Zining He
Computer Science undergraduate at Shanghai Jiao Tong University
Shanghai Jiao Tong University
Shanghai, China
hezining@sjtu.edu.cn
About Me
Hi! I’m Zining He (何子宁), a Computer Science undergraduate at Shanghai Jiao Tong University.
My research interests lie at the intersection of AI systems, formal verification, multimodal foundation models, and efficient large language models.
Research Focus
I work on reliable and efficient AI systems, formal methods for machine learning, multimodal foundation models, and efficient large language model inference.
Publications
- SpecBridge: Natural Language to Lean Specifications. NeurIPS 2026, accepted. Third author.
Research Experience
Selected research and engineering projects:
- SpecBridge: Contributed to the development and evaluation of a reconstruction-guided pipeline for translating natural-language requirements into Lean formal specifications. NeurIPS 2026, accepted; third author.
- Multimodal Large-Model Algorithms: Algorithm intern at Shanghai Chuangzhi Academy for approximately two months.
- Cross-Architecture Operator Testing: Developing differential testing frameworks for GPU/NPU neural network operators.
- MoE Acceleration: Studying adaptive expert allocation for mixture-of-experts model inference.
Education
- 2024.09 - 2028.06: B.S. in Computer Science and Technology, Shanghai Jiao Tong University.
Technical Skills
Languages: C++, Rust, Python, Java
Systems and ML: PyTorch, CUDA, Lean, Linux, computer architecture, operating systems
Feel free to check out my CV or reach out via email if you’d like to discuss research collaborations or interesting problems in AI systems!