@article{yingfa2026,
title = {Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts},
author = {Chen, Yingfa and Thai, Zhen Leng and Zhou, Zihan and Zhang, Zhu and Shen, Xingyu and Wang, Shuo and Xiao, Chaojun and Han, Xu and Liu, Zhiyuan},
journal = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
year = {2026},
month = {Jan},
}
Chen, Yingfa et al. (2026). Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing.
Chen, Yingfa, et al.. "Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts." Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026.
Chen, Yingfa, et al.. "Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts." Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (2026).
Chen, Yingfa et al., 2026. Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts. Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing.
TY - JOUR
TI - Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts
AU - Chen, Yingfa
AU - Thai, Zhen Leng
AU - Zhou, Zihan
AU - Zhang, Zhu
AU - Shen, Xingyu
AU - Wang, Shuo
AU - Xiao, Chaojun
AU - Han, Xu
AU - Liu, Zhiyuan
PY - 2026
JO - Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
ER -