TREAD

Implementation of TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training.

This implementation enhances TREAD to support RoPE variants.

Diagrams from the paper:

References

@article{krause2025tread,
  title={TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training},
  author={Krause, Felix and Phan, Timy and Gui, Ming and Baumann, Stefan Andreas and Hu, Vincent Tao and Ommer, Bj{\"o}rn},
  journal={arXiv preprint arXiv:2501.04765},
  year={2025}
}

@misc{xiong2025ndrope,
    author = {Jerry Xiong},
    title = {On n-dimensional rotary positional embeddings},
    year = {2025},
    url = {https://jerryxio.ng/posts/nd-rope/}
}

How to Cite

If you use this implementation in your research, please cite it as follows:

@software{avram_tread_rope_2025,
  author = {Avram Djordjevic},
  title = {TREAD with Golden Gate RoPE},
  year = {2025},
  url = {https://github.com/avramdj/TREAD-RoPE-diffusion-routing}
}