{"total":122,"rows":[{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365,"area":"agents"},{"id":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204,"area":null},{"id":"2409.18125","title":"LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness","created":"2024-09-26","cited_by_count":183,"area":"mllm"},{"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":"2309.05251","title":"Multi3DRefer: Grounding Text Description to Multiple 3D Objects","created":"2023-09-11","cited_by_count":146,"area":null},{"id":"2412.00493","title":"Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding","created":"2024-11-30","cited_by_count":138,"area":"mllm"},{"id":"2503.22976","title":"From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D","created":"2025-03-29","cited_by_count":138,"area":"mllm"},{"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":"2505.24625","title":"Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors","created":"2025-05-30","cited_by_count":120,"area":"mllm"},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115,"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":"2506.01946","title":"3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding","created":"2025-06-02","cited_by_count":70,"area":"lr"},{"id":"2508.13073","title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","created":"2025-08-18","cited_by_count":69,"area":"vla"},{"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":"2309.15596","title":"PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation","created":"2023-09-27","cited_by_count":56,"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":"2409.02389","title":"Multi-modal Situated Reasoning in 3D Scenes","created":"2024-09-04","cited_by_count":51,"area":"lr"},{"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":"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":"2407.01525","title":"ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities","created":"2024-07-01","cited_by_count":47,"area":"lr"},{"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":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2406.07113","title":"Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph","created":"2024-06-11","cited_by_count":32,"area":null},{"id":"2405.17427","title":"Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model","created":"2024-05-27","cited_by_count":28,"area":"lr"},{"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":"2307.13363","title":"3DRP-Net: 3D Relative Position-aware Network for 3D Visual Grounding","created":"2023-07-25","cited_by_count":25,"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":"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":"2407.06084","title":"3D Vision and Language Pretraining with Large-Scale Synthetic Data","created":"2024-07-08","cited_by_count":21,"area":"mllm"},{"id":"2407.05363","title":"Multi-branch Collaborative Learning Network for 3D Visual Grounding","created":"2024-07-07","cited_by_count":20,"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":"2309.02224","title":"Dense Object Grounding in 3D Scenes","created":"2023-09-05","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":"2310.06214","title":"CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding","created":"2023-10-10","cited_by_count":13,"area":"lr"},{"id":"2502.15011","title":"CrossOver: 3D Scene Cross-Modal Alignment","created":"2025-02-20","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":"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":"2504.18684","title":"SORT3D: Spatial Object-centric Reasoning Toolbox for Zero-Shot 3D Grounding Using Large Language Models","created":"2025-04-25","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":"2508.11952","title":"UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding","created":"2025-08-16","cited_by_count":10,"area":null},{"id":"2510.01049","title":"KeySG: Hierarchical Keyframe-Based 3D Scene Graphs","created":"2025-10-01","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":"2503.03190","title":"DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering","created":"2025-03-05","cited_by_count":9,"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":"2506.05318","title":"Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs","created":"2025-06-05","cited_by_count":8,"area":"mllm"},{"id":"2601.11442","title":"Map2Thought: Explicit 3D Spatial Reasoning via Metric Cognitive Maps","created":"2026-01-16","cited_by_count":8,"area":"lr"},{"id":"2501.01366","title":"ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding","created":"2025-01-02","cited_by_count":7,"area":null},{"id":"2603.19235","title":"Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding","created":"2026-03-19","cited_by_count":7,"area":"lr"},{"id":"2503.23024","title":"Empowering Large Language Models with 3D Situation Awareness","created":"2025-03-29","cited_by_count":6,"area":null},{"id":"2604.11789","title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","created":"2026-04-13","cited_by_count":6,"area":"lr"},{"id":"2408.03516","title":"Query3D: LLM-Powered Open-Vocabulary Scene Segmentation with Language Embedded 3D Gaussian","created":"2024-08-07","cited_by_count":5,"area":null},{"id":"2503.19914","title":"Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Models","created":"2025-03-25","cited_by_count":5,"area":"diffusion"},{"id":"2506.09935","title":"LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning","created":"2025-06-11","cited_by_count":5,"area":"mllm"},{"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":"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":"2404.16845","title":"HaLo-NeRF: Learning Geometry-Guided Semantics for Exploring Unconstrained Photo Collections","created":"2024-02-14","cited_by_count":4,"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":"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":"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":"2506.21188","title":"GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding","created":"2025-06-26","cited_by_count":4,"area":"lr"},{"id":"2509.24385","title":"Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction-Reasoning Synergy","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"id":"2604.05695","title":"Let Geometry GUIDE: Layer-wise Unrolling of Geometric Priors in Multimodal LLMs","created":"2026-04-07","cited_by_count":4,"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":"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":"2407.02846","title":"Multi-Task Domain Adaptation for Language Grounding with 3D Objects","created":"2024-07-03","cited_by_count":2,"area":null},{"id":"2408.13499","title":"R2G: Reasoning to Ground in 3D Scenes","created":"2024-08-24","cited_by_count":2,"area":null},{"id":"2504.12599","title":"3DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentation","created":"2025-04-17","cited_by_count":2,"area":"distill"},{"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":"2507.09334","title":"Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding","created":"2025-07-12","cited_by_count":2,"area":"mllm"},{"id":"2602.03361","title":"Z3D: Zero-Shot 3D Visual Grounding from Images","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2603.27507","title":"Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM","created":"2026-03-29","cited_by_count":2,"area":"mllm"},{"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":"2507.20110","title":"NeuroVoxel-LM: Language-Aligned 3D Perception via Dynamic Voxelization and Meta-Embedding","created":"2025-07-27","cited_by_count":1,"area":"mllm"},{"id":"2508.17044","title":"M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environments","created":"2025-08-23","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":"2601.14895","title":"SpatialMem: Metric-Aligned Long-Horizon Video Memory for Language Grounding and QA","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2602.00637","title":"VIZOR: Viewpoint-Invariant Zero-Shot Scene Graph Generation for 3D Scene Reasoning","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2602.03059","title":"From Speech-to-Spatial: Grounding Utterances on A Live Shared View with Augmented Reality","created":"2026-02-03","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":"2603.04976","title":"3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding","created":"2026-03-05","cited_by_count":1,"area":"lr"},{"id":"2603.24721","title":"Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models","created":"2026-03-25","cited_by_count":1,"area":"lr"},{"id":"2604.03296","title":"3D-IDE: 3D Implicit Depth Emergent","created":"2026-03-28","cited_by_count":1,"area":"mllm"},{"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":"2504.08307","title":"DSM: Constructing a Diverse Semantic Map for 3D Visual Grounding","created":"2025-04-11","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}],"next_cursor":"100"}