Tencent open-sources WeMM-Embedding: unified text/image/video embeddings, Apache 2.0
tomaarsen · x · 2026-09-02
Tencent released WeMM-Embedding, a family of universal multimodal embedding models that embed text, images, videos, and visual documents into a single vector space for cross-modal retrieval.
All three sizes (2B, 4B, 9B) are built on Qwen3.5 and released under Apache 2.0, now available on Hugging Face.
Related event: Tencent Open-Sources WeMM-Embedding, Tops MMEB Benchmarks(6 posts)→
More from Models
- Rumor: two major open-source model releases expected in September — lqiao · 2026-09-02
- Bug Hunt Bench: Fable 5.1 Low Beats Opus 5 Max at Lower Cost — PawelHuryn · 2026-09-02
- Gemini 3.8 Flash spotted in GCP Agent Studio, aimed at multimodal and coding tasks — testingcatalog · 2026-09-02
- Reported 90% on ARC-AGI-2 at $3.12/task with 32% cost reduction — eyishazyer · 2026-09-02
- Users notice GPT now starts ~80% of answers with "Yes" — Standard-Metal-3836 · 2026-09-02
- Fable 5.1 fixes prior models' "insane" SHA-256 hashing on every keystroke — johnlindquist · 2026-09-02