In this work, we study idiosyncrasies in the caption models and their downstream impact on text-to-image models. We design a systematic analysis: given either a generated caption or the corresponding image, we train neural networks to predict the originating caption model. Our results show that text classification yields very high accuracy (99.70\%), indicating that captioning models embed distinctive stylistic signatures. In contrast, these signatures largely disappear in the generated images, with classification accuracy dropping to at most 50\% even for the state-of-the-art Flux model. To better understand this cross-modal discrepancy, we further analyze the data and find that the generated images fail to preserve key variations present in captions, such as differences in the level of detail, emphasis on color and texture, and the distribution of objects within a scene. Overall, our classification-based framework provides a novel methodology for quantifying both the stylistic idiosyncrasies of caption models and the prompt-following ability of text-to-image systems.
Inconsistency-aware Multimodal Schrödinger Bridge for Deepfake Localization
Department of Computer Science and Techonology, Huaqiao University（华侨大学计算机科学与技术系）；Xiamen Key Laboratory of Computer Vision and Pattern Recognition, Huaqiao University（厦门计算机视觉与模式识别重点实验室）；Tongji University（同济大学）；School of Cyber Science and Engineering, Wuhan University（武汉大学网络空间安全学院）
Asymmetric Reinforcing against Multi-modal Representation Bias
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；The State Key Laboratory of Integrated Services Networks, Xidian University（西安电子科技大学综合业务网理论及关键技术国家重点实验室）
ARMOR: Empowering Multimodal Understanding Model with Interleaved Multimodal Generation Capability
Nankai University（南开大学）；Shanghai Innovation Institute（上海创新研究院）；University of Science and Technology of China（中国科学技术大学）；Wuhan University（武汉大学）；Shanghai AI Laboratory（上海人工智能实验室）
GeoBalance: Geometry-Aware Monitoring and Reconstruction with Asymmetric Optimization for Balanced Multimodal Learning
Beihang University（北京航空航天大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Amap, Alibaba Group（阿里巴巴集团高德）；Kuaishou Technology（快手科技）；Beijing Jiaotong University（北京交通大学）；Renmin University of China（中国人民大学）
Traits Run Deeper: Trait-Specific Asymmetric Fusion for Multimodal Personality Assessment
Hefei University of Technology（合肥工业大学）；Intelligent Interconnected Systems Laboratory of Anhui Province（安徽省智能互联系统实验室）；Jianghuai Advanced Technology Center（江淮前沿技术中心）；Anhui Provincial Industry Innovation Center of Humanoid Robots（安徽省人形机器人产业创新中心）；Anhui Provincial Key Laboratory of Humanoid Robots（安徽省人形机器人重点实验室）
提出Traits Run Deeper框架，通过多模态基础表示、特质特异性非对称融合和分布校准回归模块，解决人格评估中模态偏好差异和标签偏差问题，在AVI Challenge 2026上MSE降低约25%。
CIEC: Coupling Implicit and Explicit Cues for Multimodal Weakly Supervised Manipulation Localization
School of Computer Science and Engineering（计算机科学与工程学院）；MoE Key Laboratory of Information Technology（信息技术关键实验室）；Key Laboratory of Information Security Technology（信息安全技术重点实验室）；Sun Yat-sen University（中山大学）；State Key Laboratory of Mathematical Engineering and Advanced Computing（数学工程与先进计算国家重点实验室）；Alibaba Group（阿里巴巴集团）
PathAR: Structure-First Autoregressive Synthesis of Multimodal Pathology Images
Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education（新一代人工智能技术及其交叉应用重点实验室（东南大学），教育部）；Centre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore（创新与精准眼健康中心，新加坡国立大学 Yong Loo Lin 医学院）；Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore（眼科学系，新加坡国立大学 Yong Loo Lin 医学院）；Department of Biostatistics, Center for Global Health, School of Public Health, Nanjing Medical University（生物统计学系，全球健康中心，南京医科大学）；Institute of High-Performance Computing, Agency for Science, Technology and Research（高性能计算研究所，科技研究局）
Robust Incomplete-Modality Alignment for Ophthalmic Disease Grading and Diagnosis via Labeled Optimal Transport
University of Exeter（埃克塞特大学）；University of Liverpool（利物浦大学）；Chinese Academy of Sciences（中国科学院）；The University of Hong Kong（香港大学）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；Dalian University of Technology（大连理工大学）；A*STAR
Multimodal Connectome Fusion via Cross-Attention for Autism Spectrum Disorder Classification Using Graph Learning
Department of Medicine, Danube Private University (DPU)（丹ube私人大学医学系）；Department of Medical Physics and Biomedical Engineering, Medical University of Vienna（维也纳医学大学医学物理与生物医学工程系）；Department of Medical Informatics, Faculty of Medicine, Gonabad University of Medical Sciences（戈纳巴德医学院医学信息学系）；Austrian Center for Medical Innovation and Technology (ACMIT)（奥地利医学创新与技术中心）
Stitch and Tell: A Structured Multimodal Data Augmentation Method for Spatial Understanding
School of Computer Science, Beijing Institute of Technology（北京理工大学计算机科学学院）；School of Software and Microelectronics, Peking University（北京大学软件与微电子学院）；Xiaohongshu Inc（小红书公司）
Stitch and Tell通过结构化空间监督提升视觉-语言模型的空间理解能力，有效缓解空间幻觉并提高相关任务性能。
LoMo: Local Modality Substitution for Deeper Vision-Language Fusion
Fudan University（复旦大学）；Shanghai Innovation Institute（上海创新研究院）；Shanghai Jiao Tong University（上海交通大学）；University of Science and Technology of China（中国科学技术大学）
