{"total":93,"rows":[{"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":"2507.11539","title":"Streaming 4D Visual Geometry Transformer","created":"2025-07-15","cited_by_count":161,"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":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115,"area":null},{"id":"2405.20853","title":"MeshXL: Neural Coordinate Field for Generative 3D Foundation Models","created":"2024-05-31","cited_by_count":103,"area":null},{"id":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","cited_by_count":89,"area":null},{"id":"2412.04383","title":"SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding","created":"2024-12-05","cited_by_count":67,"area":null},{"id":"2403.14158","title":"Volumetric Environment Representation for Vision-Language Navigation","created":"2024-03-21","cited_by_count":63,"area":null},{"id":"2410.13860","title":"VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding","created":"2024-10-17","cited_by_count":56,"area":null},{"id":"2507.04047","title":"Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation","created":"2025-07-05","cited_by_count":51,"area":null},{"id":"2509.19297","title":"VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction","created":"2025-09-23","cited_by_count":48,"area":null},{"id":"2412.04380","title":"EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding","created":"2024-12-05","cited_by_count":45,"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":"2406.05132","title":"3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination","created":"2024-06-07","cited_by_count":36,"area":null},{"id":"2504.07958","title":"Detect Anything 3D in the Wild","created":"2025-04-10","cited_by_count":33,"area":null},{"id":"2507.22412","title":"UAVScenes: A Multi-Modal Dataset for UAVs","created":"2025-07-30","cited_by_count":27,"area":null},{"id":"2405.13659","title":"EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views","created":"2024-05-22","cited_by_count":26,"area":null},{"id":"2406.05785","title":"A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions","created":"2024-06-09","cited_by_count":25,"area":null},{"id":"2503.22420","title":"Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis","created":"2025-03-28","cited_by_count":23,"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":"2407.15087","title":"Navigation Instruction Generation with BEV Perception and Large Language Models","created":"2024-07-21","cited_by_count":21,"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":"2502.00392","title":"RefDrone: A Challenging Benchmark for Referring Expression Comprehension in Drone Scenes","created":"2025-02-01","cited_by_count":19,"area":null},{"id":"2411.16072","title":"Language Driven Occupancy Prediction","created":"2024-11-25","cited_by_count":17,"area":null},{"id":"2409.19972","title":"DAOcc: 3D Object Detection Assisted Multi-Sensor Fusion for 3D Occupancy Prediction","created":"2024-09-30","cited_by_count":15,"area":null},{"id":"2406.10527","title":"Panoptic-FlashOcc: An Efficient Baseline to Marry Semantic Occupancy with Panoptic via Instance Center","created":"2024-06-15","cited_by_count":14,"area":null},{"id":"2506.09378","title":"UniForward: Unified 3D Scene and Semantic Field Reconstruction via Feed-Forward Gaussian Splatting from Only Sparse-View Images","created":"2025-06-11","cited_by_count":14,"area":null},{"id":"2505.04965","title":"DenseGrounding: Improving Dense Language-Vision Semantics for Ego-Centric 3D Visual Grounding","created":"2025-05-08","cited_by_count":12,"area":null},{"id":"2511.01755","title":"3EED: Ground Everything Everywhere in 3D","created":"2025-11-03","cited_by_count":12,"area":null},{"id":"2409.19650","title":"Grounding 3D Scene Affordance From Egocentric Interactions","created":"2024-09-29","cited_by_count":11,"area":null},{"id":"2505.20294","title":"GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes","created":"2025-05-26","cited_by_count":11,"area":null},{"id":"2411.14869","title":"BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence","created":"2024-11-22","cited_by_count":10,"area":null},{"id":"2504.19500","title":"Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding","created":"2025-04-28","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":"2408.04034","title":"Task-oriented Sequential Grounding and Navigation in 3D Scenes","created":"2024-08-07","cited_by_count":9,"area":null},{"id":"2412.01398","title":"Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description","created":"2024-12-02","cited_by_count":9,"area":null},{"id":"2502.19128","title":"SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation","created":"2025-02-26","cited_by_count":9,"area":null},{"id":"2503.03190","title":"DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering","created":"2025-03-05","cited_by_count":9,"area":null},{"id":"2505.05288","title":"PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes","created":"2025-05-08","cited_by_count":9,"area":null},{"id":"2508.02261","title":"SplatSSC: Decoupled Depth-Guided Gaussian Splatting for Semantic Scene Completion","created":"2025-08-04","cited_by_count":9,"area":null},{"id":"2412.00730","title":"SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark","created":"2024-12-01","cited_by_count":8,"area":null},{"id":"2501.16684","title":"SliceOcc: Indoor 3D Semantic Occupancy Prediction with Vertical Slice Representation","created":"2025-01-28","cited_by_count":8,"area":null},{"id":"2503.10170","title":"GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction","created":"2025-03-13","cited_by_count":8,"area":null},{"id":"2412.19142","title":"CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting","created":"2024-12-26","cited_by_count":7,"area":null},{"id":"2503.12955","title":"HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding","created":"2025-03-17","cited_by_count":6,"area":null},{"id":"2503.23024","title":"Empowering Large Language Models with 3D Situation