From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities
It is a survey paper that summarizes existing research on multi-modal large language models, offering an introduction for beginners and outlining challenges, but it is incremental as it does not present new experimental results or methods.
This paper surveys Omni-MLLMs, which aim to achieve omni-modal understanding and generation by mapping various non-linguistic modalities into LLM embedding spaces, addressing the problem of handling arbitrary modality combinations in real-world scenarios, and it provides a systematic taxonomy, training methods, and future directions.
To tackle complex tasks in real-world scenarios, more researchers are focusing on Omni-MLLMs, which aim to achieve omni-modal understanding and generation. Beyond the constraints of any specific non-linguistic modality, Omni-MLLMs map various non-linguistic modalities into the embedding space of LLMs and enable the interaction and understanding of arbitrary combinations of modalities within a single model. In this paper, we systematically investigate relevant research and provide a comprehensive survey of Omni-MLLMs. Specifically, we first explain the four core components of Omni-MLLMs for unified multi-modal modeling with a meticulous taxonomy that offers novel perspectives. Then, we introduce the effective integration achieved through two-stage training and discuss the corresponding datasets as well as evaluation. Furthermore, we summarize the main challenges of current Omni-MLLMs and outline future directions. We hope this paper serves as an introduction for beginners and promotes the advancement of related research. Resources have been made publicly available at https://github.com/threegold116/Awesome-Omni-MLLMs.