Xinyang Han

large language model (3) safety alignment (2) semantic segmentation (1) image segmentation (1) adversarial learning (1) logistic regression (1) preference learning (1) self-supervised learning (1) dialogue generation (1) instance segmentation (1) model safety (1) ai safety (1) monte carlo tree search (1) preference modeling (1) diffusion model (1) adversarial defense (1) novel view synthesis (1) jailbreak attack (1) panoptic segmentation (1) jailbreak defense (1)