Jiahao Qiu

large language model (3) reward model (2) inference-time alignment (2) tree search (2) direct preference optimization (2) llm evaluation (1) language model alignment (1) transfer learning (1) gaussian process (1) world model (1) bayesian optimization (1) gaussian process prior (1) bayesian regret (1) multi-armed bandit (1) reinforcement learning from human feedback (1) language model (1) ai safety (1) hidden state (1) model adaptation (1) mathematical reasoning (1)