Zekun Moore Wang

large language model (3) instruction tuning (2) reward modeling (1) transfer learning (1) code completion (1) preference learning (1) direct preference optimization (1) preference alignment (1) speech processing (1) data annotation (1) autoregressive generation (1) multimodal learning (1) reinforcement learning from human feedback (1) model alignment (1) software engineering (1) reward model (1) foundation model (1) multimodal large language model (1) instruction fine-tuning (1) evaluation benchmark (1)