{"total":78,"rows":[{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365,"area":"agents"},{"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":"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":"2503.23463","title":"OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model","created":"2025-03-30","cited_by_count":176,"area":"vla"},{"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":"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":"2403.18036","title":"Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance","created":"2024-03-26","cited_by_count":80,"area":"diffusion"},{"id":"2501.01163","title":"3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer","created":"2025-01-02","cited_by_count":68,"area":"mllm"},{"id":"2504.01901","title":"Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness","created":"2025-04-02","cited_by_count":63,"area":"mllm"},{"id":"2409.02389","title":"Multi-modal Situated Reasoning in 3D Scenes","created":"2024-09-04","cited_by_count":51,"area":"lr"},{"id":"2407.01525","title":"ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities","created":"2024-07-01","cited_by_count":47,"area":"lr"},{"id":"2405.10255","title":"When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models","created":"2024-05-16","cited_by_count":43,"area":"mllm"},{"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":"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":"2412.01292","title":"LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences","created":"2024-12-02","cited_by_count":38,"area":"mllm"},{"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":"2309.02224","title":"Dense Object Grounding in 3D Scenes","created":"2023-09-05","cited_by_count":15,"area":null},{"id":"2505.15232","title":"DC-Scene: Data-Centric Learning for 3D Scene Understanding","created":"2025-05-21","cited_by_count":15,"area":null},{"id":"2312.01529","title":"T3D: Advancing 3D Medical Vision-Language Pre-training by Learning Multi-View Visual Consistency","created":"2023-12-03","cited_by_count":14,"area":"mllm"},{"id":"2504.09518","title":"3D CoCa: Contrastive Learners are 3D Captioners","created":"2025-04-13","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":"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":"2507.00886","title":"GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond","created":"2025-07-01","cited_by_count":12,"area":"lr"},{"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":"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":"2311.17851","title":"Leveraging VLM-Based Pipelines to Annotate 3D Objects","created":"2023-11-29","cited_by_count":10,"area":"mllm"},{"id":"2403.07469","title":"A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes","created":"2024-03-12","cited_by_count":10,"area":null},{"id":"2411.19774","title":"PerLA: Perceptive 3D Language Assistant","created":"2024-11-29","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":"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":"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":"2511.22103","title":"MoE3D: Mixture of Experts meets Multi-Modal 3D Understanding","created":"2025-11-27","cited_by_count":6,"area":"moe"},{"id":"2408.06662","title":"Bi-directional Contextual Attention for 3D Dense Captioning","created":"2024-08-13","cited_by_count":5,"area":null},{"id":"2412.06613","title":"3D Spatial Understanding in MLLMs: Disambiguation and Evaluation","created":"2024-12-09","cited_by_count":5,"area":"mllm"},{"id":"2510.18054","title":"HouseTour: A Virtual Real Estate A(I)gent","created":"2025-10-20","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":"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":"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":"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":"2408.11747","title":"OE3DIS: Open-Ended 3D Point Cloud Instance Segmentation","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2411.10639","title":"MTA: Multimodal Task Alignment for BEV Perception and Captioning","created":"2024-11-16","cited_by_count":3,"area":null},{"id":"2601.06496","title":"3D CoCa v2: Contrastive Learners with Test-Time Search for Generalizable Spatial Intelligence","created":"2026-01-10","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":"2603.09173","title":"Point Cloud as a Foreign Language for Multi-modal Large Language Model","created":"2026-03-10","cited_by_count":2,"area":"mllm"},{"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":"2606.01215","title":"Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs","created":"2026-05-31","cited_by_count":2,"area":"lr"},{"id":"2304.10224","title":"Multi-view Vision-Prompt Fusion Network: Can 2D Pre-trained Model Boost 3D Point Cloud Data-scarce Learning?","created":"2023-04-20","cited_by_count":1,"area":null},{"id":"2403.19386","title":"PointCloud-Text Matching: Benchmark Datasets and a Baseline","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2408.04909","title":"Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis","created":"2024-08-09","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":"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":"2606.06485","title":"PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding","created":"2026-06-04","cited_by_count":1,"area":"mllm"},{"id":"2609.38177","title":"Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering","created":"2026-09-29","cited_by_count":1,"area":"mllm"},{"id":"2311.16501","title":"Context-Aware Indoor Point Cloud Object Generation through User Instructions","created":"2023-11-26","cited_by_count":0,"area":null},{"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":"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":"2506.14238","title":"Unified Representation Space for 3D Visual Grounding","created":"2025-06-17","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":"2511.21191","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":"2511.22961","title":"HMR3D: Hierarchical Multimodal Representation for 3D Scene Understanding with Large Vision-Language Model","created":"2025-11-28","cited_by_count":0,"area":"mllm"},{"id":"2604.01907","title":"Lifting Unlabeled Internet-level Data for 3D Scene Understanding","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.08808","title":"Curvature-Aware Captioning:Leveraging Geodesic Attention for 3D Scene Understanding","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.19776","title":"Occ-VLM: Occupancy Grounded Vision Language Model for Indoor Scene Understanding","created":"2026-06-18","cited_by_count":0,"area":"mllm"},{"id":"2607.02908","title":"Holo-Captioning: Toward the Text Equivalent of 3D Scenes","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.06097","title":"PVCap: Towards Accurate 3D Dense Captioning via PseudoCap and VoxelCapNet","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.21595","title":"3D-Aware VLMs with Implicit and Explicit Geometries","created":"2026-07-23","cited_by_count":0,"area":"mllm"},{"id":"2608.00110","title":"Distill What RGB Can Recover: Privileged 3D Evidence for RGB-Only Vision-Language Models","created":"2026-07-31","cited_by_count":0,"area":"mllm"},{"id":"2608.05137","title":"SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.31023","title":"SMG: Semantic Motion Graph for Monocular Dynamic Gaussian Splatting","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.31595","title":"GraphWrit3R: End-to-End 3D Scene Graph Writing","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.20610","title":"Can Learning to Answer Spatial Questions Improve Novel-View Generation?","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}