@article{ontheflyadaptivedistillationof,
  title = {On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention},
  author = {Yeonju Ro and Zhenyu Zhang and Souvik Kundu and Zhangyang Wang and Aditya Akella},
  year = {2025},
  eprint = {2506.09316},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.09316v2},
}