cs.CLOct 30, 2026

From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings

Authors: Ziyin Zhang, Yuyu Guo, Ying Zhang, Siqiao Xue, Zihan Liao, Jin Qin, Wenjie Yang, Siyuan Yang, 

Organizations: Ant Group · Shanghai Jiao Tong University · Australian National University · Tongji University · 

Abstract

Embedding models underpin virtually every modern AI system, from search engines to recommendation systems. Despite shared mathematical foundations, research on embedding models remains fragmented by modality: the communities develop largely in isolation, seldom exchanging insights. We argue that this fragmentation obscures a deeper convergence. Driven by contrastive learning, Transformer architectures, and a granularity shift, embedding research across modalities is converging toward a common set of principles, even as modality-specific challenges remain underexplored. To reason across this convergence without conflating it, we propose a framework of three progressively harder capabilities: coverage, comparability, and compositionality. Three paths toward unification satisfy these in turn: transformation broadens coverage, alignment enables comparability, and joint embedding, the terminus we advocate, aims at compositionality. This position paper traces the resulting evolution, providing the first unified, cross-cutting treatment of omnimodal embedding research.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation

    Oct 1, 2026Mohammed Irfan Kurpath, Jaseel Muhammad Kaithakkodan, Sahal Shaji Mullappilly +2Cross-Modal Knowledge DistillationMultimodal Embedding