Meta’s Generative Ads Model (GEM): Scaling the Central Model and Compute Engine for Frontier Ads AI

Summary

Meta introduced GEM, the industry’s largest recommendation system foundation model, and its 2026 generation shifts from isolated per-domain optimizations on Facebook, Instagram, and Reels to a single central foundation model. The Kunlun architecture, co-designed with the latest GPU hardware, enables 2.5x model complexity and demonstrates LLM-like scaling laws with block-aligned sparse attention reducing sequence complexity. The LoopFM post-training technique transfers GEM’s internal representations to downstream models, doubling intelligence transfer at no additional compute cost or latency. GEM delivered 18.9% conversion improvement and 12% ad click-through rate improvement across all Meta ad surfaces and funnel stages, including 5.8% conversion uplift on Facebook, 4.1% on Instagram, and 1.6% on off-site conversion. Training efficiency doubled to 20-25% model FLOPS utilization while scaling total training FLOPs by 4x across thousands of GPUs using custom kernels and 5D parallelism.

Takeaways

1. 1

   GEM’s Kunlun architecture uses block-aligned sparse attention to reduce sequence complexity from quadratic to linear relative to window size, enabling longer user engagement contexts.

2. 2

   The LoopFM post-training technique transfers GEM’s internal representations to downstream models, doubling intelligence transfer at no additional compute cost or latency through computation sharing.

3. 3

   GEM achieved 18.9% conversion improvement and 12% CTR improvement across Meta’s ad surfaces, with specific uplifts of 5.8% on Facebook, 4.1% on Instagram, and 1.6% on off-site conversion for targeted users.

FAQ