% Key papers for Expert routing and specialization (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2022_mixture_65765,
  title = {{Mixture-of-Experts with Expert Choice Routing}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53703},
}

@inproceedings{icml2022_deepspeed_40432,
  title = {{DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/16671},
}

@inproceedings{cvpr2025_complexity_25750,
  title = {{Complexity Experts are Task-Discriminative Learners for Any Image Restoration}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34516},
}

@inproceedings{neurips2022_towards_64716,
  title = {{Towards Understanding the Mixture-of-Experts Layer in Deep Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53543},
}

@inproceedings{neurips2021_scaling_62052,
  title = {{Scaling Vision with Sparse Mixture of Experts}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/25989},
}

@inproceedings{neurips2022_uni_65391,
  title = {{Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54270},
}

@inproceedings{iclr2022_taming_30980,
  title = {{Taming Sparsely Activated Transformer with Stochastic Experts}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6179},
}

@inproceedings{iclr2024_from_35075,
  title = {{From Sparse to Soft Mixtures of Experts}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17998},
}

@inproceedings{neurips2022_on_65900,
  title = {{On the Representation Collapse of Sparse Mixture of Experts}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53300},
}

@inproceedings{aaai2024_efficient_5806,
  title = {{Efficient Deweahter Mixture-of-Experts with Uncertainty-Aware Feature-Wise Linear Modulation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29622},
}

@inproceedings{neurips2021_dselect_63356,
  title = {{DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28349},
}

@inproceedings{neurips2024_toward_74177,
  title = {{Toward Efficient Inference for Mixture of Experts}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93368},
}

@inproceedings{aaai2023_moec_4166,
  title = {{MoEC: Mixture of Expert Clusters}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26617},
}

@inproceedings{aaai2024_mode_6656,
  title = {{MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Experts}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29539},
}

@inproceedings{icml2023_patch_42813,
  title = {{Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24849},
}

@inproceedings{neurips2024_multilinear_72915,
  title = {{Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94496},
}

@inproceedings{neurips2024_multi_73126,
  title = {{Multi-Head Mixture-of-Experts}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94304},
}

@inproceedings{cvpr2025_ders_25866,
  title = {{DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/32392},
}

@inproceedings{icml2024_scaling_45801,
  title = {{Scaling Laws for Fine-Grained Mixture of Experts}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32651},
}

@inproceedings{neurips2024_moe_72061,
  title = {{MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95262},
}

@inproceedings{aaai2026_sub_107112,
  title = {{Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39464},
}

@inproceedings{icml2025_shortcut_46738,
  title = {{Shortcut-connected Expert Parallelism for Accelerating Mixture of Experts}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45834},
}

@inproceedings{neurips2024_mixture_70188,
  title = {{Mixture of Tokens: Continuous MoE through Cross-Example Aggregation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96896},
}

@inproceedings{neurips2024_unchosen_71041,
  title = {{Unchosen Experts Can Contribute Too: Unleashing MoE Models’ Power by Self-Contrast}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96169},
}

@inproceedings{neurips2024_mixture_71432,
  title = {{Mixture of Nested Experts: Adaptive Processing of Visual Tokens}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95822},
}

@inproceedings{neurips2024_lsh_72945,
  title = {{LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94467},
}

@inproceedings{neurips2025_flashmoe_76005,
  title = {{FlashMoE: Fast Distributed MoE in a Single Kernel}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=EZfDHprhZM},
}

@inproceedings{iclr2025_remoe_80740,
  title = {{ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/31028},
}

@inproceedings{iclr2025_layerwise_82877,
  title = {{Layerwise Recurrent Router for Mixture-of-Experts}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28923},
}

@inproceedings{iclr2026_mixture_88555,
  title = {{Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=oIdzliJAeA},
}