aiqbench analysis
This survey establishes a critical taxonomy for Efficient Multimodal Learning, mapping the evolution from architectural tweaks to full-stack hardware orchestration in multimodal large language models. By synthesizing over 300 works, it clarifies how cross-layer co-design resolves bottlenecks in computation and memory while balancing efficiency, utility, and privacy. The paper outlines a necessary paradigm shift where native efficiency becomes an intrinsic design property rather than a post-hoc constraint for ubiquitous deployment.
From Models to Systems: A Comprehensive Survey of Efficient Multimodal Learning
arXiv:2609.19445v1 Announce Type: cross 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.
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 this https URL.
Multimedia (cs.MM); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2609.19445 [cs.MM]
(or arXiv:2609.19445v1 [cs.MM] for this version)
https://doi.org/10.48550/arXiv.2609.19445 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 259 words
Related coverage
Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey
arXiv · Sep 22, 2026
Large Models for Battery Prognostics and Health Management: A Review and Future Roadmap
arXiv · Aug 28, 2026
Safe Learning for Contact-Rich Robot Tasks: A Survey from Classical Learning-Based Methods to Safe Foundation Models
arXiv · Sep 22, 2026
Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting
arXiv · Jul 31, 2026