Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models Paper • 2604.11576 • Published Apr 13
CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP Paper • 2503.03613 • Published Mar 5, 2025
DataComp-VLM: Improved Open Datasets for Vision-Language Models Paper • 2606.28551 • Published Jun 26 • 52