Caishuang Huang

large language model (5) tool learning (3) reinforcement learning (3) policy optimization (1) transfer learning (1) domain adaptation (1) curriculum learning (1) preference alignment (1) code generation (1) task-oriented dialogue (1) question generation (1) language model alignment (1) ai safety (1) reinforcement learning from human feedback (1) preference modeling (1) noise robustness (1) reward model (1) variational information bottleneck (1) jailbreak attack (1) tool selection (1)