% Key papers for In-context learning as gradient descent (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2023_transformers_43071,
  title = {{Transformers Learn In-Context by Gradient Descent}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/23828},
}

@inproceedings{aaai2017_alternating_104525,
  title = {{Alternating Back-Propagation for Generator Network}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10902},
}

@inproceedings{iclr2019_learning_28929,
  title = {{Learning concise representations for regression by evolving networks of trees}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/881},
}

@inproceedings{neurips2020_provably_60635,
  title = {{Provably Efficient Neural Estimation of Structural Equation Models: An Adversarial Approach}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17559},
}

@inproceedings{neurips2020_on_60464,
  title = {{On Infinite-Width Hypernetworks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18670},
}

@inproceedings{aaai2018_facial_104016,
  title = {{Facial Landmarks Detection by Self-Iterative Regression Based Landmarks-Attention Network}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12275},
}

@inproceedings{icml2020_a_37881,
  title = {{A Sample Complexity Separation between Non-Convex and Convex Meta-Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6663},
}

@inproceedings{neurips2023_transformers_67829,
  title = {{Transformers learn to implement preconditioned gradient descent for in-context learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71931},
}

@inproceedings{iclr2024_neural_34963,
  title = {{Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18111},
}

@inproceedings{iclr2024_one_33761,
  title = {{One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19314},
}

@inproceedings{iclr2024_causallm_34947,
  title = {{CausalLM is not optimal for in-context learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18127},
}

@inproceedings{icml2022_an_40244,
  title = {{An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/18035},
}

@inproceedings{iclr2024_first_35018,
  title = {{First-order ANIL provably learns representations despite overparametrisation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18056},
}

@inproceedings{icml2023_fundamental_42648,
  title = {{Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/25219},
}

@inproceedings{neurips2024_flexible_70958,
  title = {{Flexible task abstractions emerge in linear networks with fast and bounded units}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96245},
}

@inproceedings{neurips2024_transformers_71663,
  title = {{Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95617},
}

@inproceedings{neurips2024_in_72329,
  title = {{In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95018},
}

@inproceedings{neurips2024_unraveling_72645,
  title = {{Unraveling the Gradient Descent Dynamics of Transformers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94737},
}

@inproceedings{icml2024_transformers_44776,
  title = {{Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33676},
}

@inproceedings{icml2024_can_45356,
  title = {{Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33095},
}

@inproceedings{icml2025_training_47790,
  title = {{Training Dynamics of In-Context Learning in Linear Attention}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44810},
}

@inproceedings{icml2025_in_47858,
  title = {{In-Context Deep Learning via Transformer Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44744},
}

@inproceedings{icml2026_transformers_53426,
  title = {{Transformers Efficiently Perform In-Context Logistic Regression via Normalized Gradient Descent}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=fR1FjJwrnN},
}

@inproceedings{neurips2024_on_71165,
  title = {{On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96062},
}

@inproceedings{neurips2024_linear_73924,
  title = {{Linear Transformers are Versatile In-Context Learners}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93587},
}

@inproceedings{neurips2025_trained_76493,
  title = {{Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=JxkZyedsdS},
}

@inproceedings{neurips2025_composing_79815,
  title = {{Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=tD7MLq0dbZ},
}

@inproceedings{iclr2025_on_81049,
  title = {{On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30719},
}

@inproceedings{iclr2025_on_81897,
  title = {{On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29887},
}

@inproceedings{iclr2025_transformers_82106,
  title = {{Transformers Handle Endogeneity in In-Context Linear Regression}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29683},
}