% Key papers for RL fine-tuning of generative models (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2017_sequence_36391,
  title = {{Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/814},
}

@inproceedings{neurips2023_dpok_67046,
  title = {{DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72652},
}

@inproceedings{neurips2025_flow_79325,
  title = {{Flow-GRPO: Training Flow Matching Models via Online RL}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=oCBKGw5HNf},
}

@inproceedings{iclr2024_duolando_34048,
  title = {{Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19027},
}

@inproceedings{icml2023_optimizing_41531,
  title = {{Optimizing DDPM Sampling with Shortcut Fine-Tuning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/25253},
}

@inproceedings{neurips2025_se_76378,
  title = {{SE-GUI: Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=IbzDaIDyt6},
}

@inproceedings{neurips2023_how_68804,
  title = {{How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/71047},
}

@inproceedings{aaai2026_gui_108254,
  title = {{GUI-G²: Gaussian Reward Modeling for GUI Grounding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40606},
}

@inproceedings{cvpr2025_reward_27465,
  title = {{Reward Fine-Tuning Two-Step Diffusion Models via Learning Differentiable Latent-Space Surrogate Reward}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33042},
}

@inproceedings{icml2024_fine_43460,
  title = {{Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34992},
}

@inproceedings{neurips2024_rebel_74606,
  title = {{REBEL: Reinforcement Learning via Regressing Relative Rewards}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/92983},
}

@inproceedings{icml2024_feedback_44924,
  title = {{Feedback Efficient Online Fine-Tuning of Diffusion Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33528},
}

@inproceedings{icml2026_effects_55003,
  title = {{Effects of Structural Reward Shaping on Biophysical Properties in RL-Trained Plasmid Generators}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=uiMxVE16m3},
}

@inproceedings{neurips2025_reinforced_75090,
  title = {{Reinforced Active Learning for Large-Scale Virtual Screening with Learnable Policy Model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=49EjZytlus},
}

@inproceedings{neurips2025_adaptive_78049,
  title = {{Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=aXO0xg0ttW},
}

@inproceedings{iclr2025_online_80617,
  title = {{Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/31149},
}

@inproceedings{iclr2025_fine_81467,
  title = {{Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30308},
}

@inproceedings{iclr2026_cuda_88066,
  title = {{CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=igZItUbY6n},
}

@inproceedings{icml2025_score_47512,
  title = {{Score as Action: Fine Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45084},
}

@inproceedings{icml2025_task_48801,
  title = {{Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43821},
}

@inproceedings{icml2026_diffusion_51031,
  title = {{Diffusion Controller: Framework, Algorithms and Parameterization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=IGTMjtehxq},
}

@inproceedings{icml2026_blending_51473,
  title = {{Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=MgtyPYrC4h},
}

@inproceedings{icml2026_preference_52240,
  title = {{Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=TygL9qfa0d},
}

@inproceedings{icml2026_expected_52421,
  title = {{Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=Vr0kjNERRf},
}