Kun Liu

representation learning (2) p4 programming (2) named entity recognition (2) video understanding (2) self-supervised learning (1) convolutional neural network (1) action recognition (1) point cloud (1) video generation (1) multimodal learning (1) human-object interaction (1) program synthesis (1) supervised fine-tuning (1) mixture of expert (1) vision-language model (1) text annotation (1) multimodal large language model (1) noisy label (1) edge computing (1) anomaly detection (1)