Xun Wu

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