Xun Wu

large language model (3) reward model (2) multimodal large language model (2) direct preference optimization (2) reinforcement learning from human feedback (2) text-to-image generation (2) human preference (2) response generation (1) model alignment (1) representation learning (1) instruction tuning (1) preference learning (1) image alignment (1) generative model (1) multimodal learning (1) language model (1) diffusion model (1) mixture of expert (1) text generation (1) reinforcement learning (1)