{"ID":23475913,"CreatedAt":"2026-09-18T01:09:05.407443952Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.19445","arxiv_id":"2609.19445","title":"From Models to Systems: A Comprehensive Survey of Efficient Multimodal Learning","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.","short_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...","url_abs":"https://arxiv.org/abs/2609.19445","url_pdf":"https://arxiv.org/pdf/2609.19445v1","authors":"[\"Pan Wang\",\"Siwei Song\",\"Hui Ji\",\"Siqi Cao\",\"Heng Yu\",\"Zhijian Liu\",\"Huanrui Yang\",\"Yingyan Celine Lin\",\"Beidi Chen\",\"Mohit Bansal\",\"Xiaoming Liu\",\"Pengfei Zhou\",\"Ming-Hsuan Yang\",\"Tianlong Chen\",\"Jingtong Hu\"]","published":"2026-09-16T21:27:22Z","proceeding":"cs.MM","tasks":"[\"cs.MM\",\"cs.AI\",\"cs.CL\",\"cs.CV\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":639808,"CreatedAt":"2026-09-18T01:09:05.407443952Z","UpdatedAt":"2026-09-18T01:09:05.407443952Z","DeletedAt":null,"paper_id":23475913,"paper_url":"https://arxiv.org/abs/2609.19445","paper_title":"From Models to Systems: A Comprehensive Survey of Efficient Multimodal Learning","repo_url":"https://github.com/pwang322/Efficient-Multimodal-Learning-Survey","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}