NEWVectors or files. Pick a path.Start →
    Back to Videos

    How Meta Cut Its Ads Model Serving Cost From 24.6x to 3.9x (HILL, Explained)

    74
    Retrieval & Search Research
    Mixpeek Team
    July 19, 2026

    Summary

    Meta published the first systematic teardown of MoNN, the retrieval model behind Facebook and Instagram ads, plus HILL, the hierarchical index that made it affordable. The big model wins +9.4% recall at 24.6x serving cost; organizing every ad into a learned tree keeps +6.0% at 3.9x, and the production A/B moved online metrics +2.57%. Bonus finding: the tree's middle layers double as training sets for test-time fine-tuning. Paper: arxiv.org/abs/2604.12965

    retrievalmetarecommendation-systemsindexingads-ranking

    About this video

    Meta published the first systematic teardown of MoNN, the retrieval model behind Facebook and Instagram ads, plus HILL, the hierarchical index that made it affordable. The big model wins +9.4% recall at 24.6x serving cost; organizing every ad into a learned tree keeps +6.0% at 3.9x, and the production A/B moved online metrics +2.57%. Bonus finding: the tree's middle layers double as training sets for test-time fine-tuning. Paper: arxiv.org/abs/2604.12965

    Frequently Asked Questions