{"total":54,"rows":[{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2411.17735","title":"3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning","created":"2024-11-23","cited_by_count":75,"area":null},{"id":"2402.05741","title":"Real-World Robot Applications of Foundation Models: A Review","created":"2024-02-08","cited_by_count":61,"area":"mllm"},{"id":"2401.07745","title":"MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation","created":"2024-01-15","cited_by_count":56,"area":null},{"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":"2504.02477","title":"Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision","created":"2025-04-03","cited_by_count":40,"area":"mllm"},{"id":"2406.07113","title":"Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph","created":"2024-06-11","cited_by_count":32,"area":null},{"id":"2410.20220","title":"Neural Fields in Robotics: A Survey","created":"2024-10-26","cited_by_count":21,"area":null},{"id":"2511.11478","title":"Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective","created":"2025-11-14","cited_by_count":20,"area":"vla"},{"id":"2512.00565","title":"Describe Anything Anywhere At Any Moment","created":"2025-11-29","cited_by_count":19,"area":null},{"id":"2409.11764","title":"One Map to Find Them All: Real-time Open-Vocabulary Mapping for Zero-shot Multi-Object Navigation","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2411.15043","title":"Open-Vocabulary Online Semantic Mapping for SLAM","created":"2024-11-22","cited_by_count":12,"area":null},{"id":"2503.01309","title":"OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging","created":"2025-03-03","cited_by_count":12,"area":null},{"id":"2510.01049","title":"KeySG: Hierarchical Keyframe-Based 3D Scene Graphs","created":"2025-10-01","cited_by_count":10,"area":null},{"id":"2503.04034","title":"GaussianGraph: 3D Gaussian-based Scene Graph Generation for Open-world Scene Understanding","created":"2025-03-06","cited_by_count":8,"area":null},{"id":"2504.08603","title":"FindAnything: Open-Vocabulary and Object-Centric Mapping for Robot Exploration in Any Environment","created":"2025-04-11","cited_by_count":8,"area":null},{"id":"2403.04924","title":"$\\text{R}^2$-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations","created":"2024-03-07","cited_by_count":6,"area":null},{"id":"2508.01150","title":"OpenGS-Fusion: Open-Vocabulary Dense Mapping with Hybrid 3D Gaussian Splatting for Refined Object-Level Understanding","created":"2025-08-02","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":"2411.07848","title":"Zero-shot Object-Centric Instruction Following: Integrating Foundation Models with Traditional Navigation","created":"2024-11-12","cited_by_count":4,"area":null},{"id":"2501.13338","title":"CuriousBot: Interactive Mobile Exploration via Actionable 3D Relational Object Graph","created":"2025-01-23","cited_by_count":4,"area":null},{"id":"2503.21767","title":"Semantic Consistent Language Gaussian Splatting for Point-Level Open-vocabulary Querying","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2603.26541","title":"OVI-MAP:Open-Vocabulary Instance-Semantic Mapping","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2411.10509","title":"TESGNN: Temporal Equivariant Scene Graph Neural Networks for Efficient and Robust Multi-View 3D Scene Understanding","created":"2024-11-15","cited_by_count":3,"area":null},{"id":"2504.19266","title":"OpenFusion++: An Open-vocabulary Real-time Scene Understanding System","created":"2025-04-27","cited_by_count":3,"area":null},{"id":"2503.10331","title":"OSMa-Bench: Evaluating Open Semantic Mapping Under Varying Lighting Conditions","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2506.13629","title":"FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understanding","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2509.24528","title":"CORE-3D: Context-aware Open-vocabulary Retrieval by Embeddings in 3D","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2601.04754","title":"ProFuse: Efficient Cross-View Context Fusion for Open-Vocabulary 3D Gaussian Splatting","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2603.18510","title":"OnlinePG: Online Open-Vocabulary Panoptic Mapping with 3D Gaussian Splatting","created":"2026-03-19","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":"2506.04837","title":"OpenMaskDINO3D : Reasoning 3D Segmentation via Large Language Model","created":"2025-06-05","cited_by_count":1,"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":"2602.01930","title":"LIEREx: Language-Image Embeddings for Robotic Exploration","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2603.03935","title":"DISC: Dense Integrated Semantic Context for Large-Scale Open-Set Semantic Mapping","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2605.03669","title":"FUS3DMaps: Scalable and Accurate Open-Vocabulary Semantic Mapping by 3D Fusion of Voxel- and Instance-Level Layers","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2605.26503","title":"Uncertainty-Aware Gaussian Map for Vision-Language Navigation","created":"2026-05-26","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":"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":"2409.15493","title":"Build Once, Monitor Continuously: Persistent Semantic Mapping via Autonomous Exploration and Open-Vocabulary Object Updates","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2603.01603","title":"Sparse View Distractor-Free Gaussian Splatting","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.17647","title":"Part-Aware Open-Vocabulary 3D Affordance Grounding via Prototypical Semantic and Geometric Alignment","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2603.27970","title":"AffordMatcher: Affordance Learning in 3D Scenes from Visual Signifiers","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2606.12849","title":"SemanticXR: Low Power and Real-time Queryable Semantic Mapping with an Object-Level Device-Cloud Architecture","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.16935","title":"CrossMaps: Confidence-Aware Open-Vocabulary Semantic Mapping for Rover Navigation","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.25106","title":"IMPRINT: Image-Conditioned Query Enrichment for Long-Tail Object Goal Navigation","created":"2026-07-27","cited_by_count":0,"area":"mllm"},{"id":"2608.21136","title":"Stream3Dv2: Geometric-Semantic Fusion Enhanced Streaming Zero-Shot 3D Scene Understanding","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.00775","title":"VOIM: Training-Free Open-Vocabulary 3D Instance Mapping for RGB-D and Monocular SLAM","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.19542","title":"PerSeM: Persistent Semantic Memory for Long-Horizon Open-Vocabulary UAV Mapping","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.22385","title":"Active Spatial Inspection for Effective and Efficient Embodied Exploration","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.27462","title":"Hybrid Gaussians for Robust Open-Vocabulary 3D Segmentation with Multi-View Object Association and Boundary Refinement","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.31005","title":"TRACKGRAPH: Online Open-Vocabulary 3D Scene Graphs via Image-Space Tracking","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.31716","title":"PanOVOcc: Panoramic Embodied Open-Vocabulary Occupancy Mapping with Long-term Spatial Voxel Memory","created":"2026-09-21","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}],"next_cursor":null}