paper-with-me

Papers

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 scaling up either the model's precision or the number of parameters on longer inputs. Furthermore, we prove that the complexity class SPACE$[s(n)]$ exactly characterizes the expressive power of a constant bit-size transformer with a context window of length $s(n)$. Our approach relies on simulating Post machines, a Turing-complete computational model. Post machines can be modeled as automata equipped with a queue, exhibiting computational behaviors naturally aligned with those of transformers. The behavioral similarity between transformers and Post machines may offer new insights into the mechanisms underlying the reasoning abilities of transformers.

📄 PDF Abstract BibTeX arXiv:2506.12027

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

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

2026-06-01 · Qian Li, Xinyu Mao, Shang-Hua Teng arxiv

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 pri…

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. …

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…

Softmax Transformers are Turing-Complete

2025-11-25 · Hongjian Jiang, Michael Hahn, Georg Zetzsche, Anthony Widjaja Lin arxiv

Hard attention Chain-of-Thought (CoT) transformers are known to be Turing-complete. However, it is an open problem whether softmax attention Chain-of-Thought (CoT) transformers are Turing-complete. In this paper, we prov…

Arithmetic Reasoning

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