VLM Reasoning

VLM: Vision-Language Model

Ask about this topic

Overview

This field studies how models connect images or video with language to solve tasks involving spatial relations, time, causality, diagrams, and action. Common approaches include chain-of-thought prompting, visual tools and retrieval, structured representations such as scene graphs, and fine-tuning with process-level rewards. Benchmarks increasingly test whether answers and intermediate steps are grounded in visual evidence, including in multi-image, video, scientific, and embodied settings. A central tension is that longer reasoning can help on complex tasks but can also weaken visual grounding, amplify language-based shortcuts, or produce explanations that do not reflect how an answer was reached.

Latest papers

CardsList

853 papers96 papers in the last four weeks, up 48% on the four weeks before. 0.6% of all new papers.

  1. Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs

    Mar 23, 2026Efthymios Tsaprazlis, Tiantian Feng, Anil Ramakrishna +3VLM EvaluationPrivacy Auditing

    University of Southern California, Los Angeles CA 90089, USA · Meta Superintelligence Labs · Amazon AGI

  2. VIGIL: Part-Grounded Structured Reasoning for Generalizable Deepfake Detection

    Mar 23, 2026Xinghan Li, Junhao Xu, Jingjing ChenExplainable Deepfake DetectionDeepfake Detection

    College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China.

  3. Beyond Static Visual Tokens: Structured Sequential Visual Chain-of-Thought Reasoning

    Mar 21, 2026Guangfu Guo, Xiaoqian Lu, Yue Feng +1VLM ReasoningMultimodal CoT Reasoning

    Beijing Institute of Mathematical Sciences and Applications · University of Bristol · University of Birmingham

  4. When Negation Is a Geometry Problem in Vision-Language Models

    Mar 20, 2026Fawaz Sammani, Tzoulio Chamiti, Paul Gavrikov +1VLM ReasoningVLM Evaluation

    ETRO Department, Vrije Universiteit Brussel, Belgium · imec, Kapeldreef 75, B-3001 Leuven, Belgium · Independent Researcher

  5. CoVR-R:Reason-Aware Composed Video Retrieval

    Mar 20, 2026Omkar Thawakar, Dmitry Demidov, Vaishnav Potlapalli +5Composed Video RetrievalVLM Reasoning

    Mohamed bin Zayed University of AI · University of Chicago · University of Wisconsin-Madison +1

  6. Chain-of-Adaptation: Surgical Vision-Language Adaptation with Reinforcement Learning

    Mar 20, 2026Jiajie Li, Chenhui Xu, Meihuan Liu +1VLM AdaptationMedical VLMs

    University at Buffalo Buffalo, NY, USA

  7. Contextual inference from single objects in Vision-Language models

    Mar 20, 2026Martina G. Vilas, Timothy Schaumlöffel, Gemma RoigVision-Language ModelsVLM Reasoning

    Goethe University Frankfurt · The Hessian Center for AI

  8. Motion-o: Trajectory-Grounded Video Reasoning

    Mar 19, 2026Bishoy Galoaa, Shayda Moezzi, Xiangyu Bai +1Video ReasoningVLM Reasoning

    Northeastern University

  9. Perceptio: Perception Enhanced Vision Language Models via Spatial Token Generation

    Mar 19, 2026Yuchen Li, Amanmeet Garg, Shalini Chaudhuri +2Large Vision-Language ModelsVisual Spatial Reasoning

    Amazon

  10. Balanced Thinking: Improving Chain of Thought Training in Vision Language Models

    Mar 19, 2026Shaked Perek, Ben Wiesel, Avihu Dekel +2PEFT of VLMsVLM Reasoning

    IBM Research

  11. Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models

    Mar 19, 2026Liwei Che, Zhiyu Xue, Yihao Quan +7VLM ReasoningLarge Vision-Language Models

    Rutgers University · UC Santa Barbara · University of Washington +1

  12. Mind the Rarities: Can Rare Skin Diseases Be Reliably Diagnosed via Diagnostic Reasoning?

    Mar 19, 2026Yang Liu, Jiyao Yang, Hongjin Zhao +10Rare Disease DiagnosisMedical VLMs

    Carnegie Mellon University · University of Alabama at Birmingham · Australian National University +3

  13. Universal Skeleton Understanding via Differentiable Rendering and MLLMs

    Mar 18, 2026Ziyi Wang, Peiming Li, Xinshun Wang +3Skeleton-Based Action RecognitionMultimodal Large Language Models

    State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, China · Tencent · Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China

  14. Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models

    Mar 18, 2026Yuhao Dong, Zuyan Liu, Shulin Tian +2VLM ReasoningMultimodal Large Language Models

    S-Lab, Nanyang Technological University, Tencent Hunyuan, and Tsinghua University

