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

@inproceedings{cvpr2022_multimodal_19401,
  title = {{Multimodal Dynamics: Dynamical Fusion for Trustworthy Multimodal Classification}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2023_m3ae_4100,
  title = {{M3AE: Multimodal Representation Learning for Brain Tumor Segmentation with Missing Modalities}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25253},
}

@inproceedings{aaai2019_joint_100186,
  title = {{Joint Representation Learning for Multi-Modal Transportation Recommendation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/3894},
}

@inproceedings{cvpr2021_vectorization_18116,
  title = {{Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
}

@inproceedings{aaai2020_cross_101948,
  title = {{Cross-Modal Subspace Clustering via Deep Canonical Correlation Analysis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5808},
}

@inproceedings{aaai2021_deep_387,
  title = {{Deep Mutual Information Maximin for Cross-Modal Clustering}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/08893-deep-mutual-information-maximin-for-cross-modal-clustering/},
}

@inproceedings{aaai2024_drfuse_5753,
  title = {{DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29578},
}

@inproceedings{cvpr2022_neural_19426,
  title = {{Neural Collaborative Graph Machines for Table Structure Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2023_heterogeneous_3823,
  title = {{Heterogeneous Graph Learning for Multi-Modal Medical Data Analysis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25643},
}

@inproceedings{aaai2025_bsafusion_8219,
  title = {{BSAFusion: A Bidirectional Stepwise Feature Alignment Network for Unaligned Medical Image Fusion}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32499},
}

@inproceedings{neurips2024_healnet_71424,
  title = {{HEALNet: Multimodal Fusion for Heterogeneous Biomedical Data}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95829},
}

@inproceedings{neurips2024_coupled_72391,
  title = {{Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94962},
}

@inproceedings{cvpr2024_modality_24171,
  title = {{Modality-Agnostic Structural Image Representation Learning for Deformable Multi-Modality Medical Image Registration}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29910},
}

@inproceedings{neurips2022_otkge_65647,
  title = {{OTKGE: Multi-modal Knowledge Graph Embeddings via Optimal Transport}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55202},
}

@inproceedings{cvpr2024_mplug_25321,
  title = {{mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31761},
}

@inproceedings{aaai2023_multi_4199,
  title = {{Multi-Modal Knowledge Hypergraph for Diverse Image Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25445},
}

@inproceedings{cvpr2023_mmg_21496,
  title = {{MMG-Ego4D: Multimodal Generalization in Egocentric Action Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21130},
}

@inproceedings{aaai2024_tmformer_7481,
  title = {{TMFormer: Token Merging Transformer for Brain Tumor Segmentation with Missing Modalities}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28572},
}

@inproceedings{aaai2025_tokenization_11016,
  title = {{Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity Representation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33454},
}

@inproceedings{neurips2019_dm2c_58081,
  title = {{DM2C: Deep Mixed-Modal Clustering}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14537},
}

@inproceedings{aaai2024_dynamic_5773,
  title = {{Dynamic Weighted Combiner for Mixed-Modal Image Retrieval}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28004},
}

@inproceedings{neurips2024_unraveling_74512,
  title = {{Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for Chemistry}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97441},
}

@inproceedings{cvpr2025_multi_27031,
  title = {{Multi-modal Vision Pre-training for Medical Image Analysis}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34305},
}

@inproceedings{cvpr2025_cross_25795,
  title = {{Cross-Modal Interactive Perception Network with Mamba for Lung Tumor Segmentation in PET-CT Images}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34267},
}

@inproceedings{aaai2024_mesed_6573,
  title = {{MESED: A Multi-Modal Entity Set Expansion Dataset with Fine-Grained Semantic Classes and Hard Negative Entities}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28715},
}

@inproceedings{cvpr2025_mbq_26845,
  title = {{MBQ: Modality-Balanced Quantization 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/33438},
}

@inproceedings{aaai2024_comprehensive_5452,
  title = {{Comprehensive View Embedding Learning for Single-Cell Multimodal Integration}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29453},
}

@inproceedings{cvpr2025_incomplete_26619,
  title = {{Incomplete Multi-modal Brain Tumor Segmentation via Learnable Sorting State Space Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/33842},
}

@inproceedings{neurips2024_tackling_71477,
  title = {{Tackling Uncertain Correspondences for Multi-Modal Entity Alignment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95783},
}

@inproceedings{aaai2025_incomplete_9551,
  title = {{Incomplete Modality Disentangled Representation for Ophthalmic Disease Grading and Diagnosis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32570},
}

@inproceedings{aaai2025_mixed_9963,
  title = {{Mixed-Curvature Multi-Modal Knowledge Graph Completion}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33273},
}

@inproceedings{cvpr2025_distilled_25964,
  title = {{Distilled Prompt Learning for Incomplete Multimodal Survival Prediction}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34848},
}