@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},
doi = {10.18653/2026.emnlp-main.1946},
url = {https://doi.org/10.18653/2026.emnlp-main.1946},
}
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. https://doi.org/10.18653/2026.emnlp-main.1946
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, https://doi.org/10.18653/2026.emnlp-main.1946.
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). https://doi.org/10.18653/2026.emnlp-main.1946
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. Available at: <https://doi.org/10.18653/2026.emnlp-main.1946>.
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
DO - 10.18653/2026.emnlp-main.1946
UR - https://doi.org/10.18653/2026.emnlp-main.1946
ER -