X.PIN· @thexpin · X·· 3 小时前AI 评分61
AI 导读
X.PIN 转发了智谱团队关于统一多模态模型的研究，探讨通过结合图像生成与文本训练让 AI 生成视觉推理步骤。该方法使文本问答准确率从 12.57% 提升至 41.14%。
正文 · 原文
Zhipu AI might drop a native multimodal AI called GLM-Omni.
By pairing image generation and text training, the system allows the AI to draw out visual reasoning steps to look at before answering. This drove text QA accuracy up from 12.57% to 41.14%.
Basically me doodling during exams.
来源：X.PIN · x.com