{"total":402,"rows":[{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774,"area":null},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771,"area":null},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490,"area":null},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395,"area":null},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380,"area":null},{"id":"2402.15852","title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","created":"2024-02-24","cited_by_count":233,"area":null},{"id":"2310.13724","title":"Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots","created":"2023-10-19","cited_by_count":228,"area":null},{"id":"2303.18240","title":"Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?","created":"2023-03-31","cited_by_count":218,"area":null},{"id":"2111.09888","title":"Simple but Effective: CLIP Embeddings for Embodied AI","created":"2021-11-18","cited_by_count":191,"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":"2206.12403","title":"ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings","created":"2022-06-24","cited_by_count":178,"area":null},{"id":"2502.20110","title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","created":"2025-02-27","cited_by_count":173,"area":null},{"id":"2306.11290","title":"Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation","created":"2023-06-20","cited_by_count":167,"area":null},{"id":"2210.10716","title":"CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion","created":"2022-10-19","cited_by_count":160,"area":null},{"id":"2406.04882","title":"InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment","created":"2024-06-07","cited_by_count":157,"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":"2312.16170","title":"EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI","created":"2023-12-26","cited_by_count":147,"area":null},{"id":"2412.06974","title":"MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds","created":"2024-12-09","cited_by_count":141,"area":null},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133,"area":null},{"id":"2301.13166","title":"ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation","created":"2023-01-30","cited_by_count":127,"area":null},{"id":"2307.12907","title":"GridMM: Grid Memory Map for Vision-and-Language Navigation","created":"2023-07-24","cited_by_count":124,"area":null},{"id":"2307.15644","title":"Scaling Data Generation in Vision-and-Language Navigation","created":"2023-07-28","cited_by_count":117,"area":null},{"id":"2210.05633","title":"Habitat-Matterport 3D Semantics Dataset","created":"2022-10-11","cited_by_count":110,"area":null},{"id":"2503.16429","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","created":"2025-03-20","cited_by_count":110,"area":null},{"id":"2212.00922","title":"Navigating to Objects in the Real World","created":"2022-12-02","cited_by_count":106,"area":null},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104,"area":null},{"id":"2206.08312","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","created":"2022-06-16","cited_by_count":95,"area":null},{"id":"2404.06609","title":"GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation","created":"2024-04-09","cited_by_count":94,"area":null},{"id":"2407.07035","title":"Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models","created":"2024-07-09","cited_by_count":79,"area":null},{"id":"2305.19195","title":"PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation","created":"2023-05-30","cited_by_count":77,"area":null},{"id":"2204.13226","title":"Offline Visual Representation Learning for Embodied Navigation","created":"2022-04-27","cited_by_count":75,"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":"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":"2202.02440","title":"Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation","created":"2022-02-05","cited_by_count":67,"area":null},{"id":"2404.01943","title":"Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation","created":"2024-04-02","cited_by_count":65,"area":null},{"id":"2308.07997","title":"$A^2$Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models","created":"2023-08-15","cited_by_count":62,"area":null},{"id":"2503.16591","title":"UniK3D: Universal Camera Monocular 3D Estimation","created":"2025-03-20","cited_by_count":62,"area":null},{"id":"2402.16117","title":"RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis","created":"2024-02-25","cited_by_count":58,"area":null},{"id":"2401.02695","title":"VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model","created":"2024-01-05","cited_by_count":57,"area":null},{"id":"2211.15876","title":"Instance-Specific Image Goal Navigation: Training Embodied Agents to Find Object Instances","created":"2022-11-29","cited_by_count":55,"area":null},{"id":"2210.05805","title":"Exploration via Elliptical Episodic Bonuses","created":"2022-10-11","cited_by_count":51,"area":null},{"id":"2304.01192","title":"Navigating to Objects Specified by Images","created":"2023-04-03","cited_by_count":51,"area":null},{"id":"2208.11781","title":"Learning from Unlabeled 3D Environments for Vision-and-Language Navigation","created":"2022-08-24","cited_by_count":50,"area":null},{"id":"2412.10137","title":"Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environments","created":"2024-12-13","cited_by_count":50,"area":null},{"id":"2402.15487","title":"RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation","created":"2024-02-23","cited_by_count":48,"area":null},{"id":"2307.11984","title":"Learning Vision-and-Language Navigation from YouTube Videos","created":"2023-07-22","cited_by_count":47,"area":null},{"id":"2505.23189","title":"TrackVLA: Embodied Visual Tracking in the Wild","created":"2025-05-29","cited_by_count":47,"area":null},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46,"area":null},{"id":"2510.23607","title":"Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations","created":"2025-10-27","cited_by_count":45,"area":null},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2210.04932","title":"NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields","created":"2022-10-10","cited_by_count":44,"area":null},{"id":"2409.18313","title":"Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation","created":"2024-09-26","cited_by_count":44,"area":null},{"id":"2307.12335","title":"Learning