Zhaowei Li

multi-modal learning (3) fine-grained understanding (2) visual grounding (2) large language model (2) self-supervised learning (1) knowledge distillation (1) multi-task learning (1) vision-language alignment (1) transfer learning (1) multimodal learning (1) video understanding (1) human preference alignment (1) multi-modal large language model (1) vision-language model (1) multimodal large language model (1) preference optimization (1) multimodal understanding (1) image generation (1) image-text alignment (1) contrastive learning (1)