Xinfeng Li

jailbreak attack (2) large language model (2) model security (1) self-supervised learning (1) multilingual nlp (1) named entity recognition (1) model safety (1) neural radiance field (1) ai safety (1) optical flow (1) adversarial attack (1) benchmark dataset (1) language model (1) synthetic datum (1) zero-shot generalization (1) fine-grained classification (1) multimodal large language model (1) domain generalization (1) retrieval-augmented generation (1) adversarial learning (1)