Hugging Face Trending Papers

Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete

Read the original on Hugging Face Trending Papers →

Positional encoding (PE) is widely viewed as necessary for transformers to process ordered sequences: without them, the next-token map appears permutation-invariant in its context tokens. This intuition underlies all prior universality results, which rely on positional information to prove that transformers with chain-of-thought can perform arbitrary computation, i.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Jun 19

Efficiently Representing Algorithms With Chain-of-Thought Transformers

arXiv:2606. 19697v1 Announce Type: cross Abstract: The increasing popularity of \emph{reasoning} models -- language models that output a series of reasoning or thought tokens before producing an answer -- is justified, in part, by theoretical results showing that chain-of-thought (CoT) transformers can simulate Turing machines, and thus perform arbitrary computation.

By Yanhong Li, Anej Svete, Ashish Sabharwal, William Merrill