@misc{qwen3technicalreport,
      title={Qwen3 Technical Report}, 
      author={Qwen Team},
      year={2025},
      eprint={2505.09388},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.09388}, 
}

@misc{tan2024scatteredmixtureofexpertsimplementation,
      title={Scattered Mixture-of-Experts Implementation}, 
      author={Shawn Tan and Yikang Shen and Rameswar Panda and Aaron Courville},
      year={2024},
      eprint={2403.08245},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2403.08245}, 
}

@misc{hsu2025ligerkernelefficienttriton,
      title={Liger Kernel: Efficient Triton Kernels for LLM Training}, 
      author={Pin-Lun Hsu and Yun Dai and Vignesh Kothapalli and Qingquan Song and Shao Tang and Siyu Zhu and Steven Shimizu and Shivam Sahni and Haowen Ning and Yanning Chen},
      year={2025},
      eprint={2410.10989},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2410.10989}, 
}

@misc{wijmans2025cutlosseslargevocabularylanguage,
      title={Cut Your Losses in Large-Vocabulary Language Models}, 
      author={Erik Wijmans and Brody Huval and Alexander Hertzberg and Vladlen Koltun and Philipp Krähenbühl},
      year={2025},
      eprint={2411.09009},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2411.09009}, 
}