Tencent releases WeMM-Embedding-2B multimodal embedding model
tencent · hf · 2026-08-25
Tencent has released a new model called WeMM-Embedding-2B. It is a feature-extraction model supporting multimodal embeddings for text, images, and videos. The model is based on the Qwen3.5 architecture and utilizes MRL (Multi-Resolution Representation Learning) technology.
Related event: Tencent Releases WeMM-Embedding Family of Multimodal Embedding Models(5 posts)→
More from Multimodal
- Creative AI Video Prompt: Elevator Plunging Through Seasons — umesh_ai · 2026-08-26
- Exploring 4 Imaginary Tokens in Midjourney V8.2 and Their Visual Results — LudovicCreator · 2026-08-26
- Midjourney prompt: Weary astronaut watering wildflowers at dawn — tisch_eins · 2026-08-26
- OraRL: Efficient and Scalable RL for Video MLLMs — Yunheng Li · 2026-08-26
- Seeking Fast HD MiniMax Video Generation Without Quality Loss — OkMeat6773 · 2026-08-26
- Emotional animation of girl touching sky whale generated by Google Gemini — michaelrabone · 2026-08-26