mlsanityData to 7 Oct 2026

ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models

arXiv 2505.21500 ↗First posted 27 May 2025cs.CV cs.AI cs.CLcited by 110

On the map: LLM reasoning → Spatial and embodied reasoning

also in 1 more
Abstract (arXiv)

Vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and reasoning about visual content, but significant challenges persist in tasks requiring cross-viewpoint understanding and spatial reasoning. We identify a critical limitation: current VLMs excel primarily at egocentric spatial reasoning (from the camera's perspective) but fail to generalize to allocentric viewpoints when required to adopt another entity's spatial frame of reference. We introduce ViewSpatial-Bench, the first comprehensive benchmark designed specifically for multi-viewpoint spatial localization recognition evaluation across five distinct task types, supported by an automated 3D annotation pipeline that generates precise directional labels. Comprehensive evaluation of diverse VLMs on ViewSpatial-Bench reveals a significant performance disparity: models demonstrate reasonable performance on camera-perspective tasks but exhibit reduced accuracy when reasoning from a human viewpoint. By fine-tuning VLMs on our multi-perspective spatial dataset, we achieve an overall performance improvement of 46.24% across tasks, highlighting the efficacy of our approach. Our work establishes a crucial benchmark for spatial intelligence in embodied AI systems and provides empirical evidence that modeling 3D spatial relationships enhances VLMs' corresponding spatial comprehension capabilities.

Key facts. Cited by 110 papers in the map (data through 7 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 36 of its 41 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

36 of 41 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation24 Apr
  2. 2025How to Enable LLM with 3D Capacity? A Survey of Spatial Reasoning in LLM8 Apr
  3. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces18 Dec
  4. 20243DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark10 Dec
  5. 2024An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models9 Nov
  6. 2024GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs19 Jun
  7. 2024SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models3 Jun
  8. 2024SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors18 Mar
  9. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities22 Jan
  10. 2023What's "up" with vision-language models? Investigating their struggle with spatial reasoning30 Oct

Other references · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  5. 2025Qwen2.5-VL Technical Reportcited by 5,418
  6. 2024GPT-4o System Cardcited by 4,467
  7. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  8. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  9. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  10. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  11. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,573
  12. 2025Kimi-VL Technical Reportcited by 381
14 more
  1. 2024An Introduction to Vision-Language Modelingcited by 175
  2. 2024RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Roboticscited by 133
  3. 2024Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understandingcited by 131
  4. 2025STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?cited by 74
  5. 2025Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learningcited by 71
  6. 2024SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Groundingcited by 66
  7. 2024Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Modelscited by 45
  8. 2024ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imaginationcited by 38
  9. 2025Multi-agent Embodied AI: Advances and Future Directionscited by 36
  10. 2024SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluationcited by 31
  11. 2024Cross-aware Early Fusion with Stage-divided Vision and Language Transformer Encoders for Referring Image Segmentationcited by 21
  12. 2024Pre-trained Vision-Language Models Learn Discoverable Visual Conceptscited by 16
  13. 2024Where Do We Go from Here? Multi-scale Allocentric Relational Inference from Natural Spatial Descriptionscited by 3
  14. 2024Can VLMs be used on videos for action recognition? LLMs are Visual Reasoning Coordinatorscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 22; 2026: 88.

110 papers.

Sort:

By area:

  1. 2025OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Modelscited by 105
  2. 2025SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Modelscited by 83
  3. 2025Scaling Spatial Intelligence with Multimodal Foundation Modelscited by 75
  4. 2025Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenescited by 62
  5. 2025Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Viewscited by 58
  6. 2025How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspectivecited by 41
  7. 2025Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learningcited by 38
  8. 2025SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognitioncited by 35
  9. 2026STEP3-VL-10B Technical Reportcited by 28
  10. 2026SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecturecited by 27
  11. 2025Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methodscited by 22
  12. 2025SpaceVista: All-Scale Visual Spatial Reasoning from mm to kmcited by 18
38 more
  1. 2026HY-Embodied-0.5: Embodied Foundation Models for Real-World Agentscited by 18
  2. 2026Thinking with Geometry: Active Geometry Integration for Spatial Reasoningcited by 14
  3. 2026SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoningcited by 13
  4. 2025SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMscited by 12
  5. 2025ODI-Bench: Can MLLMs Understand Immersive Omnidirectional Environments?cited by 12
  6. 2026CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environmentscited by 8
  7. 2026MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoningcited by 8
  8. 2026PanoEnv: Exploring 3D Spatial Intelligence in Panoramic Environments with Reinforcement Learningcited by 7
  9. 2026S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligencecited by 7
  10. 2026Hy-Embodied-VLM-1.0: Efficient Physical-World Agentscited by 7
  11. 2026Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoningcited by 6
  12. 2026SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environmentscited by 6
  13. 2026Allocentric Perceiver: Disentangling Allocentric Reasoning from Egocentric Visual Priors via Frame Instantiationcited by 5
  14. 2025Video2Layout: Recall and Reconstruct Metric-Grounded Cognitive Map for Spatial Reasoningcited by 4
  15. 20263ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Modelscited by 4
  16. 2026SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environmentscited by 4
  17. 2026OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMscited by 4
  18. 2026Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulatorscited by 4
  19. 2025Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AIcited by 3
  20. 2025MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Imagescited by 3
  21. 2025Scaling Spatial Reasoning in MLLMs through Programmatic Data Synthesiscited by 3
  22. 2026ReMoT: Reinforcement Learning with Motion Contrast Tripletscited by 3
  23. 2026CRAFT: Grounded Multi-Agent Coordination Under Partial Informationcited by 3
  24. 2026ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Modelscited by 3
  25. 2026Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistencycited by 3
  26. 2026Keep It in Mind: User Centric Continual Spatial Intelligence Reasoning in Egocentric Video Streamscited by 3
  27. 2026MindEdit-Bench: Benchmarking Object-Level Counterfactual Spatial Reasoning in VLMs from In-the-Wild Photoscited by 3
  28. 2026Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoningcited by 3
  29. 2026MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMscited by 3
  30. 2025GroundAct: Can LLM Agents Ground Actions in Environmental States?cited by 2
  31. 2025Pursuing Minimal Sufficiency in Spatial Reasoningcited by 2
  32. 2025Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspectivecited by 2
  33. 2026Thinking in Structures: Evaluating Spatial Intelligence in Constraint-Governed Spacescited by 2
  34. 2026Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sportscited by 2
  35. 2026Communicating about Space: Language-Mediated Spatial Integration Across Partial Viewscited by 2
  36. 2026LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Modelscited by 2
  37. 2026ETCHR: Editing To Clarify and Harness Reasoningcited by 2
  38. 2026ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMscited by 2

50 most cited of 110 All 110 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models
  2. 2025Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models
  3. 2026Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models
  4. 2025MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence
  5. 2024Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
  6. 2026Why Far Looks Up: Probing Spatial Representation in Vision-Language Models
  7. 2026ESPIRE: A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models
  8. 2026ERGeoBench:A Comprehensive Benchmark for Embodied Reasoning and Geo-localization in Multimodal Large Language Models