% Key papers for Active and token-level preference learning (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2023_direct_67576,
  title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72164},
}

@inproceedings{cvpr2024_diffusion_23202,
  title = {{Diffusion Model Alignment Using Direct Preference Optimization}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31416},
}

@inproceedings{neurips2024_on_74054,
  title = {{On Softmax Direct Preference Optimization for Recommendation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93473},
}

@inproceedings{neurips2024_ultramedical_73963,
  title = {{UltraMedical: Building Specialized Generalists in Biomedicine}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97506},
}

@inproceedings{icml2024_is_43539,
  title = {{Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34913},
}

@inproceedings{aaai2025_controllable_8535,
  title = {{Controllable Protein Sequence Generation with LLM Preference Optimization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32030},
}

@inproceedings{iclr2024_beyond_33532,
  title = {{Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19543},
}

@inproceedings{icml2025_thinking_49130,
  title = {{Thinking LLMs: General Instruction Following with Thought Generation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43495},
}

@inproceedings{neurips2024_group_71999,
  title = {{Group Robust Preference Optimization in Reward-free RLHF}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95314},
}

@inproceedings{neurips2024_discovering_73189,
  title = {{Discovering Preference Optimization Algorithms with and for Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94244},
}

@inproceedings{neurips2024_flame_74643,
  title = {{FLAME : Factuality-Aware Alignment for Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/92950},
}

@inproceedings{neurips2025_mix_77294,
  title = {{Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=SNJhYhO3a9},
}

@inproceedings{aaai2026_multi_108356,
  title = {{Multi-Value Alignment for LLMs via Value Decorrelation and Extrapolation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40708},
}

@inproceedings{aaai2025_aligning_8081,
  title = {{Aligning Large Language Models for Faithful Integrity Against Opposing Argument}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34990},
}

@inproceedings{icml2025_alphapo_47015,
  title = {{AlphaPO: Reward Shape Matters for LLM Alignment}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45569},
}

@inproceedings{neurips2024_personalized_70700,
  title = {{Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96424},
}

@inproceedings{neurips2024_safeworld_72472,
  title = {{SafeWorld: Geo-Diverse Safety Alignment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94887},
}

@inproceedings{iclr2025_learning_83763,
  title = {{Learning Dynamics of LLM Finetuning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28056},
}

@inproceedings{iclr2026_safedpo_86385,
  title = {{SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=PJdw4VBsXD},
}

@inproceedings{aaai2026_beyond_108446,
  title = {{Beyond Step Pruning: Information Theory Based Step-level Optimization for Self-Refining Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40798},
}

@inproceedings{aaai2025_aligning_8080,
  title = {{Aligning Language Models Using Follow-up Likelihood as Reward Signal}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34776},
}