{"total":70,"rows":[{"id":"2403.17846","title":"Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation","created":"2024-03-26","cited_by_count":196,"area":null},{"id":"2412.14480","title":"GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering","created":"2024-12-19","cited_by_count":37,"area":null},{"id":"2503.07885","title":"Safety Guardrails for LLM-Enabled Robots","created":"2025-03-10","cited_by_count":35,"area":"safety"},{"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":"2410.06237","title":"BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulation","created":"2024-10-08","cited_by_count":32,"area":"lr"},{"id":"2412.18450","title":"3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding","created":"2024-12-24","cited_by_count":27,"area":null},{"id":"2504.06994","title":"RayFronts: Open-Set Semantic Ray Frontiers for Online Scene Understanding and Exploration","created":"2025-04-09","cited_by_count":23,"area":null},{"id":"2506.18019","title":"Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities","created":"2025-06-22","cited_by_count":23,"area":"agents"},{"id":"2411.13019","title":"Open-World Amodal Appearance Completion","created":"2024-11-20","cited_by_count":19,"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":"2410.03035","title":"SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environments","created":"2024-10-03","cited_by_count":18,"area":null},{"id":"2505.09108","title":"Air-Ground Collaboration for Language-Specified Missions in Unknown Environments","created":"2025-05-14","cited_by_count":11,"area":null},{"id":"2602.16356","title":"Articulated 3D Scene Graphs for Open-World Mobile Manipulation","created":"2026-02-18","cited_by_count":11,"area":null},{"id":"2502.20630","title":"Subtask-Aware Visual Reward Learning from Segmented Demonstrations","created":"2025-02-28","cited_by_count":10,"area":"deeprl"},{"id":"2506.17486","title":"Distilling On-device Language Models for Robot Planning with Minimal Human Intervention","created":"2025-06-20","cited_by_count":10,"area":"lr"},{"id":"2510.01049","title":"KeySG: Hierarchical Keyframe-Based 3D Scene Graphs","created":"2025-10-01","cited_by_count":10,"area":null},{"id":"2505.03035","title":"MORE: Mobile Manipulation Rearrangement Through Grounded Language Reasoning","created":"2025-05-05","cited_by_count":9,"area":"lr"},{"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":"2603.01761","title":"Position: Modular Memory is the Key to Continual Learning Agents","created":"2026-03-02","cited_by_count":8,"area":"lr"},{"id":"2511.11266","title":"GraphPilot: Grounded Scene Graph Conditioning for Language-Based Autonomous Driving","created":"2025-11-14","cited_by_count":7,"area":"mllm"},{"id":"2408.02297","title":"Perception Matters: Enhancing Embodied AI with Uncertainty-Aware Semantic Segmentation","created":"2024-08-05","cited_by_count":6,"area":null},{"id":"2409.15095","title":"Whole-Body Teleoperation for Mobile Manipulation at Zero Added Cost","created":"2024-09-23","cited_by_count":6,"area":null},{"id":"2410.13691","title":"Jailbreaking LLM-Controlled Robots","created":"2024-10-17","cited_by_count":6,"area":"safety"},{"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":"2501.13338","title":"CuriousBot: Interactive Mobile Exploration via Actionable 3D Relational Object Graph","created":"2025-01-23","cited_by_count":4,"area":null},{"id":"2503.09173","title":"Long-Term Planning Around Humans in Domestic Environments with 3D Scene Graphs","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2603.15386","title":"RieMind: Geometry-Grounded Spatial Agent for Scene Understanding","created":"2026-03-16","cited_by_count":4,"area":"lr"},{"id":"2606.19383","title":"3D Scene Graphs: Open Challenges and Future Directions","created":"2026-06-15","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":"2505.09477","title":"Deploying Foundation Model-Enabled Air and Ground Robots in the Field: Challenges and Opportunities","created":"2025-05-14","cited_by_count":3,"area":null},{"id":"2505.20503","title":"Embodied AI with Foundation Models for Mobile Service Robots: A Systematic Review","created":"2025-05-26","cited_by_count":3,"area":"mllm"},{"id":"2506.01174","title":"GraphPad: Inference-Time 3D Scene Graph Updates for Embodied Question Answering","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2511.14391","title":"Enhancing LLM-based Autonomous Driving with Modular Traffic Light and Sign Recognition","created":"2025-11-18","cited_by_count":3,"area":"lr"},{"id":"2512.18987","title":"Affordance RAG: Hierarchical Multimodal Retrieval with Affordance-Aware Embodied Memory for Mobile Manipulation","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2512.21243","title":"LookPlanGraph: Embodied Instruction Following Method with VLM Graph Augmentation","created":"2025-12-24","cited_by_count":3,"area":null},{"id":"2606.08277","title":"Remember