% Key papers for Reinforcement learning for visual reasoning (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2025_jarvisir_26666,
  title = {{JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34333},
}

@inproceedings{neurips2024_fine_73802,
  title = {{Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93706},
}

@inproceedings{aaai2026_medeyes_105645,
  title = {{MedEyes: Learning Dynamic Visual Focus for Medical Progressive Diagnosis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38401},
}

@inproceedings{cvpr2025_critic_25790,
  title = {{Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33205},
}

@inproceedings{neurips2025_pixel_77605,
  title = {{Pixel Reasoner: Incentivizing Pixel Space Reasoning via Curiosity-Driven Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=VeZkY3JjWV},
}

@inproceedings{neurips2025_grounded_74824,
  title = {{Grounded Reinforcement Learning for Visual Reasoning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=1amnhVRQ3l},
}

@inproceedings{neurips2025_sam_78316,
  title = {{SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=dHOSTp8MBl},
}

@inproceedings{neurips2025_vrag_76013,
  title = {{VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=EeAHhNwXPV},
}

@inproceedings{neurips2025_reason_76856,
  title = {{Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=NdScoAix25},
}

@inproceedings{neurips2025_sota_76986,
  title = {{SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=PHu9xJeAum},
}

@inproceedings{cvpr2025_vl_28054,
  title = {{VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33389},
}

@inproceedings{neurips2025_fast_76709,
  title = {{Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=MI1uT5rReV},
}

@inproceedings{aaai2026_recad_102599,
  title = {{ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37544},
}

@inproceedings{aaai2026_refine_107035,
  title = {{Refine-IQA: Multi-Stage Reinforcement Finetuning for Perceptual Image Quality Assessment}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39387},
}

@inproceedings{aaai2026_patho_107719,
  title = {{Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40071},
}

@inproceedings{cvpr2025_continual_25773,
  title = {{Continual SFT Matches Multimodal RLHF with Negative Supervision}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34637},
}

@inproceedings{neurips2025_unified_75423,
  title = {{Unified Reinforcement and Imitation Learning for Vision-Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=7wEvjzkNXg},
}

@inproceedings{neurips2025_grit_77211,
  title = {{GRIT: Teaching MLLMs to Think with Images}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=RW3cHh3HgY},
}

@inproceedings{neurips2025_mico_77405,
  title = {{MiCo: Multi-image Contrast for Reinforcement Visual Reasoning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=TUCHMVzXin},
}

@inproceedings{aaai2026_drive_102657,
  title = {{Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37602},
}