Positional Attention: Expressivity and Learnability of Algorithmic Computation

Artur Back de Luca, George Giapitzakis, Shenghao Yang, Petar Veličković, K. Fountoulakis
2/14/2026

No official code found. Best implementation: watcl-lab/positional_attention (14 stars, last commit 2025-05-26).

Semantic Scholar

Code Implementations(1)

watcl-lab/positional_attentionCommunity67%

Source code for the paper "Positional Attention: Expressivity and Learnability of Algorithmic Computation"

142PythonSep 27, 20241 years ago

Cite this paper

@article{luca2026positional,
  title  = {Positional Attention: Expressivity and Learnability of Algorithmic Computation},
  author = {Artur Back de Luca and George Giapitzakis and Shenghao Yang and Petar Veličković and K. Fountoulakis},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:f850c7de070d2a51408485cb0ff0dd4bc7cfaae9},
  journal = {ICML 2025 2025}
}

Discussion