{"total":175,"rows":[{"id":"2501.15830","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","created":"2025-01-27","cited_by_count":519,"area":"vla"},{"id":"2505.23747","title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","created":"2025-05-29","cited_by_count":217,"area":"mllm"},{"id":"2412.04453","title":"NaVILA: Legged Robot Vision-Language-Action Model for Navigation","created":"2024-12-05","cited_by_count":211,"area":"vla"},{"id":"2409.18125","title":"LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness","created":"2024-09-26","cited_by_count":183,"area":"mllm"},{"id":"2412.00493","title":"Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding","created":"2024-11-30","cited_by_count":138,"area":"mllm"},{"id":"2503.22976","title":"From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D","created":"2025-03-29","cited_by_count":138,"area":"mllm"},{"id":"2507.05240","title":"StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling","created":"2025-07-07","cited_by_count":118,"area":"inference"},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115,"area":null},{"id":"2412.07755","title":"SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models","created":"2024-12-10","cited_by_count":114,"area":"mllm"},{"id":"2501.01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","created":"2025-01-02","cited_by_count":109,"area":"mllm"},{"id":"2412.02193","title":"LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models","created":"2024-12-03","cited_by_count":96,"area":"lr"},{"id":"2503.13111","title":"MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs","created":"2025-03-17","cited_by_count":73,"area":"mllm"},{"id":"2506.01946","title":"3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding","created":"2025-06-02","cited_by_count":70,"area":"lr"},{"id":"2501.01163","title":"3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer","created":"2025-01-02","cited_by_count":68,"area":"mllm"},{"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":"2504.01901","title":"Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness","created":"2025-04-02","cited_by_count":63,"area":"mllm"},{"id":"2506.22242","title":"4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration","created":"2025-06-27","cited_by_count":56,"area":"vla"},{"id":"2502.13143","title":"SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation","created":"2025-02-18","cited_by_count":46,"area":"lr"},{"id":"2509.18905","title":"How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective","created":"2025-09-23","cited_by_count":43,"area":"lr"},{"id":"2504.05786","title":"How to Enable LLM with 3D Capacity? A Survey of Spatial Reasoning in LLM","created":"2025-04-08","cited_by_count":42,"area":"lr"},{"id":"2504.02477","title":"Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision","created":"2025-04-03","cited_by_count":40,"area":"mllm"},{"id":"2412.01292","title":"LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences","created":"2024-12-02","cited_by_count":38,"area":"mllm"},{"id":"2511.21471","title":"SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition","created":"2025-11-26","cited_by_count":35,"area":"mllm"},{"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":"2509.13317","title":"3D Aware Region Prompted Vision Language Model","created":"2025-09-16","cited_by_count":33,"area":"mllm"},{"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":"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":"2512.10719","title":"SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving","created":"2025-12-11","cited_by_count":28,"area":"lr"},{"id":"2411.06284","title":"A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Tasks","created":"2024-11-09","cited_by_count":27,"area":"mllm"},{"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":"2502.11859","title":"Defining and Evaluating Visual Language Models' Basic Spatial Abilities: A Perspective from Psychometrics","created":"2025-02-17","cited_by_count":23,"area":"mllm"},{"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":"2506.07966","title":"SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence","created":"2025-06-09","cited_by_count":23,"area":"mllm"},{"id":"2511.15722","title":"Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods","created":"2025-11-14","cited_by_count":23,"area":"lr"},{"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":"2407.21333","title":"Chat2Layout: Interactive 3D Furniture Layout with a Multimodal LLM","created":"2024-07-31","cited_by_count":21,"area":"mllm"},{"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":"2510.19400","title":"Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes","created":"2025-10-22","cited_by_count":20,"area":"lr"},{"id":"2502.09620","title":"Exploring the Potential of Encoder-free Architectures in 3D LMMs","created":"2025-02-13","cited_by_count":16,"area":"mllm"},{"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":"2512.13080","title":"Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos","created":"2025-12-15","cited_by_count":13,"area":"vla"},{"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":"2504.09848","title":"A Survey of Large Language Model-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents, Smart