微信发布多模态嵌入模型WeMM-Embedding，刷新多项基准

AI 摘要

腾讯微信视觉团队发布了WeMM-Embedding，一个支持文本、图像、视频和交错输入的多模态嵌入模型系列，包含2B、4B和9B三种规模。该模型在MMEB-v2基准上，2B版本已超越此前领先的8B开源基线，9B版本以80.6分创下新纪录。模型已在微信视频号、公众号、朋友圈和电商等场景大规模部署，并在14个在线A/B测试中表现一致提升。模型权重和代码已在GitHub开源。

正文节选

WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report Abstract WeMM-Embedding is a family of universal multimodal embedding models that align text, images, videos, and interleaved inputs in a shared space, achieving state-of-the-art retrieval and recommendation performance across public benchmarks and large-scale WeChat applications. Universal multimodal embeddings are becoming a core component of modern AI systems, enabling heterogeneous content to be represented in a shared space for a

发布时间：—

抓取时间：2026-08-26 11:35

来源机构：Hugging Face