% Key papers for Sparse and structured attention (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2017_bidirectional_28256,
  title = {{Bidirectional Attention Flow for Machine Comprehension}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=HJ0UKP9ge},
}

@inproceedings{cvpr2019_end_14146,
  title = {{End-To-End Multi-Task Learning With Attention}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2020_exploring_15508,
  title = {{Exploring Self-Attention for Image Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2022_on_19506,
  title = {{On the Integration of Self-Attention and Convolution}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_neighborhood_21664,
  title = {{Neighborhood Attention Transformer}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/23172},
}

@inproceedings{cvpr2021_scaling_17824,
  title = {{Scaling Local Self-Attention for Parameter Efficient Visual Backbones}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{iclr2019_pay_29063,
  title = {{Pay Less Attention with Lightweight and Dynamic Convolutions}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/1043},
}

@inproceedings{cvpr2022_boosting_18382,
  title = {{Boosting Crowd Counting via Multifaceted Attention}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2020_normalized_15961,
  title = {{Normalized and Geometry-Aware Self-Attention Network for Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{neurips2019_stand_59014,
  title = {{Stand-Alone Self-Attention in Vision Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13254},
}

@inproceedings{neurips2017_attentional_56168,
  title = {{Attentional Pooling for Action Recognition}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/8801},
}

@inproceedings{aaai2018_hierarchical_105905,
  title = {{Hierarchical Recurrent Attention Network for Response Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11965},
}

@inproceedings{cvpr2022_mixformer_19345,
  title = {{MixFormer: Mixing Features Across Windows and Dimensions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2021_noninvasive_1071,
  title = {{Noninvasive Self-attention for Side Information Fusion in Sequential Recommendation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/04249-noninvasive-self-attention-for-side-information-fusion-in-sequential-recommendation/},
}

@inproceedings{aaai2021_stock_1427,
  title = {{Stock Selection via Spatiotemporal Hypergraph Attention Network: A Learning to Rank Approach}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/00497-stock-selection-via-spatiotemporal-hypergraph-attention-network-a-learning-to-rank-approach/},
}

@inproceedings{icml2016_a_35712,
  title = {{A Convolutional Attention Network for Extreme Summarization of Source Code}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2016},
  url = {https://proceedings.mlr.press/v48/allamanis16.html},
}

@inproceedings{iclr2018_fusionnet_28427,
  title = {{FusionNet: Fusing via Fully-aware Attention with Application to Machine Comprehension}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/246},
}

@inproceedings{aaai2024_an_5171,
  title = {{An Attentive Inductive Bias for Sequential Recommendation beyond the Self-Attention}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28747},
}

@inproceedings{aaai2021_dual_471,
  title = {{Dual Sparse Attention Network For Session-based Recommendation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/04635-dual-sparse-attention-network-for-session-based-recommendation/},
}

@inproceedings{neurips2020_modern_60347,
  title = {{Modern Hopfield Networks and Attention for Immune Repertoire Classification}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17171},
}

@inproceedings{aaai2024_resmatch_7115,
  title = {{ResMatch: Residual Attention Learning for Feature Matching}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27915},
}

@inproceedings{neurips2024_a_71003,
  title = {{A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96203},
}

@inproceedings{neurips2024_faster_70752,
  title = {{Faster Neighborhood Attention: Reducing the O(n^2) Cost of Self Attention at the Threadblock Level}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96373},
}

@inproceedings{neurips2024_nonlocal_74287,
  title = {{Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93271},
}

@inproceedings{neurips2025_attention_80175,
  title = {{Attention (as Discrete-Time Markov) Chains}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=wy2FwyNYro},
}

@inproceedings{iclr2025_when_80921,
  title = {{When Attention Sink Emerges in Language Models: An Empirical View}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30847},
}

@inproceedings{neurips2026_ordinary_92058,
  title = {{Ordinary Least Squares as an Attention Mechanism}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/153277},
}

@inproceedings{icml2024_memory_45763,
  title = {{Memory Efficient Neural Processes via Constant Memory Attention Block}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32689},
}

@inproceedings{neurips2024_unveiling_72464,
  title = {{Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94894},
}

@inproceedings{aaai2026_aligning_108717,
  title = {{Aligning Attention with Human Rationales for Self-Explaining Hate Speech Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/41069},
}

@inproceedings{iclr2024_window_34110,
  title = {{Window Attention is Bugged: How not to Interpolate Position Embeddings}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18965},
}

@inproceedings{iclr2024_generalized_34428,
  title = {{Generalized Neural Sorting Networks with Error-Free Differentiable Swap Functions}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18647},
}

@inproceedings{icml2024_multimax_44019,
  title = {{MultiMax: Sparse and Multi-Modal Attention Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34433},
}

@inproceedings{icml2024_self_44767,
  title = {{Self-attention Networks Localize When QK-eigenspectrum Concentrates}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33685},
}

@inproceedings{icml2024_interpretabnet_45386,
  title = {{InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33065},
}

@inproceedings{icml2025_benign_46775,
  title = {{Benign Overfitting in Token Selection of Attention Mechanism}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45799},
}

@inproceedings{icml2025_neural_46914,
  title = {{Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics Discovery}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45666},
}

@inproceedings{icml2025_customizing_47328,
  title = {{Customizing the Inductive Biases of Softmax Attention using Structured Matrices}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45261},
}

@inproceedings{icml2026_stem_50045,
  title = {{Stem: Rethinking Causal Information Flow in Sparse Attention}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=8WrMPCd7Kr},
}