WeMM-Video foundation models released by researchers

arxiv.org1 min read

Researchers introduce WeMM-Video, a family of Chinese-English bilingual omni-modal foundation models spanning 2B to 35B-A3B variants that unify text, image, audio, and video processing. Trained on 1.2 trillion tokens, the flagship 35B-A3B model establishes a new open-source state of the art in video understanding and reasoning across more than 120 benchmarks. The team has publicly released the model family along with evaluation and reproduction pipelines. Open article →