Fanqi Wan

large language model (9) preference optimization (2) reinforcement learning (2) response generation (2) knowledge distillation (2) hallucination mitigation (2) policy optimization (1) reward modeling (1) contrastive learning (1) attention mechanism (1) chain-of-thought reasoning (1) zero-shot learning (1) text analysis (1) knowledge extraction (1) policy learning (1) factual knowledge (1) task-oriented dialogue (1) instruction following (1) model merging (1) k-means clustering (1)