Exploring the Transferability of Visual Prompting for Multimodal Large Language Models

1 code implementation • 17 Apr 2024 • Yichi Zhang, Yinpeng Dong, Siyuan Zhang, Tianzan Min, Hang Su, Jun Zhu

To achieve this, we propose Transferable Visual Prompting (TVP), a simple and effective approach to generate visual prompts that can transfer to different models and improve their performance on downstream tasks after trained on only one model.

Hallucination Multimodal Reasoning +2