% Key papers for Reasoning mechanisms and failure modes (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2018_measuring_36845,
  title = {{Measuring abstract reasoning in neural networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2194},
}

@inproceedings{iclr2020_permutation_29724,
  title = {{Permutation Equivariant Models for Compositional Generalization in Language}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=SylVNerFvr},
}

@inproceedings{neurips2016_deep_55669,
  title = {{Deep Learning for Predicting Human Strategic Behavior}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7215},
}

@inproceedings{iclr2023_emergent_32258,
  title = {{Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11827},
}

@inproceedings{iclr2023_interpretability_32485,
  title = {{Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11341},
}

@inproceedings{icml2024_a_44113,
  title = {{A Tale of Tails: Model Collapse as a Change of Scaling Laws}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34339},
}

@inproceedings{neurips2019_abstract_57858,
  title = {{Abstract Reasoning with Distracting Features}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13708},
}

@inproceedings{iclr2024_turning_34861,
  title = {{Turning large language models into cognitive models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18213},
}

@inproceedings{neurips2023_how_69481,
  title = {{How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70432},
}

@inproceedings{aaai2020_back_102930,
  title = {{Back to the Future – Temporal Adaptation of Text Representations}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6240},
}

@inproceedings{icml2024_emergent_43603,
  title = {{Emergent Representations of Program Semantics in Language Models Trained on Programs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34849},
}

@inproceedings{neurips2023_moca_68305,
  title = {{MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71498},
}

@inproceedings{neurips2023_exposing_68385,
  title = {{Exposing Attention Glitches with Flip-Flop Language Modeling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71426},
}

@inproceedings{aaai2026_when_108293,
  title = {{When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40645},
}

@inproceedings{neurips2023_schema_66715,
  title = {{Schema-learning and rebinding as mechanisms of in-context learning and emergence}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72915},
}

@inproceedings{neurips2023_interpretability_69405,
  title = {{Interpretability at Scale: Identifying Causal Mechanisms in Alpaca}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70504},
}

@inproceedings{iclr2025_improving_84006,
  title = {{Improving Instruction-Following in Language Models through Activation Steering}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/27819},
}

@inproceedings{iclr2022_linking_30852,
  title = {{Linking Emergent and Natural Languages via Corpus Transfer}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6044},
}

@inproceedings{iclr2026_neologism_89268,
  title = {{Neologism Learning for Controllability and Self-Verbalization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=wyolJ5sGCT},
}

@inproceedings{iclr2024_overthinking_34512,
  title = {{Overthinking the Truth: Understanding how Language Models Process False Demonstrations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18562},
}

@inproceedings{iclr2024_sudden_34250,
  title = {{Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18825},
}

@inproceedings{icml2024_in_43722,
  title = {{In-Context Learning Agents Are Asymmetric Belief Updaters}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34730},
}

@inproceedings{aaai2024_bilateral_5299,
  title = {{Bilateral Gradual Semantics for Weighted Argumentation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28945},
}

@inproceedings{aaai2025_glam_9279,
  title = {{GLAM: Global-Local Variation Awareness in Mamba-based World Model}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33880},
}

@inproceedings{iclr2024_successor_35118,
  title = {{Successor Heads: Recurring, Interpretable Attention Heads In The Wild}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17955},
}

@inproceedings{icml2024_a_44841,
  title = {{A Language Model’s Guide Through Latent Space}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33611},
}

@inproceedings{icml2025_why_46823,
  title = {{Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45753},
}

@inproceedings{neurips2024_linking_70955,
  title = {{Linking In-context Learning in Transformers to Human Episodic Memory}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96248},
}

@inproceedings{neurips2025_how_74784,
  title = {{How do Transformers Learn Implicit Reasoning?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=19ygs48nOa},
}

@inproceedings{iclr2024_understanding_34734,
  title = {{Understanding In-Context Learning from Repetitions}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18340},
}

@inproceedings{iclr2024_understanding_34863,
  title = {{Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18211},
}

@inproceedings{icml2024_language_44787,
  title = {{Language Models Represent Beliefs of Self and Others}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33665},
}

@inproceedings{icml2025_emergent_49067,
  title = {{Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43557},
}