{"total":60,"rows":[{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365,"area":null},{"id":"2406.01584","title":"SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models","created":"2024-06-03","cited_by_count":311,"area":"lr"},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279,"area":"vla"},{"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":"2403.11401","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","created":"2024-03-18","cited_by_count":175,"area":"lr"},{"id":"2309.12311","title":"LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent","created":"2023-09-21","cited_by_count":135,"area":"agents"},{"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":"2312.10671","title":"Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance","created":"2023-12-17","cited_by_count":124,"area":null},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105,"area":null},{"id":"2403.15941","title":"Explore until Confident: Efficient Exploration for Embodied Question Answering","created":"2024-03-23","cited_by_count":74,"area":null},{"id":"2503.13111","title":"MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs","created":"2025-03-17","cited_by_count":73,"area":"mllm"},{"id":"2303.16894","title":"ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance","created":"2023-03-29","cited_by_count":70,"area":null},{"id":"2509.06266","title":"Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes","created":"2025-09-08","cited_by_count":63,"area":"lr"},{"id":"2304.04909","title":"SATR: Zero-Shot Semantic Segmentation of 3D Shapes","created":"2023-04-11","cited_by_count":62,"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":"2404.04242","title":"Physical Property Understanding from Language-Embedded Feature Fields","created":"2024-04-05","cited_by_count":48,"area":null},{"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":"2510.27606","title":"Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning","created":"2025-10-31","cited_by_count":41,"area":"lr"},{"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":"2406.07544","title":"Situational Awareness Matters in 3D Vision Language Reasoning","created":"2024-06-11","cited_by_count":33,"area":null},{"id":"2406.02548","title":"Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation","created":"2024-06-04","cited_by_count":30,"area":null},{"id":"2502.17425","title":"Introducing Visual Perception Token into Multimodal Large Language Model","created":"2025-02-24","cited_by_count":26,"area":"mllm"},{"id":"2505.22657","title":"3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model","created":"2025-05-28","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":"2410.20220","title":"Neural Fields in Robotics: A Survey","created":"2024-10-26","cited_by_count":21,"area":null},{"id":"2404.01300","title":"NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields","created":"2024-04-01","cited_by_count":20,"area":null},{"id":"2506.23329","title":"IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering","created":"2025-06-29","cited_by_count":19,"area":"mllm"},{"id":"2408.16662","title":"Space3D-Bench: Spatial 3D Question Answering Benchmark","created":"2024-08-29","cited_by_count":17,"area":null},{"id":"2310.17914","title":"3D-Aware Visual Question Answering about Parts, Poses and Occlusions","created":"2023-10-27","cited_by_count":16,"area":null},{"id":"2504.15280","title":"Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs","created":"2025-04-21","cited_by_count":16,"area":"mllm"},{"id":"2410.20263","title":"EfficientEQA: An Efficient Approach to Open-Vocabulary Embodied Question Answering","created":"2024-10-26","cited_by_count":15,"area":null},{"id":"2601.15275","title":"RayRoPE: Projective Ray Positional Encoding for Multi-view Attention","created":"2026-01-21","cited_by_count":14,"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":"2504.07836","title":"AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations","created":"2025-04-10","cited_by_count":10,"area":null},{"id":"2402.11141","title":"Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Review","created":"2024-02-17","cited_by_count":9,"area":null},{"id":"2404.03836","title":"PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Model","created":"2024-04-04","cited_by_count":9,"area":"mllm"},{"id":"2311.13125","title":"DAE-Net: Deforming Auto-Encoder for fine-grained shape co-segmentation","created":"2023-11-22","cited_by_count":7,"area":null},{"id":"2406.11840","title":"LLaNA: Large Language and NeRF Assistant","created":"2024-06-17","cited_by_count":6,"area":"mllm"},{"id":"2406.16038","title":"LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Rendering and Control","created":"2024-06-23","cited_by_count":6,"area":null},{"id":"2407.14279","title":"OpenSU3D: Open World 3D Scene Understanding using Foundation Models","created":"2024-07-19","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":"2510.18054","title":"HouseTour: A Virtual Real Estate A(I)gent","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2607.08970","title":"MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs","created":"2026-07-09","cited_by_count":4,"area":null},{"id":"2503.04444","title":"ToFu: Visual Tokens Reduction via Fusion for Multi-modal, Multi-patch, Multi-image Task","created":"2025-03-06","cited_by_count":3,"area":"mllm"},{"id":"2512.02340","title":"Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective","created":"2025-12-02","cited_by_count":3,"area":"lr"},{"id":"2603.16506","title":"VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations","created":"2026-03-17","cited_by_count":3,"area":"lr"},{"id":"2604.08645","title":"3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding","created":"2026-04-09","cited_by_count":3,"area":"mllm"},{"id":"2403.11812","title":"Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery","created":"2024-03-18","cited_by_count":2,"area":null},{"id":"2407.03842","title":"Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation","created":"2024-07-04","cited_by_count":1,"area":null},{"id":"2504.08531","title":"Embodied Image Captioning: Self-supervised Learning Agents for Spatially Coherent Image Descriptions","created":"2025-04-11","cited_by_count":1,"area":"agents"},{"id":"2603.24257","title":"Memory-Augmented Vision-Language Agents for Persistent and Semantically Consistent Object Captioning","created":"2026-03-25","cited_by_count":1,"area":"mllm"},{"id":"2607.12319","title":"DM-KG: A Novel Method for Boosting Spatial Cognition of Vision-Language Models in Street View Imagery","created":"2026-07-14","cited_by_count":1,"area":"lr"},{"id":"2504.13995","title":"Scaling LLaNA: Advancing NeRF-Language Understanding Through Large-Scale Training","created":"2025-04-18","cited_by_count":0,"area":"mllm"},{"id":"2510.27088","title":"Hierarchical Transformers for Unsupervised 3D Shape Abstraction","created":"2025-10-31","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":"2609.08345","title":"CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs","created":"2026-09-08","cited_by_count":0,"area":"inference"},{"id":"2609.15137","title":"SparseTalk - Sparsifying 3D Gaussian Language Fields for Efficient 3D Visual Question Answering","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.38716","title":"SpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision--Language Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.38717","title":"Soft Spatial Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}