# Meta — From User Sequences to Scaling Laws: A Multi-Stage Architecture for Meta’s Ads Ranking

- Company: Meta (meta.com)
- Announced: 2026-08-05T19:20:20+00:00
- Category: model-update
- Subject: Llama / infrastructure
- Models affected: Generative Ads Recommendation Model (GEM)
- Source: https://engineering.fb.com/2026/08/05/ml-applications/from-user-sequences-to-scaling-laws-a-multi-stage-architecture-for-metas-ads-ranking/
- Record: https://forck.live/items/3574-from-user-sequences-to-scaling-laws-a-multi-stage-architecture-for-meta-s-ads

Meta introduces a multi-stage sequence model and dense tokenization with target-aware attention to scale sequence learning for ads ranking, achieving lifts in conversions and clicks.

## Evidence

Verbatim from https://engineering.fb.com/2026/08/05/ml-applications/from-user-sequences-to-scaling-laws-a-multi-stage-architecture-for-metas-ads-ranking/:

> Separating the sequence model into two complementary stages (upstream/offline user modeling and downstream/online ranking), enables model capacity to scale so that performance keeps improving without proportional increases in serving resources.

---

Record: https://forck.live/items/3574-from-user-sequences-to-scaling-laws-a-multi-stage-architecture-for-meta-s-ads
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md