作者位次 #4/5ACL 2026Findings· Findings of ACL
e5-omni: Explicit Cross-modal Alignment for Omni-modal Embeddings
Haonan Chen · Sicheng Gao · Radu Timofte · Tetsuya Sakai · Zhicheng Dou
摘要
Modern information systems often involve different types of items, , a text query, an image, a video clip, or an audio segment. This motivates omni-modal embedding models that map heterogeneous modalities into a shared space for direct comparison. However, most recent omni-modal embeddings still...