Han Xia

reinforcement learning (1) continual learning (1) catastrophic forgetting (1) adversarial robustness (1) few-shot learning (1) policy optimization (1) direct preference optimization (1) preference optimization (1) language model alignment (1) natural language understanding (1) instruction tuning (1) reinforcement learning from human feedback (1) human feedback (1) language model (1) low-rank adaptation (1) orthogonal subspace (1) large language model (1) prompt robustness (1) orthogonal learning (1) code-style instruction (1)