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

@inproceedings{neurips2024_are_73197,
  title = {{Are We on the Right Way for Evaluating Large Vision-Language Models?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94237},
}

@inproceedings{cvpr2024_vlp_25188,
  title = {{VLP: Vision Language Planning for Autonomous Driving}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29341},
}

@inproceedings{aaai2025_figstep_9192,
  title = {{FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34568},
}

@inproceedings{cvpr2025_molmo_26986,
  title = {{Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33073},
}

@inproceedings{cvpr2024_regiongpt_24606,
  title = {{RegionGPT: Towards Region Understanding Vision Language Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31126},
}

@inproceedings{cvpr2025_vera_28043,
  title = {{VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33523},
}

@inproceedings{neurips2024_what_73121,
  title = {{What matters when building vision-language models?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94309},
}

@inproceedings{neurips2024_visual_72858,
  title = {{Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97623},
}

@inproceedings{cvpr2025_vila_28046,
  title = {{VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33276},
}

@inproceedings{cvpr2025_vision_28117,
  title = {{Vision-Language Models Do Not Understand Negation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34106},
}

@inproceedings{cvpr2024_dress_23096,
  title = {{DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29224},
}

@inproceedings{neurips2024_vhelm_72340,
  title = {{VHELM: A Holistic Evaluation of Vision Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97677},
}

@inproceedings{cvpr2025_words_28163,
  title = {{Words or Vision: Do Vision-Language Models Have Blind Faith in Text?}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33847},
}

@inproceedings{iclr2024_jailbreak_35306,
  title = {{Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17767},
}

@inproceedings{cvpr2025_solve_27536,
  title = {{SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32830},
}

@inproceedings{cvpr2025_spa_27538,
  title = {{SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34524},
}

@inproceedings{neurips2024_vismin_72916,
  title = {{VisMin: Visual Minimal-Change Understanding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94495},
}

@inproceedings{neurips2025_disasterm3_79726,
  title = {{DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=sQO1ZEQGqX},
}

@inproceedings{cvpr2024_geochat_23622,
  title = {{GeoChat: Grounded Large Vision-Language Model for Remote Sensing}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29981},
}

@inproceedings{cvpr2025_finecaption_26213,
  title = {{FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32855},
}