Skip to content
Live
Trending storyDeveloping

WeMM-Video released

1 reports1 outlets10 hours agoUpdate

The story so far

AI overview

qwen released the WeMM-Video model, which is a bilingual Chinese-English open-source multimodal foundational model family including four versions: 2B, 4B, 9B, and 35B-A3B. This model family achieves unified processing of text, image, audio, and video through mixed thinking modes and large-scale training, supporting non-thinking instruction mode and thinking reasoning mode, aiming to achieve strong open-source video understanding.

AI-written from the reports · Updated 1 hour ago

Coverage timeline

Follow the coverage to see every side of the story.

20 Nov
  1. Hugging Face Daily Papers
    WeMM-Video: Pushing the Frontiers of Open-Source Omni-Modal Video Understanding

    WeMM-Video is a bilingual Chinese-English open-source multimodal foundational model family with four versions: 2B, 4B, 9B, and 35B-A3B. It achieves unified processing of text, image, audio, and video through a mixed thinking mode and large-scale training, supporting non-thinking instruction mode and thinking reasoning mode.

Heat over time

Not enough data yet to draw a trend.