--- title: "From User Sequences to Scaling Laws: A Multi-Stage Architecture for Meta’s Ads Ranking" url: https://daily.dev/posts/from-user-sequences-to-scaling-laws-a-multi-stage-architecture-for-meta-s-ads-ranking-p8licqint source_url: https://engineering.fb.com/2026/08/05/ml-applications/from-user-sequences-to-scaling-laws-a-multi-stage-architecture-for-metas-ads-ranking type: article source: "Facebook Engineering\n" published: 2026-08-05T19:25:22.533Z updated: 2026-08-05T19:39:18.692Z tags: ["recommendation-systems"] reading_time: 8 upvotes: 0 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # From User Sequences to Scaling Laws: A Multi-Stage Architecture for Meta’s Ads Ranking **[Facebook Engineering ](https://daily.dev/sources/facebook_code)** · 8 min read · 0 upvotes · 0 comments ## Summary Meta's engineering team presents two architectural breakthroughs for ads ranking at scale: a multi-stage sequence model that decouples heavy offline user modeling from lightweight online ranking, and a dense tokenization with target-aware attention technique. The offline stage processes thousands of user events asynchronously using deep transformers, caching embeddings that the online stage combines with real-time signals. This separation allows model complexity to scale without proportional serving cost increases. Notably, the system exhibits LLM-style log-linear scaling laws despite working with sparse ID features rather than dense text. Four scaling levers are identified: balanced model shape, multi-stage tunability, sequence diversity, and semantic feature enrichment. The architecture, a core part of Meta's GEM platform, has driven cumulative lifts of 6% in Instagram conversions, 3% in Facebook conversions, and 3.5% in Facebook ad clicks. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [How Meta Built a New AI-Powered Ads Model for 5% Better Conversions](https://daily.dev/posts/how-meta-built-a-new-ai-powered-ads-model-for-5-better-conversions-plmz0bqth) · ByteByteGo · 0 upvotes · 0 comments - [Meta Adaptive Ranking Model: Bending the Inference Scaling Curve to Serve LLM-Scale Models for Ads](https://daily.dev/posts/meta-adaptive-ranking-model-bending-the-inference-scaling-curve-to-serve-llm-scale-models-for-ads-44bxcsdvs) · Facebook Engineering · 1 upvotes · 0 comments - [Meta Details GEM Ads Model Using LLM-Scale Training, Hybrid Parallelism, and Knowledge Transfer](https://daily.dev/posts/meta-details-gem-ads-model-using-llm-scale-training-hybrid-parallelism-and-knowledge-transfer-21ryza9tt) · InfoQ · 0 upvotes · 0 comments --- Tags: [#recommendation-systems](https://daily.dev/tags/recommendation-systems) [View this post on daily.dev](https://daily.dev/posts/from-user-sequences-to-scaling-laws-a-multi-stage-architecture-for-meta-s-ads-ranking-p8licqint)