Xinyi Yang

large language model (2) benchmark evaluation (2) foundation model (2) transfer learning (1) prompt engineering (1) preference optimization (1) machine translation (1) adversarial attack (1) diffusion model (1) zero-shot generation (1) supervised fine-tuning (1) controllable generation (1) evaluation metric (1) diffusion model fine-tuning (1) prompt tuning (1) bias detection (1) trustworthy ai (1) reward function learning (1) ai agent (1) anomaly detection (1)