[
    {
        "id": "osp-23666",
        "type": "article-journal",
        "title": "From Models to Systems: A Comprehensive Survey of Efficient Multimodal Learning",
        "author": [
            {
                "family": "Wang",
                "given": "Pan"
            },
            {
                "family": "Song",
                "given": "Siwei"
            },
            {
                "family": "Ji",
                "given": "Hui"
            },
            {
                "family": "Cao",
                "given": "Siqi"
            },
            {
                "family": "Yu",
                "given": "Heng"
            },
            {
                "family": "Liu",
                "given": "Zhijian"
            },
            {
                "family": "Yang",
                "given": "Huanrui"
            },
            {
                "family": "Lin",
                "given": "Yingyan Celine"
            },
            {
                "family": "Chen",
                "given": "Beidi"
            },
            {
                "family": "Bansal",
                "given": "Mohit"
            },
            {
                "family": "Liu",
                "given": "Xiaoming"
            },
            {
                "family": "Zhou",
                "given": "Pengfei"
            },
            {
                "family": "Yang",
                "given": "Ming-Hsuan"
            },
            {
                "family": "Chen",
                "given": "Tianlong"
            },
            {
                "family": "Hu",
                "given": "Jingtong"
            }
        ],
        "URL": "https://omanscience.com/en/articles/from-models-to-systems-a-comprehensive-survey-of-efficient-multimodal-learning",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "The rapid expansion of multimodal models has surfaced formidable bottlenecks in computation, memory, and deployment, catalyzing the rise of Efficient Multimodal Learning (EML) as a pivotal research frontier. Despite intensive progress, a cohesive understanding of what, how, and where efficiency is manifested across the learning stack remains fragmented. This survey systematizes the EML landscape by introducing the first structured, model-to-system taxonomy. We distill insights from over 300 seminal works into three hierarchical levels--model, algorithm, and system--addressing architectural parsimony, execution refinement, and hardware-aware orchestration, respectively. Moving beyond a purely categorical review, we offer a methodological synthesis of the vertical synergies between these layers, elucidating how cross-layer co-design contributes to the fundamental \"Efficiency-Utility-Privacy\" trade-off. Through an integrative case study of Multimodal Large Language Models (MLLMs), we trace the field's evolutionary trajectory from initial structural adjustments to modern full-stack resource orchestration. Furthermore, we provide a holistic discussion and application-specific optimization blueprints for diverse domains and posit a paradigm shift toward self-regulating intelligence, where efficiency is an intrinsic, emergent property of the model's fundamental design rather than a post-hoc constraint. Finally, we present open challenges and future directions that will define the trajectory of EML research. This survey establishes a structured framework for multimodal systems that are not only high-performing and generalizable but natively efficient and ready for ubiquitous deployment. A continuously updated version is available at https://github.com/pwang322/Efficient-Multimodal-Learning-Survey."
    }
]