mlsanityData to 14 Oct 2026

Imagine while Reasoning in Space: Multimodal Visualization-of-Thought

arXiv 2501.07542 ↗First posted 13 Jan 2025cs.CL cs.CV cs.LGcited by 206

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

Chain-of-Thought (CoT) prompting has proven highly effective for enhancing complex reasoning in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs). Yet, it struggles in complex spatial reasoning tasks. Nonetheless, human cognition extends beyond language alone, enabling the remarkable capability to think in both words and images. Inspired by this mechanism, we propose a new reasoning paradigm, Multimodal Visualization-of-Thought (MVoT). It enables visual thinking in MLLMs by generating image visualizations of their reasoning traces. To ensure high-quality visualization, we introduce token discrepancy loss into autoregressive MLLMs. This innovation significantly improves both visual coherence and fidelity. We validate this approach through several dynamic spatial reasoning tasks. Experimental results reveal that MVoT demonstrates competitive performance across tasks. Moreover, it exhibits robust and reliable improvements in the most challenging scenarios where CoT fails. Ultimately, MVoT establishes new possibilities for complex reasoning tasks where visual thinking can effectively complement verbal reasoning.

Key facts. Cited by 206 papers in the map (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 24 of its 59 references that are in the map. First posted on arXiv 13 Jan 2025.

Builds on

24 of 59 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models13 Jun
  2. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action20 Mar

Other references · 22

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2023Mistral 7Bcited by 3,164
  5. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  6. 2016OpenAI Gymcited by 1,736
  7. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 927
  8. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  9. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 483
  10. 2023Learning Interactive Real-World Simulatorscited by 458
  11. 20243D-VLA: A 3D Vision-Language-Action Generative World Modelcited by 328
  12. 2024SpatialRGPT: Grounded Spatial Reasoning in Vision Language Modelscited by 311
10 more
  1. 2023DriveDreamer: Towards Real-world-driven World Models for Autonomous Drivingcited by 261
  2. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 179
  3. 2024ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generationcited by 114
  4. 2024SAT: Dynamic Spatial Aptitude Training for Multimodal Language Modelscited by 114
  5. 2024Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyondcited by 111
  6. 2024Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Modelscited by 57
  7. 2024No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Modelscited by 53
  8. 2024Multimodal Latent Language Modeling with Next-Token Diffusioncited by 48
  9. 2024JetFormer: An Autoregressive Generative Model of Raw Images and Textcited by 46
  10. 2024A Closer Look at Logical Reasoning with LLMs: The Choice of Tool Matterscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 109; 2026: 97.

206 papers.

Sort:

By area:

  1. 2025DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learningcited by 410
  2. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
  3. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  4. 2025Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontierscited by 199
  5. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 182
  6. 2025Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawingcited by 136
  7. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 135
  8. 2025Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokenscited by 124
  9. 2025Latent Visual Reasoningcited by 104
  10. 2025Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoningcited by 91
  11. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 90
  12. 2025Visual Planning: Let's Think Only with Imagescited by 85
38 more
  1. 2025Zebra-CoT: A Dataset for Interleaved Vision Language Reasoningcited by 84
  2. 2025Monet: Reasoning in Latent Visual Space Beyond Images and Languagecited by 82
  3. 2025Thinking with Generated Imagescited by 73
  4. 2025Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokenscited by 71
  5. 2025VL-JEPA: Joint Embedding Predictive Architecture for Vision-languagecited by 68
  6. 2025UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokenscited by 56
  7. 2025ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoningcited by 56
  8. 2025Look-Back: Implicit Visual Re-focusing in MLLM Reasoningcited by 55
  9. 2025LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?cited by 49
  10. 2025MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoningcited by 49
  11. 2025SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoningcited by 46
  12. 2025Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Taskscited by 44
  13. 2025How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspectivecited by 43
  14. 2025Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMscited by 43
  15. 2025Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmarkcited by 43
  16. 2025Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulationcited by 42
  17. 2025Visual Representation Alignment for Multimodal Large Language Modelscited by 41
  18. 2025VisRL: Intention-Driven Visual Perception via Reinforced Reasoningcited by 39
  19. 2025VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Modelscited by 37
  20. 2025Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzlescited by 36
  21. 2025Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thoughtcited by 35
  22. 2025MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoningcited by 35
  23. 2025AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPOcited by 33
  24. 2025Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarkscited by 33
  25. 2025Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecturecited by 30
  26. 2025Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Spacecited by 28
  27. 2025From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Modelscited by 26
  28. 2025Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Toolscited by 26
  29. 2025v1: Learning to Point Visual Tokens for Multimodal Grounded Reasoningcited by 25
  30. 2025SIFThinker: Spatially-Aware Image Focus for Visual Reasoningcited by 25
  31. 2025Sketch-in-Latents: Eliciting Unified Reasoning in MLLMscited by 25
  32. 2025MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Modelscited by 24
  33. 2025VeriThinker: Learning to Verify Makes Reasoning Model Efficientcited by 24
  34. 2025UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learningcited by 24
  35. 2025CMMCoT: Enhancing Complex Multi-Image Comprehension via Multi-Modal Chain-of-Thought and Memory Augmentationcited by 23
  36. 2025Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)cited by 23
  37. 2025ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Mapscited by 23
  38. 2025CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Imagescited by 23

50 most cited of 206 All 206 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs
  2. 2024Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models
  3. 2025VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning
  4. 2024Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models
  5. 2025MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models
  6. 2024Cantor: Inspiring Multimodal Chain-of-Thought of MLLM
  7. 2026SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learning
  8. 2026How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning