למידת ייצוג רב-מודאלי מותנית ביחסים סמנטיים

תקציר מקורי באנגליתarXiv:2508.17497v3 Announce Type: replace-cross Abstract: Multimodal representation learning has been largely driven by contrastive models such as CLIP, which learn a shared embedding space by aligning paired image-text samples. While effective for general-purpose representation learning, such models typically produce a single embedding per sample that is reused across different semantic relations and contexts. However, in many real-world applications, relevance between samples is inherently relation-dependent, with different semantic relations emphasizing different aspects of multimodal data. In this work, we propose Relation-Conditioned Multimodal Learning (RCML), a framework that treats semantic relations as explicit conditions of multimodal representation learning. Rather than producin