mlsanityData to 14 Oct 2026

Visual Spatial Tuning

arXiv 2511.05491 ↗First posted 7 Nov 2025cs.CVcited by 89

Not on the map. Why?

Cited by 62 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Capturing spatial relationships from visual inputs is a cornerstone of human-like general intelligence. Several previous studies have tried to enhance the spatial awareness of Vision-Language Models (VLMs) by adding extra expert encoders, which brings extra overhead and usually harms general capabilities. To enhance the spatial ability in general architectures, we introduce Visual Spatial Tuning (VST), a comprehensive framework to cultivate VLMs with human-like visuospatial abilities, from spatial perception to reasoning. We first attempt to enhance spatial perception in VLMs by constructing a large-scale dataset termed VST-P, which comprises 4.1 million samples spanning 19 skills across single views, multiple images, and videos. Then, we present VST-R, a curated dataset with 135K samples that instruct models to reason in space. In particular, we adopt a progressive training pipeline: supervised fine-tuning to build foundational spatial knowledge, followed by reinforcement learning to further improve spatial reasoning abilities. Without the side-effect to general capabilities, the proposed VST consistently achieves state-of-the-art results on several spatial benchmarks, including 34.8% on MMSI-Bench and 61.2% on VSIBench. It turns out that the Vision-Language-Action models can be significantly enhanced with the proposed spatial tuning paradigm, paving the way for more physically grounded AI.

Key facts. Cited by 89 papers in the map (data through 14 Oct 2026). Builds on 73 of its 86 references that are in the map. First posted on arXiv 7 Nov 2025.

Builds on

73 of 86 references.

References · 73

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2023Visual Instruction Tuningcited by 7,869
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2025Qwen2.5-VL Technical Reportcited by 5,587
  6. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  7. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  8. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  9. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  10. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  11. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  12. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
38 more
  1. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  2. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  3. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  4. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  5. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,516
  6. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  7. 2024Qwen2 Technical Reportcited by 2,120
  8. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  9. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  10. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  11. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  12. 2019Towards VQA Models That Can Readcited by 1,718
  13. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  14. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  15. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,479
  16. 2024Depth Anything V2cited by 1,422
  17. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  18. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  19. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  20. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,195
  21. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?cited by 914
  22. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 838
  23. 2016A Diagram Is Worth A Dozen Imagescited by 804
  24. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  25. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 706
  26. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Modelscited by 665
  27. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spacescited by 611
  28. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 604
  29. 2024LLaVA-Video: Video Instruction Tuning With Synthetic Datacited by 583
  30. 2024BLINK: Multimodal Large Language Models Can See but Not Perceivecited by 550
  31. 2024DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Modelscited by 490
  32. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 476
  33. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 454
  34. 2025Seed1.5-VL Technical Reportcited by 373
  35. 2024Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Modelscited by 329
  36. 2024SpatialRGPT: Grounded Spatial Reasoning in Vision Language Modelscited by 311
  37. 20233D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignmentcited by 204
  38. 2025MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligencecited by 183

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 86.

89 papers.

Sort:

By area:

  1. 2025Scaling Spatial Intelligence with Multimodal Foundation Modelscited by 82
  2. 2026MolmoAct2: Action Reasoning Models for Real-world Deploymentcited by 50
  3. 2025SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognitioncited by 35
  4. 2026Visual Generation Unlocks Human-Like Reasoning through Multimodal World Modelscited by 19
  5. 2026Thinking with Geometry: Active Geometry Integration for Spatial Reasoningcited by 18
  6. 2026SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoningcited by 15
  7. 2026ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoningcited by 15
  8. 2025SpatialTree: How Spatial Abilities Branch Out in MLLMscited by 12
  9. 2026Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D Worldcited by 12
  10. 2026JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generationcited by 12
  11. 2026On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMscited by 11
  12. 2026Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Trainingcited by 11
38 more
  1. 2026PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policiescited by 7
  2. 2026Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoningcited by 6
  3. 2026Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligencecited by 6
  4. 2026OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligencecited by 6
  5. 2026GEM: Generative Supervision Helps Embodied Intelligencecited by 6
  6. 2026OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMscited by 6
  7. 2026SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environmentscited by 5
  8. 2026Cambrian-P: Pose-Grounded Video Understandingcited by 5
  9. 2026Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulatorscited by 5
  10. 2026Vesta: A Generalist Embodied Reasoning Modelcited by 5
  11. 2026OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streamscited by 4
  12. 2026Let Geometry GUIDE: Layer-wise Unrolling of Geometric Priors in Multimodal LLMscited by 4
  13. 20264DThinker: Thinking with 4D Imagery for Dynamic Spatial Understandingcited by 4
  14. 2026ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Modelscited by 4
  15. 2026Watch, Remember, Reason: Human-View Video Understanding with MLLMscited by 4
  16. 2026Keep It in Mind: User Centric Continual Spatial Intelligence Reasoning in Egocentric Video Streamscited by 4
  17. 2026Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMscited by 4
  18. 2026Probing Visual Concepts in Lightweight Vision-Language Models for Automated Drivingcited by 3
  19. 2026GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Modelscited by 3
  20. 2026MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Modelcited by 3
  21. 2026Cog3DMap: Multi-View Vision-Language Reasoning with 3D Cognitive Mapscited by 3
  22. 2026HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Modelscited by 3
  23. 2026Grounded 3D-Aware Spatial Vision-Language Modelingcited by 3
  24. 2026Smooth Operator: Smooth Verifiable Reward Activates Spatial Reasoning Ability of Vision-Language Modelcited by 2
  25. 2026SSR: Pushing the Limit of Spatial Intelligence with Structured Scene Reasoningcited by 2
  26. 2026Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sportscited by 2
  27. 2026ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMscited by 2
  28. 2026SpatialUAV: Benchmarking Spatial Intelligence for Low-Altitude UAV Perception, Collaboration, and Motioncited by 2
  29. 2026OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mappingcited by 2
  30. 2026DynTrace: Tracking Dynamic Object Evidence for 4D Spatio-Temporal Reasoning in MLLMscited by 2
  31. 2026Knowing the Self, Understanding the World: A Dual-Cognition Benchmark for UAV Spatio-temporal Reasoning with MLLMscited by 2
  32. 2026Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modelingcited by 2
  33. 20263D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understandingcited by 1
  34. 2026ViewFusion: Structured Spatial Thinking Chains for Multi-View Reasoningcited by 1
  35. 2026From Where Things Are to What They Are For: Benchmarking Spatial-Functional Intelligence in Multimodal LLMscited by 1
  36. 2026SpaceMind++: Toward Allocentric Cognitive Maps for Spatially Grounded Video MLLMscited by 1
  37. 2026Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligencecited by 1
  38. 2026SpaceDG: Benchmarking Spatial Intelligence under Visual Degradationcited by 1

50 most cited of 89 All 89 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective
  2. 2024Expand VSR Benchmark for VLLM to Expertize in Spatial Rules
  3. 2025Improved Visual-Spatial Reasoning via R1-Zero-Like Training
  4. 2025Towards Visuospatial Cognition via Hierarchical Fusion of Visual Experts
  5. 2025Imagine in Space: Exploring the Frontier of Spatial Intelligence and Reasoning Efficiency in Vision Language Models
  6. 2025Defining and Evaluating Visual Language Models' Basic Spatial Abilities: A Perspective from Psychometrics
  7. 2024Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
  8. 2025Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models