BALM: A Model-Agnostic Framework for Balanced Multimodal Learning under Imbalanced Missing Rates

ArXi:2603.19718v1 Announce Type: new Learning from multiple modalities often suffers from imbalance, where information-rich modalities dominate optimization while weaker or partially missing modalities contribute less. This imbalance becomes severe in realistic settings with imbalanced missing rates (IMR), where each modality is absent with different probabilities, distorting representation learning and gradient dynamics. We revisit this issue from a