FuncAttn: Functional Attention

This repository hosts the trained model weights for the PDE benchmarks reported in the paper Functional Attention: From Pairwise Affinities to Functional Correspondences (ICML 2026).

• Project page: https://xjffff.github.io/funcattn/
• Code: https://github.com/xjffff/funcattn

Citation

@misc{xiao2026functionalattentionpairwiseaffinities,
      title={Functional Attention: From Pairwise Affinities to Functional Correspondences}, 
      author={Jiefang Xiao and Maolin Gao and Simon Weber and Guandao Yang and Daniel Cremers},
      year={2026},
      eprint={2605.31559},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2605.31559}, 
}