{"list":"other","total":65,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"2312.06741","title":"Gaussian Splatting SLAM","created":"2023-12-11","cited_by_count":415},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365},{"id":"2306.09683","title":"Scaling Open-Vocabulary Object Detection","created":"2023-06-16","cited_by_count":343},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304},{"id":"2311.11700","title":"GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting","created":"2023-11-20","cited_by_count":278},{"id":"2006.13171","title":"ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects","created":"2020-06-23","cited_by_count":244},{"id":"2212.08333","title":"AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains","created":"2022-12-16","cited_by_count":208},{"id":"2403.17846","title":"Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation","created":"2024-03-26","cited_by_count":196},{"id":"2210.13641","title":"NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields","created":"2022-10-24","cited_by_count":188},{"id":"2004.14973","title":"Improving Vision-and-Language Navigation with Image-Text Pairs from the Web","created":"2020-04-30","cited_by_count":177},{"id":"2210.05663","title":"CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory","created":"2022-10-11","cited_by_count":165},{"id":"2209.09874","title":"Open-vocabulary Queryable Scene Representations for Real World Planning","created":"2022-09-20","cited_by_count":160},{"id":"2309.12311","title":"LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent","created":"2023-09-21","cited_by_count":135},{"id":"1806.05620","title":"DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes","created":"2018-06-14","cited_by_count":134},{"id":"2210.05633","title":"Habitat-Matterport 3D Semantics Dataset","created":"2022-10-11","cited_by_count":110},{"id":"2212.00922","title":"Navigating to Objects in the Real World","created":"2022-12-02","cited_by_count":106},{"id":"2306.11565","title":"HomeRobot: Open-Vocabulary Mobile Manipulation","created":"2023-06-20","cited_by_count":106},{"id":"1808.08378","title":"Fusion++: Volumetric Object-Level SLAM","created":"2018-08-25","cited_by_count":98},{"id":"2301.07302","title":"PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav","created":"2023-01-18","cited_by_count":93},{"id":"1809.08379","title":"DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments","created":"2018-09-22","cited_by_count":91},{"id":"2311.06430","title":"GOAT: GO to Any Thing","created":"2023-11-10","cited_by_count":89},{"id":"2404.13696","title":"Clio: Real-time Task-Driven Open-Set 3D Scene Graphs","created":"2024-04-21","cited_by_count":81},{"id":"2209.09050","title":"Loc-NeRF: Monte Carlo Localization using Neural Radiance Fields","created":"2022-09-19","cited_by_count":69},{"id":"2110.09470","title":"No RL, No Simulation: Learning to Navigate without Navigating","created":"2021-10-18","cited_by_count":65},{"id":"2112.05251","title":"Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation","created":"2021-12-09","cited_by_count":59},{"id":"2406.20083","title":"PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators","created":"2024-06-28","cited_by_count":58},{"id":"2211.15876","title":"Instance-Specific Image Goal Navigation: Training Embodied Agents to Find Object Instances","created":"2022-11-29","cited_by_count":55},{"id":"2312.02976","title":"SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World","created":"2023-12-05","cited_by_count":48},{"id":"2010.07820","title":"DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM","created":"2020-10-15","cited_by_count":47},{"id":"2409.05865","title":"Robot Utility Models: General Policies for Zero-Shot Deployment in New Environments","created":"2024-09-09","cited_by_count":44},{"id":"2304.00410","title":"ASC: Adaptive Skill Coordination for Robotic Mobile Manipulation","created":"2023-04-01","cited_by_count":42},{"id":"2410.11989","title":"Dynamic Open-Vocabulary 3D Scene Graphs for Long-term Language-Guided Mobile Manipulation","created":"2024-10-15","cited_by_count":39},{"id":"2405.04378","title":"Splat-MOVER: Multi-Stage, Open-Vocabulary Robotic Manipulation via Editable Gaussian Splatting","created":"2024-05-07","cited_by_count":38},{"id":"2402.13817","title":"Khronos: A Unified Approach for Spatio-Temporal Metric-Semantic SLAM in Dynamic Environments","created":"2024-02-21","cited_by_count":36},{"id":"2403.07563","title":"Learning Generalizable Feature Fields for Mobile Manipulation","created":"2024-03-12","cited_by_count":31},{"id":"2405.07991","title":"SPIN: Simultaneous Perception, Interaction and Navigation","created":"2024-05-13","cited_by_count":29},{"id":"1703.08866","title":"Multi-View Deep Learning for Consistent Semantic Mapping with RGB-D Cameras","created":"2017-03-26","cited_by_count":28},{"id":"2108.11550","title":"The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation","created":"2021-08-26","cited_by_count":27},{"id":"2002.08584","title":"Dynamic SLAM: The Need For Speed","created":"2020-02-20","cited_by_count":24},{"id":"2205.02301","title":"BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking","created":"2022-05-04","cited_by_count":24},{"id":"2103.08022","title":"Success Weighted by Completion Time: A Dynamics-Aware Evaluation Criteria for Embodied Navigation","created":"2021-03-14","cited_by_count":22},{"id":"2109.09903","title":"AirDOS: Dynamic SLAM benefits from Articulated Objects","created":"2021-09-21","cited_by_count":21},{"id":"2109.04749","title":"A Holistic Approach to Reactive Mobile Manipulation","created":"2021-09-10","cited_by_count":17},{"id":"2312.08611","title":"UniTeam: Open Vocabulary Mobile Manipulation Challenge","created":"2023-12-14","cited_by_count":15},{"id":"2202.07600","title":"Bayesian Imitation Learning for End-to-End Mobile Manipulation","created":"2022-02-15","cited_by_count":14},{"id":"2401.02702","title":"VoxelNextFusion: A Simple, Unified and Effective Voxel Fusion Framework for Multi-Modal 3D Object Detection","created":"2024-01-05","cited_by_count":14},{"id":"2208.11500","title":"DynaVINS: A Visual-Inertial SLAM for Dynamic Environments","created":"2022-08-24","cited_by_count":12},{"id":"2304.12164","title":"USA-Net: Unified Semantic and Affordance Representations for Robot Memory","created":"2023-04-24","cited_by_count":7},{"id":"2202.12802","title":"Probabilistic Data Association for Semantic SLAM at Scale","created":"2022-02-25","cited_by_count":4},{"id":"2310.06385","title":"3DS-SLAM: A 3D Object Detection based Semantic SLAM towards Dynamic Indoor Environments","created":"2023-10-10","cited_by_count":3},{"id":"2209.10710","title":"Visual Localization and Mapping in Dynamic and Changing Environments","created":"2022-09-21","cited_by_count":1}],"next_cursor":null}