Learning the RoPEs: Better 2D and 3D Position Encodings with STRING
Abstract
We introduce $\textbf{STRING}$: Separable Translationally Invariant Position Encodings. STRING extends Rotary Position Encodings, a recently proposed and widely used algorithm in large language models, via a unifying theoretical framework. Importantly, STRING still provides $\textbf{exact}$ translation invariance, including token coordinates of arbitrary dimensionality, whilst maintaining a low computational footprint. These properties are especially important in robotics, where efficient 3D token representation is key. We integrate STRING into Vision Transformers with RGB(-D) inputs (color plus optional depth), showing substantial gains, e.g. in open-vocabulary object detection and for robotics controllers. We complement our experiments with a rigorous mathematical analysis, proving the universality of our methods. Videos of STRING-based robotics controllers can be found here: https://sites.google.com/view/string-robotics.
Cite
Text
Schenck et al. "Learning the RoPEs: Better 2D and 3D Position Encodings with STRING." Proceedings of the 42nd International Conference on Machine Learning, 2025.Markdown
[Schenck et al. "Learning the RoPEs: Better 2D and 3D Position Encodings with STRING." Proceedings of the 42nd International Conference on Machine Learning, 2025.](https://mlanthology.org/icml/2025/schenck2025icml-learning/)BibTeX
@inproceedings{schenck2025icml-learning,
title = {{Learning the RoPEs: Better 2D and 3D Position Encodings with STRING}},
author = {Schenck, Connor and Reid, Isaac and Jacob, Mithun George and Bewley, Alex and Ainslie, Joshua and Rendleman, David and Jain, Deepali and Sharma, Mohit and Dubey, Kumar Avinava and Wahid, Ayzaan and Singh, Sumeet and Wagner, René and Ding, Tianli and Fu, Chuyuan and Byravan, Arunkumar and Varley, Jake and Gritsenko, Alexey A. and Minderer, Matthias and Kalashnikov, Dmitry and Tompson, Jonathan and Sindhwani, Vikas and Choromanski, Krzysztof Marcin},
booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
year = {2025},
pages = {53295-53315},
volume = {267},
url = {https://mlanthology.org/icml/2025/schenck2025icml-learning/}
}