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. Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models

    Mar 15, 2026Ruiying Peng, Xueyu Wu, Jing Lei +3Multimodal Large Language ModelsVLM Reasoning

    Tsinghua Shenzhen International Graduate School · Huawei Technologies

  2. Improving Visual Reasoning with Iterative Evidence Refinement

    Mar 14, 2026Zeru Shi, Kai Mei, Yihao Quan +2VLM ReasoningVisually Grounded Reasoning

    Department of Computer Science Rutgers University

  3. Can AI Understand the Language of Origami?

    Mar 14, 2026Naaisha Agarwal, Yihan Wu, Xin Guan +7Physical ReasoningVLM Reasoning

    Independent Researcher · State Key Lab of CAD&CG, Zhejiang University · National Key Laboratory for Novel Software Technology, Nanjing University +2

  4. Locatability-Guided Adaptive Reasoning for Image Geo-Localization with Vision-Language Models

    Mar 13, 2026Bo Yu, Fengze Yang, Yiming Liu +6VLM ReasoningCross-View Geo-Localization

    The University of Utah · The University of Oklahoma · Worcester Polytechnic Institute +2

  5. Evaluating VLMs' Spatial Reasoning Over Robot Motion: A Step Towards Robot Planning with Motion Preferences

    Mar 13, 2026Wenxi Wu, Jingjing Zhang, Martim BrandãoVLM ReasoningVLMs for Robotics

    King’s College London · University College London

  6. Reasoning over Video: Evaluating How MLLMs Extract, Integrate, and Reconstruct Spatiotemporal Evidence

    Mar 13, 2026Seunghwan Bang, Hwanjun SongSpatiotemporal ReasoningVLM Reasoning

    UNIST · KAIST

  7. Think and Answer ME: Benchmarking and Exploring Multi-Entity Reasoning Grounding in Remote Sensing

    Mar 13, 2026Shuchang Lyu, Haiquan Wen, Guangliang Cheng +5Remote Sensing Visual GroundingVisual Grounding

    Beihang University, Beijing, China. · University of Liverpool, Liverpool, UK. · Institute of Acoustics, Chinese Academy of Sciences, Beijing, China

  8. Vision Verification Enhanced Fusion of VLMs for Efficient Visual Reasoning

    Mar 13, 2026Selim Furkan Tekin, Yichang Xu, Gaowen Liu +3VLM Hallucination MitigationVLM Reasoning

    Georgia Institute of Technology · Cisco Systems

  9. Feynman: Knowledge-Infused Diagramming Agent for Scalable Visual Designs

    Mar 13, 2026Zixin Wen, Yifu Cai, Kyle Lee +5Synthetic Data GenerationTool-Using Vision-Language Agents

    Carnegie Mellon University Pittsburgh, PA 15213, USA

  10. Surg-R1: A Hierarchical Reasoning Foundation Model for Scalable and Interpretable Surgical Decision Support with Multi-Center Clinical Validation

    Mar 12, 2026Jian Jiang, Chenxi Lin, Yiming Gu +24Medical VLMsSurgical Video Understanding

    Global College, Shanghai Jiao Tong University, Shanghai, China · Institute for Medical Engineering & Science, Massachusetts Institute of Technology, Cambridge, MA, USA · Department of Biomedical Engineering and Department of Electrical and Computer Engineering, National University of Singapore, Singapore +11

  11. Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

    Mar 12, 2026Yiran Guan, Liang Yin, Dingkang Liang +5Streaming Video UnderstandingVLM Reasoning

    Huazhong University of Science and Technology, Wuhan, China · MiLM Plus, Xiaomi Inc., Beijing, China

  12. BehaviorVLM: Unified Finetuning-Free Behavioral Understanding with Vision-Language Reasoning

    Mar 12, 2026Jingyang Ke, Weihan Li, Amartya Pradhan +2Animal Behavior AnalysisVLM Reasoning

    Georgia Institute of Technology Atlanta, GA, 30332 · Georgia Institute of Technology, Emory University Atlanta, GA, 30322

  13. Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks

    Mar 12, 2026Mei Chee Leong, Ying Gu, Hui Li Tan +2VLM EvaluationVision-Language Models

    Institute for Infocomm Research (I2R) · Present address: Institute of Advanced Intelligence and Computing (IAIC), Agency for Science, Technology and Research (A*STAR), Singapore

  14. VisDoT : Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought

    Mar 12, 2026Eunsoo Lee, Jeongwoo Lee, Minki Hong +2VLM ReasoningVisually Grounded Reasoning

    Department of Computer Science and Artificial Intelligence, Dongguk University · Department of Electronics and Electrical Engineering, Dongguk University

  15. See, Symbolize, Act: Grounding VLMs with Spatial Representations for Better Gameplay

    Mar 12, 2026Ashish Baghel, Paras ChopraVision-Language AgentsVision-Language Grounding

