{"total":109,"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":"2312.08168","title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","created":"2023-12-13","cited_by_count":175,"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":"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":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","cited_by_count":89,"area":null},{"id":"2405.11442","title":"Unifying 3D Vision-Language Understanding via Promptable Queries","created":"2024-05-19","cited_by_count":70,"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":"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":"2409.03757","title":"Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding","created":"2024-09-05","cited_by_count":49,"area":null},{"id":"2403.19589","title":"TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes","created":"2024-03-28","cited_by_count":40,"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":"2407.13761","title":"SegPoint: Segment Any Point Cloud via Large Language Model","created":"2024-07-18","cited_by_count":35,"area":null},{"id":"2406.07544","title":"Situational Awareness Matters in 3D Vision Language Reasoning","created":"2024-06-11","cited_by_count":33,"area":null},{"id":"2312.10763","title":"M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts","created":"2023-12-17","cited_by_count":32,"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":"2412.18450","title":"3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding","created":"2024-12-24","cited_by_count":27,"area":null},{"id":"2410.00255","title":"Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning","created":"2024-09-30","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":"2407.18244","title":"RefMask3D: Language-Guided Transformer for 3D Referring Segmentation","created":"2024-07-25","cited_by_count":25,"area":null},{"id":"2501.00358","title":"Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding","created":"2024-12-31","cited_by_count":24,"area":null},{"id":"2503.06271","title":"SplatTalk: 3D VQA with Gaussian Splatting","created":"2025-03-08","cited_by_count":24,"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":"2504.14151","title":"Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D","created":"2025-04-19","cited_by_count":23,"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":"2402.15933","title":"Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA","created":"2024-02-24","cited_by_count":21,"area":null},{"id":"2408.16662","title":"Space3D-Bench: Spatial 3D Question Answering Benchmark","created":"2024-08-29","cited_by_count":17,"area":null},{"id":"2502.10392","title":"TSP3D: Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding","created":"2025-02-14","cited_by_count":17,"area":null},{"id":"2405.18295","title":"Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention","created":"2024-05-28","cited_by_count":16,"area":null},{"id":"2407.03263","title":"A Unified Framework for 3D Scene Understanding","created":"2024-07-03","cited_by_count":15,"area":null},{"id":"2503.10745","title":"Unifying 2D and 3D Vision-Language Understanding","created":"2025-03-13","cited_by_count":15,"area":null},{"id":"2410.10799","title":"Towards Foundation Models for 3D Vision: How Close Are We?","created":"2024-10-14","cited_by_count":13,"area":null},{"id":"2507.08254","title":"Raptor: Scalable Train-Free Embeddings for 3D Medical Volumes Leveraging Pretrained 2D Foundation Models","created":"2025-07-11","cited_by_count":13,"area":null},{"id":"2508.03227","title":"Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing","created":"2025-08-05","cited_by_count":13,"area":null},{"id":"2310.15676","title":"Recent Advances in Multi-modal 3D Intelligence: A Comprehensive Survey and Evaluation","created":"2023-10-24","cited_by_count":12,"area":null},{"id":"2404.11525","title":"JointViT: Modeling Oxygen Saturation Levels with Joint Supervision on Long-Tailed OCTA","created":"2024-04-17","cited_by_count":12,"area":null},{"id":"2502.15011","title":"CrossOver: 3D Scene Cross-Modal Alignment","created":"2025-02-20","cited_by_count":12,"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":"2404.19221","title":"Transcrib3D: 3D Referring Expression Resolution through Large Language Models","created":"2024-04-30","cited_by_count":11,"area":null},{"id":"2412.02402","title":"RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation","created":"2024-12-03","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":"2506.03605","title":"Generating 6DoF Object Manipulation Trajectories from Action Description in Egocentric Vision","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2602.13191","title":"CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modeling","created":"2026-02-13","cited_by_count":11,"area":null},{"id":"2407.17398","title":"3D Question Answering for City Scene Understanding","created":"2024-07-24","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":"2312.03026","title":"Uni3DL: Unified Model for 3D and Language Understanding","created":"2023-12-05","cited_by_count":9,"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":"2411.19774","title":"PerLA: Perceptive 3D Language Assistant","created":"2024-11-29","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":"2411.13927","title":"Multimodal 3D Reasoning Segmentation with Complex Scenes","created":"2024-11-21","cited_by_count":8,"area":null},{"id":"2504.06553","title":"ASHiTA: Automatic Scene-grounded HIerarchical Task Analysis","created":"2025-04-09","cited_by_count":8,"area":null},{"id":"2505.12703","title":"SpatialLLM: From Multi-modality Data to Urban Spatial Intelligence","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2507.18678","title":"Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting","created":"2025-07-24","cited_by_count":8,"area":null},{"id":"2508.11058","title":"Advancing 