Yongxin Huang

transfer learning (2) reinforcement learning (1) zero-shot learning (1) few-shot learning (1) domain adaptation (1) masked language model (1) cross-lingual alignment (1) parameter sharing (1) semantic similarity (1) zero-shot transfer (1) cross-task generalization (1) zero-shot prompting (1) sentence embedding (1) symbolic music generation (1) encoder model (1) adapter training (1) statement tuning (1) large language model (1) transformer architecture (1) multilingual sentence encoder (1)