PACE: Progressive Angular-to-Norm Contrastive Embedding
Multimodal embedding models encode heterogeneous inputs into a shared embedding space, enabling efficient similarity computation across modalities and tasks. Most existing methods optimize cosine-based contrastive objectives, which promote stable training but restrict semantic compatibility to angular geometry, preclud...
Yan-Ping Li, Wei Zhou, Ya-Wen Liu et al.
· 1 citation