Qwen2.5-Omni Collection End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 • 3 items • Updated 2 days ago • 67
Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models Paper • 2501.11873 • Published Jan 21 • 65