Personalized Multimodal Large Language Models: A Survey

TL;DR

This survey reviews the architecture, training, and personalization techniques of multimodal large language models, highlighting their applications, datasets, evaluation metrics, and open challenges in the field.

Contribution

It introduces a taxonomy for personalizing multimodal large language models and synthesizes current methods, datasets, and evaluation strategies in this emerging area.

Findings

Comprehensive taxonomy for personalization techniques

Summary of datasets and evaluation metrics used

Identification of open challenges in personalized MLLMs

Abstract

Multimodal Large Language Models (MLLMs) have become increasingly important due to their state-of-the-art performance and ability to integrate multiple data modalities, such as text, images, and audio, to perform complex tasks with high accuracy. This paper presents a comprehensive survey on personalized multimodal large language models, focusing on their architecture, training methods, and applications. We propose an intuitive taxonomy for categorizing the techniques used to personalize MLLMs to individual users, and discuss the techniques accordingly. Furthermore, we discuss how such techniques can be combined or adapted when appropriate, highlighting their advantages and underlying rationale. We also provide a succinct summary of personalization tasks investigated in existing research, along with the evaluation metrics commonly used. Additionally, we summarize the datasets that are useful for benchmarking personalized MLLMs. Finally, we outline critical open challenges. This survey aims to serve as a valuable resource for researchers and practitioners seeking to understand and advance the development of personalized multimodal large language models.