Are Transformers really deeper-efficient than RNNs? Paper questions layer-count advantage

kfountou · x · 2026-09-21

With polynomial-size MLPs, it's unclear whether Transformers hold any advantage over RNNs in terms of layer count, the author argues, linking a paper on architecture depth-efficiency comparisons.

Related event: Flaw Claimed in Transformer Logarithmic Depth Proof(3 posts)→

Original post →

More from Research

Research channel →