Publications
* denotes equal contribution
 | Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias MitigationXiaotian Liu, Shuyuan Shang, Xiaopeng Wang, Pu Ren, Yaoqing Yang ICML 2026, Spotlight (Top 2.2%) |
 | Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific OptimizationYuxin Wang*, Yuanzhe Hu*, Xiaokun Zhong*, Xiaopeng Wang*, Haiquan Lu, Tianyu Pang, Michael W. Mahoney, Yujun Yan, Pu Ren, Yaoqing Yang ICML 2026 |