A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision–Language Tasks
Computation · 29.05.2026 · 14 (6) · 125
DOI: 10.3390/computation14060125 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computation, online erschienen am 29.05.2026. Verfasst von Chia Xin Liang und 11 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 217 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This survey provides a comprehensive guide to Multimodal Large Language Models (MLLMs) with a focus on vision–language tasks, including image captioning, visual question answering, cross-modal retrieval, visual grounding, multi-image reasoning, long-video understanding, and embodied AI. We examine architectures, training pipelines, and practical applications, covering visual encoders, language model backbones, connector modules, contrastive pre-training, instruction tuning, and preference alignment. We also foreground first-principles constraints—information bottlenecks, data-processing limits, and statistical co-occurrence bias—that shape architecture, robustness, and evaluation. This survey centers on vision–language systems and does not cover audio-only models or code-generation tools without visual inputs. Through task-level analysis and system-level case studies, we examine prominent MLLM implementations while addressing key challenges in scalability, memory, energy use, inference cost, robustness, and cross-modal learning. We present a unified taxonomy of the MLLM design space, a comparative overview of representative models and evaluation benchmarks, and a discussion of open problems. Concluding with ethical considerations and responsible AI development, this survey offers theoretical frameworks and practical insights for researchers, practitioners, and students working at the intersection of natural language processing and computer vision.
Zitieren
APA
Liang, C. X., Tian, P., Yin, C. H., Yua, Y., Wei, A., Li, M., Song, X., Wang, T., Bi, Z., Liu, M., Bao, R., & Feng, P. (2026). A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision–Language Tasks. Computation, 14(6), 125. https://doi.org/10.3390/computation14060125
Vancouver
Liang CX, Tian P, Yin CH, Yua Y, Wei A, Li M, et al. A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision–Language Tasks. Computation. 2026;14(6):125. doi:10.3390/computation14060125
BibTeX
@article{Liang2026,
author = {Liang, Chia Xin and Tian, Pu and Yin, Caitlyn Heqi and Yua, Yao and Wei, An-Hou and Li, Ming and Song, Xinyuan and Wang, Tianyang and Bi, Ziqian and Liu, Ming and Bao, Riyang and Feng, Pengbin},
title = {A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision–Language Tasks},
journal = {Computation},
year = {2026},
volume = {14},
number = {6},
pages = {125},
doi = {10.3390/computation14060125}
}
EUVIMED