Kyoung-Woon On

video understanding (3) large language model (2) representation learning (2) graph representation (2) self-supervised learning (2) multimodal learning (2) language model (2) graph neural network (2) binary classification (1) video classification (1) policy optimization (1) contrastive learning (1) attention mechanism (1) question answering (1) direct preference optimization (1) preference learning (1) reward modeling (1) multi-modal learning (1) visual question answering (1) response generation (1)