Xiangyu Zeng

spoken language understanding (3) knowledge transfer (3) semantic slot filling (2) continual learning (2) multimodal large language model (2) multi-task learning (1) zero-shot learning (1) transformer architecture (1) token selection (1) question answering (1) multimodal learning (1) multi-modal learning (1) video understanding (1) human pose estimation (1) catastrophic forgetting (1) adaptive inference (1) intent detection (1) progressive learning (1) vision-language model (1) logical reasoning (1)