Tianchun Wang

large language model (2) reinforcement learning (1) semi-supervised learning (1) information bottleneck (1) semi-supervised classification (1) generative model (1) normalizing flow (1) jailbreak attack (1) electronic health record (1) adversarial prompt (1) jailbreak defense (1) prompt compression (1) graph convolutional network (1) medical large language model (1) clinical test recommendation (1) diagnosis prediction (1) reinforcement learning framework (1) reject sampling (1) medical dialogue system (1) language model security (1)