Kaifu Zhang

large language model (6) supervised fine-tuning (2) reinforcement learning (2) direct preference optimization (2) agent system (2) knowledge distillation (2) chain-of-thought reasoning (1) preference learning (1) catastrophic forgetting (1) machine translation (1) preference alignment (1) cross-lingual transfer (1) model interpretability (1) factuality evaluation (1) visual question answering (1) instruction following (1) text-to-image generation (1) text-to-image synthesis (1) image synthesis (1) language model evaluation (1)