OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences
arXiv:2603.09706v1 Announce Type: new Abstract: While safety alignment for Multimodal Large Language Models (MLLMs) has gained significant attention, current paradigms primarily target malicious intent or …
Ming Wen, Kun Yang, Jingyu Zhang, Yuxuan Liu, shiwen cui, Shouling Ji, Xingjun Ma
조회수 39회