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

@inproceedings{cvpr2024_improved_23763,
  title = {{Improved Baselines with Visual Instruction Tuning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29558},
}

@inproceedings{neurips2023_visual_69876,
  title = {{Visual Instruction Tuning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70080},
}

@inproceedings{cvpr2024_smartedit_24842,
  title = {{SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30021},
}

@inproceedings{cvpr2024_quilt_24555,
  title = {{Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29468},
}

@inproceedings{neurips2023_cheap_69711,
  title = {{Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70226},
}

@inproceedings{neurips2023_lamm_68894,
  title = {{LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73519},
}

@inproceedings{cvpr2024_perceptiongpt_24450,
  title = {{PerceptionGPT: Effectively Fusing Visual Perception into LLM}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31054},
}

@inproceedings{cvpr2024_emovit_23358,
  title = {{EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29955},
}

@inproceedings{aaai2024_vigc_7740,
  title = {{VIGC: Visual Instruction Generation and Correction}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28338},
}

@inproceedings{neurips2024_biomedical_71223,
  title = {{Biomedical Visual Instruction Tuning with Clinician Preference Alignment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97787},
}

@inproceedings{cvpr2024_jack_23849,
  title = {{Jack of All Tasks Master of Many: Designing General-Purpose Coarse-to-Fine Vision-Language Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29592},
}

@inproceedings{aaai2024_visual_7779,
  title = {{Visual Instruction Tuning with Polite Flamingo}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29727},
}

@inproceedings{neurips2024_emr_73670,
  title = {{EMR-Merging: Tuning-Free High-Performance Model Merging}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93822},
}

@inproceedings{iclr2024_guiding_34453,
  title = {{Guiding Instruction-based Image Editing via Multimodal Large Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18621},
}

@inproceedings{cvpr2025_fireedit_26269,
  title = {{FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32646},
}

@inproceedings{iclr2024_llm_33877,
  title = {{LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19198},
}

@inproceedings{neurips2024_membership_73852,
  title = {{Membership Inference Attacks against Large Vision-Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93657},
}

@inproceedings{cvpr2024_llama_23898,
  title = {{LLaMA-Excitor: General Instruction Tuning via Indirect Feature Interaction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30137},
}

@inproceedings{cvpr2025_insightedit_26628,
  title = {{InsightEdit: Towards Better Instruction Following for Image Editing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34545},
}

@inproceedings{cvpr2025_llavidal_26695,
  title = {{LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33501},
}

@inproceedings{icml2024_safety_44816,
  title = {{Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33636},
}

@inproceedings{neurips2024_vlkeb_72302,
  title = {{VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97679},
}

@inproceedings{cvpr2025_filter_26259,
  title = {{Filter Images First, Generate Instructions Later: Pre-Instruction Data Selection for Visual Instruction Tuning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34872},
}