Weiyi Wu

representation learning (4) multimodal learning (3) music performance (2) question answering (2) multi-instance learning (1) visual question answering (1) feature learning (1) self-supervised learning (1) sparse learning (1) medical imaging (1) video captioning (1) medical nlp (1) video understanding (1) visual reasoning (1) efficient computing (1) direct preference optimization (1) spatial regularization (1) foundation model (1) audio-visual representation (1) temporal modeling (1)