Cai W, Liu S, Zhao J, Shi Z, Zhao Y, Yuan Y, et al. When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 25];40(42):35322-30. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/40840