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
- HyperFrames launches Reference Any Video and auto-applied Brand Kits for AI video — aftahi_ai · 2026-10-16
- Krea 2 + LoRA still beats Flux 3 Klein in pixel-art style test — Angaisb_ · 2026-10-16
- World Labs starts rolling out Atlas beta with pixel-perfect camera path control — theworldlabs · 2026-10-16
- Krea 3 image editing model lands on fal: high-quality edits in under 6 seconds — gorkem · 2026-10-16
- Tripo P2 vs Meshy 7.1: benchmarking today's best image-to-3D models for game assets — noahsolomon · 2026-10-16
- BytePlus-backed AI Film Award offers $1M grand prize for films 70% made with Seedance — DavidmComfort · 2026-10-16