{"total":135,"rows":[{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849,"area":null},{"id":"2311.18482","title":"Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding","created":"2023-11-30","cited_by_count":208,"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":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115,"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":"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":"2403.03101","title":"KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents","created":"2024-03-05","cited_by_count":61,"area":"agents"},{"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":"2401.06341","title":"AffordanceLLM: Grounding Affordance from Vision Language Models","created":"2024-01-12","cited_by_count":55,"area":"mllm"},{"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":"2402.15487","title":"RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation","created":"2024-02-23","cited_by_count":48,"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":"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":"2401.02500","title":"On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)","created":"2024-01-04","cited_by_count":40,"area":null},{"id":"2401.08577","title":"MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World","created":"2024-01-16","cited_by_count":39,"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":"2406.07544","title":"Situational Awareness Matters in 3D Vision Language Reasoning","created":"2024-06-11","cited_by_count":33,"area":null},{"id":"2401.03201","title":"3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding","created":"2024-01-06","cited_by_count":32,"area":"mllm"},{"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":"2411.04999","title":"DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation","created":"2024-11-07","cited_by_count":32,"area":"mllm"},{"id":"2508.17281","title":"From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users","created":"2025-08-24","cited_by_count":32,"area":"agents"},{"id":"2310.07968","title":"Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation","created":"2023-10-12","cited_by_count":31,"area":"lr"},{"id":"2406.03008","title":"DriVLMe: Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experiences","created":"2024-06-05","cited_by_count":27,"area":"driving"},{"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":"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":"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":"2503.18135","title":"MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation","created":"2025-03-23","cited_by_count":16,"area":"lr"},{"id":"2409.17331","title":"ChatCam: Empowering Camera Control through Conversational AI","created":"2024-09-25","cited_by_count":15,"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":"2311.00530","title":"Advances in Embodied Navigation Using Large Language Models: A Survey","created":"2023-11-01","cited_by_count":14,"area":null},{"id":"2403.14743","title":"VURF: A General-purpose Reasoning and Self-refinement Framework for Video Understanding","created":"2024-03-21","cited_by_count":13,"area":"lr"},{"id":"2410.21909","title":"SceneGenAgent: Precise Industrial Scene Generation with Coding Agent","created":"2024-10-29","cited_by_count":13,"area":"agents"},{"id":"2404.04363","title":"Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs","created":"2024-04-05","cited_by_count":12,"area":"diffusion"},{"id":"2410.20178","title":"LLMs Can Evolve Continually on Modality for X-Modal Reasoning","created":"2024-10-26","cited_by_count":12,"area":"lr"},{"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":"2310.09454","title":"LgTS: Dynamic Task Sampling using LLM-generated sub-goals for Reinforcement Learning Agents","created":"2023-10-14","cited_by_count":11,"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":"2409.19650","title":"Grounding 3D Scene Affordance From Egocentric Interactions","created":"2024-09-29","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":"2409.15959","title":"Semantics-Controlled Gaussian Splatting for Outdoor Scene Reconstruction and Rendering in Virtual Reality","created":"2024-09-24","cited_by_count":10,"area":null},{"id":"2410.09006","title":"From Interaction to Impact: Towards Safer AI Agents Through Understanding and Evaluating Mobile UI Operation Impacts","created":"2024-10-11","cited_by_count":10,"area":"agents"},{"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":"2408.04034","title":"Task-oriented Sequential Grounding and Navigation in 3D Scenes","created":"2024-08-07","cited_by_count":9,"area":null},{"id":"2411.13410","title":"A Survey On Enhancing Reinforcement Learning in Complex Environments: Insights from Human and LLM Feedback","created":"2024-11-20","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":"2403.01209","title":"Data-free Multi-label Image Recognition via LLM-powered Prompt Tuning","created":"2024-03-02","cited_by_count":8,"area":"mllm"},{"id":"2404.00413","title":"Language Models are Spacecraft Operators","created":"2024-03-30","cited_by_count":8,"area":null},{"id":"2407.16260","title":"DreamDissector: Learning Disentangled Text-to-3D Generation from 2D Diffusion