BriefGPT.xyz
Oct, 2023
GPT-4V中超凡的视觉基础通过一组标记的提示释放
Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
HTML
PDF
Jianwei Yang, Hao Zhang, Feng Li, Xueyan Zou, Chunyuan Li...
TL;DR
我们提出了Set-of-Mark(SoM),一种新的视觉提示方法,用于释放大型多模态模型(如GPT-4V)的视觉连接能力。
Abstract
We present
set-of-mark
(
som
), a new
visual prompting method
, to unleash the visual grounding abilities of large
→