Po-Wen Chang

Po-Wen Chang works at the intersection of astrophysics and machine learning, studying phenomena such as supernovae, choked jets, high-energy neutrinos, and gravitational lensing, while also developing AI and uncertainty-quantification tools for cosmology and particle physics research. Recent work includes applying deep learning methods (like vision transformers and self-supervised learning) to interpret astronomical images and building public benchmark challenges (e.g., FAIR Universe) for testing machine learning uncertainty in physics data analysis.

Publication output was minimal or absent from 2017-2021 but has grown substantially since 2022, with a sharp increase in output projected for 2026.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026