About me
I am a third-year PhD student at Peking University advised by the incredible Prof.Di He. Currently, I am an intern at ByteDance Seed. I have also previously interned at Microsoft Research Asia and DP Technology.
Recent Focus
I recently focused on enhancing the coding agent capabilities of LLMs. Selected work:
- Led the development of SWE-Swiss, a 32B open-weight model that achieves top-tier performance on SWE-bench Verified. [Notion] [code]
- Contribute to Doubao Seed Code and Seed 1.8.
Publication
Let the Code LLM Edit Itself When You Edit the Code, ICLR 2025 [paper] [code]
Zhenyu He, Jun Zhang, Shengjie Luo, Jingjing Xu, Zhi Zhang, Di He
Exploiting Pre-trained Models for Drug Target Affinity Prediction with Nearest Neighbors, CIKM 2024 [paper]
Qizhi Pei, Lijun Wu, Zhenyu He, Jinhua Zhu, Yingce Xia, Shufang Xie, Rui Yan
Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation, ICML 2024 [paper] [code] [paperweekly]
Zhenyu He*, Guhao Feng*, Shengjie Luo*, Kai Yang, Liwei Wang, Jingjing Xu, Zhi Zhang, Hongxia Yang, Di He
Do Efficient Transformers Really Save Computation?, ICML 2024 [paper]
Kai Yang, Jan Ackermann, Zhenyu He, Guhao Feng, Bohang Zhang, Yunzhen Feng, Qiwei Ye, Di He, Liwei Wang
REST: Retrieval-Based Speculative Decoding, NAACL 2024 [paper] [code] [blog] [paperweekly]
Zhenyu He*, Zexuan Zhong*, Tianle Cai*, Jason D. Lee, Di He
Uni-Fold MuSSe: De Novo Protein Complex Prediction with Protein Language Models, ICLR 2023 MLDD workshop, [paper] [code]
Jinhua Zhu*, Zhenyu He*, Ziyao Li, Guolin Ke, Linfeng Zhang
Rumor Detection on Social Media with Event Augmentations, SIGIR 2021(short) [paper] [code]
Zhenyu He*, Ce Li*, Fan Zhou, Yi Yang
Awards
2023-2024: Presidential Scholarship (the highest doctoral research honor at Peking University)
Professional Services
Reviewer for
ICML 2024, 2025, 2026
NeurIPS 2024, 2025
ICLR 2025, 2026
COLM 2024