{"total":67,"rows":[{"id":"2505.21500","title":"ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models","created":"2025-05-27","cited_by_count":118,"area":"lr"},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2510.25760","title":"Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks","created":"2025-10-29","cited_by_count":33,"area":"lr"},{"id":"2512.16561","title":"N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models","created":"2025-12-18","cited_by_count":29,"area":"lr"},{"id":"2510.13800","title":"Reasoning in Space via Grounding in the World","created":"2025-10-15","cited_by_count":19,"area":"lr"},{"id":"2511.10017","title":"AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models","created":"2025-11-13","cited_by_count":15,"area":"lr"},{"id":"2506.17545","title":"Scene-R1: Video-Grounded Large Language Models for 3D Scene Reasoning without 3D Annotations","created":"2025-06-21","cited_by_count":14,"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":"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":"2505.22643","title":"SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understanding","created":"2025-05-28","cited_by_count":10,"area":"wm"},{"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":"2506.14512","title":"SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks","created":"2025-06-17","cited_by_count":7,"area":"lr"},{"id":"2507.05260","title":"Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations","created":"2025-07-07","cited_by_count":7,"area":null},{"id":"2508.20758","title":"SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual Grounding","created":"2025-08-28","cited_by_count":7,"area":"lr"},{"id":"2512.02982","title":"U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences","created":"2025-12-02","cited_by_count":7,"area":"wm"},{"id":"2507.17664","title":"Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras","created":"2025-07-23","cited_by_count":6,"area":null},{"id":"2512.05060","title":"4DLangVGGT: 4D Language-Visual Geometry Grounded Transformer","created":"2025-12-04","cited_by_count":5,"area":null},{"id":"2503.06569","title":"Global-Aware Monocular Semantic Scene Completion with State Space Models","created":"2025-03-09","cited_by_count":3,"area":"ssm"},{"id":"2505.20148","title":"MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents","created":"2025-05-26","cited_by_count":3,"area":"agents"},{"id":"2507.10778","title":"Warehouse Spatial Question Answering with LLM Agent","created":"2025-07-14","cited_by_count":3,"area":"agents"},{"id":"2511.19119","title":"MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images","created":"2025-11-24","cited_by_count":3,"area":"lr"},{"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":"2603.25494","title":"AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environments","created":"2026-03-26","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":"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":"2602.03361","title":"Z3D: Zero-Shot 3D Visual Grounding from Images","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2603.09173","title":"Point Cloud as a Foreign Language for Multi-modal Large Language Model","created":"2026-03-10","cited_by_count":2,"area":"mllm"},{"id":"2605.13815","title":"OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation","created":"2026-05-13","cited_by_count":2,"area":"wm"},{"id":"2606.18242","title":"EventDrive: Event Cameras for Vision-Language Driving Intelligence","created":"2026-06-16","cited_by_count":2,"area":"driving"},{"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":"2506.19498","title":"T-Rex: Task-Adaptive Spatial Representation Extraction for Robotic Manipulation with Vision-Language Models","created":"2025-06-24","cited_by_count":1,"area":"mllm"},{"id":"2509.09584","title":"Visual Grounding from Event Cameras","created":"2025-09-11","cited_by_count":1,"area":null},{"id":"2510.14965","title":"ChangingGrounding: 3D Visual Grounding in Changing Scenes","created":"2025-10-16","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":"2602.00637","title":"VIZOR: Viewpoint-Invariant Zero-Shot Scene Graph Generation for 3D Scene Reasoning","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2603.04976","title":"3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding","created":"2026-03-05","cited_by_count":1,"area":"lr"},{"id":"2603.08131","title":"UniGround: Universal 3D Visual Grounding via Training-Free Scene Parsing","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2604.00528","title":"Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding","created":"2026-04-01","cited_by_count":1,"area":"lr"},{"id":"2604.02736","title":"THOM: Generating Physically Plausible Hand-Object Meshes From Text","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.05638","title":"PanopticQuery: Unified Query-Time Reasoning for 4D Scenes","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2604.08921","title":"TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2605.25326","title":"Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2606.01247","title":"Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?","created":"2026-05-31","cited_by_count":1,"area":"lr"},{"id":"2504.08307","title":"DSM: Constructing a Diverse Semantic Map for 3D Visual Grounding","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2510.07871","title":"Learning to Navigate Socially Through Proactive Risk Perception","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2511.18735","title":"Thinking Ahead: Foresight Intelligence in MLLMs and World Model","created":"2025-11-24","cited_by_count":0,"area":"wm"},{"id":"2512.21641","title":"TrackTeller: Temporal Multimodal 3D Grounding for Behavior-Dependent Object References","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2512.23020","title":"OpenGround: Planning-based Online Perception for Open-World 3D Visual Grounding","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2601.08811","title":"Reasoning Matters for 3D Visual Grounding","created":"2026-01-13","cited_by_count":0,"area":"lr"},{"id":"2603.26690","title":"SpatialPoint: Spatial-aware Point Prediction for Embodied Localization","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2604.21160","title":"Reinforcing 3D Understanding in Point-VLMs via Geometric Reward Credit Assignment","created":"2026-04-23","cited_by_count":0,"area":"lr"},{"id":"2605.21788","title":"SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.25901","title":"AgentGrounder: Zero-Shot 3D Visual Pointcloud Grounding using Multimodal Language Models","created":"2026-05-25","cited_by_count":0,"area":"mllm"},{"id":"2605.28490","title":"SSR3D-LLM: Structured Spatial Reasoning via Latent Steps for Fine-Grained Grounding in Unified 3D-LLMs","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2605.29879","title":"DGSG-Mind: Dynamic 3D Gaussian Scene Graphs for Long-Term Scene Understanding and Grounding","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.20946","title":"Scaling Diverse Language Generation for 3D Visual Grounding","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.24649","title":"Agentic Collaborative Cognition for Zero-Shot 3D Understanding","created":"2026-06-23","cited_by_count":0,"area":"mllm"},{"id":"2606.31148","title":"PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.04568","title":"Talk2Sensors: 3D Visual Grounding in Autonomous Driving via Sensor-Adaptive Physical Cue Matching","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.30451","title":"SeqAlign3DVG: A Sequence-Aligned Benchmark and Voxel Reasoning Framework for 3D Visual Grounding","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.04741","title":"Where to Look Matters: Learning Influential Views for VLM-based 3D Visual Grounding","created":"2026-09-04","cited_by_count":0,"area":"mllm"},{"id":"2609.19911","title":"CitySTAR: Structured and Topology-Aware Reasoning for Open-Vocabulary Urban 3D Grounding","created":"2026-09-17","cited_by_count":0,"area":"lr"},{"id":"2609.33109","title":"Toward Comprehensive 3D Grounding: Orientation Grounding through Vision-Language Models","created":"2026-09-27","cited_by_count":0,"area":"mllm"},{"id":"2609.36875","title":"S4VY: Segment Anything in Feed-Forward 4D Visual Geometry","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.18694","title":"GeoReader: Learning Latent Geometry for Spatial Reasoning in Vision-Language Models","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}