Chubby♨️@kimmonismus · XAI 摘要
1/ 我最近在体验 SenseNova U1，这是 @SenseTime_Al 发布的原生多模态模型系列。 它基于一种名为 NEO-unify 的架构构建，该架构在一个统一系统中同时处理图像和文本。这与通常在不同组件间传递任务的方式有很大不同。 请看这个帖子 🧵：
1/ I have been spending time with SenseNova U1， a native multimodal model series released by @SenseTime_Al.
It is built on an architecture called NEO-unify that processes images and text together in one single system. It is a big change from the usual way of handing tasks off between separate components.
Look at this thread 🧵：