WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report

tencent · hf · 2026-08-26

Tencent released the WeMM-Embedding technical report, a family of universal multimodal embedding models. It aligns text, images, videos, and interleaved inputs in a shared space, achieving SOTA retrieval and recommendation performance in public benchmarks and large-scale WeChat applications.

Related event: Tencent Releases WeMM-Embedding Family of Multimodal Embedding Models(5 posts)→

Original post →

More from Multimodal

Multimodal channel →