{"total":71,"rows":[{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314,"area":"lr"},{"id":"2311.18651","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning","created":"2023-11-30","cited_by_count":210,"area":"lr"},{"id":"2403.11401","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","created":"2024-03-18","cited_by_count":175,"area":"lr"},{"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":"2404.03622","title":"Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models","created":"2024-04-04","cited_by_count":66,"area":"lr"},{"id":"2303.11327","title":"3D Concept Learning and Reasoning from Multi-View Images","created":"2023-03-20","cited_by_count":60,"area":"lr"},{"id":"2409.02389","title":"Multi-modal Situated Reasoning in 3D Scenes","created":"2024-09-04","cited_by_count":51,"area":"lr"},{"id":"2407.01525","title":"ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities","created":"2024-07-01","cited_by_count":47,"area":"lr"},{"id":"2408.15769","title":"A Survey on Evaluation of Multimodal Large Language Models","created":"2024-08-28","cited_by_count":46,"area":"lr"},{"id":"2505.00788","title":"SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models","created":"2025-05-01","cited_by_count":38,"area":"lr"},{"id":"2405.17427","title":"Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model","created":"2024-05-27","cited_by_count":28,"area":"lr"},{"id":"2408.00754","title":"Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model","created":"2024-08-01","cited_by_count":21,"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":"2402.05889","title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion","created":"2024-02-08","cited_by_count":17,"area":"lr"},{"id":"2506.05414","title":"SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing","created":"2025-06-04","cited_by_count":15,"area":"lr"},{"id":"2505.20640","title":"IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios","created":"2025-05-27","cited_by_count":13,"area":"lr"},{"id":"2507.07644","title":"FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations","created":"2025-07-10","cited_by_count":13,"area":"lr"},{"id":"2509.24473","title":"Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks","created":"2025-09-29","cited_by_count":13,"area":"lr"},{"id":"2507.00886","title":"GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond","created":"2025-07-01","cited_by_count":12,"area":"lr"},{"id":"2512.19683","title":"From Indoor to Open World: Revealing the Spatial Reasoning Gap in MLLMs","created":"2025-12-22","cited_by_count":12,"area":"lr"},{"id":"2507.07781","title":"SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes","created":"2025-07-10","cited_by_count":11,"area":"lr"},{"id":"2603.00515","title":"MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence","created":"2026-02-28","cited_by_count":10,"area":"lr"},{"id":"2601.05172","title":"CoV: Chain-of-View Prompting for Spatial Reasoning","created":"2026-01-08","cited_by_count":9,"area":"lr"},{"id":"2601.11442","title":"Map2Thought: Explicit 3D Spatial Reasoning via Metric Cognitive Maps","created":"2026-01-16","cited_by_count":8,"area":"lr"},{"id":"2603.19235","title":"Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding","created":"2026-03-19","cited_by_count":7,"area":"lr"},{"id":"2505.16663","title":"CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"id":"2511.17384","title":"IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation","created":"2025-11-21","cited_by_count":5,"area":"lr"},{"id":"2511.20644","title":"Vision-Language Memory for Spatial Reasoning","created":"2025-11-25","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":"2503.19794","title":"PAVE: Patching and Adapting Video Large Language Models","created":"2025-03-25","cited_by_count":4,"area":"lr"},{"id":"2506.21188","title":"GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding","created":"2025-06-26","cited_by_count":4,"area":"lr"},{"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":"2510.03896","title":"GAE: Unleashing Physical Potential of VLM with Generalizable Action Expert","created":"2025-10-04","cited_by_count":4,"area":"lr"},{"id":"2510.04479","title":"VaseVQA-3D: Benchmarking 3D VLMs on Ancient Greek Pottery","created":"2025-10-06","cited_by_count":4,"area":"lr"},{"id":"2511.19119","title":"MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images","created":"2025-11-24","cited_by_count":3,"area":"lr"},{"id":"2603.00409","title":"SSR: Pushing the Limit of Spatial Intelligence with Structured Scene