Priors","created":"2024-07-23","cited_by_count":8,"area":"diffusion"},{"id":"2411.13927","title":"Multimodal 3D Reasoning Segmentation with Complex Scenes","created":"2024-11-21","cited_by_count":8,"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":"2506.16652","title":"CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity","created":"2025-06-19","cited_by_count":8,"area":"diffusion"},{"id":"2507.16524","title":"Spatial 3D-LLM: Exploring Spatial Awareness in 3D Vision-Language Models","created":"2025-07-22","cited_by_count":8,"area":"mllm"},{"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":"2405.17104","title":"LLM-Optic: Unveiling the Capabilities of Large Language Models for Universal Visual Grounding","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2405.17846","title":"Safety Control of Service Robots with LLMs and Embodied Knowledge Graphs","created":"2024-05-28","cited_by_count":7,"area":null},{"id":"2408.05478","title":"Multi-Agent Planning Using Visual Language Models","created":"2024-08-10","cited_by_count":7,"area":"mllm"},{"id":"2411.14594","title":"Solving Zero-Shot 3D Visual Grounding as Constraint Satisfaction Problems","created":"2024-11-21","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":"2403.19603","title":"Semantic Map-based Generation of Navigation Instructions","created":"2024-03-28","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":"2506.02112","title":"SAB3R: Semantic-Augmented Backbone in 3D Reconstruction","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2402.00290","title":"MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments","created":"2024-02-01","cited_by_count":5,"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":"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":"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":"2501.13338","title":"CuriousBot: Interactive Mobile Exploration via Actionable 3D Relational Object Graph","created":"2025-01-23","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":"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":"2508.01740","title":"AG$^2$aussian: Anchor-Graph Structured Gaussian Splatting for Instance-Level 3D Scene Understanding and Editing","created":"2025-08-03","cited_by_count":4,"area":null},{"id":"2312.09625","title":"Weakly-Supervised 3D Visual Grounding based on Visual Language Alignment","created":"2023-12-15","cited_by_count":3,"area":"mllm"},{"id":"2408.17379","title":"EMPOWER: Embodied Multi-role Open-vocabulary Planning with Online Grounding and Execution","created":"2024-08-30","cited_by_count":3,"area":null},{"id":"2505.20503","title":"Embodied AI with Foundation Models for Mobile Service Robots: A Systematic Review","created":"2025-05-26","cited_by_count":3,"area":"mllm"},{"id":"2506.15828","title":"Context Matters! Relaxing Goals with LLMs for Feasible 3D Scene Planning","created":"2025-06-18","cited_by_count":3,"area":null},{"id":"2507.10778","title":"Warehouse Spatial Question Answering with LLM Agent","created":"2025-07-14","cited_by_count":3,"area":"agents"},{"id":"2511.18845","title":"UNeMo: Collaborative Visual-Language Reasoning and Navigation via a Multimodal World Model","created":"2025-11-24","cited_by_count":3,"area":"wm"},{"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":"2411.03287","title":"The Future of Intelligent Healthcare: A Systematic Analysis and Discussion on the Integration and Impact of Robots Using Large Language Models for Healthcare","created":"2024-11-05","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":"2503.17703","title":"RAIDER: Tool-Equipped Large Language Model Agent for Robotic Action Issue Detection, Explanation and Recovery","created":"2025-03-22","cited_by_count":2,"area":"agents"},{"id":"2505.15373","title":"RAZER: Robust Accelerated Zero-Shot 3D Open-Vocabulary Panoptic Reconstruction with Spatio-Temporal Aggregation","created":"2025-05-21","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":"2506.09989","title":"Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes","created":"2025-06-11","cited_by_count":2,"area":null},{"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":"2510.16924","title":"Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models?","created":"2025-10-19","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":"2602.07082","title":"MosaicThinker: On-Device Visual Spatial Reasoning for Embodied AI via Iterative Construction of Space Representation","created":"2026-02-06","cited_by_count":2,"area":"lr"},{"id":"2606.31471","title":"Think While You Map: Asynchronous Vision-Language Agents for Incremental 3D Scene Graphs","created":"2026-06-30","cited_by_count":2,"area":"lr"},{"id":"2608.30821","title":"Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling","created":"2026-08-31","cited_by_count":2,"area":null},{"id":"2507.12916","title":"Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2508.17044","title":"M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environments","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2509.19571","title":"Agentic Scene Policies: Unifying Space, Semantics, and Affordances for Robot Action","created":"2025-09-23","cited_by_count":1,"area":"agents"},{"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}],"next_cursor":"100"}