@article{fastmmoeacceleratingmultimodallargelangu,
  title = {FastMMoE: Accelerating Multimodal Large Language Models through Dynamic Expert Activation and Routing-Aware Token Pruning},
  author = {Guoyang Xia and Yifeng Ding and Fengfa Li and Lei Ren and Wei Chen and Fangxiang Feng and Xiaojie Wang},
  year = {2025},
  eprint = {2511.17885},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.17885},
}