Jheng-hong Yang
Founder at Stencilzeit
Ontario, Taiwan
Summary
🤩
Rockstar🎓
Top SchoolJheng-hong Yang is a researcher-founder with nine years of experience at the intersection of representation learning, recommender systems, and information retrieval, currently leading Stencilzeit. His PhD work at the University of Waterloo and prior roles at NAVER LABS Europe and Academia Sinica focus on neural ranking, sparse/dense and multimodal retrieval, and he helped organize and curate influential multimedia test collections such as AToMiC for TREC. A practical engineer by training—earlier in his career he delivered SPICE models and manufacturing improvements at TSMC—he brings strong systems and tooling skills to research problems. He contributes to open-source IR infrastructure, notably enhancing Anserini’s support for BEIR datasets and regression tests, which underpins reproducible evaluation in the community.
9 years of coding experience
7 years of employment as a software developer
Master's degree, Electrical and Electronics Engineering, Master's degree, Electrical and Electronics Engineering at National Chiao Tung UniversityDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of Waterloo
Github Skills (5)
lucene10
javas10
information-retrieval10
java10
testing10
Programming languages (6)
Github contributions (5)
castorini/anserini
Aug 2019 - Dec 2022
Anserini is a Lucene toolkit for reproducible information retrieval research
Role in this project:
Back-end Developer
Back-end DeveloperContributions:26 reviews, 15 commits, 40 PRs in 3 years 4 months
Contributions summary:Jheng-hong primarily contributed to enhancing the information retrieval capabilities of the Anserini project, focusing on the integration of BEIR datasets and associated resources. They added new topic readers, qrels, and test cases for various BEIR datasets, specifically addressing the needs of the BEIR regression tests and SPLADE-distill CoCocodenser medium. Their work included modifying existing code to incorporate these new datasets and models, and adjusting test configurations to ensure data integrity.
reproducibleretrievalluceneinformation-retrievaljava
justram/anserini
Mar 2022 - Mar 2024
Anserini is a Lucene toolkit for reproducible information retrieval research
Contributions:60 pushes, 30 branches in 2 years 1 month
solrreproducibleretrievalluceneinformation-retrieval
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.