{"total":54,"rows":[{"id":"2504.00992","title":"SuperDec: 3D Scene Decomposition with Superquadric Primitives","created":"2025-04-01","cited_by_count":21,"area":null},{"id":"2509.01708","title":"Articulated Object Estimation in the Wild","created":"2025-09-01","cited_by_count":19,"area":null},{"id":"2512.00565","title":"Describe Anything Anywhere At Any Moment","created":"2025-11-29","cited_by_count":19,"area":null},{"id":"2504.13617","title":"Compile Scene Graphs with Reinforcement Learning","created":"2025-04-18","cited_by_count":11,"area":"lr"},{"id":"2602.16356","title":"Articulated 3D Scene Graphs for Open-World Mobile Manipulation","created":"2026-02-18","cited_by_count":11,"area":null},{"id":"2510.01049","title":"KeySG: Hierarchical Keyframe-Based 3D Scene Graphs","created":"2025-10-01","cited_by_count":10,"area":null},{"id":"2512.05343","title":"SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling","created":"2025-12-05","cited_by_count":9,"area":null},{"id":"2512.16909","title":"MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Model for Embodied Task Planning","created":"2025-12-18","cited_by_count":9,"area":"mllm"},{"id":"2509.11301","title":"UnLoc: Leveraging Depth Uncertainties for Floorplan Localization","created":"2025-09-14","cited_by_count":8,"area":null},{"id":"2603.28732","title":"Pandora: Articulated 3D Scene Graphs from Egocentric Vision","created":"2026-03-30","cited_by_count":6,"area":null},{"id":"2604.27895","title":"Graph World Models: Concepts, Taxonomy, and Future Directions","created":"2026-04-30","cited_by_count":6,"area":"wm"},{"id":"2509.24966","title":"Social 3D Scene Graphs: Modeling Human Actions and Relations for Interactive Service Robots","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2601.10168","title":"RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation","created":"2026-01-15","cited_by_count":5,"area":"rag"},{"id":"2604.03696","title":"FunFact: Building Probabilistic Functional 3D Scene Graphs via Factor-Graph Reasoning","created":"2026-04-04","cited_by_count":5,"area":"lr"},{"id":"2505.08124","title":"SLAG: Scalable Language-Augmented Gaussian Splatting","created":"2025-05-12","cited_by_count":4,"area":null},{"id":"2510.04714","title":"Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2606.19383","title":"3D Scene Graphs: Open Challenges and Future Directions","created":"2026-06-15","cited_by_count":4,"area":null},{"id":"2509.21576","title":"Vision Language Models Cannot Plan, but Can They Formalize?","created":"2025-09-25","cited_by_count":3,"area":"mllm"},{"id":"2601.20835","title":"Open-Vocabulary Functional 3D Human-Scene Interaction Generation","created":"2026-01-28","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":"2601.08876","title":"The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Models","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2603.25539","title":"PAWS: Perception of Articulation in the Wild at Scale from Egocentric Videos","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2606.05975","title":"T-FunS3D: Task-Driven Hierarchical Open-Vocabulary 3D Functionality Segmentation","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2606.31471","title":"Think While You Map: Asynchronous Vision-Language Agents for Incremental 3D Scene Graphs","created":"2026-06-30","cited_by_count":2,"area":"lr"},{"id":"2508.17044","title":"M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environments","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2509.19571","title":"Agentic Scene Policies: Unifying Space, Semantics, and Affordances for Robot Action","created":"2025-09-23","cited_by_count":1,"area":"agents"},{"id":"2512.02450","title":"HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2603.20530","title":"Memory Over Maps: 3D Object Localization Without Reconstruction","created":"2026-03-20","cited_by_count":1,"area":"mllm"},{"id":"2604.11038","title":"EgoFun3D: Modeling Interactive Objects from Egocentric Videos using Function Templates","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2605.14393","title":"Analogical Trajectory Transfer","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.15753","title":"Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2606.08655","title":"PhysGraph: A Physics-aware 3D Scene Graph for Perception and Reasoning","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2606.29786","title":"OP3DSG: Open-Vocabulary Part-Aware 3D Scene Graph Generation for Real-World Environments","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2607.13245","title":"Just-In-Time Scene Graph Growth: Combating Perceptual Saturation in Long-Horizon Robotics","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2608.11017","title":"R4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric Video","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2511.22364","title":"BINDER: Instantly Adaptive Mobile Manipulation with Open-Vocabulary Commands","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2603.23478","title":"UniFunc3D: Unified Active Spatial-Temporal Grounding for 3D Affordance Segmentation","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.16482","title":"A Survey of Spatial Memory Representations for Efficient Robot Navigation","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.10484","title":"OpenSGA: Efficient 3D Scene Graph Alignment in the Open World","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.20823","title":"RelWitness: Open-Vocabulary 3D Scene Graph Generation with Visual-Geometric Relation Witnesses","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.15417","title":"From Frames to Temporal Graphs: In-Context Egocentric Action Recognition with Vision-Language Models","created":"2026-06-13","cited_by_count":0,"area":"mllm"},{"id":"2606.20946","title":"Scaling Diverse Language Generation for 3D Visual Grounding","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.00529","title":"NoPA: Non-Parametric Online 3D Scene Graph Generation","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.06170","title":"Prior-SG: Task and Prior Driven Region Segmentation for Scene Graphs in Arbitrarily-Structured Environments","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"id":"2608.10886","title":"GESTO: Human-Centric Spatio-Temporal Memory for Reasoning in Dynamic Scenes","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.18058","title":"Finder: Agentic Closed-Loop Object Finding for Embodied Grounding","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.19815","title":"SnapPhysics: A Physics-Aware Scene Graph from a Single View for Interactive Mixed Reality Scenes","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.20673","title":"FunArt: Decoding Functional Structure and Articulation from Generative 3D Latents","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.25247","title":"Geometric and Semantic Coupling for Interaction Understanding in 3D Scenes","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.31595","title":"GraphWrit3R: End-to-End 3D Scene Graph Writing","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33258","title":"PORTER: Edge-Cloud Residency for Persistent 3D Scene Graph Memory","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.39665","title":"ChronoGraph: Functional 4D Scene Graphs with Vision-Language Models for Interaction Understanding and Grounded Planning","created":"2026-09-30","cited_by_count":0,"area":"mllm"},{"id":"2610.08800","title":"A Review Of Robotic World Models For Dynamic Environments Based On Factor And Scene Graphs","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2610.16455","title":"GHOST: Geometry-Constrained Hybrid Diffusion for Open-Vocabulary 3D Scene Graph Generation","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}