{"total":99,"rows":[{"id":"2311.18651","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning","created":"2023-11-30","cited_by_count":210,"area":"lr"},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194,"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":"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":"2306.06687","title":"LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark","created":"2023-06-11","cited_by_count":169,"area":null},{"id":"2309.05251","title":"Multi3DRefer: Grounding Text Description to Multiple 3D Objects","created":"2023-09-11","cited_by_count":146,"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":"2501.01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","created":"2025-01-02","cited_by_count":109,"area":"mllm"},{"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":"2311.15383","title":"Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding","created":"2023-11-26","cited_by_count":64,"area":null},{"id":"2504.01901","title":"Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness","created":"2025-04-02","cited_by_count":63,"area":"mllm"},{"id":"2503.00513","title":"Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning","created":"2025-03-01","cited_by_count":51,"area":"mllm"},{"id":"2309.02999","title":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning","created":"2023-09-06","cited_by_count":39,"area":null},{"id":"2308.16632","title":"3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation","created":"2023-08-31","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":"2411.19235","title":"InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception","created":"2024-11-28","cited_by_count":35,"area":null},{"id":"2212.06250","title":"ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes","created":"2022-12-12","cited_by_count":32,"area":null},{"id":"2309.04561","title":"Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding","created":"2023-09-08","cited_by_count":32,"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":"2410.00255","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":"2508.00265","title":"Multimodal Referring Segmentation: A Survey","created":"2025-08-01","cited_by_count":22,"area":null},{"id":"2407.05363","title":"Multi-branch Collaborative Learning Network for 3D Visual Grounding","created":"2024-07-07","cited_by_count":20,"area":null},{"id":"2310.18773","title":"CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data","created":"2023-10-28","cited_by_count":18,"area":null},{"id":"2405.12821","title":"Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression Comprehension","created":"2024-05-21","cited_by_count":18,"area":null},{"id":"2407.20664","title":"3D-GRES: Generalized 3D Referring Expression Segmentation","created":"2024-07-30","cited_by_count":18,"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":"2503.18135","title":"MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation","created":"2025-03-23","cited_by_count":16,"area":"lr"},{"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":"2503.22436","title":"NuGrounding: A Multi-View 3D Visual Grounding Framework in Autonomous Driving","created":"2025-03-28","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":"2506.21924","title":"SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding","created":"2025-06-27","cited_by_count":12,"area":"lr"},{"id":"2511.01755","title":"3EED: Ground Everything Everywhere in 3D","created":"2025-11-03","cited_by_count":12,"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":"2507.07781","title":"SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes","created":"2025-07-10","cited_by_count":11,"area":"lr"},{"id":"2305.13876","title":"Cross3DVG: Cross-Dataset 3D Visual Grounding on Different RGB-D Scans","created":"2023-05-23","cited_by_count":10,"area":null},{"id":"2501.09428","title":"AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring","created":"2025-01-16","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":"2304.05645","title":"WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language","created":"2023-04-12","cited_by_count":8,"area":null},{"id":"2502.01401","title":"Language-to-Space Programming for Training-Free 3D Visual Grounding","created":"2025-02-03","cited_by_count":8,"area":null},{"id":"2503.02593","title":"CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Framework","created":"2025-03-04","cited_by_count":8,"area":null},{"id":"2507.11261","title":"ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition","created":"2025-07-15","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":"2501.01366","title":"ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding","created":"2025-01-02","cited_by_count":7,"area":null},{"id":"2308.11887","title":"A Unified Framework for 3D Point Cloud Visual Grounding","created":"2023-08-23","cited_by_count":6,"area":null},{"id":"2512.01352","title":"OpenBox: Annotate Any Bounding Boxes in 3D","created":"2025-12-01","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":"2405.15274","title":"Talk to Parallel LiDARs: A Human-LiDAR Interaction Method Based on 3D Visual Grounding","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2410.13294","title":"LESS: Label-Efficient and Single-Stage Referring 3D Segmentation","created":"2024-10-17","cited_by_count":5,"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":"2512.08135","title":"CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning","created":"2025-12-09","cited_by_count":5,"area":"lr"},{"id":"2403.08182","title":"SeCG: