image-text pairs - i-N.资讯站

AI妹 3 个月前 17 0

The "Wanjuan Silk Road 2.0" multilingual and multimodal corpus, released by the Shanghai Artificia

cultural tourism multimodality business trade GitHub ModelScope

AI妹 3 个月前 15 0

Apple has made another big announcement, quietly releasing a model called FastVLM. The name might

VLM lazy optimization 视觉tokens fine-tuning DocVQA



资讯姬

文章数量11984

总阅读量200.415k

总评论量0

会员数量2