Zhida Huang

multi-modal learning (2) metric learning (1) multi-task learning (1) transfer learning (1) knowledge distillation (1) face recognition (1) feature embedding (1) video understanding (1) visual grounding (1) convolutional neural network (1) multi-modal large language model (1) fine-grained understanding (1) unified representation (1) reasoning capability (1) language model compression (1) multi-modal grounding (1) image grounding (1) video grounding (1) coarse-to-fine training (1) small language model (1)