Kuan-hao Huang
Assistant Professor at Texas A&M University
College Station, Texas, United States
Summary
👤
Senior🎓
Top SchoolKuan-hao Huang is an assistant professor and NLP/ML researcher with 11 years of hands-on experience, completing a Ph.D. in Computer Science at UCLA under Kai-Wei Chang and collaborating closely with Nanyun Peng. His work focuses on monolingual and multilingual text representations, cross-lingual transfer, low-resource information extraction, and prompt tuning, translating cutting-edge research into practical systems. He has applied his expertise to open-source ML tooling—contributing active learning strategies and robustness-focused query methods to projects used on datasets like SVHN and CIFAR-10. After a postdoc at UIUC, he joined Texas A&M, bringing a blend of rigorous academic training from UCLA and NTU and a pragmatic engineering approach to reproducible, dataset-adaptive modeling. Colleagues know him for bridging theoretical insight with practical model improvements that enhance transfer and data efficiency.
11 years of coding experience
1 year of employment as a software developer
M.S. Computer Science and Information Engineering, M.S. Computer Science and Information Engineering at National Taiwan UniversityUniversity of California, Los Angeles
Github Skills (13)
pytorch10
adversarial-machine-learning10
machine-learning10
python10
active-learning10
modeling9
trainings9
tensorflow9
cifar1009
evaluation9
eval9
tensor9
deep-learning8
Programming languages (1)
Github contributions (5)
ej0cl6/deep-active-learning
May 2018 - Oct 2022
Deep Active Learning
Role in this project:
ML Engineer
ML EngineerContributions:24 commits, 1 PR, 35 pushes in 4 years 5 months
Contributions summary:Kuan-hao contributed significantly to the active learning project by implementing and refining various query strategies. They added strategies like AdversarialBIM and AdversarialDeepFool, modifying the core code and parameters. Further improvements involved fixing bugs and adapting the framework for different datasets like SVHN and CIFAR10, demonstrating a focus on practical application and model performance.
deep-learningneural-networksactive-learningmachine-learningdeep-active-learning
ej0cl6/pytorch-adversarial-examples
Jun 2018 - Jun 2018
Contributions:6 commits, 7 pushes, 1 branch in 8 days
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.