3D Scene Understanding with MV-ScanQA Multi-View Reasoning Evaluation and TripAlign Pre-training Dataset","created":"2025-08-14","cited_by_count":8,"area":null},{"id":"2411.14594","title":"Solving Zero-Shot 3D Visual Grounding as Constraint Satisfaction Problems","created":"2024-11-21","cited_by_count":7,"area":null},{"id":"2502.20389","title":"From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2508.08199","title":"Generalizable Operating Room Expert with Multimodal Enhancement","created":"2025-08-11","cited_by_count":7,"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":"2404.13044","title":"Unified Scene Representation and Reconstruction for 3D Large Language Models","created":"2024-04-19","cited_by_count":5,"area":null},{"id":"2406.09126","title":"3D-AVS: LiDAR-based 3D Auto-Vocabulary Segmentation","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2501.01119","title":"Leverage Cross-Attention for End-to-End Open-Vocabulary Panoptic Reconstruction","created":"2025-01-02","cited_by_count":5,"area":null},{"id":"2501.08575","title":"GOTPR: General Outdoor Text-based Place Recognition Using Scene Graph Retrieval with OpenStreetMap","created":"2025-01-15","cited_by_count":5,"area":null},{"id":"2512.12622","title":"D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation","created":"2025-12-14","cited_by_count":5,"area":null},{"id":"2410.22306","title":"Multi-Object 3D Grounding with Dynamic Modules and Language-Informed Spatial Attention","created":"2024-10-29","cited_by_count":4,"area":null},{"id":"2503.17044","title":"ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail","created":"2025-03-21","cited_by_count":4,"area":null},{"id":"2506.04897","title":"From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2511.16567","title":"POMA-3D: The Point Map Way to 3D Scene Understanding","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2408.11747","title":"OE3DIS: Open-Ended 3D Point Cloud Instance Segmentation","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2507.12795","title":"City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning","created":"2025-07-17","cited_by_count":3,"area":null},{"id":"2507.14555","title":"Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions","created":"2025-07-19","cited_by_count":3,"area":null},{"id":"2512.20907","title":"PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding","created":"2025-12-24","cited_by_count":3,"area":null},{"id":"2601.05991","title":"3D Instruction Ambiguity Detection","created":"2026-01-09","cited_by_count":3,"area":null},{"id":"2503.12974","title":"Exploring 3D Reasoning-Driven Planning: From Implicit Human Intentions to Route-Aware Activity Planning","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2508.05269","title":"B4DL: A Benchmark for 4D LiDAR LLM in Spatio-Temporal Understanding","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2510.03200","title":"MonSTeR: a Unified Model for Motion, Scene, Text Retrieval","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2608.30821","title":"Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling","created":"2026-08-31","cited_by_count":2,"area":null},{"id":"2407.14419","title":"HOTS3D: Hyper-Spherical Optimal Transport for Semantic Alignment of Text-to-3D Generation","created":"2024-07-19","cited_by_count":1,"area":null},{"id":"2411.03405","title":"Fine-Grained Spatial and Verbal Losses for 3D Visual Grounding","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2507.12916","title":"Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2508.07904","title":"CTC Transcription Alignment of the Bullinger Letters: Automatic Improvement of Annotation Quality","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2509.16721","title":"Text-Scene: A Scene-to-Language Parsing Framework for 3D Scene Understanding","created":"2025-09-20","cited_by_count":1,"area":null},{"id":"2509.25528","title":"LLM-RG: Referential Grounding in Outdoor Scenarios using Large Language Models","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2510.14965","title":"ChangingGrounding: 3D Visual Grounding in Changing Scenes","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2511.14086","title":"Error-Driven Scene Editing for 3D Grounding in Large Language Models","created":"2025-11-18","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":"2607.03789","title":"G$^2$TAM: Geometry Grounded Track Anything Model","created":"2026-07-04","cited_by_count":1,"area":null},{"id":"2608.15710","title":"Beyond Single Object: Learning 3D Relations with Large Language Models","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2507.00669","title":"Audio-3DVG: Unified Audio -- Point Cloud Fusion for 3D Visual Grounding","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2508.05064","title":"A Study of the Framework and Real-World Applications of Language Embedding for 3D Scene Understanding","created":"2025-08-07","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":"2512.23020","title":"OpenGround: Planning-based Online Perception for Open-World 3D Visual Grounding","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2603.09632","title":"X-GS: An Extensible Framework for Perceiving and Thinking with 3D Gaussian Splatting","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.17753","title":"PC-CrossDiff: Point-Cluster Dual-Level Cross-Modal Differential Attention for Unified 3D Referring and Segmentation","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.01907","title":"Lifting Unlabeled Internet-level Data for 3D Scene Understanding","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.02546","title":"RGB-Pointmap Pretraining for Unified 3D Scene Understanding","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.21788","title":"SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching","created":"2026-05-20","cited_by_count":0,"area":null}],"next_cursor":"100"}