Saved in:
Bibliographic Details
Main Authors: Jiang, Shixin, Liang, Jiafeng, Wang, Jiyuan, Dong, Xuan, Chang, Heng, Yu, Weijiang, Du, Jinhua, Liu, Ming, Qin, Bing
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.11694
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929740192940032
author Jiang, Shixin
Liang, Jiafeng
Wang, Jiyuan
Dong, Xuan
Chang, Heng
Yu, Weijiang
Du, Jinhua
Liu, Ming
Qin, Bing
author_facet Jiang, Shixin
Liang, Jiafeng
Wang, Jiyuan
Dong, Xuan
Chang, Heng
Yu, Weijiang
Du, Jinhua
Liu, Ming
Qin, Bing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11694
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities
Jiang, Shixin
Liang, Jiafeng
Wang, Jiyuan
Dong, Xuan
Chang, Heng
Yu, Weijiang
Du, Jinhua
Liu, Ming
Qin, Bing
Artificial Intelligence
Computation and Language
Machine Learning
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.
title From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities
topic Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2412.11694