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

@inproceedings{neurips2022_flashattention_64476,
  title = {{FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54008},
}

@inproceedings{aaai2020_real_102999,
  title = {{Real-Time Emotion Recognition via Attention Gated Hierarchical Memory Network}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6309},
}

@inproceedings{iclr2021_random_30304,
  title = {{Random Feature Attention}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3213},
}

@inproceedings{iclr2021_rethinking_30355,
  title = {{Rethinking Attention with Performers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2726},
}

@inproceedings{icml2020_sparse_38774,
  title = {{Sparse Sinkhorn Attention}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6539},
}

@inproceedings{iclr2022_cosformer_30990,
  title = {{cosFormer: Rethinking Softmax In Attention}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6040},
}

@inproceedings{neurips2021_luna_61781,
  title = {{Luna: Linear Unified Nested Attention}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28250},
}

@inproceedings{aaai2020_not_102267,
  title = {{Not All Attention Is Needed: Gated Attention Network for Sequence Data}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6129},
}

@inproceedings{iclr2023_mega_33219,
  title = {{Mega: Moving Average Equipped Gated Attention}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11941},
}

@inproceedings{iclr2018_monotonic_28545,
  title = {{Monotonic Chunkwise Attention}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/211},
}

@inproceedings{neurips2021_scatterbrain_62271,
  title = {{Scatterbrain: Unifying Sparse and Low-rank Attention}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26519},
}

@inproceedings{neurips2024_bridging_72170,
  title = {{Bridging the Divide: Reconsidering Softmax and Linear Attention}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95169},
}

@inproceedings{iclr2025_differential_81993,
  title = {{Differential Transformer}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29792},
}

@inproceedings{cvpr2025_dig_25922,
  title = {{DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35093},
}

@inproceedings{neurips2021_stable_62432,
  title = {{Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27095},
}

@inproceedings{icml2022_improving_40695,
  title = {{Improving Transformers with Probabilistic Attention Keys}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17955},
}

@inproceedings{icml2024_gated_45103,
  title = {{Gated Linear Attention Transformers with Hardware-Efficient Training}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33349},
}

@inproceedings{neurips2024_perceiving_70549,
  title = {{Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96564},
}

@inproceedings{aaai2025_vig_11235,
  title = {{ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32550},
}

@inproceedings{neurips2024_gated_73527,
  title = {{Gated Slot Attention for Efficient Linear-Time Sequence Modeling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93950},
}

@inproceedings{iclr2024_the_33623,
  title = {{The Hedgehog \& the Porcupine: Expressive Linear Attentions with Softmax Mimicry}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19452},
}

@inproceedings{aaai2025_iterative_9615,
  title = {{Iterative Sparse Attention for Long-sequence Recommendation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33323},
}

@inproceedings{cvpr2025_parallel_27217,
  title = {{Parallel Sequence Modeling via Generalized Spatial Propagation Network}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33001},
}

@inproceedings{iclr2024_transformer_35244,
  title = {{Transformer-VQ: Linear-Time Transformers via Vector Quantization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17829},
}

@inproceedings{icml2024_polysketchformer_45035,
  title = {{PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33417},
}

@inproceedings{neurips2024_metala_72670,
  title = {{MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94714},
}

@inproceedings{neurips2025_flash_78594,
  title = {{Flash Invariant Point Attention}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=gKsG5qR3Bt},
}

@inproceedings{iclr2025_forgetting_83548,
  title = {{Forgetting Transformer: Softmax Attention with a Forget Gate}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28268},
}

@inproceedings{iclr2025_explaining_84004,
  title = {{Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/27821},
}

@inproceedings{iclr2024_sea_34139,
  title = {{SEA: Sparse Linear Attention with Estimated Attention Mask}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18936},
}

@inproceedings{icml2024_various_44190,
  title = {{Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34262},
}

@inproceedings{icml2026_sema_50934,
  title = {{SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=H3vDDSHWos},
}

@inproceedings{icml2026_a_51180,
  title = {{A Provable Expressiveness Hierarchy in Hybrid Linear-Full Attention}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=JPnA2BI6U5},
}