Wenya Xie

large language model (3) benchmark evaluation (1) policy optimization (1) transfer learning (1) domain adaptation (1) self-supervised learning (1) chain-of-thought reasoning (1) factual knowledge (1) token efficiency (1) reinforcement learning from human feedback (1) error propagation (1) pairwise comparison (1) supervised fine-tuning (1) multimodal large language model (1) reasoning model (1) hidden state analysis (1) knowledge boundary (1) experience replay (1) memory management (1) interactive reasoning (1)