Zhuoming Liu

vision-language model (2) active learning (1) domain adaptation (1) knowledge distillation (1) multimodal learning (1) multi-modal learning (1) efficient inference (1) model adaptation (1) gradient descent (1) adaptive inference (1) uncertainty sampling (1) annotation cost (1) multi-modal large language model (1) parameter-efficient tuning (1) token pruning (1) visual token (1) feature distillation (1) cross-modal fusion (1) model performance (1) token merging (1)