Huaisheng Zhu

large language model (2) reinforcement learning (1) imitation learning (1) policy optimization (1) direct preference optimization (1) self-supervised learning (1) preference optimization (1) text-to-image generation (1) instruction following (1) language model alignment (1) reinforcement learning from human feedback (1) model alignment (1) density ratio estimation (1) reward model (1) multimodal large language model (1) proximal policy optimization (1) reward shaping (1) jailbreak attack (1) human preference alignment (1) graph contrastive learning (1)