% Key papers for Efficient and robust vision transformers (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2022_metaformer_19337,
  title = {{MetaFormer Is Actually What You Need for Vision}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2023_biformer_20469,
  title = {{BiFormer: Vision Transformer With Bi-Level Routing Attention}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21785},
}

@inproceedings{icml2021_training_40060,
  title = {{Training data-efficient image transformers \& distillation through attention}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8671},
}

@inproceedings{cvpr2023_efficientvit_20903,
  title = {{EfficientViT: Memory Efficient Vision Transformer With Cascaded Group Attention}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22623},
}

@inproceedings{neurips2021_coatnet_62743,
  title = {{CoAtNet: Marrying Convolution and Attention for All Data Sizes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28746},
}

@inproceedings{cvpr2022_mobile_19349,
  title = {{Mobile-Former: Bridging MobileNet and Transformer}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{neurips2022_vitpose_64014,
  title = {{ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55265},
}

@inproceedings{cvpr2022_topformer_20027,
  title = {{TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{neurips2021_dynamicvit_63022,
  title = {{DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26013},
}

@inproceedings{neurips2021_transgan_61207,
  title = {{TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26286},
}

@inproceedings{cvpr2022_adavit_18261,
  title = {{AdaViT: Adaptive Vision Transformers for Efficient Image Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2022_vision_2937,
  title = {{Vision Transformers Are Robust Learners}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/02071-vision-transformers-are-robust-learners/},
}

@inproceedings{cvpr2022_patch_19562,
  title = {{Patch Slimming for Efficient Vision Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{neurips2022_hornet_66240,
  title = {{HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54820},
}

@inproceedings{cvpr2024_shvit_24707,
  title = {{SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31487},
}

@inproceedings{neurips2021_hrformer_61661,
  title = {{HRFormer: High-Resolution Vision Transformer for Dense Predict}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27341},
}

@inproceedings{aaai2022_nested_2463,
  title = {{Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/03417-nested-hierarchical-transformer-towards-accurate-data-efficient-and-interpretable-visual-understanding/},
}

@inproceedings{neurips2021_vitae_62582,
  title = {{ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27784},
}

@inproceedings{aaai2023_head_3821,
  title = {{Head-Free Lightweight Semantic Segmentation with Linear Transformer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25126},
}

@inproceedings{cvpr2023_comprehensive_20617,
  title = {{Comprehensive and Delicate: An Efficient Transformer for Image Restoration}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21386},
}

@inproceedings{cvpr2025_lsnet_26706,
  title = {{LSNet: See Large, Focus Small}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34284},
}

@inproceedings{iclr2024_vision_33534,
  title = {{Vision Transformers Need Registers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19541},
}

@inproceedings{aaai2024_s2wat_7196,
  title = {{S2WAT: Image Style Transfer via Hierarchical Vision Transformer Using Strips Window Attention}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28529},
}

@inproceedings{cvpr2025_learning_26747,
  title = {{Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33552},
}

@inproceedings{icml2024_learning_44961,
  title = {{Learning Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33491},
}

@inproceedings{cvpr2025_bhvit_25554,
  title = {{BHViT: Binarized Hybrid Vision Transformer}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34363},
}

@inproceedings{cvpr2024_on_24345,
  title = {{On the Faithfulness of Vision Transformer Explanations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30060},
}

@inproceedings{cvpr2024_token_25020,
  title = {{Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30742},
}

@inproceedings{iclr2025_vision_83404,
  title = {{Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28412},
}

@inproceedings{iclr2025_an_83790,
  title = {{An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28029},
}

@inproceedings{aaai2024_dtmformer_5581,
  title = {{DTMFormer: Dynamic Token Merging for Boosting Transformer-Based Medical Image Segmentation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28394},
}

@inproceedings{cvpr2024_heal_23656,
  title = {{HEAL-SWIN: A Vision Transformer On The Sphere}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31442},
}

@inproceedings{neurips2024_scalekd_70156,
  title = {{ScaleKD: Strong Vision Transformers Could Be Excellent Teachers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96927},
}

@inproceedings{iclr2024_skip_35532,
  title = {{Skip-Attention: Improving Vision Transformers by Paying Less Attention}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17541},
}

@inproceedings{icml2024_slab_44765,
  title = {{SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33687},
}

@inproceedings{iclr2024_sparseformer_33540,
  title = {{SparseFormer: Sparse Visual Recognition via Limited Latent Tokens}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19535},
}

@inproceedings{aaai2024_bvt_5260,
  title = {{BVT-IMA: Binary Vision Transformer with Information-Modified Attention}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29505},
}

@inproceedings{aaai2026_vision_106951,
  title = {{Vision Transformers Are Circulant Attention Learners}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39303},
}

@inproceedings{neurips2025_frequency_75939,
  title = {{Frequency-Aware Token Reduction for Efficient Vision Transformer}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=Dr06Wjh45k},
}