{"ID":2881724,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.12149","arxiv_id":"2508.12149","title":"MOVER: Multimodal Optimal Transport with Volume-based Embedding Regularization","abstract":"Recent advances in multimodal learning have largely relied on pairwise contrastive objectives to align different modalities, such as text, video, and audio, in a shared embedding space. While effective in bi-modal setups, these approaches struggle to generalize across multiple modalities and often lack semantic structure in high-dimensional spaces. In this paper, we propose MOVER, a novel framework that combines optimal transport-based soft alignment with volume-based geometric regularization to build semantically aligned and structured multimodal representations. By integrating a transport-guided matching mechanism with a geometric volume minimization objective (GAVE), MOVER encourages consistent alignment across all modalities in a modality-agnostic manner. Experiments on text-video-audio retrieval tasks demonstrate that MOVER significantly outperforms prior state-of-the-art methods in both zero-shot and finetuned settings. Additional analysis shows improved generalization to unseen modality combinations and stronger structural consistency in the learned embedding space.","short_abstract":"Recent advances in multimodal learning have largely relied on pairwise contrastive objectives to align different modalities, such as text, video, and audio, in a shared embedding space. While effective in bi-modal setups, these approaches struggle to generalize across multiple modalities and often lack semantic structu...","url_abs":"https://arxiv.org/abs/2508.12149","url_pdf":"https://arxiv.org/pdf/2508.12149v1","authors":"[\"Haochen You\",\"Baojing Liu\"]","published":"2025-08-16T20:17:06Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[]","has_code":false}