@inproceedings{qian-etal-2026-improved,
    title = "Improved Policy Optimization for Mixture-of-Experts Models: Importance Sampling and Rewarding from an Expert-Centric Perspective",
    author = "Qian, Yining  and
      Li, Jinpeng  and
      Mi, Fei  and
      Shang, Lifeng  and
      Zhang, Xiang",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1944/",
    pages = "39029--39038",
    ISBN = "979-8-89176-395-1"
}