Xin Zhang
Assistant Professor at The University of Georgia
Athens-Clarke County Unified Government, Georgia, United States
Summary
🤩
Rockstar🎓
Top SchoolXin Zhang is an assistant professor and leader in sensing and automation for agricultural systems with 11 years of experience bridging academic research and practical ML/engineering work. Currently building the SAAS lab and transitioning from Mississippi State to the University of Georgia, she focuses on robust AI and automation for agri-systems informed by a PhD in Agricultural Automation Engineering. Her work spans from deploying neural network verification tools (co-leading the award-winning alpha-beta-CROWN) to hands-on GPU acceleration contributions for the widely used LightGBM library, highlighting a rare mix of formal verification and high-performance ML engineering. She publishes actively and maintains an interdisciplinary profile across environmental, civil, agricultural and mechanical engineering domains. Less obvious: she blends deep domain expertise in horticulture and facility agriculture with low-level GPU/kernel optimization skills, enabling both field-ready sensing systems and scalable ML tooling.
12 years of coding experience
9 years of employment as a software developer
Bachelor's degree, Facility Agriculture Science & Engineering, Bachelor's degree, Facility Agriculture Science & Engineering at Gansu Agricultural UniversityMaster's degree, Horticulture Engineering, Master's degree, Horticulture Engineering at Northwest A&F UniversityDoctor of Philosophy - PhD, Agricultural Automation Engineering, Doctor of Philosophy - PhD, Agricultural Automation Engineering at Washington State University
Chinese, English
Github Skills (12)
opencl10
c-language10
cprogramming-language10
gpu10
lightgbm10
gradient-boosting10
parallel-computing9
decision-tree9
gbm8
data-mining8
machine-learning7
cuda3
Programming languages (9)
Github contributions (5)
lightgbm-org/LightGBM
Apr 2017 - Sep 2018
A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.
Role in this project:
ML Engineer
ML EngineerContributions:16 commits, 24 PRs, 19 pushes in 1 year 5 months
Contributions summary:Xin primarily contributed to initial GPU acceleration support for LightGBM. They focused on implementing GPU-specific code, including OpenCL kernels and memory management, while also addressing bug fixes and optimization. Their work involved parallelizing histogram reads and incorporating support for sparse features on the GPU. The contributions included double precision support and dependency management.
classificationdecision-treegbmgradient-boostingmachine-learning
huanzhang12/RecurJac-and-CROWN
Oct 2018 - Nov 2019
Reference implementations for RecurJac, CROWN, FastLin and FastLip (Neural Network verification and robustness certification algorithms) [Do not use this repo, use https://github.com/Verified-Intelligence/auto_LiRPA instead]
Contributions:18 commits, 10 pushes, 4 comments in 1 year 1 month
neural-networkcrown-boundsjacobian-boundsrobustness-certificationrobustness-verification
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.