{"total":83,"rows":[{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346,"area":null},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194,"area":null},{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179,"area":null},{"id":"2201.10029","title":"PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning","created":"2022-01-25","cited_by_count":150,"area":null},{"id":"2312.02010","title":"Towards Learning a Generalist Model for Embodied Navigation","created":"2023-12-04","cited_by_count":138,"area":null},{"id":"2203.12667","title":"Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions","created":"2022-03-22","cited_by_count":117,"area":null},{"id":"2301.07302","title":"PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav","created":"2023-01-18","cited_by_count":93,"area":null},{"id":"2110.05122","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","created":"2021-10-11","cited_by_count":86,"area":null},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"area":null},{"id":"2403.15941","title":"Explore until Confident: Efficient Exploration for Embodied Question Answering","created":"2024-03-23","cited_by_count":74,"area":null},{"id":"2308.04758","title":"Bird's-Eye-View Scene Graph for Vision-Language Navigation","created":"2023-08-09","cited_by_count":72,"area":null},{"id":"2303.07798","title":"OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNav","created":"2023-03-14","cited_by_count":70,"area":null},{"id":"2406.14240","title":"CityNav: A Large-Scale Dataset for Real-World Aerial Navigation","created":"2024-06-20","cited_by_count":42,"area":null},{"id":"2111.14843","title":"Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds","created":"2021-11-29","cited_by_count":41,"area":null},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"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":"2210.03087","title":"Iterative Vision-and-Language Navigation","created":"2022-10-06","cited_by_count":35,"area":null},{"id":"2108.11544","title":"Vision-Language Navigation: A Survey and Taxonomy","created":"2021-08-26","cited_by_count":34,"area":null},{"id":"2103.07894","title":"Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images","created":"2021-03-14","cited_by_count":33,"area":null},{"id":"2205.01652","title":"Episodic Memory Question Answering","created":"2022-05-03","cited_by_count":32,"area":null},{"id":"2212.06250","title":"ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes","created":"2022-12-12","cited_by_count":32,"area":null},{"id":"2106.13948","title":"Core Challenges in Embodied Vision-Language Planning","created":"2021-06-26","cited_by_count":30,"area":null},{"id":"2503.11117","title":"Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering","created":"2025-03-14","cited_by_count":30,"area":null},{"id":"2108.11550","title":"The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation","created":"2021-08-26","cited_by_count":27,"area":null},{"id":"2410.03878","title":"SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models","created":"2024-10-04","cited_by_count":27,"area":null},{"id":"2106.00596","title":"Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks","created":"2021-06-01","cited_by_count":26,"area":null},{"id":"2202.07028","title":"One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestones","created":"2022-02-14","cited_by_count":26,"area":null},{"id":"2406.09613","title":"ImageNet3D: Towards General-Purpose Object-Level 3D Understanding","created":"2024-06-13","cited_by_count":25,"area":null},{"id":"2505.22657","title":"3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model","created":"2025-05-28","cited_by_count":25,"area":null},{"id":"2106.11650","title":"A Survey on Human-aware Robot Navigation","created":"2021-06-22","cited_by_count":24,"area":null},{"id":"2412.08591","title":"RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation","created":"2024-12-11","cited_by_count":23,"area":null},{"id":"2105.00931","title":"GridToPix: Training Embodied Agents with Minimal Supervision","created":"2021-04-14","cited_by_count":21,"area":null},{"id":"2303.11910","title":"360BEV: Panoramic Semantic Mapping for Indoor Bird's-Eye View","created":"2023-03-21","cited_by_count":18,"area":null},{"id":"2303.16485","title":"TriVol: Point Cloud Rendering via Triple Volumes","created":"2023-03-29","cited_by_count":16,"area":null},{"id":"2308.05602","title":"Object Goal Navigation with Recursive Implicit Maps","created":"2023-08-10","cited_by_count":16,"area":null},{"id":"2410.20263","title":"EfficientEQA: An Efficient Approach to Open-Vocabulary Embodied Question Answering","created":"2024-10-26","cited_by_count":15,"area":null},{"id":"2507.12846","title":"Enter the Mind Palace: Reasoning and Planning for Long-term Active Embodied Question Answering","created":"2025-07-17","cited_by_count":14,"area":null},{"id":"2101.00151","title":"DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue","created":"2021-01-01","cited_by_count":13,"area":null},{"id":"2503.11081","title":"MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation","created":"2025-03-14","cited_by_count":12,"area":null},{"id":"2505.13948","title":"Memory-Centric Embodied Question Answering","created":"2025-05-20","cited_by_count":12,"area":null},{"id":"2303.01396","title":"MLANet: Multi-Level Attention Network with Sub-instruction for Continuous Vision-and-Language Navigation","created":"2023-03-02","cited_by_count":11,"area":null},{"id":"2502.00342","title":"Embodied Intelligence for 3D Understanding: A Survey on 3D Scene Question Answering","created":"2025-02-01","cited_by_count":11,"area":null},{"id":"2405.18831","title":"Evaluating Zero-Shot GPT-4V Performance on 3D Visual Question Answering Benchmarks","created":"2024-05-29","cited_by_count":10,"area":null},{"id":"2407.17398","title":"3D Question Answering for City Scene