On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention

@misc{wang2025ontheflyadaptivedistillation,
      title={On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear  Attention},
      author={Zhangyang Wang and Zhenyu Zhang and Souvik Kundu and Aditya Akella and Yeonju Ro},
      year={2025},
      eprint={2506.09316},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2506.09316},
}