从割裂到融合：全模态嵌入综述与路线图
原标题：From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings
AI 摘要
这篇 arXiv 综述论文指出，嵌入模型研究长期按模态（文本、图像、音频、图、表格、时间序列）各自为战，研究社区、综述文献和评测基准都相互割裂。作者认为，在对比学习、Transformer 架构和粒度转变的推动下，各模态嵌入研究正走向共同原则，并提出覆盖度、可比性、组合性三层递进能力框架，以及变换、对齐、联合嵌入三条统一路径。该文自称是首个跨模态统一梳理全模态嵌入研究的立场论文。
正文节选
From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings 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 gra