Reasoning","created":"2026-02-28","cited_by_count":2,"area":"lr"},{"id":"2603.18002","title":"Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2603.22057","title":"SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning","created":"2026-03-23","cited_by_count":2,"area":"lr"},{"id":"2605.22036","title":"GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation","created":"2026-05-21","cited_by_count":2,"area":"lr"},{"id":"2210.00858","title":"Enhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic Approach","created":"2022-10-03","cited_by_count":1,"area":"lr"},{"id":"2512.03284","title":"SpatialReasoner: Active Perception for Large-Scale 3D Scene Understanding","created":"2025-12-02","cited_by_count":1,"area":"lr"},{"id":"2602.06041","title":"Predicting Camera Pose from Perspective Descriptions for Spatial Reasoning","created":"2026-02-05","cited_by_count":1,"area":"lr"},{"id":"2602.19063","title":"Direction-aware 3D Large Multimodal Models","created":"2026-02-22","cited_by_count":1,"area":"lr"},{"id":"2603.24721","title":"Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models","created":"2026-03-25","cited_by_count":1,"area":"lr"},{"id":"2607.01784","title":"SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video","created":"2026-07-02","cited_by_count":1,"area":"lr"},{"id":"2608.01899","title":"SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Models","created":"2026-08-03","cited_by_count":1,"area":"lr"},{"id":"2608.04610","title":"HiSC: Hierarchical Spatial Clustering Token Compression for Efficient 3D Scene Understanding","created":"2026-08-05","cited_by_count":1,"area":"lr"},{"id":"2608.13226","title":"CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport","created":"2026-08-13","cited_by_count":1,"area":"lr"},{"id":"2507.01800","title":"HCNQA: Enhancing 3D VQA with Hierarchical Concentration Narrowing Supervision","created":"2025-07-02","cited_by_count":0,"area":"lr"},{"id":"2508.04350","title":"Chain of Questions: Guiding Multimodal Curiosity in Language Models","created":"2025-08-06","cited_by_count":0,"area":"lr"},{"id":"2510.17034","title":"Where, Not What: Compelling Video LLMs to Learn Geometric Causality for 3D-Grounding","created":"2025-10-19","cited_by_count":0,"area":"lr"},{"id":"2602.15237","title":"Ground-Truth Depth in Vision Language Models: Spatial Context Understanding in Conversational AI for XR-Robotic Support in Emergency First Response","created":"2026-02-16","cited_by_count":0,"area":"lr"},{"id":"2603.17980","title":"Feeling the Space: Egomotion-Aware Video Representation for Efficient and Accurate 3D Scene Understanding","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.02689","title":"Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2604.07070","title":"EVGeoQA: Benchmarking LLMs on Dynamic, Multi-Objective Geo-Spatial Exploration","created":"2026-04-08","cited_by_count":0,"area":"lr"},{"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":"2605.09719","title":"Distilling 3D Spatial Reasoning into a Lightweight Vision-Language Model with CoT","created":"2026-05-10","cited_by_count":0,"area":"lr"},{"id":"2605.26232","title":"Not All Modalities Are Equal: Instruction-Aware Gating for Multimodal Videos","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"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":"2606.03100","title":"Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2606.07529","title":"CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models","created":"2026-04-21","cited_by_count":0,"area":"lr"},{"id":"2607.06620","title":"SpaR3D-MoE: Adaptive 3D Spatial Reasoning from Sparse Views Meets Geometry-Inductive Mixture-of-Experts","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2608.01185","title":"3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering","created":"2026-08-02","cited_by_count":0,"area":"lr"},{"id":"2608.10864","title":"Multi-View Relational Distillation for Spatial Reasoning with Vision-Language Models","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.14741","title":"PolyComp: A Polycube-based Benchmark for Compositional 3D Spatial Reasoning in Multimodal Models","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2609.01059","title":"Dyn-3D: Unveiling and Resolving Ego-Motion Ambiguity in Vision-Language Models","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2609.13158","title":"TestHallVQA: Exploring LVLMs' Document-Level Reasoning under Redundant Contexts from Scientific Exams","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2609.37187","title":"InsightMap: Structured Spatial Modeling for Embodied Multimodal Reasoning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.05417","title":"Render to Reason: Novel-View Semantic Prediction Improves Spatial Understanding in VLMs","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.17844","title":"What Makes a Good Visual Representation for Spatial Understanding in MLLMs?","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}