Zhengyi Li

11 papers A* 3Journal 7Unranked 1
YearRankTypeTitle / Venue / Authors
2025 A* conf
An Efficient Private GPT Never Autoregressively Decodes.
ICML
Zhengyi Li, Yue Guan, Kang Yang, Yu Feng, Ning Liu, Yu Yu, Jingwen Leng, Minyi Guo
2025 J jnl
An Efficient Private GPT Never Autoregressively Decodes.
CoRR
Zhengyi Li, Yue Guan, Kang Yang, Yu Feng, Ning Liu, Yu Yu, Jingwen Leng, Minyi Guo
2025 J jnl
An Efficient Private GPT Never Autoregressively Decodes.
IACR Cryptol. ePrint Arch.
Zhengyi Li, Yue Guan, Kang Yang, Yu Feng, Ning Liu, Yu Yu, Jingwen Leng, Minyi Guo
2025 J jnl
Nimbus: Secure and Efficient Two-Party Inference for Transformers.
IACR Cryptol. ePrint Arch.
Zhengyi Li, Kang Yang, Jin Tan, Wen-jie Lu, Haoqi Wu, Xiao Wang, Yu Yu, Derun Zhao, Yancheng Zheng, Minyi Guo, Jingwen Leng
2024 A* conf
Nimbus: Secure and Efficient Two-Party Inference for Transformers.
NeurIPS
Zhengyi Li, Kang Yang, Jin Tan, Wen-jie Lu, Haoqi Wu, Xiao Wang, Yu Yu, Derun Zhao, Yancheng Zheng, Minyi Guo, Jingwen Leng
2024 J jnl
Nimbus: Secure and Efficient Two-Party Inference for Transformers.
CoRR
Zhengyi Li, Kang Yang, Jin Tan, Wen-jie Lu, Haoqi Wu, Xiao Wang, Yu Yu, Derun Zhao, Yancheng Zheng, Minyi Guo, Jingwen Leng
2022 A* conf
Block-Skim: Efficient Question Answering for Transformer.
AAAI
Yue Guan, Zhengyi Li, Zhouhan Lin, Yuhao Zhu, Jingwen Leng, Minyi Guo
2022 J jnl
Efficient Activation Quantization via Adaptive Rounding Border for Post-Training Quantization.
CoRR
Zhengyi Li, Cong Guo, Zhanda Zhu, Yangjie Zhou, Yuxian Qiu, Xiaotian Gao, Jingwen Leng, Minyi Guo
2022 — conf
Transkimmer: Transformer Learns to Layer-wise Skim.
ACL (1)
Yue Guan, Zhengyi Li, Jingwen Leng, Zhouhan Lin, Minyi Guo
2022 J jnl
Transkimmer: Transformer Learns to Layer-wise Skim.
CoRR
Yue Guan, Zhengyi Li, Jingwen Leng, Zhouhan Lin, Minyi Guo
2021 J jnl
Block-Skim: Efficient Question Answering for Transformer.
CoRR
Yue Guan, Zhengyi Li, Jingwen Leng, Zhouhan Lin, Minyi Guo, Yuhao Zhu