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

@inproceedings{cvpr2024_seed_24701,
  title = {{SEED-Bench: Benchmarking 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/30703},
}

@inproceedings{neurips2025_mme_75921,
  title = {{MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=DgH9YCsqWm},
}

@inproceedings{cvpr2024_rlhf_24567,
  title = {{RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31610},
}

@inproceedings{aaai2020_multimodal_103215,
  title = {{Multimodal Summarization with Guidance of Multimodal Reference}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6525},
}

@inproceedings{icml2024_next_44252,
  title = {{NExT-GPT: Any-to-Any Multimodal LLM}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34200},
}

@inproceedings{neurips2024_emotion_74031,
  title = {{Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93492},
}

@inproceedings{cvpr2024_q_24547,
  title = {{Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31760},
}

@inproceedings{aaai2024_pathasst_6936,
  title = {{PathAsst: A Generative Foundation AI Assistant towards Artificial General Intelligence of Pathology}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28308},
}

@inproceedings{cvpr2025_towards_27937,
  title = {{Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35020},
}

@inproceedings{cvpr2025_xlrs_28166,
  title = {{XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35068},
}

@inproceedings{aaai2025_divide_8783,
  title = {{Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32852},
}

@inproceedings{cvpr2025_drivegpt4_26008,
  title = {{DriveGPT4-V2: Harnessing Large Language Model Capabilities for Enhanced Closed-Loop Autonomous Driving}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33516},
}

@inproceedings{cvpr2025_cross_25800,
  title = {{Cross-modal Information Flow in Multimodal Large Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33685},
}

@inproceedings{cvpr2025_multi_27018,
  title = {{Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33317},
}

@inproceedings{cvpr2025_bridging_25620,
  title = {{Bridging Modalities: Improving Universal Multimodal Retrieval by Multimodal Large Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34475},
}

@inproceedings{cvpr2024_hrvda_23674,
  title = {{HRVDA: High-Resolution Visual Document Assistant}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29985},
}

@inproceedings{cvpr2025_distraction_25972,
  title = {{Distraction is All You Need for Multimodal Large Language Model Jailbreaking}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33971},
}

@inproceedings{cvpr2025_docopilot_25989,
  title = {{Docopilot: Improving Multimodal Models for Document-Level Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33306},
}

@inproceedings{cvpr2025_peace_27180,
  title = {{PEACE: Empowering Geologic Map Holistic Understanding with MLLMs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34989},
}

@inproceedings{iclr2025_mmed_83672,
  title = {{MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28145},
}

@inproceedings{aaai2025_math_9916,
  title = {{Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34815},
}