Cities, and Earth Science","created":"2025-04-14","cited_by_count":12,"area":"wm"},{"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":"2512.07733","title":"SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagery","created":"2025-12-08","cited_by_count":11,"area":"lr"},{"id":"2601.14339","title":"CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments","created":"2026-01-20","cited_by_count":11,"area":"lr"},{"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":"2505.22143","title":"3D Question Answering via only 2D Vision-Language Models","created":"2025-05-28","cited_by_count":10,"area":"mllm"},{"id":"2506.04220","title":"Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs","created":"2025-06-04","cited_by_count":10,"area":"lr"},{"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":"2409.03256","title":"E2CL: Exploration-based Error Correction Learning for Embodied Agents","created":"2024-09-05","cited_by_count":9,"area":"agents"},{"id":"2411.19774","title":"PerLA: Perceptive 3D Language Assistant","created":"2024-11-29","cited_by_count":9,"area":null},{"id":"2601.05172","title":"CoV: Chain-of-View Prompting for Spatial Reasoning","created":"2026-01-08","cited_by_count":9,"area":"lr"},{"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":"2510.16714","title":"SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes","created":"2025-10-19","cited_by_count":8,"area":"lr"},{"id":"2505.04911","title":"SpatialPrompting: Keyframe-driven Zero-Shot Spatial Reasoning with Off-the-Shelf Multimodal Large Language Models","created":"2025-05-08","cited_by_count":7,"area":"lr"},{"id":"2510.15530","title":"VO-DP: Semantic-Geometric Adaptive Diffusion Policy for Vision-Only Robotic Manipulation","created":"2025-10-17","cited_by_count":7,"area":"diffusion"},{"id":"2511.13647","title":"Part-X-MLLM: Part-aware 3D Multimodal Large Language Model","created":"2025-11-17","cited_by_count":7,"area":"mllm"},{"id":"2411.15714","title":"ROOT: VLM based System for Indoor Scene Understanding and Beyond","created":"2024-11-24","cited_by_count":6,"area":"mllm"},{"id":"2503.12955","title":"HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding","created":"2025-03-17","cited_by_count":6,"area":null},{"id":"2510.10976","title":"Video-STR: Reinforcing MLLMs in Video Spatio-Temporal Reasoning with Relation Graph","created":"2025-10-13","cited_by_count":6,"area":"lr"},{"id":"2511.22103","title":"MoE3D: Mixture of Experts meets Multi-Modal 3D Understanding","created":"2025-11-27","cited_by_count":6,"area":"moe"},{"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":"2502.00954","title":"Hypo3D: Exploring Hypothetical Reasoning in 3D","created":"2025-02-02","cited_by_count":5,"area":"mllm"},{"id":"2505.12782","title":"AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning","created":"2025-05-19","cited_by_count":5,"area":"mllm"},{"id":"2505.16663","title":"CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"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":"2512.01223","title":"S$^2$-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance","created":"2025-12-01","cited_by_count":5,"area":"lr"},{"id":"2512.08135","title":"CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning","created":"2025-12-09","cited_by_count":5,"area":"lr"},{"id":"2512.23365","title":"SpatialMosaic: A Multiview VLM Dataset for Partial Visibility","created":"2025-12-29","cited_by_count":5,"area":"lr"},{"id":"2603.08592","title":"Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations","created":"2026-03-09","cited_by_count":5,"area":"lr"},{"id":"2608.02980","title":"Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding","created":"2026-08-04","cited_by_count":5,"area":"mllm"},{"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":"2503.19794","title":"PAVE: Patching and Adapting Video Large Language Models","created":"2025-03-25","cited_by_count":4,"area":"lr"},{"id":"2504.16061","title":"Vision language models are unreliable at trivial spatial cognition","created":"2025-04-22","cited_by_count":4,"area":"mllm"},{"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":"2509.24385","title":"Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction-Reasoning Synergy","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"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":"2601.19847","title":"Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation Steering","created":"2026-01-27","cited_by_count":4,"area":"lr"},{"id":"2605.24456","title":"EgoProx: Evaluating MLLMs on Egocentric 3D Proximity Reasoning Across a Cognitive Hierarchy","created":"2026-05-23","cited_by_count":4,"area":"lr"},{"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":"2411.06752","title":"Semantic Enhancement for Object SLAM with Heterogeneous Multimodal Large Language Model Agents","created":"2024-11-11","cited_by_count":3,"area":"mllm"},{"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":"2510.17603","title":"ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling","created":"2025-10-20","cited_by_count":3,"area":"agents"},{"id":"2512.01821","title":"Seeing through Imagination: Learning Scene Geometry via Implicit Spatial World Modeling","created":"2025-12-01","cited_by_count":3,"area":"wm"}],"next_cursor":"100"}