This repository contains the official implementation for the paper:

Reparameterized LLM Training via Orthogonal Equivalence Transformation (paper).

🚧 Work in Progress 🚧

This codebase is currently under development. The implementation will be made available soon.

If you find this work useful in your research, please cite our paper:

@article{qiu2025poet,
  title={Reparameterized LLM Training via Orthogonal Equivalence Transformation},
  author={Qiu, Zeju and Buchholz, Simon and Xiao, Tim Z. and Dax, Maximilian and Sch\"olkopf, Bernhard and Liu, Weiyang},
  journal={arXiv preprint arXiv:2506.08001},
  year={2025}
}