Zhichang Wang

spoken language understanding (2) contrastive learning (2) prototype learning (1) multimodal learning (1) cross-modal learning (1) automatic speech recognition (1) task-oriented dialogue (1) audio-text retrieval (1) pre-trained language model (1) prototype alignment (1) prototype calibration (1) semantic comprehension (1) large language model (1) multimodal semantics (1) asymmetric decoupling (1) learnable attention (1) global contrastive (1) zero-shot learning (1)