Cheng Han

prompt tuning (3) parameter-efficient finetuning (2) transfer learning (2) vision-language model (2) visual prompt tuning (2) manifold learning (1) robotic manipulation (1) semantic segmentation (1) depth estimation (1) multimodal learning (1) instance segmentation (1) parameter-efficient learning (1) instruction tuning (1) parameter efficient (1) few-shot learning (1) parameter-efficient fine-tuning (1) adversarial attack (1) video captioning (1) mixture of expert (1) optical flow estimation (1)