% Key papers for Robust optimization for distribution shift (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2021_out_39757,
  title = {{Out-of-Distribution Generalization via Risk Extrapolation (REx)}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9185},
}

@inproceedings{neurips2020_improving_60073,
  title = {{Improving robustness against common corruptions by covariate shift adaptation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17278},
}

@inproceedings{neurips2021_adaptive_61162,
  title = {{Adaptive Risk Minimization: Learning to Adapt to Domain Shift}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28817},
}

@inproceedings{icml2020_robustness_38717,
  title = {{Robustness to Spurious Correlations via Human Annotations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6818},
}

@inproceedings{neurips2022_wild_64384,
  title = {{Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55759},
}

@inproceedings{icml2022_improving_40690,
  title = {{Improving Out-of-Distribution Robustness via Selective Augmentation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/18011},
}

@inproceedings{icml2022_test_41241,
  title = {{Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensing}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17923},
}

@inproceedings{neurips2021_online_61385,
  title = {{Online Adaptation to Label Distribution Shift}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26153},
}

@inproceedings{iclr2021_coping_30094,
  title = {{Coping with Label Shift via Distributionally Robust Optimisation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3242},
}

@inproceedings{neurips2021_bayesian_61200,
  title = {{Bayesian Adaptation for Covariate Shift}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26976},
}

@inproceedings{neurips2022_robust_65061,
  title = {{Robust Calibration with Multi-domain Temperature Scaling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55037},
}

@inproceedings{neurips2023_can_69728,
  title = {{Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70210},
}

@inproceedings{cvpr2025_sufficient_27775,
  title = {{Sufficient Invariant Learning for Distribution Shift}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34665},
}

@inproceedings{iclr2023_first_32120,
  title = {{First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/10920},
}

@inproceedings{iclr2023_a_33248,
  title = {{A Learning Based Hypothesis Test for Harmful Covariate Shift}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11571},
}

@inproceedings{iclr2022_tracking_31284,
  title = {{Tracking the risk of a deployed model and detecting harmful distribution shifts}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6896},
}

@inproceedings{iclr2022_distributionally_31436,
  title = {{Distributionally Robust Models with Parametric Likelihood Ratios}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6425},
}

@inproceedings{neurips2024_reconstruct_73249,
  title = {{Reconstruct and Match: Out-of-Distribution Robustness via Topological Homogeneity}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94189},
}

@inproceedings{neurips2022_automl_64564,
  title = {{AutoML Two-Sample Test}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54059},
}

@inproceedings{neurips2023_beyond_67130,
  title = {{Beyond Invariance: Test-Time Label-Shift Adaptation for Addressing "Spurious" Correlations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72578},
}

@inproceedings{neurips2024_sequential_73545,
  title = {{Sequential Harmful Shift Detection Without Labels}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93934},
}

@inproceedings{neurips2025_multi_76679,
  title = {{Multi-Expert Distributionally Robust Optimization for Out-of-Distribution Generalization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=Lz5BUjArK4},
}

@inproceedings{neurips2025_generalization_78967,
  title = {{Generalization vs Specialization under Concept Shift}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=kKPP6q5vBs},
}

@inproceedings{icml2024_multiply_45052,
  title = {{Multiply Robust Estimation for Local Distribution Shifts with Multiple Domains}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33400},
}

@inproceedings{neurips2024_auc_74559,
  title = {{AUC Maximization under Positive Distribution Shift}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93025},
}

@inproceedings{iclr2025_learning_82885,
  title = {{Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28915},
}

@inproceedings{iclr2026_mitigating_88455,
  title = {{Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Sets}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=mruL1LDjzV},
}

@inproceedings{neurips2026_what_94021,
  title = {{"What is Different Between These Datasets?" A Framework for Explaining Data Distribution Shifts}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/156666},
}

@inproceedings{cvpr2026_bridging_97898,
  title = {{Bridging Domain Expertise and Generalization for Performance Estimation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://openaccess.thecvf.com/content/CVPR2026/html/Li_Bridging_Domain_Expertise_and_Generalization_for_Performance_Estimation_CVPR_2026_paper.html},
}

@inproceedings{icml2025_test_46171,
  title = {{Test-Time Selective Adaptation for Uni-Modal Distribution Shift in Multi-Modal Data}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46389},
}

@inproceedings{neurips2026_dynamic_91260,
  title = {{Dynamic Context Modeling for Longitudinal Mental Health Monitoring under Distribution Shift}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/151758},
}