Linghao Zhang

About Me

Hey there! 👋 I’m Linghao. I received my Bachelor in Software Engineering from Wuhan University in 2025. Previously, I worked as a research intern at Microsoft Research, advised by Shilin He and Yu Kang. I was also fortunate to work with Prof. Saikat Dutta from Cornell for wonderful months.

I build something verifiable and scalable for code.

Research Interests

• ML for SE: Language Models for Code, Evaluating and Benchmarking for Code LLMs.
• SE for ML: MLOps, MLSys, Software Testing for ML-based Systems.

News

• [May. 2025] [Media Coverage] [Twitter Thread] SWE-bench Goes Live! I’m very excited to share our latest work, SWE-bench-Live. We’ve built a live, continuously updatable benchmark for issue resolving, offering a more rigorous and contamination-free evaluation for Code LLMs.
• [Jan. 2025] Our latest paper, DI-Bench, is now available on arXiv! We introduce a novel CI-based benchmark curation pipeline for software engineering tasks at the repository level. (Accepted to ACL Findings 2025 🥳)
• [Aug. 2024] 🥳 I will be joining Microsoft Research (MSRA Shanghai, DKI Group) as a research intern. Ping me if you are in Shanghai and want to grab a meal together!
• [Jun. 2024] 🧐 Check out our latest work 🔎REACT exploring how commit message generation can be enhanced by retrieving similar examples!
• [Dec. 2023] 🤠 My academic rookie has been accepted by SANER 2024 ERA track, have a look if you are interested in LLM for CMG!

Publications