Mayi Xu

large language model (3) reward modeling (1) generative adversarial network (1) domain adaptation (1) in-context learning (1) relation extraction (1) question answering (1) prompt engineering (1) information retrieval (1) multi-modal learning (1) model safety (1) natural language understanding (1) empirical evaluation (1) knowledge graph (1) few-shot learning (1) heterogeneous datum (1) vision-language model (1) jailbreak attack (1) privacy protection (1) adversarial learning (1)