Hongzhan Chen

knowledge distillation (2) model compression (2) reinforcement learning (1) benchmark evaluation (1) mathematical reasoning (1) preference optimization (1) policy learning (1) language model alignment (1) social intelligence (1) deep learning (1) language model (1) tool use (1) task planning (1) multi-turn dialogue (1) conversational agent (1) role-playing agent (1) chain-of-thought prompting (1) integrated gradient (1) dialogue system (1) tool learning (1)