% Key papers for DPO design choices (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2024_simpo_70356,
  title = {{SimPO: Simple Preference Optimization with a Reference-Free Reward}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96741},
}

@inproceedings{neurips2024_beta_72773,
  title = {{\$beta\$-DPO: Direct Preference Optimization with Dynamic \$beta\$}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94622},
}

@inproceedings{neurips2024_iterative_70448,
  title = {{Iterative Reasoning Preference Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96659},
}

@inproceedings{neurips2024_preference_72712,
  title = {{Preference Learning Algorithms Do Not Learn Preference Rankings}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94675},
}

@inproceedings{icml2024_a_44887,
  title = {{A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33565},
}

@inproceedings{aaai2025_robust_10575,
  title = {{Robust Multi-Objective Preference Alignment with Online DPO}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34942},
}

@inproceedings{iclr2025_tpo_81938,
  title = {{TPO: Aligning Large Language Models with Multi-branch \& Multi-step Preference Trees}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29846},
}

@inproceedings{iclr2025_mallowspo_82794,
  title = {{MallowsPO: Fine-Tune Your LLM with Preference Dispersions}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29005},
}

@inproceedings{aaai2025_multi_10028,
  title = {{Multi-Reference Preference Optimization for Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34615},
}

@inproceedings{aaai2025_wepo_11260,
  title = {{WEPO: Web Element Preference Optimization for LLM-based Web Navigation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34863},
}

@inproceedings{neurips2025_aligning_75279,
  title = {{Aligning Compound AI Systems via System-level DPO}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=6IuURCuooO},
}

@inproceedings{neurips2025_optiscene_77980,
  title = {{OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=ZnrM5RGrgR},
}

@inproceedings{aaai2026_smpro_108780,
  title = {{SMPRO: Self-Supervised Visual Preference Alignment via Differentiable Multi-Preference Multi-Group Ranking}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/41132},
}

@inproceedings{aaai2026_preference_108863,
  title = {{Preference Robustness for DPO with Applications to Public Health}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/41215},
}

@inproceedings{icml2025_understanding_46077,
  title = {{Understanding the Logic of Direct Preference Alignment through Logic}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46481},
}

@inproceedings{icml2025_improving_46954,
  title = {{Improving LLM Safety Alignment with Dual-Objective Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45626},
}

@inproceedings{icml2025_right_47900,
  title = {{Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44703},
}

@inproceedings{icml2025_energy_48830,
  title = {{Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43792},
}

@inproceedings{icml2026_tokenratio_49369,
  title = {{TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=1twve5mNUU},
}

@inproceedings{icml2026_autoregressive_50578,
  title = {{Autoregressive Direct Preference Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=DmeFAFUO6f},
}