Understanding","created":"2024-07-24","cited_by_count":10,"area":null},{"id":"2512.04597","title":"When Robots Should Say \"I Don't Know\": Benchmarking Abstention in Embodied Question Answering","created":"2025-12-04","cited_by_count":10,"area":null},{"id":"2311.03357","title":"Exploitation-Guided Exploration for Semantic Embodied Navigation","created":"2023-11-06","cited_by_count":9,"area":null},{"id":"2402.14304","title":"Vision-Language Navigation with Embodied Intelligence: A Survey","created":"2024-02-22","cited_by_count":9,"area":null},{"id":"2405.16559","title":"Map-based Modular Approach for Zero-shot Embodied Question Answering","created":"2024-05-26","cited_by_count":9,"area":null},{"id":"2311.02018","title":"Active Reasoning in an Open-World Environment","created":"2023-11-03","cited_by_count":8,"area":null},{"id":"2210.02709","title":"Embodied Referring Expression for Manipulation Question Answering in Interactive Environment","created":"2022-10-06","cited_by_count":7,"area":null},{"id":"2108.09823","title":"Embodied AI-Driven Operation of Smart Cities: A Concise Review","created":"2021-08-22","cited_by_count":6,"area":null},{"id":"2112.12612","title":"Towards Disturbance-Free Visual Mobile Manipulation","created":"2021-12-17","cited_by_count":6,"area":null},{"id":"2212.00767","title":"Exploiting Proximity-Aware Tasks for Embodied Social Navigation","created":"2022-12-01","cited_by_count":6,"area":null},{"id":"2301.07150","title":"Embodied Agents for Efficient Exploration and Smart Scene Description","created":"2023-01-17","cited_by_count":6,"area":null},{"id":"2307.13957","title":"Heterogeneous Embodied Multi-Agent Collaboration","created":"2023-07-26","cited_by_count":6,"area":null},{"id":"2308.08854","title":"Language-enhanced RNR-Map: Querying Renderable Neural Radiance Field maps with natural language","created":"2023-08-17","cited_by_count":5,"area":null},{"id":"2404.11327","title":"Following the Human Thread in Social Navigation","created":"2024-04-17","cited_by_count":4,"area":null},{"id":"2511.19033","title":"ReEXplore: Improving MLLMs for Embodied Exploration with Contextualized Retrospective Experience Replay","created":"2025-11-24","cited_by_count":4,"area":null},{"id":"2212.01186","title":"A General Purpose Supervisory Signal for Embodied Agents","created":"2022-12-01","cited_by_count":3,"area":null},{"id":"2302.04865","title":"ELBA: Learning by Asking for Embodied Visual Navigation and Task Completion","created":"2023-02-09","cited_by_count":3,"area":null},{"id":"2406.10918","title":"Multi-LLM QA with Embodied Exploration","created":"2024-06-16","cited_by_count":3,"area":null},{"id":"2603.27577","title":"Structured Observation Language for Efficient and Generalizable Vision-Language Navigation","created":"2026-03-29","cited_by_count":3,"area":null},{"id":"2604.17969","title":"E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2103.00446","title":"Learning for Visual Navigation by Imagining the Success","created":"2021-02-28","cited_by_count":2,"area":null},{"id":"2108.04097","title":"Deep Learning for Embodied Vision Navigation: A Survey","created":"2021-07-07","cited_by_count":2,"area":null},{"id":"2210.05556","title":"ViLPAct: A Benchmark for Compositional Generalization on Multimodal Human Activities","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2503.08604","title":"EMMOE: A Comprehensive Benchmark for Embodied Mobile Manipulation in Open Environments","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2607.10180","title":"ActiveFly-Bench: Aligning Embodied Question Answering with Vision-Language-Action for Aerial Embodied Perception","created":"2026-07-11","cited_by_count":2,"area":null},{"id":"2411.04351","title":"LidaRefer: Context-aware Outdoor 3D Visual Grounding for Autonomous Driving","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2411.18539","title":"AdaVLN: Towards Visual Language Navigation in Continuous Indoor Environments with Moving Humans","created":"2024-11-27","cited_by_count":1,"area":null},{"id":"2603.09541","title":"Memory-Guided View Refinement for Dynamic Human-in-the-loop EQA","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2109.08677","title":"Realistic PointGoal Navigation via Auxiliary Losses and Information Bottleneck","created":"2021-09-17","cited_by_count":0,"area":null},{"id":"2203.07679","title":"Energy-efficient Dense DNN Acceleration with Signed Bit-slice Architecture","created":"2022-03-15","cited_by_count":0,"area":null},{"id":"2210.03787","title":"Learning a Visually Grounded Memory Assistant","created":"2022-10-07","cited_by_count":0,"area":null},{"id":"2304.02738","title":"Core Challenges in Embodied Vision-Language Planning","created":"2023-04-05","cited_by_count":0,"area":null},{"id":"2504.00775","title":"Visual Environment-Interactive Planning for Embodied Complex-Question Answering","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2507.21450","title":"Recursive Visual Imagination and Adaptive Linguistic Grounding for Vision Language Navigation","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2511.11777","title":"Large Language Models and 3D Vision for Intelligent Robotic Perception and Autonomy","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2602.09255","title":"STaR: Scalable Task-Conditioned Retrieval for Long-Horizon Multimodal Robot Memory","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.09259","title":"Implicit Geometry Representations for Vision-and-Language Navigation from Web Videos","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.16166","title":"SignNav: Leveraging Signage for Semantic Visual Navigation in Large-Scale Indoor Environments","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2608.08596","title":"Goal-oriented Navigation Instruction Generation with Tour Video Priors","created":"2026-08-09","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}],"next_cursor":null}