Models 29.07.2026 07:11

Digest · past 24h

  1. Qwen2.5 Omni: Sees, Hears, Speaks, Writes – All in One
    Alibaba Qwen has released Qwen2.5-Omni, a flagship multimodal model capable of processing text, images, audio, and video, as well as generating real-time speech. The model uses the Thinker-Talker architecture and surpasses similar models across all modalities.
Source: dnb66 · Digest — original
Our earlier posts on this topic ↓
Fresh news