Zhaoyang Wang

large language model (4) preference tuning (2) small language model (2) model robustness (2) adversarial attack (2) natural language processing (2) remote sensing (1) text classification (1) transfer learning (1) instruction following (1) semantic consistency (1) modality alignment (1) deep neural network (1) knowledge base (1) preference alignment (1) diffusion model (1) knowledge distillation (1) sequential learning (1) synthetic data generation (1) knowledge transfer (1)