Yinghao Zhu

reinforcement learning (1) model security (1) direct preference optimization (1) text-to-image generation (1) clinical prediction (1) monte carlo tree search (1) adversarial attack (1) diffusion model (1) vision-language model (1) jailbreak attack (1) electronic health record (1) security vulnerability (1) large language model (1) attention guidance (1) medical multimodal large language model (1) cross-modality attack (1)