Yanru Wu

large language model (3) model compression (1) federated learning (1) catastrophic forgetting (1) few-shot learning (1) transfer learning (1) ensemble learning (1) question answering (1) text generation (1) token efficiency (1) hierarchical decomposition (1) diffusion model (1) personalized model (1) parameter-efficient fine-tuning (1) heterogeneous datum (1) supervised fine-tuning (1) parameter aggregation (1) prompt tuning (1) latent code (1) gradient conflict (1)