Liangming Pan
Assistant Professor at Peking University
Beijing, China
Summary
👤
Senior🎓
Top SchoolLiangming Pan is an Assistant Professor at Peking University leading the PILLAR group in the Institute of Computational Linguistics, specializing in interpretable large language models, reasoning, and explainable AI. With eight years of experience across academia — including appointments at University of Arizona, UCSB (postdoc under William Yang Wang), and MBZUAI — he blends rigorous research in NLP and machine learning with applied model interpretability. He earned his PhD from the National University of Singapore after advanced study at Tsinghua and Beihang, giving him a strong foundation in both theoretical and engineering aspects of AI. Liangming’s work emphasizes making LLM reasoning transparent and auditable, aiming to bridge cutting-edge research with practical, trustworthy systems. Colleagues note his international trajectory and rapid transition from postdoc to faculty roles as evidence of both research impact and leadership potential.
8 years of coding experience
1 year of employment as a software developer
Bachelor, Software Engineering, Bachelor, Software Engineering at Beihang UniversityMaster, Computer Science, Master, Computer Science at Tsinghua UniversityDoctor of Philosophy (PhD), Computer Science, Doctor of Philosophy (PhD), Computer Science at National University of Singapore
Github Skills (8)
visual-question-answering9
deep-learning8
question-answering8
nlp6
natural-language-processing6
pytorch5
acl5
semantic4
Programming languages (2)
Github contributions (5)
teacherpeterpan/Question-Generation-Paper-List
Dec 2019 - Jun 2021
A summary of must-read papers for Neural Question Generation (NQG)
Contributions:26 commits, 2 PRs, 50 pushes in 1 year 5 months
deep-learningquestion-generationquestion
teacherpeterpan/Unsupervised-Multi-hop-QA
Mar 2021 - Apr 2021
Codes for NAACL 2021 Paper "Unsupervised Multi-hop Question Answering by Question Generation"
Contributions:31 commits, 32 pushes, 1 branch in 9 days
pytorchnlpnaaclquestiondeep-learning
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.