Multimodal neurons in artificial neural networks
核心要点速览
We’ve discovered neurons in CLIP that respond to the same concept whether presented literally, symbolically, or conceptually. This may explain CLIP’s accuracy in classifying surprising visual renditions of concepts, and is also an important step toward understanding the associations and biases that CLIP and similar models learn.
查看完整报道与分享
完整图文、背景资料与讨论归原始发布平台 OpenAI News 所有。