About Me
I am a Master’s student in Data Science (MSE) at the Department of Applied Mathematics and Statistics, Johns Hopkins University (Jan 2026 – Present). [Resume]
Generally, I’m curious about what phenomena are common across different kinds of models, why these phenomena happen and how I can affect them in various ways. My research broadly falls under AI for Science, with two threads: understanding how and why ML models behave the way they do in scientific settings, and building systems that can reason over scientific knowledge.
On the first thread, I have worked on Scientific Machine Learning (SciML) — specifically the loss landscape geometry, training dynamics, and transfer learning of physics-informed models — advised by Prof. Yaoqing Yang and Pu Ren. On the second thread, I am currently working on scientific claim verification and evaluation, building multi-agent frameworks that evaluate scientific reports via claim-specific obligation maps and LLM-as-judge pipelines, advised by Prof. Benjamin Van Durme and William Walden.
I have also worked on AI for Health, designing a self-evolving pipeline for ICU clinical prediction using counterfactual reasoning and confidence-gated memory injection, advised by Xing Han.
Previously, I received my B.E. in Data Science and Big Data Technology from Tongji University (2019–2023). Then I worked as a Software Development Engineer at Beijing Dajia Internet Information Technology (Kuaishou) (2023–2025), where I built performance analysis tools and maintained a JS container for large-scale mobile systems.
News
- [May 2026] Paper accepted at ICML 2026: Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization
Selected Publications
Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization
Yuxin Wang*, Yuanzhe Hu*, Xiaokun Zhong*, Xiaopeng Wang*, Haiquan Lu, Tianyu Pang, Michael W. Mahoney, Yujun Yan, Pu Ren, Yaoqing Yang
International Conference on Machine Learning (ICML), 2026
[Paper] [Code]
Contact
ruangyx@gmail.com / ywan1150@jh.edu
Other
I enjoy reading various kinds of novels! My happiness comes from building imagination within reality and seeking reality within those fantasies. Actually, I’m trying to make my life an adventure novel and my future research a detective novel.