% Key papers for Hybrid and interpretable ViT designs (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2022_scaling_19797,
  title = {{Scaling Vision Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{icml2021_convit_39152,
  title = {{ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8525},
}

@inproceedings{cvpr2022_scaling_19798,
  title = {{Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_shunted_19872,
  title = {{Shunted Self-Attention via Multi-Scale Token Aggregation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_a_18226,
  title = {{A-ViT: Adaptive Tokens for Efficient Vision Transformer}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{neurips2022_efficientformer_64753,
  title = {{EfficientFormer: Vision Transformers at MobileNet Speed}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54929},
}

@inproceedings{cvpr2024_rmt_24568,
  title = {{RMT: Retentive Networks Meet Vision Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30086},
}

@inproceedings{iclr2022_how_31022,
  title = {{How Do Vision Transformers Work?}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6017},
}

@inproceedings{cvpr2022_towards_20061,
  title = {{Towards Robust Vision Transformer}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2022_evo_2060,
  title = {{Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/02964-evo-vit-slow-fast-token-evolution-for-dynamic-vision-transformer/},
}

@inproceedings{cvpr2024_vit_25209,
  title = {{ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29480},
}

@inproceedings{cvpr2022_minivit_19340,
  title = {{MiniViT: Compressing Vision Transformers With Weight Multiplexing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{icml2023_scaling_42101,
  title = {{Scaling Vision Transformers to 22 Billion Parameters}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/23644},
}

@inproceedings{neurips2022_fast_64865,
  title = {{Fast Vision Transformers with HiLo Attention}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55402},
}

@inproceedings{iclr2022_regionvit_31317,
  title = {{RegionViT: Regional-to-Local Attention for Vision Transformers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6345},
}

@inproceedings{aaai2022_when_2955,
  title = {{When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/02423-when-shift-operation-meets-vision-transformer-an-extremely-simple-alternative-to-attention-mechanism/},
}

@inproceedings{iclr2022_vitgan_31505,
  title = {{ViTGAN: Training GANs with Vision Transformers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6287},
}

@inproceedings{aaai2023_cf_3212,
  title = {{CF-ViT: A General Coarse-to-Fine Method for Vision Transformer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25860},
}

@inproceedings{cvpr2023_castling_20570,
  title = {{Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21063},
}

@inproceedings{cvpr2025_similarity_27676,
  title = {{Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33871},
}

@inproceedings{cvpr2025_your_28171,
  title = {{Your ViT is Secretly an Image Segmentation Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33107},
}

@inproceedings{neurips2024_multi_74075,
  title = {{Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93455},
}

@inproceedings{cvpr2024_deit_23139,
  title = {{DeiT-LT: Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31116},
}

@inproceedings{aaai2024_bi_5291,
  title = {{Bi-ViT: Pushing the Limit of Vision Transformer Quantization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28109},
}

@inproceedings{aaai2024_viteraser_7765,
  title = {{ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28245},
}

@inproceedings{aaai2024_lf_6398,
  title = {{LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28001},
}

@inproceedings{aaai2024_curved_5539,
  title = {{Curved Representation Space of Vision Transformers}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29213},
}

@inproceedings{cvpr2024_a_22648,
  title = {{A General and Efficient Training for Transformer via Token Expansion}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29624},
}

@inproceedings{cvpr2024_dense_23145,
  title = {{Dense Vision Transformer Compression with Few Samples}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30118},
}

@inproceedings{iclr2024_channel_33897,
  title = {{Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19178},
}

@inproceedings{aaai2025_boosting_8286,
  title = {{Boosting ViT-based MRI Reconstruction from the Perspectives of Frequency Modulation, Spatial Purification, and Scale Diversification}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32656},
}

@inproceedings{cvpr2025_sata_27504,
  title = {{SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34047},
}

@inproceedings{neurips2024_hydravit_73616,
  title = {{HydraViT: Stacking Heads for a Scalable ViT}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93871},
}

@inproceedings{neurips2024_scaling_74443,
  title = {{Scaling White-Box Transformers for Vision}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93129},
}

@inproceedings{aaai2024_ddvit_5556,
  title = {{DDViT: Double-Level Fusion Domain Adapter Vision Transformer (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30516},
}

@inproceedings{iclr2024_data_33713,
  title = {{Data-independent Module-aware Pruning for Hierarchical Vision Transformers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19362},
}

@inproceedings{icml2024_statistical_45620,
  title = {{Statistical Test for Attention Maps in Vision Transformers}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32832},
}