Tencent open-sources WeMM-Embedding multimodal models

Tencent's WeChat Vision team released WeMM-Embedding, a family of multimodal embedding models in 2B, 4B, and 9B sizes, with the 9B ranking first on MMEB-v2 and MMEB-v3 benchmarks. Already deployed in WeChat Channels, Official Accounts, Moments, and e-commerce, the models are available with code, evaluation tools, and weights.