Zhiheng Xi

large language model (15) reinforcement learning (8) language model (5) reinforcement learning from human feedback (4) mathematical reasoning (3) language model alignment (3) mixture of expert (2) reward model (2) tool use (2) few-shot learning (2) reward modeling (2) transfer learning (2) benchmark evaluation (2) low-rank adaptation (2) adversarial defense (2) adversarial training (2) question answering (2) model compression (2) code generation (2) instruction tuning (2)