% Key papers for Efficient MoE language model systems (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2022_glam_40601,
  title = {{GLaM: Efficient Scaling of Language Models with Mixture-of-Experts}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17377},
}

@inproceedings{icml2021_base_39076,
  title = {{BASE Layers: Simplifying Training of Large, Sparse Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9213},
}

@inproceedings{iclr2025_olmoe_84048,
  title = {{OLMoE: Open Mixture-of-Experts Language Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/27777},
}

@inproceedings{aaai2025_ewmoe_8883,
  title = {{EWMoE: An Effective Model for Global Weather Forecasting with Mixture-of-Experts}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/31997},
}

@inproceedings{aaai2025_bigmac_8269,
  title = {{BigMac: A Communication-Efficient Mixture-of-Experts Model Structure for Fast Training and Inference}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33945},
}

@inproceedings{iclr2025_fiddler_81884,
  title = {{Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29900},
}

@inproceedings{iclr2025_your_82861,
  title = {{Your Mixture-of-Experts LLM Is Secretly an Embedding Model for Free}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28939},
}

@inproceedings{neurips2025_flexolmo_74855,
  title = {{FlexOLMo: Open Language Models for Flexible Data Use}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=1rUj9ZN6Bz},
}

@inproceedings{iclr2025_efficiently_81666,
  title = {{Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30111},
}

@inproceedings{aaai2026_evomoe_107053,
  title = {{EvoMoE: Expert Evolution in Mixture of Experts for Multimodal Large Language Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39405},
}

@inproceedings{aaai2026_commitmoe_107102,
  title = {{CommitMoE: Efficient Fallback-Free MoE Inference with Offloading Under GPU Memory Constraints}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39454},
}

@inproceedings{aaai2026_camera_107605,
  title = {{CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39957},
}

@inproceedings{icml2025_moequant_45869,
  title = {{MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46674},
}

@inproceedings{icml2025_qos_48119,
  title = {{QoS-Efficient Serving of Multiple Mixture-of-Expert LLMs Using Partial Runtime Reconfiguration}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44489},
}

@inproceedings{icml2025_retraining_48219,
  title = {{Retraining-free Merging of Sparse MoE via Hierarchical Clustering}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44392},
}

@inproceedings{icml2025_parameters_48403,
  title = {{Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44214},
}

@inproceedings{icml2026_mose_49296,
  title = {{MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=18C6xMcD96},
}

@inproceedings{icml2026_rq_49373,
  title = {{RQ-MoE: Residual Quantization via Mixture of Experts for Efficient Input-Dependent Vector Compression}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=1wnPjWrw18},
}

@inproceedings{icml2026_capacity_50523,
  title = {{Capacity-Aware Mixture Law Enables Efficient LLM Data Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=DDtL4VOUcT},
}

@inproceedings{icml2026_zipmoe_51854,
  title = {{ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=QUL7jp4QDQ},
}

@inproceedings{icml2026_team_52359,
  title = {{TEAM: Temporal–Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Acceleration}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=V6d1eHy6KE},
}

@inproceedings{icml2026_dot_52522,
  title = {{DOT-MoE: Differentiable Optimal Transport for MoEfication}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=WrXyXq11Yc},
}