Looped models converge: three papers reuse compute instead of adding parameters

LucaAmb · x · 2026-09-05

@diffusionllms highlights three recent papers converging on the same insight: reuse computation instead of adding parameters, turning fixed training-time depth into an inference-time resource.

The author teases more on looped models Monday.

Related event: Three papers converge: looped computation boosts masked models without more parameters(2 posts)→

Original post →

More from Research

Research channel →