Visual CoT

CoT: Chain-of-Thought

Visual Chain-of-Thought explores whether making intermediate visual reasoning explicit helps multimodal models interpret images and act on them. Approaches include attending to image regions in sequence, exploring reconstructed 3D scenes, predicting coordinates, and generating sketches or other visual intermediates; these are trained with supervised reasoning traces and reinforcement learning. Evaluations span spatial and geometry problems, visual grounding, medical question answering, video segmentation, image editing, and robotics. Visual intermediates can help with spatial tasks, but are not consistently better than text-only reasoning, and a central challenge is ensuring that intermediate steps are accurate and genuinely contribute to the answer.

Latest papers

19 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Flow-of-Thought: A Framework for Visual Reasoning
Oct 7, 2026Mariia Baidachna, Nicolas PugeaultVisual Reasoning Spatial Reasoning
University of Glasgow
Beyond Generation and Accuracy: Diagnosing and Enhancing Visual Chain-of-Thought for Geometry Problem Solving
Sep 11, 2026Zhitong Dong, Jicai Pan, Yingguo Gao +3Mathematical Reasoning Multimodal CoT Reasoning
1Key Laboratory of New Generation Artificial Intelligence Technology, Southeast University Group · 2Ant
CoVA-SFT: A Large-Scale Dataset for Chain of Visual Abstractions
Aug 29, 2026Tsung-Han Wu, Heekyung Lee, Anya Ji +4Multimodal Dataset Visual CoT
University of California, Berkeley
X-Mind: Efficient Visual Chain-of-Thought via Predictive World Model for End-to-End Driving
Jun 27, 2026Bohao Zhao, Chengrui Wei, Guangfeng Jiang +17World Model Learning End-to-End Autonomous Driving
PWM Team, XPeng Inc.
PointVG-R: Internalizing Geometric Reasoning in MLLMs for Precise Pointing Localization via Visual Chain of Thought
Jun 23, 2026Ling Li, Bowen Liu, Zinuo Zhan +5Visual Spatial Reasoning Vision-Language Grounding
Tsinghua University Beijing Shi, China · Dalian University of Technology Dalian Shi, China · Northwestern Polytechnical University Xi’an Shi, China +1
ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models
Jun 22, 2026Jun Zhang, Jiasheng Zheng, Boxi Cao +5LLM Auditing LLM Interpretability
Chinese Information Processing Laboratory Institute of Software, Chinese Academy of Sciences · University of Chinese Academy of Sciences
Gen-VCoT: Generative Visual Chain-of-Thought Reasoning via Diffusion-Based RGB Intermediate Representations
Jun 15, 2026Zhiqiang Zhou, Junliang Dai, Xu lingVLM Interpretability Multimodal CoT Reasoning
Hunan Chemical Industry Vocational and Technical College, Zhuzhou, Hunan 412000, China
SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learning
Jun 10, 2026Chao Lei, Yanbei Jiang, Markus Hiller +4Visual Spatial Reasoning Reinforcement Learning with Verifiable Rewards
School of Computing and Information Systems The University of Melbourne Melbourne, Australia
VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation
Jun 5, 2026Ming Dai, Sen Yang, Boqiang Duan +4Video Object Segmentation Referring Video Object Segmentation
School of Automation, Southeast University, Nanjing, China · Baidu Inc, Beijing, China · College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, China
What's Holding Back Latent Visual Reasoning?
May 18, 2026André G. Viveiros, Nuno Gonçalves, André F. T. Martins +1Vision-Language Models Latent Visual Reasoning
Instituto Superior Técnico, Universidade de Lisboa · Instituto de Telecomunicações · Carnegie Mellon University +1
Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoning
Apr 8, 2026Jiahua Chen, Qihong Tang, Weinong Wang +13D Spatial Reasoning VLM Reasoning
Tsinghua University · Nanjing University · Tencent
Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision
Mar 27, 2026Ling Li, Bowen Liu, Zinuo Zhan +4Multimodal Grounding Visual Grounding
Tsinghua University, Beijing, China · Dalian University of Technology, Dalian, China · Northwestern Polytechnical University, Xi’an, China +1
Beyond Static Visual Tokens: Structured Sequential Visual Chain-of-Thought Reasoning
Mar 21, 2026Guangfu Guo, Xiaoqian Lu, Yue Feng +1VLM Reasoning Multimodal CoT Reasoning
Beijing Institute of Mathematical Sciences and Applications · University of Bristol · University of Birmingham
VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning
Mar 15, 2026Chaoyang Wang, Wenrui Bao, Sicheng Gao +5Vision-Language-Action Models Reasoning for VLA Models
University of Central Florida · University of Würzburg · University of Southern California +1
Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering
Mar 14, 2026Lin Fan, Yafei Ou, Zhipeng Deng +8Medical VQA Visual CoT
Southwest Jiaotong University · RIKEN · Hokkaido University +4
Generative Visual Chain-of-Thought for Image Editing
Mar 2, 2026Zijin Yin, Tiankai Hang, Yiji Cheng +9Text-Guided Image Editing Visual CoT
Beijing University of Posts and Telecommunications · Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance · Tencent Hunyuan +1
Thinking with Images as Continuous Actions: Numerical Visual Chain-of-Thought
Feb 27, 2026Kesen Zhao, Beier Zhu, Junbao Zhou +3Multimodal CoT Reasoning Visual CoT
Nanyang Technological University · Chalmers University of Technology and University of Gothenburg · University of Science and Technology of China
VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning
Nov 21, 2025Lingxiao Li, Yifan Wang, Xinyan Gao +3Visual Spatial Reasoning Visual Reasoning
Boston University, Boston, MA, USA · Stony Brook University, Stony Brook, NY, USA · MMLab, The Chinese University of Hong Kong, Hong Kong SAR, China
Vis-CoT: A Human-in-the-Loop Framework for Interactive Visualization and Intervention in LLM Chain-of-Thought Reasoning
Sep 1, 2025Kaviraj Pather, Elena Hadjigeorgiou, Arben Krasniqi +4LLM Interpretability Human-in-the-Loop AI
Department of Computer Science & Engineering University of Mauritius R´eduit 80837, Mauritius · Department of Electrical & Computer Engineering Cyprus University of Technology 3036 Limassol, Cyprus · Faculty of Electrical & Computer Engineering University of Prishtina ”Hasan Prishtina” 10000 Prishtina, Kosovo +4

Oct 7, 2026J/K move · Enter open · S save

Flow-of-Thought: A Framework for Visual Reasoning

Mariia Baidachna, Nicolas Pugeault

University of Glasgow

Visual Reasoning Spatial Reasoning Visual CoT Flow Map Learning

Open paper AskPDF arXiv

Mental imagery, ``seeing with the mind's eye'' is an essential aspect of human cognition. Despite rapid progress Large Language Models (LLMs) and Vision Transformers (ViTs) still underperform on tasks requiring spatial understanding. To address this, we introduce Flow-of-Thought (FoT), a framework that integrates the generation of visual sketches as intermediate reasoning steps, mimicking mental imagery in humans. We train coordinate-aware trajectory flow fields on

SO(2)

group orbits and cumulative shortest paths, then freeze the learned dynamics; same vs. different decisions compare competing generative hypotheses using foreground-weighted reconstruction energy. On locked tests FoT reaches 100.0% accuracy on Tetris and 99.0% on colored shapes. Under frozen transfer, the orbit-trained 2D flow improves over its endpoint-only control on BLINK Multi-view (72.2% vs. 63.9% on 133 public validation pairs), supporting continuous visual traces as an effective and interpretable representation for spatial reasoning in some out-of-distribution settings.