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

@inproceedings{cvpr2017_dual_12223,
  title = {{Dual Attention Networks for Multimodal Reasoning and Matching}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{cvpr2018_multimodal_13409,
  title = {{Multimodal Explanations: Justifying Decisions and Pointing to the Evidence}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Park_Multimodal_Explanations_Justifying_CVPR_2018_paper.html},
}

@inproceedings{aaai2019_block_103422,
  title = {{BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4818},
}

@inproceedings{iclr2017_hadamard_28353,
  title = {{Hadamard Product for Low-rank Bilinear Pooling}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=r1rhWnZkg},
}

@inproceedings{aaai2019_vistanet_99706,
  title = {{VistaNet: Visual Aspect Attention Network for Multimodal Sentiment Analysis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/3799},
}

@inproceedings{cvpr2020_multi_15913,
  title = {{Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{cvpr2024_monkey_24181,
  title = {{Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30904},
}

@inproceedings{aaai2024_bliva_5257,
  title = {{BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27999},
}

@inproceedings{cvpr2023_reveal_21963,
  title = {{REVEAL: Retrieval-Augmented Visual-Language Pre-Training With Multi-Source Multimodal Knowledge Memory}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22444},
}

@inproceedings{neurips2018_bilinear_56913,
  title = {{Bilinear Attention Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11171},
}

@inproceedings{cvpr2018_stacked_13610,
  title = {{Stacked Latent Attention for Multimodal Reasoning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Fan_Stacked_Latent_Attention_CVPR_2018_paper.html},
}

@inproceedings{cvpr2024_can_22947,
  title = {{Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31396},
}

@inproceedings{cvpr2022_dual_18706,
  title = {{Dual-Key Multimodal Backdoors for Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2025_augmenting_25530,
  title = {{Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34931},
}

@inproceedings{aaai2025_interpretable_9592,
  title = {{Interpretable Face Anti-Spoofing: Enhancing Generalization with Multimodal Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33073},
}

@inproceedings{cvpr2025_mimo_26862,
  title = {{MIMO: A Medical Vision Language Model with Visual Referring Multimodal Input and Pixel Grounding Multimodal Output}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35156},
}

@inproceedings{cvpr2025_sting_27552,
  title = {{STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security Inspection}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34647},
}

@inproceedings{cvpr2024_causal_22956,
  title = {{Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30460},
}

@inproceedings{cvpr2025_jtd_26661,
  title = {{JTD-UAV: MLLM-Enhanced Joint Tracking and Description Framework for Anti-UAV Systems}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33012},
}

@inproceedings{aaai2025_deqa_8601,
  title = {{DEQA: Descriptions Enhanced Question-Answering Framework for Multimodal Aspect-Based Sentiment Analysis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34572},
}

@inproceedings{cvpr2025_socialgesture_27700,
  title = {{SocialGesture: Delving into Multi-person Gesture Understanding}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34623},
}

@inproceedings{cvpr2025_upme_27975,
  title = {{UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33765},
}

@inproceedings{cvpr2025_ctrl_25669,
  title = {{CTRL-O: Language-Controllable Object-Centric Visual Representation Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32790},
}

@inproceedings{neurips2024_live_72111,
  title = {{LIVE: Learnable In-Context Vector for Visual Question Answering}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95218},
}

@inproceedings{neurips2024_searchlvlms_73679,
  title = {{SearchLVLMs: A Plug-and-Play Framework for Augmenting Large Vision-Language Models by Searching Up-to-Date Internet Knowledge}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93813},
}

@inproceedings{neurips2024_yo_73767,
  title = {{Yo'LLaVA: Your Personalized Language and Vision Assistant}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93737},
}

@inproceedings{aaai2026_regionrag_102652,
  title = {{RegionRAG: Region-level Retrieval-Augmented Generation for Visual Document Understanding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37597},
}

@inproceedings{icml2025_watch_48949,
  title = {{Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43674},
}

@inproceedings{neurips2024_flexcap_71979,
  title = {{FlexCap: Describe Anything in Images in Controllable Detail}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95332},
}

@inproceedings{neurips2024_impact_73634,
  title = {{IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design Patents}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97529},
}