    Lossfunk

  16. Seeing Isn't Orienting: A Cognitively Grounded Benchmark Reveals Systematic Orientation Failures in MLLMs Supplementary

    Mar 12, 2026Nazia Tasnim, Keanu Nichols, Yuting Yang +4VLM ReasoningVLM Evaluation

    Boston University · Johns Hopkins University · Runway

  17. Learning to Wander: Improving the Global Image Geolocation Ability of LMMs via Actionable Reasoning

    Mar 11, 2026Yushuo Zheng, Huiyu Duan, Zicheng Zhang +2Multimodal Large Language ModelsVLM Reasoning

    Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory

  18. From Imitation to Intuition: Intrinsic Reasoning for Open-Instance Video Classification

    Mar 11, 2026Ke Zhang, Xiangchen Zhao, Yunjie Tian +3VLM ReasoningVideo Reasoning

    Johns Hopkins University · ByteDance Inc

  19. GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervision

    Mar 10, 2026Lang Sun, Ronghao Fu, Zhuoran Duan +3VLM ReasoningProcess Reward Models

    College of Computer Science and Technology, Jilin University, Changchun 130012, China · Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University

  20. Probing the Reliability of Driving VLMs: From Inconsistent Responses to Grounded Temporal Reasoning

    Mar 10, 2026Chun-Peng Chang, Chen-Yu Wang, Holger Caesar +1PEFT of VLMsTemporal Reasoning in VLMs

    DFKI Augmented Vision · TU Delft

  21. MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

    Mar 10, 2026Zongxia Li, Hongyang Du, Chengsong Huang +8Vision-Language ModelsVLM Reasoning

    University of Maryland · Brown University · Washington University in St. Louis +4

  22. NaviDriveVLM: Decoupling High-Level Reasoning and Motion Planning for Autonomous Driving

    Mar 9, 2026Ximeng Tao, Pardis Taghavi, Dimitar Filev +2VLMs for Autonomous DrivingAutonomous Driving Planning

    J. Mike Walker ’66 Department of Mechanical Engineering, Texas A&M University, College Station, TX 77843, USA · The Department of Engineering Technology and Industrial Distribution Texas A&M University, College Station, TX 77843, USA

  23. VLM-SubtleBench: How Far Are VLMs from Human-Level Subtle Comparative Reasoning?

    Mar 9, 2026Minkyu Kim, Sangheon Lee, Dongmin ParkVLM EvaluationVLM Reasoning

    KRAFTON · KAIST

  24. OrdinalBench: A Benchmark Dataset for Diagnosing Generalization Limits in Ordinal Number Understanding of Vision-Language Models

    Mar 8, 2026Yusuke Tozaki, Hisashi MiyamoriVLM EvaluationVLM Reasoning

    Division of Frontier Informatics, Kyoto Sangyo University, Kyoto, Japan

  25. Scaling Test-Time Robustness of Vision-Language Models via Self-Critical Inference Framework

    Mar 8, 2026Kaihua Tang, Jiaxin Qi, Jinli Ou +2VLM RobustnessTest-Time Scaling for VLMs

    Tongji University, China · Computer Network Information Center, CAS, China · University of Chinese Academy of Sciences, China +1

  26. Vision Language Models Cannot Reason About Physical Transformation

    Mar 7, 2026Dezhi Luo, Yijiang Li, Maijunxian Wang +7Physical ReasoningVision-Language Models

    University of Michigan · University of California San Diego · University of California Berkeley +6

  27. Looking Back and Forth: Cross-Image Attention Calibration and Attentive Preference Learning for Multi-Image Hallucination Mitigation

    Mar 7, 2026Xiaochen Yang, Hao Fang, Jiawei Kong +3VLM Hallucination MitigationVision-Language Models

    Tsinghua Shenzhen International Graduate School, Tsinghua University · Harbin Institute of Technology · Beijing Institute of Technology +1

  28. BEVLM: Distilling Semantic Knowledge from LLMs into Bird's-Eye View Representations

    Mar 6, 2026Thomas Monninger, Shaoyuan Xie, Qi Alfred Chen +1VLMs for Autonomous DrivingEnd-to-End Autonomous Driving

    Mercedes-Benz Research & Development North America, San Jose, USA · University of California, Irvine, USA

  29. SUREON: A Benchmark and Vision-Language-Model for Surgical Reasoning

    Mar 6, 2026Alejandra Perez, Anita Rau, Lee White +4Surgical Video UnderstandingMedical VQA

    Intuitive Surgical Inc., Sunnyvale, United States

  30. Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders

    Mar 6, 2026Boqiang Zhang, Lei Ke, Ruihan Yang +5Vision-Language ModelsVision-Language Pretraining