with Confidence: Uncertainty Quantification for Spatio-temporal Memory with Probabilistic Guarantees","created":"2026-06-06","cited_by_count":3,"area":null},{"id":"2601.02905","title":"LOST-3DSG: Lightweight Open-Vocabulary 3D Scene Graphs with Semantic Tracking in Dynamic Environments","created":"2026-01-06","cited_by_count":2,"area":null},{"id":"2604.06750","title":"How Well Do Vision-Language Models Understand Sequential Driving Scenes? A Sensitivity Study","created":"2026-04-08","cited_by_count":2,"area":"mllm"},{"id":"2605.19314","title":"ContextFlow: Hierarchical Task-State Alignment for Long-Horizon Embodied Agents","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2404.14968","title":"CenterArt: Joint Shape Reconstruction and 6-DoF Grasp Estimation of Articulated Objects","created":"2024-04-23","cited_by_count":1,"area":null},{"id":"2503.19764","title":"OpenLex3D: A Tiered Evaluation Benchmark for Open-Vocabulary 3D Scene Representations","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2508.17044","title":"M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environments","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2508.19074","title":"An LLM-powered Natural-to-Robotic Language Translation Framework with Correctness Guarantees","created":"2025-08-26","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":"2512.18386","title":"RecurGS: Interactive Scene Modeling via Discrete-State Recurrent Gaussian Fusion","created":"2025-12-20","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":"2609.19315","title":"GAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning","created":"2026-09-16","cited_by_count":1,"area":"wm"},{"id":"2409.19459","title":"Language-guided Robust Navigation for Mobile Robots in Dynamically-changing Environments","created":"2024-09-28","cited_by_count":0,"area":null},{"id":"2501.00432","title":"OV-HHIR: Open Vocabulary Human Interaction Recognition Using Cross-modal Integration of Large Language Models","created":"2024-12-31","cited_by_count":0,"area":null},{"id":"2505.00831","title":"SmallPlan: Leverage Small Language Models for Sequential Path Planning with Simulation-Powered, LLM-Guided Distillation","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2505.21754","title":"Visual Loop Closure Detection Through Deep Graph Consensus","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2509.24163","title":"Preference-Based Long-Horizon Robotic Stacking with Multimodal Large Language Models","created":"2025-09-29","cited_by_count":0,"area":"mllm"},{"id":"2511.22364","title":"BINDER: Instantly Adaptive Mobile Manipulation with Open-Vocabulary Commands","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2603.00455","title":"Test-Driven Agentic Framework for Reliable Robot Controller","created":"2026-02-28","cited_by_count":0,"area":"agents"},{"id":"2603.05642","title":"Relational Semantic Reasoning on 3D Scene Graphs for Open World Interactive Object Search","created":"2026-03-05","cited_by_count":0,"area":"lr"},{"id":"2603.08544","title":"The Neural Compass: Probabilistic Relative Feature Fields for Robotic Search","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.24083","title":"Knowledge-Guided Manipulation Using Multi-Task Reinforcement Learning","created":"2026-03-25","cited_by_count":0,"area":"deeprl"},{"id":"2604.22274","title":"CAGE-SGG: Counterfactual Active Graph Evidence for Open-Vocabulary Scene Graph Generation","created":"2026-04-24","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":"2605.25706","title":"Towards Open-World Referring Expression Comprehension: A Benchmark with Training-free Multi-task Consistency Checker","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.07529","title":"CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models","created":"2026-04-21","cited_by_count":0,"area":"lr"},{"id":"2607.06534","title":"CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models","created":"2026-07-07","cited_by_count":0,"area":"mllm"},{"id":"2607.09455","title":"Hydra++: Real-Time Hierarchical 3D Scene Graph Construction With Object-Level Shape Estimation","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2609.18548","title":"HAP: A Hand-Driven Active Perception Framework for Egocentric Head Motion Prediction","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.29091","title":"From Passive Execution to Active Exploration: Agentic Embodied Manipulation in Realistic Environments","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"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":"2610.02023","title":"SPHERE: Adaptive VR Indoor Scene Generation via LLM-Enhanced Spatial Preference Learning and Human-in-the-Loop RL","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.17089","title":"Interactive Navigation Beyond Reachability: Benchmark and Agentic Framework","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}