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

@inproceedings{cvpr2020_what_16486,
  title = {{What Makes Training Multi-Modal Classification Networks Hard?}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2021_smil_1313,
  title = {{SMIL: Multimodal Learning with Severely Missing Modality}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/02302-smil-multimodal-learning-with-severely-missing-modality/},
}

@inproceedings{cvpr2020_mmtm_15862,
  title = {{MMTM: Multimodal Transfer Module for CNN Fusion}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{neurips2021_attention_61921,
  title = {{Attention Bottlenecks for Multimodal Fusion}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26737},
}

@inproceedings{cvpr2017_missing_12458,
  title = {{Missing Modalities Imputation via Cascaded Residual Autoencoder}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{iclr2019_learning_29218,
  title = {{Learning Factorized Multimodal Representations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/925},
}

@inproceedings{aaai2020_modality_99746,
  title = {{Modality to Modality Translation: An Adversarial Representation Learning and Graph Fusion Network for Multimodal Fusion}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5347},
}

@inproceedings{cvpr2023_multi_21611,
  title = {{Multi-Modal Learning With Missing Modality via Shared-Specific Feature Modelling}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22508},
}

@inproceedings{cvpr2019_improving_14315,
  title = {{Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition With Multimodal Training}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{cvpr2022_are_18298,
  title = {{Are Multimodal Transformers Robust to Missing Modality?}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{aaai2018_efficient_105885,
  title = {{Efficient Large-Scale Multi-Modal Classification}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11945},
}

@inproceedings{neurips2018_multimodal_57406,
  title = {{Multimodal Generative Models for Scalable Weakly-Supervised Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11544},
}

@inproceedings{cvpr2023_multimodal_21626,
  title = {{Multimodal Prompting With Missing Modalities for Visual Recognition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22597},
}

@inproceedings{cvpr2023_pmr_21816,
  title = {{PMR: Prototypical Modal Rebalance for Multimodal Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/21218},
}

@inproceedings{neurips2020_deep_59657,
  title = {{Deep Multimodal Fusion by Channel  Exchanging}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17216},
}

@inproceedings{neurips2022_mind_64960,
  title = {{Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55406},
}

@inproceedings{neurips2019_variational_59181,
  title = {{Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14459},
}

@inproceedings{aaai2023_towards_4841,
  title = {{Towards Good Practices for Missing Modality Robust Action Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25378},
}

@inproceedings{cvpr2024_binding_22851,
  title = {{Binding Touch to Everything: Learning Unified Multimodal Tactile Representations}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31269},
}

@inproceedings{cvpr2023_efficient_20892,
  title = {{Efficient Multimodal Fusion via Interactive Prompting}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023},
  url = {https://cvpr.thecvf.com/virtual/2023/poster/22625},
}

@inproceedings{cvpr2024_multimodal_24229,
  title = {{Multimodal Representation Learning by Alternating Unimodal Adaptation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31623},
}

@inproceedings{cvpr2024_embracing_23355,
  title = {{Embracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30988},
}

@inproceedings{neurips2024_fusemoe_73536,
  title = {{FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93942},
}

@inproceedings{cvpr2024_enhancing_23371,
  title = {{Enhancing Multimodal Cooperation via Sample-level Modality Valuation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29937},
}

@inproceedings{cvpr2024_omnivec2_24337,
  title = {{OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31731},
}

@inproceedings{aaai2024_token_7569,
  title = {{Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29656},
}

@inproceedings{aaai2024_gradient_6145,
  title = {{Gradient-Guided Modality Decoupling for Missing-Modality Robustness}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29474},
}

@inproceedings{neurips2024_flex_73480,
  title = {{Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93993},
}

@inproceedings{aaai2024_redcore_7082,
  title = {{RedCore: Relative Advantage Aware Cross-Modal Representation Learning for Missing Modalities with Imbalanced Missing Rates}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29440},
}

@inproceedings{cvpr2024_modaverse_24170,
  title = {{ModaVerse: Efficiently Transforming Modalities with LLMs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30292},
}

@inproceedings{cvpr2025_adaptive_25447,
  title = {{Adaptive Unimodal Regulation for Balanced Multimodal Information Acquisition}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34252},
}

@inproceedings{aaai2025_retrieval_10544,
  title = {{Retrieval-Augmented Dynamic Prompt Tuning for Incomplete Multimodal Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33984},
}

@inproceedings{neurips2024_humanoid_71378,
  title = {{Humanoid Locomotion as Next Token Prediction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95871},
}

@inproceedings{aaai2025_multi_10054,
  title = {{Multi-to-Single: Reducing Multimodal Dependency in Emotion Recognition Through Contrastive Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32134},
}

@inproceedings{cvpr2025_unialign_27971,
  title = {{UNIALIGN: Scaling Multimodal Alignment within One Unified Model}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35260},
}

@inproceedings{neurips2024_classifier_73899,
  title = {{Classifier-guided Gradient Modulation for Enhanced Multimodal Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93612},
}

@inproceedings{neurips2024_deep_74637,
  title = {{Deep Correlated Prompting for Visual Recognition with Missing Modalities}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/92955},
}

@inproceedings{aaai2025_asymmetric_8156,
  title = {{Asymmetric Reinforcing Against Multi-Modal Representation Bias}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33841},
}

@inproceedings{cvpr2024_c3net_22890,
  title = {{C3Net: Compound Conditioned ControlNet for Multimodal Content Generation}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/31392},
}