% Key papers for Reward modeling versus direct optimization (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2017_deep_56245,
  title = {{Deep Reinforcement Learning from Human Preferences}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9209},
}

@inproceedings{aaai2020_what_102995,
  title = {{What Makes A Good Story? Designing Composite Rewards for Visual Storytelling}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6305},
}

@inproceedings{neurips2019_text_59055,
  title = {{Text-Based Interactive Recommendation via Constraint-Augmented Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://papers.nips.cc/paper_files/paper/2019/hash/52130c418d4f02c74f74a5bc1f8020b2-Abstract.html},
}

@inproceedings{iclr2022_surf_31319,
  title = {{SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6054},
}

@inproceedings{aaai2024_towards_7578,
  title = {{Towards Automated RISC-V Microarchitecture Design with Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27750},
}

@inproceedings{cvpr2024_prdp_24417,
  title = {{PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30264},
}

@inproceedings{aaai2024_rating_7066,
  title = {{Rating-Based Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28886},
}

@inproceedings{aaai2025_radiology_10459,
  title = {{Radiology Report Generation via Multi-objective Preference Optimization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32936},
}

@inproceedings{iclr2024_statistical_35623,
  title = {{Statistical Rejection Sampling Improves Preference Optimization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17450},
}

@inproceedings{icml2023_aligning_43090,
  title = {{Aligning Language Models with Preferences through \$f\$-divergence Minimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24706},
}

@inproceedings{iclr2023_preference_32537,
  title = {{Preference Transformer: Modeling Human Preferences using Transformers for RL}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11308},
}

@inproceedings{iclr2023_causal_32580,
  title = {{Causal Confusion and Reward Misidentification in Preference-Based Reward Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/10822},
}

@inproceedings{icml2024_a_43485,
  title = {{A Minimaximalist Approach to Reinforcement Learning from Human Feedback}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34967},
}

@inproceedings{neurips2025_drivedpo_78408,
  title = {{DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=eIf9GNcA5n},
}

@inproceedings{aaai2025_forward_9223,
  title = {{Forward KL Regularized Preference Optimization for Aligning Diffusion Policies}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33576},
}

@inproceedings{icml2024_human_43346,
  title = {{Human Alignment of Large Language Models through Online Preference Optimisation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35106},
}

@inproceedings{icml2026_human_54812,
  title = {{Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=svT8c2GPJK},
}

@inproceedings{neurips2024_stepwise_72493,
  title = {{Stepwise Alignment for Constrained Language Model Policy Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94870},
}

@inproceedings{neurips2024_aligning_72549,
  title = {{Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94822},
}

@inproceedings{neurips2025_aligning_77315,
  title = {{Aligning Transformers with Continuous Feedback via Energy Rank Alignment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=SXxlb1miXS},
}

@inproceedings{iclr2024_parl_33884,
  title = {{PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19191},
}

@inproceedings{iclr2024_aligndiff_34759,
  title = {{AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18315},
}

@inproceedings{icml2024_pearl_43279,
  title = {{PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35173},
}

@inproceedings{icml2024_reward_44076,
  title = {{Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34376},
}

@inproceedings{neurips2024_the_71403,
  title = {{The Importance of Online Data: Understanding Preference Fine-tuning via Coverage}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95849},
}

@inproceedings{neurips2024_guide_71637,
  title = {{GUIDE: Real-Time Human-Shaped Agents}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95640},
}

@inproceedings{neurips2025_kl_74676,
  title = {{KL Penalty Control via Perturbation for Direct Preference Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=00oRAPDWsX},
}