Personalized Multimodal Large Language Models: A Survey

TL;DR

This survey addresses the problem of personalizing multimodal large language models to individual users across text, image, and retrieval tasks. It introduces a symmetric taxonomy that organizes personalization techniques by how they follow multimodal instructions, perform multimodal alignment, generate personalized outputs, or implement personalization through fine-tuning. The authors comprehensively review architectures, training methods, applications, evaluation metrics, and benchmarking datasets, and identify open challenges such as data heterogeneity, noise, scalability, and modality fusion. The work provides a structured roadmap for researchers and practitioners to advance personalized multimodal reasoning and generation with practical implications for domains like healthcare, fashion, and information retrieval.

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.