LLMs Meet Multimodal Generation and Editing: A Survey

TL;DR

This survey reviews recent progress in multimodal generation and editing using large language models, covering technical methods, datasets, applications, and safety considerations across various media types.

Contribution

It provides a comprehensive overview of multimodal generation and editing techniques involving LLMs, categorizing methods, analyzing technical components, and discussing future directions.

Findings

Summarizes milestone works in multimodal generation and editing.

Categorizes methods into LLM-based and CLIP/T5-based approaches.

Discusses tool-augmented multimodal agents and safety advancements.

Abstract

With the recent advancement in large language models (LLMs), there is a growing interest in combining LLMs with multimodal learning. Previous surveys of multimodal large language models (MLLMs) mainly focus on multimodal understanding. This survey elaborates on multimodal generation and editing across various domains, comprising image, video, 3D, and audio. Specifically, we summarize the notable advancements with milestone works in these fields and categorize these studies into LLM-based and CLIP/T5-based methods. Then, we summarize the various roles of LLMs in multimodal generation and exhaustively investigate the critical technical components behind these methods and the multimodal datasets utilized in these studies. Additionally, we dig into tool-augmented multimodal agents that can leverage existing generative models for human-computer interaction. Lastly, we discuss the advancements in the generative AI safety field, investigate emerging applications, and discuss future prospects. Our work provides a systematic and insightful overview of multimodal generation and processing, which is expected to advance the development of Artificial Intelligence for Generative Content (AIGC) and world models. A curated list of all related papers can be found at https://github.com/YingqingHe/Awesome-LLMs-meet-Multimodal-Generation