Zhiyuan Zeng 曾致远

My name is Zhiyuan Zeng. I am a Ph.D. student (2024–present) at the Paul G. Allen School of Computer Science & Engineering, University of Washington, where I have the privilege of being advised by Prof. Hannaneh Hajishirzi and Prof. Pang Wei Koh. I previously received my Bachelor of Engineering degree from the Department of Computer Science and Technology at Tsinghua University in June 2024. During my undergraduate years, I was fortunate to work with Prof. Zhiyuan Liu at Tsinghua University and Prof. Danqi Chen at Princeton University.

Email  /  Google Scholar  /  Twitter  /  Github

profile photo
Selected Papers

* denotes equal contribution

Exploring the Benefit of Activation Sparsity in Pre-training
Zhengyan Zhang, Chaojun Xiao, Qiujieli Qin, Yankai Lin, Zhiyuan Zeng, Xu Han, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Jie Zhou
ICML 2024
[paper][code]
Evaluating Large Language Models at Evaluating Instruction Following
Zhiyuan Zeng, Jiatong Yu, Tianyu Gao, Yu Meng, Tanya Goyal, Danqi Chen
ICLR 2024
[paper][code]
Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
Mengzhou Xia, Tianyu Gao, Zhiyuan Zeng, Danqi Chen
ICLR 2024
[paper][code][blog]
Emergent Modularity in Pre-trained Transformers
Zhengyan Zhang*, Zhiyuan Zeng*, Yankai Lin, Chaojun Xiao, Xiaozhi Wang, Xu Han, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Jie Zhou
Findings of ACL 2023
[paper][code]
Plug-and-Play Knowledge Injection for Pre-trained Language Models
Zhengyan Zhang*, Zhiyuan Zeng*, Yankai Lin, Huadong Wang, Deming Ye, Chaojun Xiao, Xu Han, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou
ACL 2023
[paper][code]

Website design from Jon Barron