Cai, W. et al. 2026. When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 42 (Mar. 2026), 35322–35330. DOI:https://doi.org/10.1609/aaai.v40i42.40840.