Ali Thousand-Question Full-Modal Large Model Qwen3.5-Omni Launched

BlockBeats News, March 30th, Alibaba DAMO Academy announced the launch of the full-modal large model Qwen3.5-Omni. The Qwen3.5-Omni series includes three sizes of Instruct versions: Plus, Flash, Light, supporting 256k-length context. The model supports over 10 hours of audio input and over 400 seconds of 720P (1FPS) audiovisual input. The model undergoes native multi-modal pre-training on massive text, visual, and over 1 billion hours of audiovisual data, demonstrating outstanding full-modal perception and generation capabilities. Compared to Qwen3-Omni, Qwen3.5-Omni has significantly enhanced multilingual capabilities, supporting speech recognition in 113 languages and dialects and speech generation in 36 languages and dialects. (Jinse)