Jinchuan Zhang

Privacy (1)

contrastive learning (1) reinforcement learning (1) zero-shot learning (1) adversarial learning (1) few-shot learning (1) model security (1) text classification (1) attention mechanism (1) relation extraction (1) model alignment (1) backdoor attack (1) adversarial attack (1) language model (1) multi-turn interaction (1) red teaming (1) masked language modeling (1) bidirectional lstm (1) event extraction (1) knowledge-guided pre-training (1) natural language interface (1)