{"total":133,"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":"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":"2411.16537","title":"RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics","created":"2024-11-25","cited_by_count":136,"area":"mllm"},{"id":"2404.09465","title":"PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI","created":"2024-04-15","cited_by_count":125,"area":null},{"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":"2405.20853","title":"MeshXL: Neural Coordinate Field for Generative 3D Foundation Models","created":"2024-05-31","cited_by_count":103,"area":null},{"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":"2405.11442","title":"Unifying 3D Vision-Language Understanding via Promptable Queries","created":"2024-05-19","cited_by_count":70,"area":null},{"id":"2409.10161","title":"SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting","created":"2024-09-16","cited_by_count":69,"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":"2502.19459","title":"ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting","created":"2025-02-26","cited_by_count":67,"area":null},{"id":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65,"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":"2504.18904","title":"RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning","created":"2025-04-26","cited_by_count":54,"area":"offlinerl"},{"id":"2406.16866","title":"Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Models","created":"2024-06-24","cited_by_count":53,"area":"mllm"},{"id":"2503.18052","title":"SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining","created":"2025-03-23","cited_by_count":52,"area":"mllm"},{"id":"2409.02389","title":"Multi-modal Situated Reasoning in 3D Scenes","created":"2024-09-04","cited_by_count":51,"area":"lr"},{"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":"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":"2412.01292","title":"LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences","created":"2024-12-02","cited_by_count":38,"area":"mllm"},{"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":"2411.19626","title":"GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding","created":"2024-11-29","cited_by_count":28,"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":"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":"2507.07984","title":"OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding","created":"2025-07-10","cited_by_count":24,"area":"mllm"},{"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":"2505.11383","title":"Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation","created":"2025-05-16","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":"2502.02548","title":"Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation","created":"2025-02-04","cited_by_count":22,"area":null},{"id":"2409.04234","title":"UniDet3D: Multi-dataset Indoor 3D Object Detection","created":"2024-09-06","cited_by_count":20,"area":null},{"id":"2509.10813","title":"InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts","created":"2025-09-13","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":"2512.00565","title":"Describe Anything Anywhere At Any Moment","created":"2025-11-29","cited_by_count":19,"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":"2505.15232","title":"DC-Scene: Data-Centric Learning for 3D Scene Understanding","created":"2025-05-21","cited_by_count":15,"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":"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":"2511.01755","title":"3EED: Ground Everything Everywhere in 3D","created":"2025-11-03","cited_by_count":12,"area":null},{"id":"2411.19492","title":"Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modeling","created":"2024-11-29","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":"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":"2603.12255","title":"Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training","created":"2026-03-12","cited_by_count":11,"area":null},{"id":"2412.11457","title":"MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenes","created":"2024-12-16","cited_by_count":10,"area":"diffusion"},{"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":"2510.12099","title":"G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior","created":"2025-10-14","cited_by_count":10,"area":"diffusion"},{"id":"2408.04034","title":"Task-oriented Sequential Grounding and Navigation in 3D Scenes","created":"2024-08-07","cited_by_count":9,"area":null},{"id":"2412.01398","title":"Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description","created":"2024-12-02","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":"2502.01401","title":"Language-to-Space Programming for Training-Free 3D Visual Grounding","created":"2025-02-03","cited_by_count":8,"area":null},{"id":"2503.17406","title":"IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D Scenes","created":"2025-03-20","cited_by_count":8,"area":"mllm"},{"id":"2503.17827","title":"4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding","created":"2025-03-22","cited_by_count":8,"area":"mllm"},{"id":"2510.16714","title":"SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes","created":"2025-10-19","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":"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":"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":"2506.23120","title":"Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation","created":"2025-06-29","cited_by_count":6,"area":"lr"},{"id":"2511.19430","title":"Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution","created":"2025-11-24","cited_by_count":6,"area":"agents"},{"id":"2603.02910","title":"Articulation in Motion: Prior-free Part Mobility Analysis for Articulated Objects By Dynamic-Static Disentanglement","created":"2026-03-03","cited_by_count":6,"area":null},{"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":"2502.00954","title":"Hypo3D: Exploring Hypothetical Reasoning in 3D","created":"2025-02-02","cited_by_count":5,"area":"mllm"},{"id":"2505.16663","title":"CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"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":"2510.18054","title":"HouseTour: A Virtual Real Estate A(I)gent","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2512.03000","title":"DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling","created":"2025-12-02","cited_by_count":5,"area":"wm"},{"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":"2602.03890","title":"4DPC$^2$hat: Towards Dynamic Point Cloud Understanding with Failure-Aware Bootstrapping","created":"2026-02-03","cited_by_count":5,"area":"mllm"},{"id":"2503.15897","title":"Learning 3D Scene Analogies with Neural Contextual Scene Maps","created":"2025-03-20","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":"2506.21188","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":"2507.19232","title":"Event-Driven Storytelling with Multiple Lifelike Humans in a 3D Scene","created":"2025-07-25","cited_by_count":4,"area":null},{"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":"2511.16567","title":"POMA-3D: The Point Map Way to 3D Scene Understanding","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2601.08831","title":"3AM: 3egment Anything with Geometric Consistency in Videos","created":"2026-01-13","cited_by_count":4,"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":"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":"2412.14837","title":"ObjVariantEnsemble: Advancing Point Cloud LLM Evaluation in Challenging Scenes with Subtly Distinguished Objects","created":"2024-12-19","cited_by_count":2,"area":null},{"id":"2503.14161","title":"CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models","created":"2025-03-18","cited_by_count":2,"area":"mllm"},{"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":"2507.12123","title":"Open-Vocabulary Indoor Object Grounding with 3D Hierarchical Scene Graph","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2509.20401","title":"SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment","created":"2025-09-23","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":"2510.11509","title":"Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model","created":"2025-10-13","cited_by_count":2,"area":"mllm"},{"id":"2511.12676","title":"BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections","created":"2025-11-16","cited_by_count":2,"area":"agents"},{"id":"2602.03361","title":"Z3D: Zero-Shot 3D Visual Grounding from Images","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2602.06033","title":"Can Vision Language Models Learn Intuitive Physics from Interaction?","created":"2026-02-05","cited_by_count":2,"area":"mllm"},{"id":"2603.03177","title":"Neuro-Symbolic Artificial Intelligence: A Task-Directed Survey in the Black-Box Models Era","created":"2026-03-03","cited_by_count":2,"area":null},{"id":"2603.06445","title":"What if? Emulative Simulation with World Models for Situated Reasoning","created":"2026-03-06","cited_by_count":2,"area":"wm"},{"id":"2603.18002","title":"Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2604.20395","title":"SpaCeFormer: Fast Proposal-Free Open-Vocabulary 3D Instance Segmentation","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2606.01215","title":"Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs","created":"2026-05-31","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}