Multi-agent systems are increasingly equipped with heterogeneous multimodal sensors, enabling richer perception but introducing modality-specific and agent-dependent uncertainty. Existing multi-agent collaboration frameworks typically reason at the agent level, assume homogeneous sensing, and handle uncertainty implicitly, limiting robustness under sensor corruption. We propose Active Asymmetric Multi-Agent Multimodal Learning under Uncertainty (A2MAML), a principled approach for uncertainty-aware, modality-level collaboration. A2MAML models each modality-specific feature as a stochastic estimate with uncertainty prediction, actively selects reliable agent-modality pairs, and aggregates information via Bayesian inverse-variance weighting. This formulation enables fine-grained, modality-level fusion, supports asymmetric modality availability, and provides a principled mechanism to suppress corrupted or noisy modalities. Extensive experiments on connected autonomous driving scenarios for collaborative accident detection demonstrate that A2MAML consistently outperforms both single-agent and collaborative baselines, achieving up to 18.7% higher accident detection rate.
FedUAF: Uncertainty-Aware Fusion with Reliability-Guided Aggregation for Multimodal Federated Sentiment Analysis
Shanghai University（上海大学）；North China Electric Power University（华北电力大学）；Université de Technologie de Compiègne（法国图卢兹国立理工学院）；Nanyang Technological University（南洋理工大学）；City University of Hong Kong（香港城市大学）；Macquarie University（麦考瑞大学）
Orthogonalized Multimodal Contrastive Learning with Asymmetric Masking for Structured Representations
Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School（图林根工业大学和汉诺威医学院医学信息学研究所）；Lower Saxony Center for AI and Causal Methods in Medicine (CAIMed)（下萨克森人工智能与因果医学中心（CAIMed））
EviDep: Uncertainty-Aware Multimodal Depression Estimation via Disentangled Evidential Learning
School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机科学与信息工程学院）；Department of Psychiatry, The First Affiliated Hospital of University of Science and Technology of China, Division of Life Sciences and Medicine, University of Science and Technology of China（中国科学技术大学附属第一医院精神科，生命科学与医学学院）
EmoEUS: Uncertainty Supervision for Multimodal Emotion Recognition in Conversation
Dept. of Electrical and Electronic Engineering, The Hong Kong Polytechnic University（香港理工大学电子与电气工程系）；Speech, Language, and Cognition Laboratory, The University of Hong Kong（香港大学语音、语言与认知实验室）
National University of Singapore（新加坡国立大学）；Genome Institute of Singapore, A*STAR（新加坡科技研究局下属基因组研究所）；Yong Loo Lin School of Medicine, National University of Singapore（新加坡国立大学杨潞龄医学院）
Multi-task learning (MTL) is frequently used in settings where a target task has to be learnt based on limited training data, but knowledge can be leveraged from related auxiliary tasks. While MTL can improve task performance overall relative to single-task learning (STL), these improvements can hide negative transfer (NT), where STL may deliver better performance for many individual tasks. Asymmetric multitask feature learning (AMTFL) is an approach that tries to address this by allowing tasks with higher loss values to have smaller influence on feature representations for learning other task…
Embracing Aleatoric Uncertainty in Medical Multimodal Learning with Missing Modalities
HKUST (GZ)（香港科技大学）；Tongji University（同济大学）；University of Rochester（罗切斯特大学）；Meta；Fudan University（复旦大学）；The University of British Columbia（不列颠哥伦比亚大学）；University of California, Davis（加州大学戴维斯分校）
Multimodal regression is a fundamental task, which integrates the information from different sources to improve the performance of follow-up applications. However, existing methods mainly focus on improving the performance and often ignore the confidence of prediction for diverse situations. In this study, we are devoted to trustworthy multimodal regression which is critical in cost-sensitive domains. To this end, we introduce a novel Mixture of Normal-Inverse Gamma distributions (MoNIG) algorithm, which efficiently estimates uncertainty in principle for adaptive integration of different modal…
Reliable uncertainty quantification in deep neural networks is very crucial in safety-critical applications such as automated driving for trustworthy and informed decision-making. Assessing the quality of uncertainty estimates is challenging as ground truth for uncertainty estimates is not available. Ideally, in a well-calibrated model, uncertainty estimates should perfectly correlate with model error. We propose a novel error aligned uncertainty optimization method and introduce a trainable loss function to guide the models to yield good quality uncertainty estimates aligning with the model e…
Uncertainty-Aware Multimodal Learning via Conformal Shapley Intervals
Department of Statistics and Data Science, UCLA（统计与数据科学系， UCLA）；Merck & Co（默克公司）；Department of Biostatistics, UCLA（生物统计学系， UCLA）；Departments of Statistics and Data Science, and of Biostatistics, UCLA（统计与数据科学系以及生物统计学系， UCLA）
TU Darmstadt（达姆施塔特工业大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；Goethe University（歌德大学）
Assistive robots can potentially improve the quality of life and personal independence of elderly people by supporting everyday life activities. To guarantee a safe and intuitive interaction between human and robot, human intentions need to be recognized automatically. As humans communicate their intentions multimodally, the use of multiple modalities for intention recognition may not just increase the robustness against failure of individual modalities but especially reduce the uncertainty about the intention to be predicted. This is desirable as particularly in direct interaction between rob…
Uncertainty-Aware Collaborative System of Large and Small Models for Multimodal Sentiment Analysis
School of Computer Science, South China Normal University（计算机科学学院，华南师范大学）；School of Artificial Intelligence, South China Normal University（人工智能学院，华南师范大学）；School of Electronics and Information Technology, Sun Yat-sen University（电子与信息工程学院，中山大学）
MEWL: Few-shot multimodal word learning with referential uncertainty
Peking University（北京大学）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）；Beijing Institute of Technology（北京理工大学）；Yangtze Delta Region Academy of Beijing Institute of Technology（北京理工大学长三角研究院）
The fusion of multiple sensor modalities, especially through deep learning architectures, has been an active area of study. However, an under-explored aspect of such work is whether the methods can be robust to degradations across their input modalities, especially when they must generalize to degradations not seen during training. In this work, we propose an uncertainty-aware fusion scheme to effectively fuse inputs that might suffer from a range of known and unknown degradations. Specifically, we analyze a number of uncertainty measures, each of which captures a different aspect of uncertain…
MSEG-VCUQ: Multimodal SEGmentation with Enhanced Vision Foundation Models, Convolutional Neural Networks, and Uncertainty Quantification for High-Speed Video Phase Detection Data
