Scholar
Jiaxuan Wang
Google Scholar ID: X0saqiUAAAAJ
GE HealthCare
Citations & Impact
Citations
632
H-index
8
i10-index
8
Publications
11
Co-authors
14
list available
Publications
Resume (English only)
Academic Achievements
- Published 'Learning Concept Credible Models for Mitigating Shortcuts', which explores mitigating shortcuts with partial knowledge on relevant concepts and extends credible models to the image domain.
Research Experience
- Senior AI research scientist at GE HealthCare, working on improving perinatal health outcomes through AI models that interpret fetal heart rate signals. Previously, worked as a research scientist at Meta to protect user privacy by building a reinforcement learning agent to prevent misuse of user data. Interned at Microsoft Research in the Adaptive Systems and Interaction Group, mentored by Scott Lundberg, unifying Shapley value-based model interpretation methods. During undergraduate studies, worked with Professor Jia Deng to augment CNNs with rotation-invariant filters.
Education
- Received a PhD in Computer Science from the University of Michigan in April 2022, advised by Professor Jenna Wiens; completed a Bachelor's degree in Computer Science with a minor in Mathematics at the University of Michigan in 2017.
Background
- Research interests include model interpretability and robustness, particularly in healthcare applications. Also interested in a wide range of topics such as time series analysis, non-convex optimization, reinforcement learning, and sports analytics.
Miscellany
- Hobbies include basketball (20+ years), guitar (4 years), and violin (20+ years). Skills: C++ (4 years), Python (10+ years), Java (1 year), PyTorch (6 years).
