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）
Zongmeng Zhang, Wengang Zhou, Jie Zhao, Houqiang Li
Despite the impressive capabilities of multimodal large language models (MLLMs) in vision-language tasks, they are prone to hallucinations in real-world scenarios. This paper investigates the hallucination phenomenon in MLLMs from the perspective of modality conflict. Unlike existing works focusing on the conflicts between model responses and inputs, we study the inherent conflicts in inputs from different modalities that place MLLMs in a dilemma and directly lead to hallucinations. We formally define the modality conflict and construct a dataset named Multimodal Modality Conflict (MMMC) to simulate this phenomenon in vision-language tasks. Three methods based on prompt engineering, supervised fine-tuning, and reinforcement learning are proposed to alleviate the hallucination caused by modality conflict. Extensive experiments are conducted on the MMMC dataset to analyze the merits and demerits of these methods. Our results show that the reinforcement learning method achieves the best performance in mitigating the hallucination under modality conflict, while the supervised fine-tuning method shows promising and stable performance. Our work sheds light on the unnoticed modality conflict that leads to hallucinations and provides more insights into the robustness of MLLMs.
Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Zhongke Fanyu Technology Co., Ltd（中科泛语科技有限公司）
Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning
Huazhong University of Science and Technology（华中科技大学）；Nanyang Technological University（南洋理工大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Renmin University of China（中国人民大学）
Is Cognition Consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document Understanding
Zhejiang Key Laboratory of Accessible Perception and Intelligent Systems, Zhejiang University（浙江可感知智能系统重点实验室，浙江大学）；Alibaba Group（阿里巴巴集团）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and DataSecurity（杭州高新技术区（滨江）区块链与数据安全研究院）
Multimodal processing has attracted much attention lately especially with the success of pre-training. However, the exploration has mainly focused on vision-language pre-training, as introducing more modalities can greatly complicate model design and optimization. In this paper, we extend the stateof-the-art Vision-Language model CLIP to accommodate the audio modality for Vision-Language-Audio multimodal processing. Specifically, we apply inter-modal and intra-modal contrastive learning to explore the correlation between audio and other modalities in addition to the inner characteristics of th…
MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference
School of Software, Tsinghua University, Beijing, China（清华大学软件学院，北京，中国）；TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China（天津大学计算机科学与技术学院，中国）；School of New Media and Communication, Tianjin University, China（天津大学新媒体与传播学院，中国）
School of Cyber Science and Technology, Beihang University（北京航空航天大学网络科学与技术学院）；College of Cyber Security, Jinan University（暨南大学网络安全学院）
Multimodal summarization with multimodal output (MSMO) generates a summary with both textual and visual content. Multimodal news report contains heterogeneous contents, which makes MSMO nontrivial. Moreover, it is observed that different modalities of data in the news report correlate hierarchically. Traditional MSMO methods indistinguishably handle different modalities of data by learning a representation for the whole data, which is not directly adaptable to the heterogeneous contents and hierarchical correlation. In this paper, we propose a hierarchical cross-modality semantic correlation l…
CorMulT: A Semi-supervised Modality Correlation-aware Multimodal Transformer for Sentiment Analysis
Information Networking Institute at Carnegie Mellon University (CMU)（卡内基梅隆大学信息网络研究所）；School of Computer Science and Technology at Tongji University（同济大学计算机科学与技术学院）
Multimodal emotion recognition leverages complementary information across modalities to gain performance. However, we cannot guarantee that the data of all modalities are always present in practice. In the studies to predict the missing data across modalities, the inherent difference between heterogeneous modalities, namely the modality gap, presents a challenge. To address this, we propose to use invariant features for a missing modality imagination network (IF-MMIN) which includes two novel mechanisms: 1) an invariant feature learning strategy that is based on the central moment discrepancy …
Zhejiang University-University of Illinois at Urbana-Champaign Institute（浙江大学-伊利诺伊大学厄巴纳香槟分校联合学院）；Zhejiang University（浙江大学）
Multimodal sentiment analysis (MSA) is an important way of observing mental activities with the help of data captured from multiple modalities. However, due to the recording or transmission error, some modalities may include incomplete data. Most existing works that address missing modalities usually assume a particular modality is completely missing and seldom consider a mixture of missing across multiple modalities. In this paper, we propose a simple yet effective meta-sampling approach for multimodal sentiment analysis with missing modalities, namely Missing Modality-based Meta Sampling (M3…
School of Artificial Intelligence, Sun Yat-sen University（中山大学人工智能学院）；School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）
MMoT: Mixture-of-Modality-Tokens Transformer for Composed Multimodal Conditional Image Synthesis
South China University of Technology（华南理工大学）；JD Explore Academy（京东探索研究院）；Nanyang Technological University（南洋理工大学）；Shanghai Jiao Tong University（上海交通大学）
Twins-PainViT: Towards a Modality-Agnostic Vision Transformer Framework for Multimodal Automatic Pain Assessment using Facial Videos and fNIRS
Computational Biomedicine Laboratory of the Foundation for Research and Technology (FORTH)（希腊国家研究与技术基金会计算生物医学实验室）；Department of Electrical & Computer Engineering Hellenic Mediterranean University（希腊地中海大学电气与计算机工程系）
Deep Multimodal Learning with Missing Modality: A Survey
The Australian National University（澳大利亚国立大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Adelaide University（阿德莱德大学）；The University of Surrey（萨里大学）
With the assumption that a video dataset is multimodality annotated in which auditory and visual modalities both are labeled or class-relevant, current multimodal methods apply modality fusion or cross-modality attention. However, effectively leveraging the audio modality in vision-specific annotated videos for action recognition is of particular challenge. To tackle this challenge, we propose a novel audio-visual framework that effectively leverages the audio modality in any solely vision-specific annotated dataset. We adopt the language models (e.g., BERT) to build a semantic audio-video lab…
PDMP: Rethinking Balanced Multimodal Learning via Performance-Dominant Modality Prioritization
Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China（电子科技大学智能协同计算实验室）；School of Information and Communication Engineering, University of Electronic Science and Technology of China（电子科技大学信息与通信工程学院）；Peng Cheng Laboratory（鹏城实验室）
