Han Hu

Han Hu

Han Hu 胡晗

About Me

I am Han Hu (胡晗), a Research Scientist at Huawei Hong Kong Research Center (Feb 2025 – Present).
I hold a Ph.D. in Computer Science from Monash University (Jul 2021–Dec 2024), an M.S. from Tsinghua University, and a B.S. from UESTC.
I am the lead algorithm designer of an AI-driven performance analysis system deployed in production. I also work on Code LLM post-training, evaluation, and domain-specific model training. My PhD publications have accumulated 1,000+ citations (Google Scholar), with work at NeurIPS, ICLR, FSE, ICSE, and TOSEM.

LLM: Code LLM (SFT/RLHF) · Benchmark & Evaluation
AI Systems: AI Infrastructure (LLM Inference · On-device AI · GPU/CPU Optimization) · AIOps
Compilation & Program Analysis: Binary Code Analysis · Decompilation

Research Interests

① AI-Driven Performance Analysis System (Code LLM · Compilation · Program Analysis · Systems) (Core)
In applied research, at the intersection of Code LLM, binary/compilation analysis, program analysis, and systems performance engineering, I independently researched and implemented core AI algorithms deployed at scale: redundant GPU computation detection (20% GPU performance improvement in key scenarios · FSE 2026 · First-author Patent, 2025), binary code analysis for optimization-level recognition (top SE conference, to appear), redundant thread detection (3–5% CPU improvement), and LLM-based automated root cause attribution via an agentic decompilation pipeline (2025).
(FSE 2026 · TOSEM 2023 · First-author Patent, 2025 · MLSys · AIOps)

② Code LLM: Post-training, Domain Modeling & Evaluation (Core)
In fundamental research, my work focuses on post-training large language models for code (SFT/RLHF) and training domain-specific small models; LLM benchmark construction and evaluation; AI coding tools.
(Core contributor: BigCodeBench (ICLR 2025) · StarCoder 2 — widely adopted in the Code LLM community)
🏆 Best Special Theme Paper Award @ EMNLP 2025

③ Automated App Analysis & GUI Agent
Autonomous GUI agent for mobile app testing; dynamic app exploration; on-device ML model analysis (Android/iOS).
(NeurIPS 2024 · TOSEM 2024 · TOSEM 2023)

Collaboration & Opportunities

Our team, based in Hong Kong, is currently open to research interns (long-term recruitment, applications accepted year-round) and full-time researchers focusing on app/model performance, automated app analysis and AI4SE.
We can support visa applications and offer a highly competitive compensation package for qualified candidates.
If you are interested in collaborating on research projects or joining our team, please feel free to contact me at agmaiofhuhan@gmail.com.

Notice

This page and my CV are for personal reference only. Please do not submit, forward, or share my profile, this page, or any version of my CV to recruitment agencies, talent programs, or third-party platforms without my explicit prior consent.

Latest News