Tianrong Zhang

adversarial attack (3) network diagnosis (2) multimodal learning (2) text classification (1) preference optimization (1) model alignment (1) conversational ai (1) task-oriented dialogue (1) language model alignment (1) harmful content (1) safety alignment (1) network monitoring (1) machine learning (1) adversarial training (1) visual question answering (1) few-shot learning (1) adversarial perturbation (1) pre-trained model (1) vision-language model (1) certified robustness (1)