% Key papers for Plain and high-resolution ViTs (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2022_a_18195,
  title = {{A ConvNet for the 2020s}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_swin_19966,
  title = {{Swin Transformer V2: Scaling Up Capacity and Resolution}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{neurips2021_segformer_62093,
  title = {{SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27580},
}

@inproceedings{cvpr2022_mvitv2_19306,
  title = {{MViTv2: Improved Multiscale Vision Transformers for Classification and Detection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2024_transnext_25079,
  title = {{TransNeXt: Robust Foveal Visual Perception for Vision Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29525},
}

@inproceedings{cvpr2022_mpvit_19297,
  title = {{MPViT: Multi-Path Vision Transformer for Dense Prediction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{iclr2022_crossformer_31425,
  title = {{CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6267},
}

@inproceedings{cvpr2025_mambavision_26917,
  title = {{MambaVision: A Hybrid Mamba-Transformer Vision Backbone}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33047},
}

@inproceedings{cvpr2022_multi_19392,
  title = {{Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{neurips2021_xcit_63041,
  title = {{XCiT: Cross-Covariance Image Transformers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26881},
}

@inproceedings{iclr2023_vision_33208,
  title = {{Vision Transformer Adapter for Dense Predictions}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/12048},
}

@inproceedings{cvpr2022_few_18853,
  title = {{Few-Shot Object Detection With Fully Cross-Transformer}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{neurips2021_you_63124,
  title = {{You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27220},
}

@inproceedings{cvpr2022_an_18289,
  title = {{An Image Patch Is a Wave: Phase-Aware Vision MLP}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_transmix_20081,
  title = {{TransMix: Attend To Mix for Vision Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_hire_19004,
  title = {{Hire-MLP: Vision MLP via Hierarchical Rearrangement}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{neurips2022_segvit_63869,
  title = {{SegViT: Semantic Segmentation with Plain Vision Transformers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55225},
}

@inproceedings{neurips2022_rtformer_65808,
  title = {{RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54099},
}

@inproceedings{neurips2021_focal_61268,
  title = {{Focal Attention for Long-Range Interactions in Vision Transformers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26359},
}

@inproceedings{iclr2022_quadtree_31531,
  title = {{Quadtree Attention for Vision Transformers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6822},
}

@inproceedings{aaai2024_spatial_7382,
  title = {{Spatial Transform Decoupling for Oriented Object Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28502},
}

@inproceedings{aaai2024_attention_5219,
  title = {{Attention Guided CAM: Visual Explanations of Vision Transformer Guided by Self-Attention}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28077},
}

@inproceedings{iclr2024_fastervit_35083,
  title = {{FasterViT: Fast Vision Transformers with Hierarchical Attention}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17990},
}

@inproceedings{cvpr2025_mr_27013,
  title = {{Mr. DETR: Instructive Multi-Route Training for Detection Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33945},
}

@inproceedings{neurips2024_adaptiveisp_73977,
  title = {{AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93538},
}

@inproceedings{cvpr2025_token_27879,
  title = {{Token Cropr: Faster ViTs for Quite a Few Tasks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32592},
}

@inproceedings{aaai2026_adaptive_105545,
  title = {{Adaptive Morph-Patch Transformer for Aortic Vessel Segmentation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38301},
}

@inproceedings{neurips2024_rethinking_71486,
  title = {{Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95774},
}

@inproceedings{iclr2025_deco_82253,
  title = {{DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29537},
}

@inproceedings{aaai2025_maskvim_9912,
  title = {{MaskViM: Domain Generalized Semantic Segmentation with State Space Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32502},
}

@inproceedings{neurips2025_polyline_76024,
  title = {{Polyline Path Masked Attention for Vision Transformer}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=EkoAKNikAj},
}

@inproceedings{iclr2025_progressive_82835,
  title = {{Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28965},
}

@inproceedings{neurips2026_adaptopass_89719,
  title = {{AdapToPASS: Ambiguity-aware Adaptive Spherical Transformer for Panoramic Semantic Segmentation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/151962},
}

@inproceedings{cvpr2026_the_95779,
  title = {{The Missing Point in Vision Transformers for Universal Image Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Shahabodini_The_Missing_Point_in_Vision_Transformers_for_Universal_Image_Segmentation_CVPR_2026_paper.html},
}

@inproceedings{cvpr2026_task_96827,
  title = {{Task-Aware Image Signal Processor for Advanced Visual Perception}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Chen_Task-Aware_Image_Signal_Processor_for_Advanced_Visual_Perception_CVPR_2026_paper.html},
}

@inproceedings{cvpr2026_computer_97227,
  title = {{Computer Vision with a Superpixelation Camera}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Mahalingam_Computer_Vision_with_a_Superpixelation_Camera_CVPR_2026_paper.html},
}

@inproceedings{cvpr2026_spar_98547,
  title = {{SPAR: Single-Pass Any-Resolution ViT for Open-vocabulary Segmentation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Kombol_SPAR_Single-Pass_Any-Resolution_ViT_for_Open-vocabulary_Segmentation_CVPR_2026_paper.html},
}

@inproceedings{icml2025_not_46532,
  title = {{Not All Tokens Matter All The Time: Dynamic Token Aggregation Towards Efficient Detection Transformers}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46036},
}