Lihang Liu
算法工程师 at Baidu Inc.
United States
Summary
🤩
Rockstar🎓
Top SchoolLihang Liu is an algorithm engineer with 10 years of experience applying machine learning and data-driven solutions at scale, currently building algorithms at Baidu in the United States. He holds a CS BS from Shanghai Jiao Tong University and a master's in Computer Science from UT Austin, blending strong academic foundations with industry experience. His background includes anomaly detection and time-series forecasting from an SDE internship at Amazon, and a focus on practical model evaluation workflows demonstrated by contributions to PaddleHelix’s dataset splitters for bio-computing tasks. Comfortable working across research and production code, he specializes in designing robust data-splitting strategies that improve model generalization in multi-task and representation learning settings. Colleagues know him for combining rigorous algorithmic thinking with pragmatic engineering to move prototypes into reliable systems.
10 years of coding experience
Master's degree, Computer Science, Master's degree, Computer Science at The University of Texas at AustinBachelor of Science - BS, Computer Science, Bachelor of Science - BS, Computer Science at Shanghai Jiao Tong University
Github Skills (5)
splitting10
machine-learning10
python10
splits10
deep-learning8
Programming languages (3)
Github contributions (5)
PaddlePaddle/PaddleHelix
Dec 2020 - Nov 2022
Bio-Computing Platform Featuring Large-Scale Representation Learning and Multi-Task Deep Learning “螺旋桨”生物计算工具集
Role in this project:
Data Scientist
Data ScientistContributions:30 reviews, 40 commits, 76 PRs in 1 year 11 months
Contributions summary:Lihang's commits focused on the `pahelix/utils/splitters.py` file, indicating work related to data splitting strategies for the project. The code changes involve defining and implementing various data splitting classes like `RandomSplitter`, `IndexSplitter`, `ScaffoldSplitter`, and `RandomScaffoldSplitter`. These splitters are designed for dividing datasets into training, validation, and test sets based on different criteria, essential for machine learning model training and evaluation in the bio-computing domain.
representation-learningself-supervised-learningtensorflowprotein-designbio
LihangLiu/3d-colorization
Feb 2017 - Oct 2017
Contributions:25 commits, 111 pushes, 4 comments in 7 months
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.