Zhaorun Chen

vision-language model (2) representation learning (1) contrastive learning (1) reinforcement learning (1) zero-shot learning (1) self-supervised learning (1) knowledge editing (1) question decomposition (1) preference optimization (1) video understanding (1) semantic representation (1) modality alignment (1) knowledge base (1) safety alignment (1) backdoor attack (1) vision language model (1) poisoning attack (1) multimodal large language model (1) language-image pretraining (1) hallucination reduction (1)