New paper: Transformers are inherently succinct, probing a theory-practice gap

chrmanning · x · 2026-08-19

Stanford's Chris Manning highlights "Transformers are Inherently Succinct" by Pascal Bergsträßer, Ryan Cotterell & Anthony Widjaja Lin.

Context: prior work (Hahn 2020, Li & Cotterell 2025) showed transformers are formally less powerful than RNNs—yet they excel in practice. The paper offers an interesting new angle on this apparent paradox.

Related event: New Paper: Transformers Are Inherently Succinct, Explaining Edge Over RNNs(2 posts)→

Original post →

More from Research

Research channel →