% Key papers for Training dynamics of in-context learning (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2022_what_65621,
  title = {{What Can Transformers Learn In-Context? A Case Study of Simple Function Classes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53586},
}

@inproceedings{icml2024_can_43955,
  title = {{Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34497},
}

@inproceedings{icml2025_tabicl_45862,
  title = {{TabICL: A Tabular Foundation Model for In-Context Learning on Large Data}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46681},
}

@inproceedings{cvpr2025_mimic_26951,
  title = {{Mimic In-Context Learning for Multimodal Tasks}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34092},
}

@inproceedings{neurips2023_the_67968,
  title = {{The Transient Nature of Emergent In-Context Learning in Transformers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71806},
}

@inproceedings{icml2024_in_43395,
  title = {{In-Context Language Learning: Architectures and Algorithms}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35057},
}

@inproceedings{icml2024_in_43639,
  title = {{In-context Convergence of Transformers}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34813},
}

@inproceedings{iclr2024_the_34706,
  title = {{The mechanistic basis of data dependence and abrupt learning in an in-context classification task}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18368},
}

@inproceedings{iclr2024_how_35024,
  title = {{How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18050},
}

@inproceedings{icml2024_what_44276,
  title = {{What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34176},
}

@inproceedings{icml2024_why_44578,
  title = {{Why Larger Language Models Do In-context Learning Differently?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33874},
}

@inproceedings{neurips2024_in_73683,
  title = {{In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93809},
}

@inproceedings{iclr2025_mlps_81859,
  title = {{MLPs Learn In-Context on Regression and Classification Tasks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29924},
}

@inproceedings{icml2024_breaking_43341,
  title = {{Breaking through the learning plateaus of in-context learning in Transformer}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35111},
}

@inproceedings{icml2024_how_44017,
  title = {{How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34435},
}

@inproceedings{neurips2024_learning_72852,
  title = {{Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94548},
}

@inproceedings{neurips2024_towards_73067,
  title = {{Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94359},
}

@inproceedings{neurips2024_how_73218,
  title = {{How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94218},
}

@inproceedings{iclr2024_is_34414,
  title = {{Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18661},
}

@inproceedings{icml2024_exact_44159,
  title = {{Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34293},
}

@inproceedings{icml2025_emergence_45883,
  title = {{Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46660},
}

@inproceedings{icml2025_when_47683,
  title = {{When can in-context learning generalize out of task distribution?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44914},
}