Preprint
Aug 2026
WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report
Universal multimodal embeddings are becoming a core component of modern AI systems, enabling heterogeneous content to be represented in a shared space for applications such as retrieval, recommendation, classification, and agentic systems. In this report, we present WeMM-Embedding, a family of universal multimodal embe...
Jun-Jie Zhou, Ke Mei, Lei Li et al.
· 4 citations