{"list":"other","total":64,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"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":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"2503.21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","created":"2025-03-27","cited_by_count":484},{"id":"2108.08877","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","created":"2021-08-19","cited_by_count":463},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"2206.14651","title":"BoT-SORT: Robust Associations Multi-Pedestrian Tracking","created":"2022-06-29","cited_by_count":320},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304},{"id":"2307.06135","title":"SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning","created":"2023-07-12","cited_by_count":294},{"id":"1910.02527","title":"3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera","created":"2019-10-06","cited_by_count":281},{"id":"2004.03967","title":"Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions","created":"2020-04-08","cited_by_count":208},{"id":"2312.03275","title":"VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation","created":"2023-12-06","cited_by_count":205},{"id":"2403.17846","title":"Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation","created":"2024-03-26","cited_by_count":196},{"id":"1910.02490","title":"Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping","created":"2019-10-06","cited_by_count":184},{"id":"2211.16312","title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding","created":"2022-11-29","cited_by_count":177},{"id":"2501.09898","title":"FoundationStereo: Zero-Shot Stereo Matching","created":"2025-01-17","cited_by_count":173},{"id":"2210.05663","title":"CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory","created":"2022-10-11","cited_by_count":165},{"id":"2103.14898","title":"SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences","created":"2021-03-27","cited_by_count":163},{"id":"2209.09874","title":"Open-vocabulary Queryable Scene Representations for Real World Planning","created":"2022-09-20","cited_by_count":160},{"id":"2002.06289","title":"3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans","created":"2020-02-15","cited_by_count":144},{"id":"2101.06894","title":"Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs","created":"2021-01-18","cited_by_count":144},{"id":"2403.12722","title":"HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting","created":"2024-03-19","cited_by_count":142},{"id":"2312.02010","title":"Towards Learning a Generalist Model for Embodied Navigation","created":"2023-12-04","cited_by_count":138},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133},{"id":"2410.08189","title":"SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation","created":"2024-10-10","cited_by_count":109},{"id":"2504.16072","title":"Describe Anything: Detailed Localized Image and Video Captioning","created":"2025-04-22","cited_by_count":84},{"id":"2404.13696","title":"Clio: Real-time Task-Driven Open-Set 3D Scene Graphs","created":"2024-04-21","cited_by_count":81},{"id":"2411.17735","title":"3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning","created":"2024-11-23","cited_by_count":75},{"id":"2407.07775","title":"Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs","created":"2024-07-10","cited_by_count":73},{"id":"2403.08605","title":"Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation","created":"2024-03-13","cited_by_count":70},{"id":"2409.13682","title":"ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation","created":"2024-09-20","cited_by_count":67},{"id":"2305.07154","title":"Foundations of Spatial Perception for Robotics: Hierarchical Representations and Real-time Systems","created":"2023-05-11","cited_by_count":60},{"id":"2503.10630","title":"UniGoal: Towards Universal Zero-shot Goal-oriented Navigation","created":"2025-03-13","cited_by_count":57},{"id":"2310.03923","title":"Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation","created":"2023-10-05","cited_by_count":54},{"id":"2503.19199","title":"Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces","created":"2025-03-24","cited_by_count":54},{"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},{"id":"2412.14480","title":"GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering","created":"2024-12-19","cited_by_count":37},{"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":"2411.04999","title":"DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation","created":"2024-11-07","cited_by_count":32},{"id":"2309.13549","title":"Towards Robust Robot 3D Perception in Urban Environments: The UT Campus Object Dataset","created":"2023-09-24","cited_by_count":28},{"id":"2405.05792","title":"RoboHop: Segment-based Topological Map Representation for Open-World Visual Navigation","created":"2024-05-09","cited_by_count":25},{"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},{"id":"2209.07896","title":"3D VSG: Long-term Semantic Scene Change Prediction through 3D Variable Scene Graphs","created":"2022-09-16","cited_by_count":24},{"id":"2412.13652","title":"RelationField: Relate Anything in Radiance Fields","created":"2024-12-18","cited_by_count":16},{"id":"2405.00552","title":"Long-Term Human Trajectory Prediction using 3D Dynamic Scene Graphs","created":"2024-05-01","cited_by_count":15},{"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},{"id":"2508.04678","title":"Open Scene Graphs for Open-World Object-Goal Navigation","created":"2025-08-06","cited_by_count":14},{"id":"2412.01539","title":"The Bare Necessities: Designing Simple, Effective Open-Vocabulary Scene Graphs","created":"2024-12-02","cited_by_count":11},{"id":"2010.09859","title":"A Unified Approach for Autonomous Volumetric Exploration of Large Scale Environments under Severe Odometry Drift","created":"2020-10-19","cited_by_count":8},{"id":"2504.06553","title":"ASHiTA: Automatic Scene-grounded HIerarchical Task Analysis","created":"2025-04-09","cited_by_count":8},{"id":"2506.06862","title":"Multimodal Spatial Language Maps for Robot Navigation and Manipulation","created":"2025-06-07","cited_by_count":6},{"id":"2503.05949","title":"Bayesian Fields: Task-driven Open-Set Semantic Gaussian Splatting","created":"2025-03-07","cited_by_count":5},{"id":"2503.16413","title":"M3: 3D-Spatial MultiModal Memory","created":"2025-03-20","cited_by_count":3},{"id":"2510.16643","title":"Structured Interfaces for Automated Reasoning with 3D Scene Graphs","created":"2025-10-18","cited_by_count":3}],"next_cursor":null}