Yinghao Zhu

reinforcement learning (3) model security (1) sim-to-real transfer (1) curriculum learning (1) direct preference optimization (1) text-to-image generation (1) clinical prediction (1) monte carlo tree search (1) knowledge graph (1) adversarial attack (1) diffusion model (1) information gain (1) vision-language model (1) jailbreak attack (1) electronic health record (1) shapley value (1) security vulnerability (1) large language model (1) search agent (1) attention guidance (1)