Local to Global: Learning Dynamics and Effect of Initialization for Transformers

A. Makkuva, Marco Bondaschi, Adway Girish, Alliot Nagle, Hyeji Kim +2 more
2/3/2026

No confident code implementation found for this paper. 1 possible match can be shown below.

Semantic Scholar

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Cite this paper

@article{makkuva2026local,
  title  = {Local to Global: Learning Dynamics and Effect of Initialization for Transformers},
  author = {A. Makkuva and Marco Bondaschi and Adway Girish and Alliot Nagle and Hyeji Kim and Michael Gastpar and C. Ekbote},
  year   = {2026},
  url    = {https://www.semanticscholar.org/paper/4ec7e9417c31d74b79da2a21040e3894fa203737},
  journal = {NEURIPS 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/4ec7e9417c31d74b79da2a21040e3894fa203737.svg)](https://codeofpaper.com/paper/4ec7e9417c31d74b79da2a21040e3894fa203737)

Discussion