Semantic-Enhanced 3D Visual Grounding via Cross-modal Graph Attention","created":"2024-03-13","cited_by_count":4,"area":null},{"id":"2505.21079","title":"Uni3D-MoE: Scalable Multimodal 3D Scene Understanding via Mixture of Experts","created":"2025-05-27","cited_by_count":4,"area":"mllm"},{"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":"2312.09625","title":"Weakly-Supervised 3D Visual Grounding based on Visual Language Alignment","created":"2023-12-15","cited_by_count":3,"area":"mllm"},{"id":"2403.16539","title":"Data-Efficient 3D Visual Grounding via Order-Aware Referring","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2404.17845","title":"Instance-free Text to Point Cloud Localization with Relative Position Awareness","created":"2024-04-27","cited_by_count":3,"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":"2507.14555","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":"2505.22429","title":"Zero-Shot 3D Visual Grounding from Vision-Language Models","created":"2025-05-28","cited_by_count":2,"area":"mllm"},{"id":"2506.13629","title":"FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understanding","created":"2025-06-16","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":"2509.07825","title":"Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model","created":"2025-09-09","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":"2411.04351","title":"LidaRefer: Context-aware Outdoor 3D Visual Grounding for Autonomous Driving","created":"2024-11-07","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":"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":"2510.14965","title":"ChangingGrounding: 3D Visual Grounding in Changing Scenes","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2603.02896","title":"3D-DRES: Detailed 3D Referring Expression Segmentation","created":"2026-03-03","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":"2604.00528","title":"Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding","created":"2026-04-01","cited_by_count":1,"area":"lr"},{"id":"2404.11064","title":"Rethinking 3D Dense Caption and Visual Grounding in A Unified Framework through Prompt-based Localization","created":"2024-04-17","cited_by_count":0,"area":null},{"id":"2406.08907","title":"Dual Attribute-Spatial Relation Alignment for 3D Visual Grounding","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2407.14491","title":"PD-APE: A Parallel Decoding Framework with Adaptive Position Encoding for 3D Visual Grounding","created":"2024-07-19","cited_by_count":0,"area":"inference"},{"id":"2411.18666","title":"3D Scene Graph Guided Vision-Language Pre-training","created":"2024-11-27","cited_by_count":0,"area":"mllm"},{"id":"2503.08336","title":"Talk2PC: Enhancing 3D Visual Grounding through LiDAR and Radar Point Clouds Fusion for Autonomous Driving","created":"2025-03-11","cited_by_count":0,"area":"driving"},{"id":"2504.08307","title":"DSM: Constructing a Diverse Semantic Map for 3D Visual Grounding","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2505.04058","title":"LSVG: Language-Guided Scene Graphs with 2D-Assisted Multi-Modal Encoding for 3D Visual Grounding","created":"2025-05-07","cited_by_count":0,"area":null},{"id":"2506.14238","title":"Unified Representation Space for 3D Visual Grounding","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2506.20991","title":"MR-COSMO: Visual-Text Memory Recall and Direct CrOSs-MOdal Alignment Method for Query-Driven 3D Segmentation","created":"2025-06-26","cited_by_count":0,"area":"mllm"},{"id":"2510.10194","title":"B2N3D: Progressive Learning from Binary to N-ary Relationships for 3D Object Grounding","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2511.21191","title":"Scenes as Tokens: Multi-Scale Normal Distributions Transform Tokenizer for General 3D Vision-Language Understanding","created":"2025-11-26","cited_by_count":0,"area":"mllm"},{"id":"2601.08811","title":"Reasoning Matters for 3D Visual Grounding","created":"2026-01-13","cited_by_count":0,"area":"lr"},{"id":"2603.06250","title":"Hierarchical Collaborative Fusion for 3D Instance-aware Referring Expression Segmentation","created":"2026-03-06","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":"2604.26261","title":"Multiple Consistent 2D-3D Mappings for Robust Zero-Shot 3D Visual Grounding","created":"2026-04-29","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},{"id":"2605.24622","title":"PoseRefer: Pathway-Local Parameters for Semantically Grounded Reference Resolution","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.31148","title":"PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.04568","title":"Talk2Sensors: 3D Visual Grounding in Autonomous Driving via Sensor-Adaptive Physical Cue Matching","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.05137","title":"SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.05569","title":"CoordRefer: Coordinate-Aware 3D Visual Grounding from Multiview Images","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.16011","title":"ReRef-3D: A Benchmark for Spatial Referring Expression-Guided 3D Scene Rearrangement","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.36875","title":"S4VY: Segment Anything in Feed-Forward 4D Visual Geometry","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.18356","title":"Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}