Tencent open-sources WeMM-Embedding multimodal models
Tencent's WeChat Vision team open-sourced WeMM-Embedding, a family of multimodal embedding models in 2B, 4B, and 9B sizes, already deployed in WeChat Channels, Official Accounts, Moments, and e-commerce. The 9B model ranks first on MMEB-v2 and MMEB-v3 benchmarks.
2 sources
Tencent Hunyuan by email
Get an email when Tencent Hunyuan has news
No news that day, no email.
More stories today
- Claude Code silently deletes local history older than 30 days
- Split sigmas speed up video reference in Stable Diffusion
- MiniMax tool turns anything into realistic human video
- MirroS' Code-as-World rewrites videos into executable MuJoCo programs
- PRAXIST research system boosts MLE-bench scores 44%