hbar to AI · 1 年前Visual captions: Using large language models to augment video conferences with dynamic visualsai.googleblog.comexternal-linkmessage-square0fedilinkarrow-up13arrow-down11file-text
arrow-up12arrow-down1external-linkVisual captions: Using large language models to augment video conferences with dynamic visualsai.googleblog.comhbar to AI · 1 年前message-square0fedilinkfile-text