{"total":47,"rows":[{"id":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65,"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":"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":"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":"2512.04012","title":"Emergent Outlier View Rejection in Visual Geometry Grounded Transformers","created":"2025-12-03","cited_by_count":22,"area":null},{"id":"2411.17385","title":"DepthCues: Evaluating Monocular Depth Perception in Large Vision Models","created":"2024-11-26","cited_by_count":19,"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":"2503.10745","title":"Unifying 2D and 3D Vision-Language Understanding","created":"2025-03-13","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":"2503.22436","title":"NuGrounding: A Multi-View 3D Visual Grounding Framework in Autonomous Driving","created":"2025-03-28","cited_by_count":12,"area":null},{"id":"2512.20617","title":"SpatialTree: How Spatial Abilities Branch Out in MLLMs","created":"2025-12-23","cited_by_count":12,"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":"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":"2507.18678","title":"Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting","created":"2025-07-24","cited_by_count":8,"area":null},{"id":"2508.08199","title":"Generalizable Operating Room Expert with Multimodal Enhancement","created":"2025-08-11","cited_by_count":7,"area":null},{"id":"2603.07660","title":"Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence","created":"2026-03-08","cited_by_count":6,"area":null},{"id":"2511.09555","title":"SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation","created":"2025-11-12","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":"2503.17044","title":"ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail","created":"2025-03-21","cited_by_count":4,"area":null},{"id":"2511.20253","title":"Zoo3D: Zero-Shot 3D Object Detection at Scene Level","created":"2025-11-25","cited_by_count":4,"area":null},{"id":"2512.03040","title":"Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation","created":"2025-12-02","cited_by_count":3,"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":"2601.05991","title":"3D Instruction Ambiguity Detection","created":"2026-01-09","cited_by_count":3,"area":null},{"id":"2601.20835","title":"Open-Vocabulary Functional 3D Human-Scene Interaction Generation","created":"2026-01-28","cited_by_count":3,"area":null},{"id":"2604.17472","title":"UniMesh: Unifying 3D Mesh Understanding and Generation","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2606.22631","title":"4DVLT: Dynamic Scene Understanding with Worldline-Centered Vision-Language Tracking","created":"2026-06-21","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":"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":"2512.01009","title":"FOM-Nav: Frontier-Object Maps for Object Goal Navigation","created":"2025-11-30","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":"2603.23447","title":"3DCity-LLM: Empowering Multi-modality Large Language Models for 3D City-scale Perception and Understanding","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2609.25832","title":"PartLLM: A Unified Multimodal Foundation for 3D Part Segmentation","created":"2026-09-22","cited_by_count":1,"area":null},{"id":"2512.00226","title":"DenseScan: Advancing 3D Scene Understanding with 2D Dense Annotation","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2603.09961","title":"BEACON: Language-Conditioned Navigation Affordance Prediction under Occlusion","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.19515","title":"ItinBench: Benchmarking Planning Across Multiple Cognitive Dimensions with Large Language Models","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2603.26690","title":"SpatialPoint: Spatial-aware Point Prediction for Embodied Localization","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2608.05137","title":"SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.05569","title":"CoordRefer: Coordinate-Aware 3D Visual Grounding from Multiview Images","created":"2026-08-06","cited_by_count":0,"area":null},{"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":"2609.29835","title":"Retrieve-to-Localize: Bridging Large Language Models and LiDAR Geometry for Spatial Grounding","created":"2026-09-24","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}],"next_cursor":null}