Alibaba's Qwen3.5-Omni, a new multimodal large-scale model, was released.

Alibaba Group's Qianwen recently released its new multimodal large-scale model, Qwen3.5-Omni. This model has made significant progress in multimodal understanding and generation capabilities, seamlessly understanding text, images, audio, and audio/video input, and supporting fine-grained, timestamped audio/video caption generation.