% Key papers for Token merging and masked pretraining (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2022_masked_19316,
  title = {{Masked Autoencoders Are Scalable Vision Learners}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_simmim_19877,
  title = {{SimMIM: A Simple Framework for Masked Image Modeling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2022_maxim_19287,
  title = {{MAXIM: Multi-Axis MLP for Image Processing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2022_transfg_2877,
  title = {{TransFG: A Transformer Architecture for Fine-Grained Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/00852-transfg-a-transformer-architecture-for-fine-grained-recognition/},
}

@inproceedings{cvpr2017_inverse_12364,
  title = {{Inverse Compositional Spatial Transformer Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2025_transformers_27950,
  title = {{Transformers without Normalization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32739},
}

@inproceedings{neurips2021_all_61264,
  title = {{All Tokens Matter: Token Labeling for Training Better Vision Transformers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28187},
}

@inproceedings{cvpr2023_revealing_22055,
  title = {{Revealing the Dark Secrets of Masked Image Modeling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21152},
}

@inproceedings{cvpr2024_parameternet_24438,
  title = {{ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30541},
}

@inproceedings{cvpr2023_mixmae_21570,
  title = {{MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21461},
}

@inproceedings{icml2019_efficient_37329,
  title = {{Efficient Training of BERT by Progressively Stacking}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3819},
}

@inproceedings{aaai2024_fft_5935,
  title = {{FFT-Based Dynamic Token Mixer for Vision}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29457},
}

@inproceedings{aaai2023_hvtsurv_3816,
  title = {{HVTSurv: Hierarchical Vision Transformer for Patient-Level Survival Prediction from Whole Slide Image}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25315},
}

@inproceedings{aaai2024_vision_7772,
  title = {{Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28396},
}

@inproceedings{aaai2022_explainable_2064,
  title = {{Explainable Survival Analysis with Convolution-Involved Vision Transformer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/02207-explainable-survival-analysis-with-convolution-involved-vision-transformer/},
}

@inproceedings{neurips2023_white_68230,
  title = {{White-Box Transformers via Sparse Rate Reduction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71567},
}

@inproceedings{aaai2023_active_3064,
  title = {{Active Token Mixer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25376},
}

@inproceedings{cvpr2024_algm_22683,
  title = {{ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31162},
}

@inproceedings{icml2023_architecture_42371,
  title = {{Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24861},
}

@inproceedings{aaai2023_emotion_3566,
  title = {{Emotion-Aware Music Recommendation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26911},
}

@inproceedings{aaai2025_sparx_10799,
  title = {{SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34103},
}

@inproceedings{aaai2025_selective_10714,
  title = {{Selective Visual Prompting in Vision Mamba}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34361},
}

@inproceedings{neurips2024_accelerating_71997,
  title = {{Accelerating Transformers with Spectrum-Preserving Token Merging}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95316},
}

@inproceedings{aaai2024_electron_5817,
  title = {{Electron Microscopy Images as Set of Fragments for Mitochondrial Segmentation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28191},
}

@inproceedings{aaai2025_maximizing_9921,
  title = {{Maximizing the Position Embedding for Vision Transformers with Global Average Pooling}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33997},
}

@inproceedings{neurips2024_learning_73964,
  title = {{Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93549},
}

@inproceedings{cvpr2024_chada_22958,
  title = {{ChAda-ViT : Channel Adaptive Attention for Joint Representation Learning of Heterogeneous Microscopy Images}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29667},
}

@inproceedings{cvpr2024_pre_24506,
  title = {{Pre-training Vision Models with Mandelbulb Variations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29847},
}

@inproceedings{cvpr2025_spectral_27724,
  title = {{Spectral State Space Model for Rotation-Invariant Visual Representation Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32565},
}

@inproceedings{neurips2025_register_76565,
  title = {{Register and [CLS] tokens induce a decoupling of local and global features in large ViTs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=KhavyzO9kK},
}

@inproceedings{iclr2025_sparse_83132,
  title = {{Sparse autoencoders reveal selective remapping of visual concepts during adaptation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28675},
}

@inproceedings{aaai2025_multi_10052,
  title = {{Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33127},
}

@inproceedings{iclr2024_adaptive_34971,
  title = {{Adaptive Window Pruning for Efficient Local Motion Deblurring}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18103},
}

@inproceedings{icml2024_convnet_43634,
  title = {{ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34818},
}

@inproceedings{neurips2024_cluster_70795,
  title = {{Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96334},
}