Awareness","created":"2025-03-29","cited_by_count":6,"area":null},{"id":"2604.07296","title":"OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence","created":"2026-04-08","cited_by_count":6,"area":null},{"id":"2502.19247","title":"ProxyTransformation: Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Grounding","created":"2025-02-26","cited_by_count":5,"area":null},{"id":"2508.07842","title":"DETACH: Cross-domain Learning for Long-Horizon Tasks via Mixture of Disentangled Experts","created":"2025-08-11","cited_by_count":5,"area":null},{"id":"2506.05199","title":"DEGround: An Effective Baseline for Ego-centric 3D Visual Grounding with a Homogeneous Framework","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2605.30115","title":"Large Depth Completion Model from Sparse Observations","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2508.00169","title":"Robust 3D Object Detection using Probabilistic Point Clouds from Single-Photon LiDARs","created":"2025-07-31","cited_by_count":3,"area":null},{"id":"2503.05086","title":"Fake It To Make It: Virtual Multiviews to Enhance Monocular Indoor Semantic Scene Completion","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2505.12606","title":"Diff-MM: Exploring Pre-trained Text-to-Image Generation Model for Unified Multi-modal Object Tracking","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2507.14904","title":"TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP","created":"2025-07-20","cited_by_count":2,"area":null},{"id":"2511.17048","title":"RoomPlanner: Explicit Layout Planner for Easier LLM-Driven 3D Room Generation","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2603.09798","title":"Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2606.27876","title":"SpatialUAV: Benchmarking Spatial Intelligence for Low-Altitude UAV Perception, Collaboration, and Motion","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2503.08367","title":"Embodied Crowd Counting","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2507.18331","title":"Boosting Multi-View Indoor 3D Object Detection via Adaptive 3D Volume Construction","created":"2025-07-24","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":"2603.08131","title":"UniGround: Universal 3D Visual Grounding via Training-Free Scene Parsing","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2604.10573","title":"Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2604.19673","title":"InHabit: Leveraging Image Foundation Models for Scalable 3D Human Placement","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.01498","title":"Towards Visual Query Localization in the 3D World","created":"2026-05-02","cited_by_count":1,"area":null},{"id":"2605.16258","title":"IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2606.11909","title":"Embodied-BenchClaw: An Autonomous Multi-Agent System for Embodied Spatial Intelligence Benchmark Construction","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.22971","title":"Humanoid-OmniOcc: Stereo-Based Full-View Occupancy Dataset for Embodied AI","created":"2026-06-22","cited_by_count":1,"area":null},{"id":"2411.18644","title":"Scene Co-pilot: Procedural Text to Video Generation with Human in the Loop","created":"2024-11-26","cited_by_count":0,"area":null},{"id":"2502.09624","title":"Efficient and Trustworthy Block Propagation for Blockchain-enabled Mobile Embodied AI Networks: A Graph Resfusion Approach","created":"2025-01-26","cited_by_count":0,"area":null},{"id":"2504.10048","title":"Multi-Object Grounding via Hierarchical Contrastive Siamese Transformers","created":"2025-04-14","cited_by_count":0,"area":null},{"id":"2506.21056","title":"SAMURAI: Shape-Aware Multimodal Retrieval for 3D Object Identification","created":"2025-06-26","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":"2512.03418","title":"YOLOA: Real-Time Affordance Detection via LLM Adapter","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2512.16077","title":"Auto-Vocabulary 3D Object Detection","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2603.14076","title":"SGR-OCC: Evolving Monocular Priors for Embodied 3D Occupancy Prediction via Soft-Gating Lifting and Semantic-Adaptive Geometric Refinement","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2605.12542","title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.14923","title":"SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.28132","title":"Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.20946","title":"Scaling Diverse Language Generation for 3D Visual Grounding","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.02908","title":"Holo-Captioning: Toward the Text Equivalent of 3D Scenes","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.02921","title":"R3D: Quantitative 3D Spatial Reasoning for Egocentric Wearables","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.28935","title":"Group-wise Supervision with Focal-Dice Loss for Long-Tailed Indoor Semantic Occupancy Prediction","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.02432","title":"Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioning","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.08696","title":"OccAnyScene: Towards Unified Indoor-Outdoor 3D Occupancy Prediction","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2608.09147","title":"RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.17257","title":"Exploring 2D backbone effects for indoor semantic occupancy prediction","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.23286","title":"RegVGGT: Sustainable Visual Geometry Grounding for Streaming via Regulated Memory","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.31716","title":"PanOVOcc: Panoramic Embodied Open-Vocabulary Occupancy Mapping with Long-term Spatial Voxel Memory","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.34833","title":"Multi-Scale Semantic Mapping in Urban Environments via Observation Calibration and Policy Dependence Regularization","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38864","title":"AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Tasks","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.13021","title":"EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}