Tang, P. et al. 2026. SafetyReminder: Reviving Delayed Safety Awareness of Vision-Language Models to Defend Against Jailbreak Attacks. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 39 (Mar. 2026), 33223–33231. DOI:https://doi.org/10.1609/aaai.v40i39.40607.