François Fleuret explains a memory trick: pay O(time steps) instead of O(steps × components)

francoisfleuret · x · 2026-11-17

Former Meta/Apple research scientist François Fleuret shares what he calls a "wonderful trick" for state memory: instead of storing the state as S(t)={x1(t),...,xt(t)} (each step holding only current components), keep the full history S(t)={x1(1),...,xt(t)}, cutting memory from O(nbtimesteps × nbstatecomponents) to O(nbtimesteps) — while you want both factors large. Useful for long-sequence / long-horizon state modeling.

Related event: Fleuret Explains Memory Trick That Cuts State Storage Complexity by a Dimension(2 posts)→

Original post →

More from Research

Research channel →