  15. WeatherReasonSeg: A Benchmark for Weather-Aware Reasoning Segmentation in Visual Language Models

    Mar 18, 2026Wanjun Du, Zifeng Yuan, Tingting Chen +3VLM RobustnessVLM Reasoning

    Beijing Jiaotong University · National University of Singapore · Monash University

  16. MCoT-MVS: Multi-level Vision Selection by Multi-modal Chain-of-Thought Reasoning for Composed Image Retrieval

    Mar 18, 2026Xuri Ge, Chunhao Wang, Xindi Wang +3Composed Image RetrievalVLM Reasoning

    Shandong University Jinan, China · Shandong University Qingdao, China

  17. Recurrent Reasoning with Vision-Language Models for Estimating Long-Horizon Embodied Task Progress

    Mar 18, 2026Yuelin Zhang, Sijie Cheng, Chen Li +4Robot Task Progress EstimationVLMs for Robotics

    Gaoling School of Artificial Intelligence, Renmin University of China · Beijing Key Laboratory of Research on Large Models and Intelligent Governance · Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE +2

  18. HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

    Mar 17, 2026Shenzhi Wang, Shixuan Liu, Jing Zhou +8Reasoning for VLMsVLM Reasoning

    Qwen Team, Alibaba Inc. · LeapLab, Tsinghua University

  19. Retrieving Counterfactuals Improves Visual In-Context Learning

    Mar 17, 2026Guangzhi Xiong, Sanchit Sinha, Zhenghao He +1Multimodal ICLRetrieval-Augmented ICL

    University of Virginia

  20. The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models

    Mar 17, 2026Robert Welch, Emir Konuk, Kevin SmithConfidence Estimation for VLMsVLM Reasoning

    KTH Royal Institute of Technology, Stockholm, Sweden · Science for Life Laboratory, Stockholm, Sweden

  21. Understanding Pruning Regimes in Vision-Language Models Through Domain-Aware Layer Selection

    Mar 17, 2026Saeed Khaki, Nima Safaei, Kamal GinotraLVLM PruningNeural Network Pruning

    Ohio State University

  22. Visual Distraction Undermines Moral Reasoning in Vision-Language Models

    Mar 17, 2026Xinyi Yang, Chenheng Xu, Weijun Hong +4Multimodal Multi-Turn Safety AlignmentVLM Reasoning

    Institute for Artificial Intelligence, Peking University · School of Psychological and Cognitive Sciences, Peking University · State Key Lab of General Artificial Intelligence, Peking University +3

  23. When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition

    Mar 17, 2026Xiaokun Sun, Yubo Wang, Haoyu Cao +1Video ReasoningVideo QA

    University of Science and Technology of China · State Key Laboratory of Cognitive Intelligence

  24. Grounding the Score: Explicit Visual Premise Verification for Reliable Vision-Language Process Reward Models

    Mar 17, 2026Junxin Wang, Dai Guan, Weijie Qiu +7Process Reward ModelsVLM Reasoning

    Qwen Large Model Application Team, Alibaba · Institute of Automation, Chinese Academy of Sciences · Beijing University of Posts and Telecommunications

  25. Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement Learning

    Mar 17, 2026Haomin Wang, Qi Wei, Qianli Ma +4Text-to-SVG GenerationVLM Reasoning

    Shanghai Jiao Tong University · Shanghai AI Laboratory · Nanjing University +1

  26. PhysQuantAgent: An Inference Pipeline of Mass Estimation for Vision-Language Models

    Mar 17, 2026Hisayuki Yokomizo, Taiki Miyanishi, Yan Gang +3VLM ReasoningVLMs for Robotics

    The University of Tokyo · Institute of Science Tokyo · National Institute of Informatics

  27. Clue Matters: Leveraging Latent Visual Clues to Empower Video Reasoning

    Mar 16, 2026Kaixin zhang, Xiaohe Li, Jiahao Li +4Video ReasoningVideo QA

    Aerospace Information Research Institute, Chinese Academy of Sciences · University of Chinese Academy of Sciences

  28. Video-CoE: Reinforcing Video Event Prediction via Chain of Events

    Mar 16, 2026Qile Su, Jing Tang, Rui Chen +2Video PredictionTemporal Video Understanding

    AMAP, Alibaba Group

  29. WorldVLM: Combining World Model Forecasting and Vision-Language Reasoning

    Mar 15, 2026Stefan Englmeier, Katharina Winter, Fabian B. FlohrVLMs for Autonomous DrivingWorld Models for Autonomous Driving

    Munich University of Applied Sciences, Intelligent Vehicles Lab (IVL), 80335 Munich, Germany

  30. StAR: Segment Anything Reasoner

    Mar 15, 2026Seokju Yun, Dongheon Lee, Noori Bae +3Reasoning SegmentationVLM Reasoning

    KAIST AI · University of Seoul