% Key papers for Layer-wise analysis of language models (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2016_social_11873,
  title = {{Social LSTM: Human Trajectory Prediction in Crowded Spaces}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2016},
}

@inproceedings{neurips2022_locating_63664,
  title = {{Locating and Editing Factual Associations in GPT}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53864},
}

@inproceedings{icml2016_a_35718,
  title = {{A Neural Autoregressive Approach to Collaborative Filtering}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2016},
  url = {https://proceedings.mlr.press/v48/zheng16.html},
}

@inproceedings{icml2024_feature_45707,
  title = {{Feature Reuse and Scaling: Understanding Transfer Learning with Protein Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32745},
}

@inproceedings{iclr2022_exploring_31341,
  title = {{Exploring the Limits of Large Scale Pre-training}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6231},
}

@inproceedings{neurips2018_multi_57399,
  title = {{Multi-Task Zipping via Layer-wise Neuron Sharing}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11584},
}

@inproceedings{neurips2023_does_67437,
  title = {{Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72296},
}

@inproceedings{iclr2018_beyond_28450,
  title = {{Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/49},
}

@inproceedings{aaai2021_maximum_972,
  title = {{Maximum Roaming Multi-Task Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/09331-maximum-roaming-multi-task-learning/},
}

@inproceedings{iclr2022_the_31140,
  title = {{The MultiBERTs: BERT Reproductions for Robustness Analysis}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6291},
}

@inproceedings{iclr2021_what_30412,
  title = {{What they do when in doubt: a study of inductive biases in seq2seq learners}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3006},
}

@inproceedings{neurips2018_dirichlet_57049,
  title = {{Dirichlet belief networks for topic structure learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11763},
}

@inproceedings{iclr2017_diet_28320,
  title = {{Diet Networks: Thin Parameters for Fat Genomics}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=Sk-oDY9ge},
}

@inproceedings{icml2021_lime_39501,
  title = {{LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9435},
}

@inproceedings{neurips2021_gradinit_61166,
  title = {{GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26950},
}

@inproceedings{iclr2024_teaching_34833,
  title = {{Teaching Arithmetic to Small Transformers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18241},
}

@inproceedings{icml2020_identifying_38292,
  title = {{Identifying Statistical Bias in Dataset Replication}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6807},
}

@inproceedings{neurips2022_a_64969,
  title = {{A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55229},
}

@inproceedings{neurips2022_first_66471,
  title = {{First is Better Than Last for Language Data Influence}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54338},
}

@inproceedings{neurips2023_transformers_69588,
  title = {{Transformers learn through gradual rank increase}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70343},
}

@inproceedings{iclr2024_small_34801,
  title = {{Small-scale proxies for large-scale Transformer training instabilities}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18273},
}

@inproceedings{iclr2025_sparse_81584,
  title = {{Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30192},
}

@inproceedings{neurips2024_initialization_72684,
  title = {{Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94702},
}

@inproceedings{iclr2025_not_82791,
  title = {{Not All Language Model Features Are One-Dimensionally Linear}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29008},
}

@inproceedings{iclr2024_model_33923,
  title = {{Model Merging by Uncertainty-Based Gradient Matching}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19152},
}

@inproceedings{icml2025_layer_47568,
  title = {{Layer by Layer: Uncovering Hidden Representations in Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45028},
}

@inproceedings{neurips2024_transformers_72677,
  title = {{Transformers Represent Belief State Geometry in their Residual Stream}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94708},
}

@inproceedings{neurips2024_reasons_74511,
  title = {{Reasons and Solutions for the Decline in Model Performance after Editing}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93066},
}

@inproceedings{aaai2024_composing_5445,
  title = {{Composing Biases by Using CP to Decompose Minimal Functional Dependencies for Acquiring Complex Formulae}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28641},
}

@inproceedings{neurips2025_towards_74706,
  title = {{Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=0KOfAUiHua},
}

@inproceedings{neurips2025_do_76594,
  title = {{Do Language Models Use Their Depth Efficiently?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=Kz6eUL86XP},
}

@inproceedings{neurips2025_equitabpfn_76666,
  title = {{EquiTabPFN: A Target-Permutation Equivariant Prior Fitted Network}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=LrnZDU9g7N},
}

@inproceedings{neurips2025_angular_78313,
  title = {{Angular Steering: Behavior Control via Rotation in Activation Space}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=dGi2d5yDs4},
}

@inproceedings{neurips2025_towards_78918,
  title = {{Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=jcvX8XFNqX},
}

@inproceedings{aaai2025_exploring_9069,
  title = {{Exploring Activation Patterns of Parameters in Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34730},
}

@inproceedings{cvpr2025_learning_26760,
  title = {{Learning on Model Weights using Tree Experts}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34466},
}

@inproceedings{iclr2024_what_33519,
  title = {{What does the Knowledge Neuron Thesis Have to do with Knowledge?}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19556},
}

@inproceedings{iclr2024_debiasing_34618,
  title = {{Debiasing Algorithm through Model Adaptation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18456},
}