Tencent Open-Sources WeMM-Embedding, a Top-Ranking Multimodal Model
abhishek__AI · x · 2026-08-28
Tencent's WeChat Vision Team has open-sourced WeMM-Embedding, a family of universal multimodal embedding models. Supporting unified representations for text, images, videos, and visual documents, it comes in 2B, 4B, and 9B sizes. The model achieves #1 on MMEB-v2 and v3 benchmarks, is designed for multimodal retrieval, and is 100% open source on Hugging Face.
Related event: Tencent Open-Sources WeMM-Embedding, Tops MMEB Leaderboard(3 posts)→
More from Multimodal
- MiniMax H3 Community Roundup: Reverse Painting Video, PDD Acceleration, Audio Fix — optimisticalish · 2026-08-28
- MiniMax H3 First Attempt: Best Way to Upscale Rev2Video for Quality/Time Ratio? — mFcCr0niC · 2026-08-28
- When does AI video stop being a demo and become filmmaking? — johnstro12 · 2026-08-28
- Would you watch a full AI-generated movie with a good story? — johnstro12 · 2026-08-28
- Unreal City Sample update: procedural city built with PCG and an LLM via MCP — petewoodbridge · 2026-08-28
- GPT-5.6 Sol Animates 3D Fish with Procedural Swimming Motions — techartist_ · 2026-08-28