Zhiheng Xi

large language model (18) reinforcement learning (10) language model (5) reinforcement learning from human feedback (4) mathematical reasoning (3) question answering (3) language model alignment (3) benchmark evaluation (2) policy optimization (2) reward model (2) few-shot learning (2) transfer learning (2) reward modeling (2) adversarial defense (2) instruction tuning (2) code generation (2) visual reasoning (2) knowledge distillation (2) model compression (2) adversarial training (2)