Spatial consistency is a fundamental property of the visual world and a key requirement for models that aim to understand physical reality. Despite recent advances, multimodal large language models (MLLMs) often struggle to reason about 3D geometry across multiple views. Rather than asking models to describe scene attributes, we introduce a more challenging task: given two views of the same scene, identify the object that violates 3D motion consistency. We propose a simple and scalable method for generating realistic, spatially inconsistent image pairs from multi-view scenes, enabling systematic evaluation of this capability. Our results show that state-of-the-art MLLMs significantly underperform human observers and exhibit substantial variability across different scene attributes, revealing a fragile and incomplete understanding of 3D structure. We hope our findings underscore the need for approaches that develop a more deeply grounded understanding of the physical world.
Spotlight on Token Perception for Multimodal Reinforcement Learning
Shanghai AI Laboratory(上海人工智能实验室);Shanghai Jiao Tong University(上海交通大学);The Chinese University of Hong Kong(香港中文大学);Nanjing University(南京大学);Wuhan University(武汉大学)
MEGC2025: Micro-Expression Grand Challenge on Spot Then Recognize and Visual Question Answering
Department of Computing and Mathematics, Manchester Metropolitan University(计算与数学系,曼彻斯特 Metropolitan 大学);State Key Laboratory of Cognitive Science and Mental Health, Institute of Psychology, Chinese Academy of Sciences(认知科学与心理健康国家重点实验室,心理学研究所,中国科学院);Department of Psychology, University of the Chinese Academy of Sciences(心理学系,中国科学院大学);National Taiwan University(台湾大学);Zhejiang University(浙江大学);University of Oulu(奥卢大学);Harbin Institute of Technology(哈尔滨工业大学)
PRISMM-Bench: A Benchmark of Peer-Review Grounded Multimodal Inconsistencies
Johannes Kepler University Linz(约翰内斯·开普勒大学林茨分校);Interdisciplinary Transformation University Austria(跨学科转型大学奥地利);MIT CSAIL(麻省理工学院计算机科学与人工智能实验室);Stanford University(斯坦福大学);MIT-IBM Watson AI Lab(麻省理工-IBM沃森人工智能实验室)
GThinker: Towards General Multimodal Reasoning via Cue-Guided Rethinking
Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences(基础模型研究中心,自动化研究所,中国科学院);ByteDance(字节跳动);School of Artificial Intelligence, University of Chinese Academy of Sciences(人工智能学院,中国科学院大学);Peng Cheng Laboratory(鹏城实验室);Wuhan AI Research(武汉人工智能研究所);Xi’an Jiaotong University(西安交通大学);Renmin University of China(中国人民大学)
Deep Residual Injection for Full-Spectrum Forensic Signal Perception in Multimodal Large Language Models
National University of Singapore(新加坡国立大学);Tsinghua University(清华大学);University of Science and Technology of China(中国科学技术大学);University of Electronic Science and Technology of China(电子科技大学);University of California, Berkeley(加州大学伯克利分校)
Unsupervised Multimodal Deepfake Detection Using Intra- and Cross-Modal Inconsistencies
USC Information Sciences Institute(南加州大学信息科学研究所);USC Ming Hsieh Department of Electrical and Computer Engineering(南加州大学明氏电气与计算机工程学院);Clemson University(克莱姆森大学);Holcombe Department of Electrical and Computer Engineering(霍尔科姆电气与计算机工程学院)
Uncertainty-Guided Multimodal Consensus for Multimodal Sentiment Analysis
College of Information Science and Electronic Engineering, Zhejiang University(信息科学与电子工程学院,浙江大学);College of Computer Science and Technology, Zhejiang University of Technology(计算机科学与技术学院,浙江工业大学);Zhejiang University Jinhua Research Institute(浙江大学金华研究院)
OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models
School of Information Science and Engineering, East China University of Science and Technology(东华大学信息科学与工程学院);School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(华中科技大学人工智能与自动化学院);School of Software Engineering, Huazhong University of Science and Technology(华中科技大学软件工程学院);School of Electronic Information and Communications, Huazhong University of Science and Technology(华中科技大学电子信息与通信学院);Alibaba Group(阿里巴巴集团)
When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding
University of Trento(特伦托大学);Hong Kong University of Science and Technology(香港科学与技术大学);University of International Relations(国际关系大学);Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院);Nanjing University of Science and Technology(南京理工大学);VCIP & TMCC & DISSec, College of Computer Science, Nankai University(南开大学计算机学院);University of Central Florida(佛罗里达中央大学)
Survey of Action Recognition, Spotting and Spatio-Temporal Localization in Soccer -- Current Trends and Research Perspectives
NASK - National Research Institute(国家研究 institute);Faculty of Mathematics and Information Science, Warsaw University of Technology(数学与信息科学学院,华沙技术大学);Faculty of Physics and Applied Computer Science, AGH University of Science and Technology(物理与应用计算机科学学院,AGH科技大学)
Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Sun Yat-Sen University(中山大学);Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University(北京未来区块链与隐私计算高级创新中心,北京航空航天大学);Shanghai Jiao Tong University(上海交通大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))
Multimodal Detection of Fake Reviews using BERT and ResNet-50
College of Business Administration Kansas State University Manhattan, USA(商学院学院 华盛顿州立大学 曼哈顿 美国);Department of Computer Science Kansas State University Manhattan, USA(计算机科学系 华盛顿州立大学 曼哈顿 美国)
针对单模态检测无法捕捉跨模态语义不一致的问题,提出集成 BERT 文本与 ResNet-50 图像特征的多模态虚假评论检测框架,在 21,142 张图像数据集上 F1 达 0.934,有效识别图文不一致的虚假评论。
ST-Align: A Multimodal Foundation Model for Image-Gene Alignment in Spatial Transcriptomics
National Institute for Data Science in Health and Medicine, Xiamen University(厦门大学健康与医学数据科学国家研究院);School of Informatics, Xiamen University(厦门大学信息学院);Aginome Scientific(Aginome科技公司);School of Life Sciences, Xiamen University(厦门大学生命科学学院)
Spot the Difference: A Cooperative Object-Referring Game in Non-Perfectly Co-Observable Scene
Beijing University of Posts and Telecommunications(北京邮电大学);Tencent(腾讯);Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);University of Trento(特伦托大学)
Beyond Generation: Using Multimodal LLMs as Detectors of LLM-Generated Deepfake Facial Images
Institute of Cyber Security for Society (iCSS)(社会网络安全研究所(iCSS));School of Computing, University of Kent(肯特大学计算学院);London and South East University Group(伦敦与东南大学集团)
AIGC Video Detection based on the fusion of spatial-frequency-optical flow multimodal features
Beihang University(北京航空航天大学);Nanchang University(南昌大学);DBAPPSecurity Co., Ltd. (DAS-Security)(杭州安恒信息技术股份有限公司);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)