Navigational Visual Representations with Semantic Map Supervision","created":"2023-07-23","cited_by_count":43,"area":null},{"id":"2112.02306","title":"Toward Practical Monocular Indoor Depth Estimation","created":"2021-12-04","cited_by_count":42,"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":"2406.09401","title":"MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations","created":"2024-06-13","cited_by_count":40,"area":null},{"id":"2501.02464","title":"Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera","created":"2025-01-05","cited_by_count":40,"area":null},{"id":"2401.08577","title":"MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World","created":"2024-01-16","cited_by_count":39,"area":null},{"id":"2411.09823","title":"Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting","created":"2024-11-14","cited_by_count":38,"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":"2604.14141","title":"LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction","created":"2026-04-15","cited_by_count":37,"area":null},{"id":"2206.00997","title":"Is Mapping Necessary for Realistic PointGoal Navigation?","created":"2022-06-02","cited_by_count":35,"area":null},{"id":"2210.03087","title":"Iterative Vision-and-Language Navigation","created":"2022-10-06","cited_by_count":35,"area":null},{"id":"2406.09371","title":"LRM-Zero: Training Large Reconstruction Models with Synthesized Data","created":"2024-06-13","cited_by_count":35,"area":null},{"id":"2301.13261","title":"Emergence of Maps in the Memories of Blind Navigation Agents","created":"2023-01-30","cited_by_count":33,"area":null},{"id":"2412.10439","title":"CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs","created":"2024-12-11","cited_by_count":33,"area":null},{"id":"2508.00288","title":"UAV-ON: A Benchmark for Open-World Object Goal Navigation with Aerial Agents","created":"2025-08-01","cited_by_count":33,"area":null},{"id":"2403.11650","title":"Prioritized Semantic Learning for Zero-shot Instance Navigation","created":"2024-03-18","cited_by_count":31,"area":null},{"id":"2503.18944","title":"DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation","created":"2025-03-24","cited_by_count":31,"area":null},{"id":"2506.03642","title":"Spatial Understanding from Videos: Structured Prompts Meet Simulation Data","created":"2025-06-04","cited_by_count":28,"area":null},{"id":"2212.04819","title":"Phone2Proc: Bringing Robust Robots Into Our Chaotic World","created":"2022-12-08","cited_by_count":26,"area":null},{"id":"2503.22430","title":"MVSAnywhere: Zero-Shot Multi-View Stereo","created":"2025-03-28","cited_by_count":26,"area":null},{"id":"2602.11598","title":"ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation","created":"2026-02-12","cited_by_count":25,"area":null},{"id":"2408.13711","title":"SceneDreamer360: Text-Driven 3D-Consistent Scene Generation with Panoramic Gaussian Splatting","created":"2024-08-25","cited_by_count":24,"area":null},{"id":"2412.06250","title":"Splatter-360: Generalizable 360$^{\\circ}$ Gaussian Splatting for Wide-baseline Panoramic Images","created":"2024-12-09","cited_by_count":24,"area":null},{"id":"2210.14791","title":"ViNL: Visual Navigation and Locomotion Over Obstacles","created":"2022-10-26","cited_by_count":23,"area":null},{"id":"2406.13807","title":"AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding","created":"2024-06-19","cited_by_count":23,"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":"2504.21853","title":"A Survey of Interactive Generative Video","created":"2025-04-30","cited_by_count":23,"area":null},{"id":"2207.11365","title":"EgoEnv: Human-centric environment representations from egocentric video","created":"2022-07-22","cited_by_count":22,"area":null},{"id":"2212.02497","title":"PEANUT: Predicting and Navigating to Unseen Targets","created":"2022-12-05","cited_by_count":22,"area":null},{"id":"2310.07473","title":"FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation","created":"2023-10-11","cited_by_count":22,"area":null},{"id":"2411.17030","title":"g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks","created":"2024-11-26","cited_by_count":22,"area":null},{"id":"2502.02548","title":"Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation","created":"2025-02-04","cited_by_count":22,"area":null},{"id":"2510.15352","title":"GaussGym: An open-source real-to-sim framework for learning locomotion from pixels","created":"2025-10-17","cited_by_count":22,"area":null},{"id":"2511.10560","title":"OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer","created":"2025-11-13","cited_by_count":22,"area":null},{"id":"2506.04633","title":"Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations","created":"2025-06-05","cited_by_count":21,"area":null},{"id":"2603.03283","title":"Utonia: Toward One Encoder for All Point Clouds","created":"2026-03-03","cited_by_count":21,"area":null},{"id":"2306.03236","title":"A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2312.01990","title":"SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust Attention","created":"2023-12-04","cited_by_count":20,"area":null},{"id":"2403.18821","title":"Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark","created":"2024-03-27","cited_by_count":20,"area":null},{"id":"2404.01300","title":"NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields","created":"2024-04-01","cited_by_count":20,"area":null},{"id":"2412.08467","title":"Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel","created":"2024-12-11","cited_by_count":20,"area":null},{"id":"2509.10813","title":"InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts","created":"2025-09-13","cited_by_count":20,"area":null},{"id":"2512.00565","title":"Describe Anything Anywhere At Any Moment","created":"2025-11-29","cited_by_count":19,"area":null},{"id":"2210.05064","title":"VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement","created":"2022-10-11","cited_by_count":18,"area":null},{"id":"2211.09960","title":"Ask4Help: Learning to Leverage an Expert for Embodied Tasks","created":"2022-11-18","cited_by_count":18,"area":null},{"id":"2303.11329","title":"Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation","created":"2023-03-20","cited_by_count":18,"area":null}],"next_cursor":"100"}