I am a Ph.D. student in Computer Science and Technology at Tsinghua University, advised by Prof. Jianyong Wang. My research interests focus on efficient AI/ML.

Publications

• LeanK: Learnable K Cache Channel Pruning for Efficient Decoding (EMNLP 2025)
  Yike Zhang, Zhiyuan He, Huiqiang Jiang, Chengruidong Zhang, Yuqing Yang, Jianyong Wang, Lili Qiu
  Paper / Code

• Efficient Attention Mechanisms for Large Language Models: A Survey (Cell Patterns 2026)
  Yutao Sun^†, Zhenyu Li^†, Yike Zhang^†, Tengyu Pan^†, Bowen Dong^†, Yuyi Guo, Jianyong Wang (^† equal contribution)
  Paper

• FocusLLM: Precise Understanding of Long Context by Dynamic Condensing (ACL 2025)
  Zhenyu Li, Yike Zhang, Tengyu Pan, Yutao Sun, Zhichao Duan, Junjie Fang, Jianyong Wang
  Paper / Code

• TriangleMix: Accelerating Prefilling via Decoding-time Contribution Sparsity (ACL 2026 Findings)
  Zhiyuan He, Yike Zhang, Chengruidong Zhang, Huiqiang Jiang, Yuqing Yang, Lili Qiu
  Paper / Code

• VL Norm: Rethink Loss Aggregation in RLVR
  Zhiyuan He, Xufang Luo, Yike Zhang, Yuqing Yang, Lili Qiu
  Paper / Code

Education

• Ph.D. in Computer Science and Technology, Tsinghua University (2025/09 ~ )
• B.S. in Computer Science and Technology, Tsinghua University (2021/09 ~ 2025/06)
• High School Affiliated to Renmin University of China (2018/09 ~ 2021/06)

Experience

• Research Intern, Microsoft Research Asia, 2024/02 ~ 2026/03
  • Mentored by Zhiyuan He and Yuqing Yang
  • Worked on efficient inference of LLMs and efficient Reinforcement Learning algorithm design
  • Received MSRA “Stars of Tomorrow” award

Honors & Awards

• (06/2025) Outstanding Thesis of Tsinghua University
• (06/2025) Outstanding Graduate of Tsinghua University
• (10/2024, 10/2023, 10/2022) Overall Excellence Scholarship, Tsinghua University