Menglan Chen, Xianghe Pang, Jingjing Dong, Wenhao Wang 0002, Yaxin Du, Siheng Chen. VLMGuard-R1: Proactive Safety Alignment for VLMs via Reasoning-Driven Prompt Optimization. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Findings of the Association for Computational Linguistics, ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 39914-39932, Association for Computational Linguistics, 2026. [doi]
Abstract is missing.