@article{dynamicexpertsharingdecouplingmemoryfrom,
  title = {Dynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMs},
  author = {Hao Mark Chen and Zhiwen Mo and Royson Lee and Qianzhou Wang and Da Li and Shell Xu Hu and Wayne Luk and Timothy Hospedales and Hongxiang Fan},
  year = {2026},
  eprint = {2602.00879},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.00879},
}