Cao, Shijie
2 publications
NeurIPS
2025
SeerAttention: Self-Distilled Attention Gating for Efficient Long-Context Prefilling
Yizhao Gao, Zhichen Zeng, DaYou Du, Shijie Cao, Peiyuan Zhou, Jiaxing Qi, Junjie Lai, Hayden Kwok-Hay So, Ting Cao, Fan Yang, Mao Yang