Haodong Wang

large language model (2) multi-task learning (1) few-shot learning (1) domain adaptation (1) feature extraction (1) preference learning (1) direct preference optimization (1) question answering (1) cross-modal learning (1) instruction following (1) remote sensing (1) reinforcement learning from human feedback (1) image registration (1) language model (1) safety evaluation (1) online shopping (1) knowledge reasoning (1) preference datum (1) multi-turn instruction (1) large language model alignment (1)