{"total":60,"rows":[{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115,"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":"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":"2406.07113","title":"Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph","created":"2024-06-11","cited_by_count":32,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"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":"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":"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":"2503.06271","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":"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":"2508.01242","title":"MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh","created":"2025-08-02","cited_by_count":20,"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":"2412.02402","title":"RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation","created":"2024-12-03","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":"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":"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":"2503.12955","title":"HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding","created":"2025-03-17","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":"2412.11409","title":"Multi-modal and Multi-scale Spatial Environment Understanding for Immersive Visual Text-to-Speech","created":"2024-12-16","cited_by_count":4,"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":"2511.16567","title":"POMA-3D: The Point Map Way to 3D Scene Understanding","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2407.04180","title":"Slice-100K: A Multimodal Dataset for Extrusion-based 3D Printing","created":"2024-07-04","cited_by_count":3,"area":null},{"id":"2502.14273","title":"LLM-EvRep: Learning an LLM-Compatible Event Representation Using a Self-Supervised Framework","created":"2025-02-20","cited_by_count":3,"area":null},{"id":"2507.12795","title":"City-VLM: Towards Multidomain Perception Scene Understanding via Multimodal Incomplete Learning","created":"2025-07-17","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":"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":"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":"2512.19178","title":"Vision-Language-Policy Model for Dynamic Robot Task Planning","created":"2025-12-22","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":"2607.06565","title":"ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation","created":"2026-07-07","cited_by_count":2,"area":null},{"id":"2404.10836","title":"Semantic-Based Active Perception for Humanoid Visual Tasks with Foveal Sensors","created":"2024-04-16","cited_by_count":1,"area":null},{"id":"2506.03760","title":"Understanding Physical Properties of Unseen Deformable Objects by Leveraging Large Language Models and Robot Actions","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2507.13061","title":"Advancing Complex Wide-Area Scene Understanding with Hierarchical Coresets Selection","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2507.13985","title":"DreamScene: 3D Gaussian-based End-to-end Text-to-3D Scene Generation","created":"2025-07-18","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":"2509.16721","title":"Text-Scene: A Scene-to-Language Parsing Framework for 3D Scene Understanding","created":"2025-09-20","cited_by_count":1,"area":null},{"id":"2510.16518","title":"DIV-Nav: Open-Vocabulary Spatial Relationships for Multi-Object Navigation","created":"2025-10-18","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":"2603.03564","title":"Modeling Cross-vision Synergy for Unified Large Vision Model","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2603.06168","title":"JOPP-3D: Joint Open Vocabulary Semantic Segmentation on Point Clouds and Panoramas","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2607.07001","title":"Ego-Human Motion Prediction with 3D-Aware LLM","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2608.15710","title":"Beyond Single Object: Learning 3D Relations with Large Language Models","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2609.02350","title":"LookStep: Efficient Vision-Language Navigation with Linguistic Foresight and Event Driven Memory","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2411.18644","title":"Scene Co-pilot: Procedural Text to Video Generation with Human in the Loop","created":"2024-11-26","cited_by_count":0,"area":null},{"id":"2509.18173","title":"TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Route","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2509.18576","title":"LCMF: Lightweight Cross-Modality Mambaformer for Embodied Robotics VQA","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2603.09632","title":"X-GS: An Extensible Framework for Perceiving and Thinking with 3D Gaussian Splatting","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2605.12542","title":"Earth Science Foundation Models: From Perception to Reasoning and Discovery","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.00508","title":"V-LynX: Token Interface Alignment for Video+X LLMs","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2610.06611","title":"Lens3D: Target-Conditioned Visual Foveation for Fine-Grained 3D Understanding","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.16176","title":"EgoAlign: Situated 3D Understanding without Situation Descriptions","created":"2026-10-12","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}