Although Multimodal Large Language Models (MLLMs) have demonstrated promising
versatile capabilities, their performance is still inferior to specialized
models on downstream tasks, which makes adaptation necessary to enhance their
utility. However, fine-tuning methods require independent training for every
model, leading to huge computation and memory overheads. In this paper, we
propose a novel setting where we aim to improve the performance of diverse
MLLMs with a group of shared parameters optimized for a downstream task. 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. We introduce two strategies to address the issue of cross-model
feature corruption of existing visual prompting methods and enhance the
transferability of the learned prompts, including 1) Feature Consistency
Alignment: which imposes constraints to the prompted feature changes to
maintain task-agnostic knowledge; 2) Task Semantics Enrichment: which
encourages the prompted images to contain richer task-specific semantics with
language guidance. We validate the effectiveness of TVP through extensive
experiments with 6 modern MLLMs on a wide variety of tasks ranging from object
recognition and counting to multimodal reasoning and hallucination correction.

通过 Transferable Visual Prompting (TVP) 这一新方法，在只对一个模型进行训练的情况下，有效改善多样化的 Multimodal Large Language Models (MLLMs) 的性能，以提高其在下游任务中的应用能力。