Yao Huang

adversarial attack (6) object detection (2) physical attack (2) domain generalization (2) model safety (1) text classification (1) benchmark evaluation (1) text generation (1) online learning (1) autonomous driving (1) prompt engineering (1) neural radiance field (1) sequence-to-sequence learning (1) vision language model (1) vision-language model (1) adversarial robustness (1) multimodal large language model (1) jailbreak attack (1) retrieval-augmented generation (1) continual learning (1)