M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning

TL;DR

This paper introduces M$^2$PT, a multimodal prompt tuning method that enhances zero-shot instruction learning in large multimodal models by efficiently integrating visual and textual prompts during finetuning.

Contribution

The paper proposes a novel multimodal prompt tuning approach that effectively incorporates prompts into vision and language components, improving zero-shot generalization in MLLMs.

Findings

Outperforms state-of-the-art baselines on multiple multimodal datasets.

Demonstrates the efficiency of prompt-based finetuning over traditional methods.

Ablation studies confirm the effectiveness of the prompt design.

Abstract

Multimodal Large Language Models (MLLMs) demonstrate remarkable performance across a wide range of domains, with increasing emphasis on enhancing their zero-shot generalization capabilities for unseen tasks across various modalities. Instruction tuning has emerged as an effective strategy for achieving zero-shot generalization by finetuning pretrained models on diverse multimodal tasks. As the scale of MLLMs continues to grow, parameter-efficient finetuning becomes increasingly critical. However, most existing parameter-efficient approaches focus only on single modalities and often overlook the multimodal characteristics during finetuning. In this work, we introduce a novel Multimodal Prompt Tuning (M$^2$PT) approach for efficient instruction tuning of MLLMs. M$^2$PT effectively integrates visual and textual prompts into the vision encoder and language processor respectively during finetuning, facilitating the extraction and alignment of features across modalities. Empirical results on various multimodal evaluation datasets demonstrate the superior performance of our approach compared to several state-of-the-art baselines. A comprehensive set of ablation studies validates the effectiveness of our prompt design and the efficiency of our approach.