Xiaoyan Cai

large language model (3) multimodal learning (2) representation learning (1) reinforcement learning (1) zero-shot learning (1) multi-task learning (1) direct preference optimization (1) model alignment (1) text generation (1) inductive reasoning (1) preference learning (1) multi-modal learning (1) instruction following (1) medical image analysis (1) contrastive learning (1) low-rank adaptation (1) parameter efficient fine-tuning (1) universal learning (1) mixture of expert (1) causal inference (1)