Introduces Closed-Loop Bidirectional Prompting with Semantic Anchor for cross-modal agreement recovery, claiming SOTA adversarial robustness and generalization on 11 datasets.
Few-shot adversarial prompt learning on vision-language models.Advances in Neural Information Processing Systems, 37: 3122–3156, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Closed-Loop Bidirectional Prompting for Adversarial Robustness of Vision Language Models
Introduces Closed-Loop Bidirectional Prompting with Semantic Anchor for cross-modal agreement recovery, claiming SOTA adversarial robustness and generalization on 11 datasets.