I am an undergraduate student at Beijing University of Posts and Telecommunications (BUPT), majoring in Internet of Things Engineering in the BUPT-QM joint program.

My research interests focus on LLM post-training and self-evolving agents. Feel free to contact me for collaboration, work opportunities, or just a chat.

In the long run, I hope to build AI systems that can significantly advance real-world productivity, broaden access to knowledge and high-quality work, and contribute to more inclusive social progress.

โ€œBelieve in the beauty of life, maintain an optimistic attitude, and know that revolution is always invincible.โ€

โ€”โ€” Valery Sablin

๐Ÿ”ฅ News

  • 2026.09: We released iCoder-27B, a frontier-competitive industrial coding model for RTL design and GPU kernel optimization. See the media coverage.
  • 2026.03: I hope this section will eventually contain news genuinely worth your attention.

๐Ÿ“ Publications

Preprint
iCoder-27B human-guided, agent-led model development framework

iCoder-27B: Recursive AI-Led Development of Frontier Industrial Coding Model

Cheng Yang*, Jiayang Lyu*, Shangyuan Liu*, Guibin Zhang*, Jiong Lin, Xinlei Yu, Junchi Yan, Shuicheng Yan, Weinan E, Linfeng Zhang, Linfeng Zhang, Qibing Ren

Preprint | Paper | Code

Preprint
Latent On-Policy Self-Distillation: learnable privileged context compared with fixed privileged context

Latent On-Policy Self-Distillation

Guibin Zhang*, Jiayang Lyu*, Ran Sun, Xinlei Yu, Haoyu Zhao, Qibing Ren, Shuicheng Yan

Preprint | Paper | Code

ACL 2026
Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning

Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning

Bowen Ding, Yuhan Chen, Jiayang Lyu, Jiyao Yuan, Qi Zhu, Shuangshuang Tian, Dantong Zhu, Futing Wang, Heyuan Deng, Fei Mi, Lifeng Shang, Tao Lin

ACL 2026 | Paper | Code

๐ŸŽ– Honors and Awards

  • 2024.10 China International College Studentsโ€™ Innovation Competition, National Gold Award.
  • 2023.08 Outstanding Volunteer in Flood Relief, honored by the local Communist Youth League for volunteer service during the 2023 Songhua River flood response.

๐Ÿ“– Education

Beijing University of Posts and Telecommunications

B.Eng. in Internet of Things Engineering

Sep. 2023 - Jun. 2027 (Expected)

Queen Mary University of London

B.Eng. in Internet of Things Engineering

Sep. 2023 - Jun. 2027 (Expected)

๐Ÿ’ผ Experience

Shanghai Jiao Tong University

Research Intern, supervised by Prof. Qibing Ren

Mar. 2026 - Sep. 2026

Westlake University

Research Intern, supervised by Prof. Tao Lin

Jul. 2025 - Feb. 2026