Jiazheng Xu

visual language model (2) visual question answering (2) reinforcement learning from human feedback (2) reward model (2) in-context learning (1) model evaluation (1) multimodal learning (1) image captioning (1) visual grounding (1) out-of-distribution generalization (1) model alignment (1) generative model (1) large multimodal model (1) vision language model (1) zero-shot generalization (1) text-to-video generation (1) prompt optimization (1) reasoning ability (1) multimodal alignment (1) human preference (1)