Google's Retrieve-for-Train uses diffusion models to make complex AI search 20x faster
steveplunkett · x · 2026-09-16
Google Research introduced Retrieve-for-Train (RFT), a framework that replaces slow, redundant autoregressive query fan-out with a lightweight diffusion model, moving the reasoning to an offline training phase. The result: expert-level, multi-faceted search slates delivered in sub-second time, up to 20x faster at a fraction of the cost.
A "Vendi Score" guarantees diversity so results don't repeat the same ideas. The author notes it likely has implications for Search itself, but the paper is dated March 2026 and deployment status is unclear.
More from Infra
- Big Tech's Future Data Center Leases Top $1.3T, 70% Added in Last Four Quarters — rohanpaul_ai · 2026-11-02
- Daniel Lemire: AI is exploding demand for boring compute, server CPUs to double — lemire · 2026-11-02
- Physical AI's real story: a 4-layer map of 15 companies behind humanoid robots — pdamodaran · 2026-11-02
- Under 5% of US consumers pay for AI, yet compute demand is already forcing usage cuts — NinaDSchick · 2026-11-02
- Sam Altman: AI query energy cost fell 1,000x-100,000x in 3-4 years — rohanpaul_ai · 2026-11-02
- Marvell and Lumentum to merge, targeting $550B AI connectivity market — BenBajarin · 2026-11-02