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

• URL: http://arxiv.org/abs/2603.24963v2
• Date: Fri, 27 Mar 2026 19:14:43 GMT
• Title: Design Once, Deploy at Scale: Template-Driven ML Development for Large Model Ecosystems
• Abstract summary: We present a study comparing model performance, efficiency, and ML technique propagation between a standardized model-building approach and independent per-model optimization in recommendation systems.<n>By utilizing standardized, composable ML model components, we reduce technique propagation complexity from $O(n cdot 2k)$ to $O(n + k)$ where $n$ is the number of models and $k$ the number of techniques.
• Score: 8.291206271989822
• License: http://creativecommons.org/licenses/by/4.0/
• 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 facilitate this standardization, we propose the Standard Model Template (SMT) -- a framework that generates high-performance models adaptable to diverse data distributions and optimization events. By utilizing standardized, composable ML model components, SMT reduces technique propagation complexity from $O(n \cdot 2^k)$ to $O(n + k)$ where $n$ is the number of models and $k$ the number of techniques. Evaluating an extensive suite of models over four global development cycles within Meta's production ads ranking ecosystem, our results demonstrate: (1) a 0.63% average improvement in cross-entropy at neutral serving capacity, (2) a 92% reduction in per-model iteration engineering time, and (3) a $6.3\times$ increase in technique-model pair adoption throughput. These findings challenge the conventional wisdom that diverse optimization goals inherently require diversified ML model design.

Related papers

• Model-Driven Discipline for Multi-Agent LLMs: Requirement-to-Verification Generation of Traceable System Models [62.62160094849002]
  RADIANT is an engineering methodology that combines MDE with Multi-Agent Large Language Models.<n>It automatically generates heterogeneous models across engineering phases.<n>It provides exact, automated change-impact analysis.
  arXiv  Detail & Related papers  (2026-07-18T08:50:55Z)
• M*: A Modular, Extensible, Serving System for Multimodal Models [62.77975969000349]
  We present M*, a universal serving system for efficient serving of composite AI models.<n>We show how it can concisely capture composite models from a broad range of families.<n>M* also outperforms the V-JEPA 2-AC rollout baseline for robotic planning by up to 12.5x.
  arXiv  Detail & Related papers  (2026-06-10T21:22:22Z)
• Bending the Scaling Law Curve in Large-Scale Recommendation Systems [25.722146264492096]
  We present ULTRA-HSTU, a novel sequential recommendation model developed through end-to-end model and system co-design.<n>Our solution is fully deployed at scale, serving billions of users daily and driving significant 4% to 8% consumption and engagement improvements in real-world production environments.
  arXiv  Detail & Related papers  (2026-02-19T01:15:17Z)
• OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging [124.91183814854126]
  Model merging seeks to combine multiple expert models into a single model.<n>We introduce a benchmark for model merging research that clearly divides the tasks for MLLM training and evaluation.<n>We find that model merging offers a promising way for building improved MLLMs without requiring training data.
  arXiv  Detail & Related papers  (2025-05-26T12:23:14Z)
• Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models [48.15777554876988]
  Traditional alignment methods often require retraining large pretrained models.<n>We propose a novel textitResidual Alignment Model (textitRAM) that formalizes the alignment process as a type of importance sampling.<n>We develop a resampling algorithm with iterative token-level decoding to address the common first-token latency issue in comparable methods.
  arXiv  Detail & Related papers  (2025-05-26T08:53:02Z)
• Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization [65.64108848398696]
  We introduce a preference optimization (PO) process to enhance the multimodal reasoning capabilities of MLLMs.<n>Specifically, we design an automated preference data construction pipeline to create MMPR, a high-quality, large-scale multimodal reasoning preference dataset.<n>We explore integrating PO with MLLMs, developing a simple yet effective method, termed Mixed Preference Optimization (MPO), which boosts multimodal CoT performance.
  arXiv  Detail & Related papers  (2024-11-15T18:59:27Z)
• Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild [84.57103623507082]
  This paper introduces Model-GLUE, a holistic Large Language Models scaling guideline.<n>We benchmark existing scaling techniques, especially selective merging, and variants of mixture.<n>We then formulate an optimal strategy for the selection and aggregation of a heterogeneous model zoo.<n>Our methodology involves the clustering of mergeable models and optimal merging strategy selection, and the integration of clusters.
  arXiv  Detail & Related papers  (2024-10-07T15:55:55Z)
• CubicML: Automated ML for Large ML Systems Co-design with ML Prediction of Performance [7.425372356516303]
  Scaling up deep learning models has been proven effective to improve intelligence of machine learning (ML) models. In this paper, we propose CubicML which uses ML to automatically optimize training performance of large distributed ML systems. We prove that CubicML can effectively optimize training speed of in-house recommendation models with 73 billion parameters and large language models up to 405 billion parameters at Meta ads.
  arXiv  Detail & Related papers  (2024-09-06T19:55:21Z)
• EMR-Merging: Tuning-Free High-Performance Model Merging [55.03509900949149]
  We show that Elect, Mask & Rescale-Merging (EMR-Merging) shows outstanding performance compared to existing merging methods. EMR-Merging is tuning-free, thus requiring no data availability or any additional training while showing impressive performance.
  arXiv  Detail & Related papers  (2024-05-23T05:25:45Z)
• When Parameter-efficient Tuning Meets General-purpose Vision-language Models [65.19127815275307]
  PETAL revolutionizes the training process by requiring only 0.5% of the total parameters, achieved through a unique mode approximation technique. Our experiments reveal that PETAL not only outperforms current state-of-the-art methods in most scenarios but also surpasses full fine-tuning models in effectiveness.
  arXiv  Detail & Related papers  (2023-12-16T17:13:08Z)
• AutoML for Large Capacity Modeling of Meta's Ranking Systems [29.717756064694278]
  We present a sampling-based AutoML method for building large capacity models. We show that our method achieves outstanding Return on Investment (ROI) versus human tuned baselines. The proposed AutoML method has already made real-world impact where a discovered Instagram CTR model with up to -0.36% NE gain was selected for large-scale online A/B test and show statistically significant gain.
  arXiv  Detail & Related papers  (2023-11-14T03:00:50Z)
• Modeling Choice via Self-Attention [8.394221523847325]
  We show that our attention-based choice model is a low-optimal generalization of the Halo Multinomial Logit (Halo-MNL) model. We also establish the first realistic-scale benchmark for choice estimation on real data, conducting an evaluation of existing models.
  arXiv  Detail & Related papers  (2023-11-11T11:13:07Z)
• Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale [11.121380180647769]
  We share in this paper our search strategies to adapt reference recommendation models to low-precision hardware. We also discuss the design and development of tool chain so as to maintain our models' accuracy throughout their lifespan. We believe these lessons from the trenches promote better co-design between hardware architecture and software engineering.
  arXiv  Detail & Related papers  (2021-05-26T16:42:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.