Less is More: Removing Text-regions Improves CLIP Training Efficiency and RobustnessLiangliang Cao,Bowen Zhang,Chen Chen,Yinfei Yang,Xianzhi Du, Wencong Zhang,Zhiyun Lu,Yantao ZhengCoRR（2023）引用 6|浏览142AI 理解论文溯源树样例生成溯源树，研究论文发展脉络Chat Paper正在生成论文摘要
