthesis","created":"2025-08-26","cited_by_count":6,"area":"diffusion"},{"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":"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":"2506.14315","title":"ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2601.16532","title":"AnchoredDream: Zero-Shot 360{\\deg} Indoor Scene Generation from a Single View via Geometric Grounding","created":"2026-01-23","cited_by_count":5,"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":"2605.18451","title":"Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis","created":"2026-05-18","cited_by_count":5,"area":"agents"},{"id":"2504.15049","title":"ScanEdit: Hierarchically-Guided Functional 3D Scan Editing","created":"2025-04-21","cited_by_count":4,"area":null},{"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":"2507.06484","title":"3D-Generalist: Self-Improving Vision-Language-Action Models for Crafting 3D Worlds","created":"2025-07-09","cited_by_count":3,"area":"lr"},{"id":"2510.12095","title":"IL3D: A Large-Scale Indoor Layout Dataset for LLM-Driven 3D Scene Generation","created":"2025-10-14","cited_by_count":3,"area":null},{"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":"2512.02340","title":"Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective","created":"2025-12-02","cited_by_count":3,"area":"lr"},{"id":"2602.08735","title":"From Correspondence to Actions: Human-Like Multi-Image Spatial Reasoning in Multi-modal Large Language Models","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2603.17583","title":"Edit-As-Act: Goal-Regressive Planning for Open-Vocabulary 3D Indoor Scene Editing","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2604.16299","title":"Repurposing 3D Generative Model for Autoregressive Layout Generation","created":"2026-04-17","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":"2605.16137","title":"STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System","created":"2026-05-15","cited_by_count":3,"area":null},{"id":"2606.14168","title":"MUSE: Agentic 3D Scene Authoring via Memory-Grounded Incremental Requirement Satisfaction","created":"2026-06-12","cited_by_count":3,"area":"agents"},{"id":"2503.04496","title":"Learning to Place Objects with Programs and Iterative Self Training","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2601.07218","title":"SceneNAT: Masked Generative Modeling for Language-Guided Indoor Scene Synthesis","created":"2026-01-12","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":"2603.19708","title":"WorldAgents: Can Foundation Image Models be Agents for 3D World Models?","created":"2026-03-20","cited_by_count":2,"area":"wm"},{"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":"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":"2510.04057","title":"MetaFind: Scene-Aware 3D Asset Retrieval for Coherent Metaverse Scene Generation","created":"2025-10-05","cited_by_count":1,"area":null},{"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":"2512.04832","title":"BIM-Native Tokenization for Constraint-Aware Room Layout Synthesis","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2602.07104","title":"Extended to Reality: Prompt Injection in 3D Environments","created":"2026-02-06","cited_by_count":1,"area":"mllm"},{"id":"2604.02736","title":"THOM: Generating Physically Plausible Hand-Object Meshes From Text","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.10772","title":"HOG-Layout: Hierarchical 3D Scene Generation, Optimization and Editing via Vision-Language Models","created":"2026-04-12","cited_by_count":1,"area":"mllm"},{"id":"2604.11808","title":"Pair2Scene: Learning Local Object Relations for Procedural Scene Generation","created":"2026-04-13","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":"2605.31148","title":"SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.01649","title":"PhyScene3D: Physically Consistent Interactive 3D Tabletop Scene Generation","created":"2026-06-01","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":"2608.06161","title":"iARCS: Iterative Agentic RL for Controllable 3D Scene Generation","created":"2026-08-06","cited_by_count":1,"area":"agents"},{"id":"2608.12314","title":"StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization","created":"2026-08-12","cited_by_count":1,"area":null},{"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":"2506.04562","title":"Handle-based Mesh Deformation Guided By Vision Language Model","created":"2025-06-05","cited_by_count":0,"area":"mllm"},{"id":"2507.04770","title":"FurniMAS: Language-Guided Furniture Decoration using Multi-Agent System","created":"2025-07-07","cited_by_count":0,"area":"agents"},{"id":"2601.14679","title":"HCVR Scene Generation: High Compatibility Virtual Reality Environment Generation for Extended Redirected Walking","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2602.07100","title":"TLC-Plan: A Two-Level Codebook Based Network for End-to-End Vector Floorplan Generation","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2603.07704","title":"PARSE: Part-Aware Relational Spatial Modeling","created":"2026-03-08","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":"2604.20093","title":"FurnSet: Exploiting Repeats for 3D Scene Reconstruction","created":"2026-04-22","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":"2605.02288","title":"LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.02537","title":"Orchestrating Spatial Semantics via a Zone-Graph Paradigm for Intricate Indoor Scene Generation","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.20733","title":"Sketch2MinSurf: Vision-Language Guided Generation of Editable Minimal Surfaces from Hand-Drawn Sketches","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.06390","title":"HomeWorld: A Unified Floorplan-to-Furnished Framework for Generating Controllable, Densely Interactive Whole-Home Scenes","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.10953","title":"Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans","created":"2026-06-09","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":"2607.13539","title":"ThinkBLOX: 3D Indoor Scene Generation with Progressive Reasoning","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2608.01106","title":"SG-Layout: Structured Scene Graph-Guided Layout Generation with LLMs","created":"2026-08-02","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":"2608.30307","title":"ScenePilot: Grow-and-Repair Policy for Text-Driven 3D Indoor Scene Generation","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2609.05594","title":"SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"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":"2609.25741","title":"Fysiverse-3D-Vision Technical Report: Generating Executable 3D Worlds from Images through Unified Spatial Reasoning","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.36801","title":"Scene Retargeting: Learning Object Placement with Analogical Transfer","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00447","title":"Frozen Scenes, Shifting Winners: Configuration Fragility in Text-to-3D Evaluation","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":"2610.13145","title":"VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.19420","title":"From Failures to Learnable Worlds: Policy-Conditioned Environment Generation for Navigation Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}