SOURCE-LINKED INTELLIGENCE

PACE: Progressive Angular-to-Norm Contrastive Embedding

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

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, precluding embedding norms from serving as an additional semantic signal. However, directly optimizing the more expressive dot-product similarity, which leverages both angular and norm information, underperforms cosine-based training and exhibits unstable training dynamics. We attribute

Read original source ↗ Open in workspace

recordType

paper

region

Global