Large Multimodal Models (LMMs) have demonstrated impressive capabilities in video reasoning via Chain-of-Thought (CoT). However, the robustness of their reasoning chains remains questionable. In this paper, we identify a critical failure mode termed textual inertia, where once a textual hallucination occurs in the thinking process, models tend to blindly adhere to the erroneous text while neglecting conflicting visual evidence. To systematically investigate this, we propose the LogicGraph Perturbation Protocol that structurally injects perturbations into the reasoning chains of diverse LMMs spanning both native reasoning architectures and prompt-driven paradigms to evaluate their self-reflection capabilities. The results reveal that models successfully self-correct in less than 10% of cases and predominantly succumb to blind textual error propagation. To mitigate this, we introduce Active Visual-Context Refinement, a training-free inference paradigm which orchestrates an active visual re-grounding mechanism to enforce fine-grained verification coupled with an adaptive context refinement strategy to summarize and denoise the reasoning history. Experiments demonstrate that our approach significantly stifles hallucination propagation and enhances reasoning robustness.
Robust Multimodal Large Language Models Against Modality Conflict
School of Artificial Intelligence（人工智能学院）；Data Science, University of Science（数据科学，科学大学）；Department of Electronic Engineering（电子工程系）；Information Science, University of Science（信息科学，科学大学）；Huawei Technologies Co., Ltd.（华为技术有限公司）
Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment
Nanyang Technological University（南洋理工大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Tsinghua University（清华大学）；Fudan University（复旦大学）；University of Science and Technology of China（中国科学技术大学）；Renmin University of China（中国人民大学）
ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM
Institute of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）；Shanghai AI Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）
Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；School of Intelligence Science and Technology, University of Science and Technology Beijing（北京科技大学智能科学与技术学院）
Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillation
Columbia University（哥伦比亚大学）；University of Washington（华盛顿大学）
Absorbing Gradient Conflicts: Modeling Semantic Variance via Kent Distributions for Cross-Modal Hashing
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空间安全学院）；School of Cyber Science and Engineering, Southeast University（东南大学网络空间安全学院）
针对现有跨模态哈希方法因代理为静态点引发的梯度冲突问题，提出 KDPH 框架，将代理建模为 Kent 分布，结合定制损失函数，在基准数据集上性能优于现有最优方法。
The Multi-Modal Video Reasoning and Analyzing Competition
Singapore University of Technology and Design（新加坡科技设计大学）；Lancaster University（兰卡斯特大学）；University of Melbourne（墨尔本大学）；Xidian University（西安电子科技大学）；Jiangnan University（江南大学）；Wuhan University（武汉大学）；Tsinghua University（清华大学）；Sun Yat-sen University（中山大学）；BOE Technology Group Co., Ltd（京东方科技集团股份有限公司）
CAD: A General Multimodal Framework for Video Deepfake Detection via Cross-Modal Alignment and Distillation
Peking University（北京大学）；Shenzhen Graduate School（深圳研究生院）；University of Science and Technology of China（中国科学技术大学）；Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
EmAvatar: Multimodal Empathetic Response Generation via Conflict Resolution and Expressive Guidance
National University of Singapore（新加坡国立大学）；Southern University of Science and Technology（南方科技大学）；Fudan University（复旦大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
Perceive and Calibrate: Analyzing and Enhancing Robustness of Medical Multi-Modal Large Language Models
Department of Computer Science and Engineering, CUHK, Hong Kong, China（计算机科学与工程系，CUHK，香港，中国）；Institute of Medical Intelligence and XR, CUHK, Hong Kong, China（医学智能与XR研究所，CUHK，香港，中国）
Conflict-Aware Multimodal Fusion for Ambivalence and Hesitancy Recognition
University of the Basque Country UPV/EHU（巴斯克大学UPV/EHU）；Laboratory of LESIA, University of Biskra（贝斯克拉大学LESIA实验室）；Lab. de Génie Electrique (LAGE), University Kasdi Merbah Ouargla（奥尔加拉大学LAGE实验室）；Institute of Electronics, Microelectronics and Nanotechnology (IEMN), Polytechnic University of Hauts-de-France, University of Lille（电子、微电子与纳米技术研究所（IEMN），法国 Hauts-de-France 工业大学，里尔大学）；Sorbonne Center for Artificial Intelligence, Sorbonne University Abu Dhabi, UAE（索邦人工智能中心，索邦大学阿布扎比校区，阿联酋）
