[2603.24963] Design Once, Deploy at Scale: Template-Driven ML Development for Large Model Ecosystems

Computer Science > Artificial Intelligence arXiv:2603.24963 (cs) [Submitted on 26 Mar 2026] Title:Design Once, Deploy at Scale: Template-Driven ML Development for Large Model Ecosystems Authors:Jiang Liu, John Martabano Landy, Yao Xuan, Swamy Muddu, Nhat Le, Munaf Sahaf, Luc Kien Hang, Rupinder Khandpour, Kevin De Angeli, Chang Yang, Shouyuan Chen, Shiblee Sadik, Ani Agrawal, Djordje Gligorijevic, Jingzheng Qin, Peggy Yao, Alireza Vahdatpour View a PDF of the paper titled Design Once, Deploy at Scale: Template-Driven ML Development for Large Model Ecosystems, by Jiang Liu and 16 other authors View PDF HTML (experimental) Abstract:Modern computational advertising platforms typically rely on recommendation systems to predict user responses, such as click-through rates, conversion rates, and other optimization events. To support a wide variety of product surfaces and advertiser goals, these platforms frequently maintain an extensive ecosystem of machine learning (ML) models. However, operating at this scale creates significant development and efficiency challenges. Substantial engineering effort is required to regularly refresh ML models and propagate new techniques, which results in long latencies when deploying ML innovations across the ecosystem. We present a large-scale empirical study comparing model performance, efficiency, and ML technique propagation between a standardized model-building approach and independent per-model optimization in recommendation systems. To fac...