揭示视觉语言模型中的视觉计数瓶颈 Unveiling the Visual Counting Bottleneck in Vision-Language Models.pdf

揭示视觉语言模型中的视觉计数瓶颈 Unveiling the Visual Counting Bottleneck in Vision-Language Models.pdf

UnveilingtheVisualCountingBottleneckinVision-LanguageModels

XingzhouPang*1YifanHou*1JunlingWang1MrinmayaSachan1

{xingzhou.pang,yifan.hou,junling.wang,mrinmaya.sachan}@inf.ethz.ch

您可能关注的文档

文档评论(0)

1亿VIP精品文档

相关文档