paper-with-me

Papers

Efficient Turing Machine Simulation with Transformers

2025-09-28 · Qian Li, Yuyi Wang arxiv

Constant bit-size Transformers are known to be Turing complete, but existing constructions require $Ω(s(n))$ chain-of-thought (CoT) steps per simulated Turing machine (TM) step, leading to impractical reasoning lengths. In this paper, we significantly reduce this efficiency gap by proving that any $(t(n),s(n))$-bounded multi-tape TM can be simulated by a constant bit-size Transformer with an optimal $O(s(n))$-long context window and only $O(s(n)^c)$ CoT steps per TM step, where $c>0$ can be made arbitrarily small by letting the Transformers' head-layer product sufficiently large. In addition, our construction shows that sparse attention with fixed geometric offsets suffices for efficient universal computation. Our proof leverages multi-queue TMs as a bridge. The main technical novelty is a more efficient simulation of multi-tape TMs by synchronous multi-queue TMs, improving both time and space complexity under stricter model assumptions.

📄 PDF Abstract BibTeX arXiv:2512.00003

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Efficiently Representing Algorithms With Chain-of-Thought Transformers

2026-06-18 · Yanhong Li, Anej Svete, Ashish Sabharwal, William Merrill arxiv

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-o…

Constant Bit-size Transformers Are Turing Complete

2025-05-22 · Qian Li, Yuyi Wang

We prove that any Turing machine running on inputs of arbitrary length can be simulated by a constant bit-size transformer, as long as the context window is sufficiently long. This improves previous works, which require …

Barriers to Universal Reasoning With Transformers (And How to Overcome Them)

2026-04-28 · Oliver Kraus, Yash Sarrof, Yuekun Yao, Alexander Koller 외 arxiv

Chain-of-Thought (CoT) has been shown to empirically improve Transformers' performance, and theoretically increase their expressivity to Turing completeness. However, whether Transformers can learn to generalize to CoT t…

On the Computational Power of Transformers and its Implications in Sequence Modeling

2020-06-16 · CONLL 2020 · Satwik Bhattamishra, Arkil Patel, Navin Goyal

Transformers are being used extensively across several sequence modeling tasks. Significant research effort has been devoted to experimentally probe the inner workings of Transformers. However, our conceptual and theoret…

Machine TranslationTranslation

A Relative Church-Turing-Deutsch Thesis from Special Relativity and Undecidability

2022-06-13 · Blake Wilson, Ethan Dickey, Vaishnavi Iyer, Sabre Kais

Beginning with Turing's seminal work in 1950, artificial intelligence proposes that consciousness can be simulated by a Turing machine. This implies a potential theory of everything where the universe is a simulation on …