I am a PhD student in the Applied Mathematics, Statistics and Scientific Computation (AMSC) program at The University of Maryland, College Park. I am advised by Maria Cameron and working closely with Furong Huang and Haizhao Yang. My research primarily focuses on causal inference in machine learning and understanding rare events in molecular biology using ML techniques. My recent research covers a broad range of topics including optimal control, model reduction, causality in machine learning, Large language model, vision language models and computational methods for differential equations. I have experience in causality in LLM/VLM, large models for differential equations and AI for molecular biology.

Publications and preprints

• Jiaxin Yuan, Shashank Sule, Yeuk Yin Lam, Maria Cameron; Learning collective variables that respect permutational symmetry. J. Chem. Phys. 7 October 2025; 163 (12): 124101. https://doi.org/10.1063/5.0288154. arXiv: 2507.00408.
• Xiaoyu Liu^*, Jiaxin Yuan^*, Yuhang Zhou, Jingling Li, Furong Huang, Wei Ai. CSRec: Rethinking Sequential Recommendation from A Causal Perspective. SIGIR 2025. arXiv: 2409.05872. *equal contribution
• Zezheng Song^*, Jiaxin Yuan^* and Haizhao Yang. FMint: Bridging Human Designed and Data Pretrained Models for Differential Equation Foundation Model for Dynamical Simulation. Adv. Theory Simul. 2025, 8, 2500062. https://doi.org/10.1002/adts.202500062. arXiv: 2404.14688. *equal contribution.
• Jiaxin Yuan, Amar Shah, Channing Bentz, and Maria Cameron. Optimal control for sampling the transition path process and estimating rates. Communications in Nonlinear Science and Numerical Simulation. Volume 129, February 2024, 107701.
• Xiaoyu Liu, Jiaxin Yuan, Bang An, Yuancheng Xu, Yifan Yang, and Furong Huang. C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder. Conference on Neural Information Processing Systems (NeurIPS), 2023
• Xiaoyu Liu, Jiaxin Yuan, Bang An, Yuancheng Xu, Yifan Yang, Furong Huang. C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder. International Conference on Machine Learning (ICML) workshop on Structured Probabilistic Inference & Generative Modeling, 2023.

Education

• Ph.D. in Applied Mathematics, University of Maryland,
  May 2026(expected), GPA: 3.84/4.00

• B.S. in Mathematics, Minor in Economics,
  Schreyer Honors College, The Pennsylvania State University,
  May 2020, GPA: 4.0/4.0

Teaching

• Teaching assistant for summer REU at University of Maryland, 2022.
• Teaching assistant for pre-calculus, calculus I, calculus II, ordinary differential equations, elementary statistics and probability and linear algebra, 2020-2023