Runtao Liu

multimodal large language model (3) model alignment (2) visual reasoning (2) direct preference optimization (2) transfer learning (1) symbolic reasoning (1) zero-shot learning (1) mathematical reasoning (1) image generation (1) motion estimation (1) self-supervised learning (1) preference alignment (1) in-context learning (1) code generation (1) referring expression (1) video understanding (1) video generation (1) image translation (1) text-to-image generation (1) semantic segmentation (1)