← Search

Haoqi Hu

2 accepted papers

2026

Omni-Attack: Adversarial Attacks on Open-Ended VQA in Black-Box Multimodal LLMs

CVPR 2026

Multimodal large language models (MLLMs) have achieved remarkable success across diverse applications, from autonomous driving to document understanding. As these models are deployed in safety-critical contexts, understanding their adversarial robustness becomes crucial. However, current evaluations

Cited by 0SourcecodeScholar