{"total":133,"rows":[{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225,"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":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133,"area":null},{"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":"2405.20853","title":"MeshXL: Neural Coordinate Field for Generative 3D Foundation Models","created":"2024-05-31","cited_by_count":103,"area":null},{"id":"2407.07035","title":"Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models","created":"2024-07-09","cited_by_count":79,"area":null},{"id":"2411.17735","title":"3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning","created":"2024-11-23","cited_by_count":75,"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":"2404.10179","title":"Scaling Instructable Agents Across Many Simulated Worlds","created":"2024-03-13","cited_by_count":71,"area":null},{"id":"2405.11442","title":"Unifying 3D Vision-Language Understanding via Promptable Queries","created":"2024-05-19","cited_by_count":70,"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":"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":"2406.17741","title":"Point-SAM: Promptable 3D Segmentation Model for Point Clouds","created":"2024-06-25","cited_by_count":50,"area":null},{"id":"2406.14240","title":"CityNav: A Large-Scale Dataset for Real-World Aerial Navigation","created":"2024-06-20","cited_by_count":42,"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":"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":"2406.03866","title":"LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Model","created":"2024-06-06","cited_by_count":34,"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":"2404.03590","title":"SemGrasp: Semantic Grasp Generation via Language Aligned Discretization","created":"2024-04-04","cited_by_count":29,"area":null},{"id":"2506.00742","title":"ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary","created":"2025-05-31","cited_by_count":28,"area":null},{"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":"2410.00255","title":"Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning","created":"2024-09-30","cited_by_count":26,"area":null},{"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":"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":"2502.13759","title":"Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework","created":"2025-02-19","cited_by_count":24,"area":null},{"id":"2503.06271","title":"SplatTalk: 3D VQA with Gaussian Splatting","created":"2025-03-08","cited_by_count":24,"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":"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":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","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":"2504.04744","title":"Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions","created":"2025-04-07","cited_by_count":19,"area":null},{"id":"2412.00174","title":"SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters","created":"2024-11-29","cited_by_count":18,"area":null},{"id":"2505.20897","title":"Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation","created":"2025-05-27","cited_by_count":17,"area":null},{"id":"2511.07222","title":"Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images","created":"2025-11-10","cited_by_count":17,"area":null},{"id":"2410.12836","title":"EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing","created":"2024-10-03","cited_by_count":15,"area":null},{"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":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"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":"2412.08468","title":"Multi-GraspLLM: A Multimodal LLM for Multi-Hand Semantic Guided Grasp Generation","created":"2024-12-11","cited_by_count":12,"area":null},{"id":"2511.01755","title":"3EED: Ground Everything Everywhere in 3D","created":"2025-11-03","cited_by_count":12,"area":null},{"id":"2603.02133","title":"SimRecon: SimReady Compositional Scene Reconstruction from Real Videos","created":"2026-03-02","cited_by_count":12,"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":"2602.13191","title":"CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modeling","created":"2026-02-13","cited_by_count":11,"area":null},{"id":"2410.06195","title":"EgoSocialArena: Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective","created":"2024-10-08","cited_by_count":10,"area":null},{"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":"2508.11952","title":"UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding","created":"2025-08-16","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":"2411.19774","title":"PerLA: Perceptive 3D Language Assistant","created":"2024-11-29","cited_by_count":9,"area":null},{"id":"2412.10410","title":"GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents","created":"2024-12-07","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":"2603.23523","title":"Do 3D Large Language Models Really Understand 3D Spatial Relationships?","created":"2026-03-06","cited_by_count":9,"area":null},{"id":"2505.12703","title":"SpatialLLM: From Multi-modality Data to Urban Spatial Intelligence","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2507.18678","title":"Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting","created":"2025-07-24","cited_by_count":8,"area":null},{"id":"2508.11058","title":"Advancing 3D Scene Understanding with MV-ScanQA Multi-View Reasoning Evaluation and TripAlign Pre-training Dataset","created":"2025-08-14","cited_by_count":8,"area":null},{"id":"2407.13748","title":"General Geometry-aware Weakly Supervised 3D Object Detection","created":"2024-07-18","cited_by_count":7,"area":null},{"id":"2412.19142","title":"CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting","created":"2024-12-26","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":"2503.02505","title":"ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignment","created":"2025-03-04","cited_by_count":7,"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":"2602.10161","title":"Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment","created":"2026-02-10","cited_by_count":6,"area":null},{"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":"2607.12477","title":"Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence","created":"2026-07-14","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":"2410.15885","title":"VLASCD: A Visual Language Action Model for Simultaneous Chatting and Decision Making","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2509.01728","title":"Constrained Decoding for Safe Robot Navigation Foundation Models","created":"2025-09-01","cited_by_count":5,"area":null},{"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":"2605.13169","title":"PanoWorld: Towards Spatial Supersensing in 360$^\\circ$ Panorama World","created":"2026-05-13","cited_by_count":5,"area":null},{"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":"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":"2511.16567","title":"POMA-3D: The Point Map Way to 3D Scene Understanding","created":"2025-11-20","cited_by_count":4,"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":"2512.22830","title":"3D Scene Change Modeling With Consistent Multi-View Aggregation","created":"2025-12-28","cited_by_count":3,"area":null},{"id":"2607.01166","title":"Structured 4D Latent Predictive Model for Robot Planning","created":"2026-07-01","cited_by_count":3,"area":null},{"id":"2409.10525","title":"\"Is This It?\": Towards Ecologically Valid Benchmarks for Situated Collaboration","created":"2024-08-30","cited_by_count":2,"area":null},{"id":"2410.02787","title":"Navigation with VLM framework: Towards Going to Any Language","created":"2024-09-18","cited_by_count":2,"area":null},{"id":"2503.08604","title":"EMMOE: A Comprehensive Benchmark for Embodied Mobile Manipulation in Open Environments","created":"2025-03-11","cited_by_count":2,"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":"2510.22917","title":"HyPerNav: Hybrid Perception for Object-Oriented Navigation in Unknown Environment","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2511.00041","title":"Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical World","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2601.07218","title":"SceneNAT: Masked Generative Modeling for Language-Guided Indoor Scene Synthesis","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2602.00937","title":"CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2602.23739","title":"U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation","created":"2026-02-27","cited_by_count":2,"area":null},{"id":"2607.06565","title":"ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation","created":"2026-07-07","cited_by_count":2,"area":null},{"id":"2502.08503","title":"Revisiting 3D LLM Benchmarks: Are We Really Testing 3D Capabilities?","created":"2025-02-12","cited_by_count":1,"area":null},{"id":"2504.01952","title":"Image Difference Grounding with Natural Language","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2508.19074","title":"An LLM-powered Natural-to-Robotic Language Translation Framework with Correctness Guarantees","created":"2025-08-26","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":"2509.25466","title":"Data-Efficient Multitask DAgger","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2511.14086","title":"Error-Driven Scene Editing for 3D Grounding in Large Language Models","created":"2025-11-18","cited_by_count":1,"area":null},{"id":"2511.15279","title":"Look, Zoom, Understand: The Robotic Eyeball for Embodied Perception","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2512.00532","title":"Image Generation as a Visual Planner for Robotic Manipulation","created":"2025-11-29","cited_by_count":1,"area":null},{"id":"2512.06013","title":"VAT: Vision Action Transformer by Unlocking Full Representation of ViT","created":"2025-12-03","cited_by_count":1,"area":null}],"next_cursor":"100"}