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

@inproceedings{cvpr2024_mmmu_24071,
  title = {{MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31040},
}

@inproceedings{aaai2018_towards_100584,
  title = {{Towards Building Large Scale Multimodal Domain-Aware Conversation Systems}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11331},
}

@inproceedings{cvpr2024_pixellm_24472,
  title = {{PixelLM: Pixel Reasoning with Large Multimodal Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31700},
}

@inproceedings{cvpr2024_vip_25208,
  title = {{ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29580},
}

@inproceedings{cvpr2024_omnimedvqa_24332,
  title = {{OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30658},
}

@inproceedings{icml2024_mm_44108,
  title = {{MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34344},
}

@inproceedings{aaai2020_v_103778,
  title = {{V-PROM: A Benchmark for Visual Reasoning Using Visual Progressive Matrices}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6885},
}

@inproceedings{neurips2024_mmlongbench_73694,
  title = {{MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97524},
}

@inproceedings{neurips2024_measuring_72096,
  title = {{Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97697},
}

@inproceedings{cvpr2025_chatgarment_25698,
  title = {{ChatGarment: Garment Estimation, Generation and Editing via Large Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33886},
}

@inproceedings{neurips2025_ocrbench_77598,
  title = {{OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=Vb6i3Dp24N},
}

@inproceedings{neurips2025_mmada_80144,
  title = {{MMaDA: Multimodal Large Diffusion Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=wczmXLuLGd},
}

@inproceedings{neurips2024_gmai_71591,
  title = {{GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97754},
}

@inproceedings{aaai2025_urbench_11193,
  title = {{UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33163},
}

@inproceedings{cvpr2024_glitchbench_23629,
  title = {{GlitchBench: Can Large Multimodal Models Detect Video Game Glitches?}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29782},
}

@inproceedings{neurips2024_cares_72897,
  title = {{CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97614},
}

@inproceedings{cvpr2025_all_25471,
  title = {{All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33480},
}

@inproceedings{icml2024_gpt_45420,
  title = {{GPT-4V(ision) is a Generalist Web Agent, if Grounded}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33031},
}

@inproceedings{cvpr2025_fsbench_26224,
  title = {{FSBench: A Figure Skating Benchmark for Advancing Artistic Sports Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33747},
}

@inproceedings{cvpr2025_microvqa_26950,
  title = {{MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32974},
}

@inproceedings{neurips2025_eagle_77731,
  title = {{Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=X2xLfqX24x},
}

@inproceedings{cvpr2025_forensics_26301,
  title = {{Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34175},
}