MiMIC: Mitigating Visual Modality Collapse in Universal Multimodal Retrieval While Avoiding Semantic Misalignment

arXiv:2604.21326v1 Announce Type: cross Abstract: Universal Multimodal Retrieval (UMR) aims to map different modalities (e.g., visual and textual) into a shared embedding space for multi-modal retrieval. Existing UMR methods can be broadly divided into two categories: early-fusion approaches, such as Marvel, which projects visual features into the language model (LM) space for integrating with text modality, and late-fusion approaches, such as UniVL-DR, which encode visual and textual inputs usi